The CM5 high-performance HMI series provides ample data storage, fast communication with a host of popular protocols (EtherNet/IP, MQTT, etc.), and supports various file types including jpegs.
• Ethernet port included for easy network data sharing
• 16.7M colors and LED backlights
• Models from 4” up to 22” (widescreen) available
• 800MHz or 1.6GHz quad core CPU
• 43MB project memory
• NEMA 4/4X (indoor use only), IP65
• FREE HMI programming software with powerful design tools and a project simulator
Starting at $340.00 (CM5-T4W)
C-more Micro HMI Panels
C-more CM5 Headless HMIs
Harness the power of CM5 HMIs without display size limitations! Easily connect the CM5-RHMI to C-more CTM series monitors, televisions, projectors, and most HDMI display devices of any size to display real-time operational data and messages.
When cost is the most important consideration, check out the C-more Micro HMIs, loaded with features and available with up to 4” diagonal screens that clearly display text, graphics, and bitmaps to effectively communicate critical data to operators.
• Built-in Ethernet (select models)
• Five function keys with LED indicators (except EA3-T4CL)
• Key functions customizable for each independent screen
• Indicator LEDs can be programmed to display alarms/status
• Software-selectable screen colors (3” panels)
• 32,768 colors with LED backlight (4” panels)
• NEMA 1, NEMA 4/4X indoor ratings
• FREE HMI programming software
Starting at $184.00 (EA3-S3ML-RN)
• HDMI video/audio outputs for VGA, SD, HD, and FHD; USB audio adapter (not included)
• (4) USB-A ports for USB HID devices such as USB hub, pen drives, touch screen displays, keyboard, mouse & scanners
18”, 22”, 24”and 27”models
C-more CTM Industrial LCD Flat Panel Monitors
• Standard analog VGA, HDMI, and USB Type-B inputs
• 16.7 million colors & 1920 x 1080 @ 60Hz video modes
• Ideal for SCADA systems, Andon boards, and for use with C-more CM5-RHMI headless HMI
• IP65 front bezel rating
• SD card slot for log files, project memory, or graphic media
• Remote HMI app provides virtual-only functionality for applications that only require remote monitoring
These new CTM series flat panels are rugged monitors that can withstand the rigors of industrial environments. With 10-point PCAP touchscreens, these monitors are super responsive even when wearing gloves.
Starting at $599.00 (CM5-RHMI) XGA,
C-more/C-more Micro Software
C-more/C-more Micro programming software packages are FREE and provide the tools needed to develop simple or very complex projects.
• Includes screen objects such as switches, meters, PID faceplates, and an analog digital clock (depending on HMI series)
• Up to 9999 screens (C-more), 999 (C-more Micro)
• Password protection available for every touch object or screen (depending on HMI series)
• Import bitmaps or bitmap objects
Starting at $827.00 (CTM-22W-M-PM)
• Other features such as alarm functions; data logging (C-more HMIs only); animation objects (C-more HMIs only); project simulation; object grouping; recipes with up to 99 or 100 entries
HMI Accessories
C-more HMI accessories include SD memory cards, USB flash drives, protective overlays, connectors, mounting brackets, and more.
Potable Water Needle Valves
A complete measurement and isolation package for potable-water, food and beverage, and industrial utility lines that must stay online.
NEW! NSF Economy Pressure Gauges
Starting at only $22.00
Reliable, cost-efficient gauges covering the most common pressure needs with NSF-certified materials ideal for potable-water and utility systems.
• Dial sizes from 2” to 4.5” and multiple mount options simplify retrofits and replacements
• Durable cases in plastic or stainless support diverse environmental demands
NEW! NSF Liquid Filled Pressure Gauges
Starting at only $37.00
Stainless-steel, glycerin-filled gauges engineered for stable readings in high-vibration environments where accuracy and durability are critical.
• Glycerin fill minimizes pointer flutter from shock, pulsation, and vibration
• Stainless-steel body resists corrosion for extended service life
• FlexWindow models available eliminate air-bubble distortion common in liquid-filled gauges
• Integrated venting plug maintains long-term accuracy under pressure shifts
NEW! 316L Potable Water Stainless-Steel
Needle Valves
Starting at only $116.00
High-pressure 316L stainless-steel needle valves built for dependable isolation, long service life, and leak-tight performance in demanding plant systems.
• Rated up to 10,000 psi for severe-duty isolation and throttling tasks
• Non-rotating spindle reduces seat wear for long-term durability
• Blow-out-proof bonnet enhances safety in high-pressure applications
• Leak-tight construction tested to stringent industry sealing standards
YOUR EQUIPMENT IS STRESSED SHIFT AFTER SHIFT. YOU DON’T HAVE TO BE.
When the pressure’s on to get the job done, our lubricants keep your operation running strong. Mystik® Greases contain shear-stable thickeners and a proprietary combination of high-performance additives that provide superior protection for pump and motor bearings.
MADE TO MAKE IT LAST.
VIEWPOINT
5 | How in-person learning can beat AI every time
In a head-to-head comparison of in-person events and using AI, the in-person meetings are unbeatable.
When it comes to maintenance, there are many approaches and philosophies.
SOLUTIONS
12 | How to sustain valve operation through proper lubrication
Proper lubrication is essential to maintaining reliable valve operation, extending service life and preventing leaks, spills and unplanned downtime.
16 | How to save money by avoiding the what-ifs of valve corrosion
Corrosion on valves can inflict serious costs that take plants by surprise.
20 | Why valves and seals are important in compressed air systems
Manufacturing maintenance professionals should understand valves and seals within compressed air systems.
24 | How to ready operational technology for intelligent AI orchestration
The adoption of AI is accelerating and forwardlooking teams must strengthen their data ecosystem.
30 | Reengineering the future of process industries with automation
AI-enabled knowledge management, automation and other breakthroughs act as a multiplier of human capabilities.
34 | Incorporating AI and ML
AI and ML are integral to industrial plant engineering.
40 | Ways to automate changeover for the era of mass customization
Frequent product changeovers are costing manufacturers valuable production time, but automation is changing the economics.
44 | Fall protection equipment inspection questions
Fall protection equipment inspections ensure equipment is working properly and will keep workers safe.
YOUR SOURCE
Lubriplate’s ultra-high-performance, 100% synthetic lubricants have been engineered to provide unsurpassed performance in the most demanding plant environments. They provide a wide range of benefits designed to make your plant run better. Benefits include: extended lubrication intervals, lubrication consolidation through multiple application capability, reduced friction, extended machinery life and reduced downtime. Products include...
AMANDA PELLICCIONE, Marketing Research Manager A Pelliccione@WTWHMedia.com
EDITORIAL ADVISORY BOARD
H. LANDIS “LANNY” FLOYD, IEEE Life Fellow
JOHN GLENSKI, Principal, Automation & Digital Strategy, Plus Group, A Salas O'Brien Company
MATTHEW GOSS , PE, PMP, CEM, CEA, CDSM, LEED AP, Senior Vice President, CDM Smith
CONTRIBUTORS WANTED
Are you a subject matter expert in one of these topics? Would you like to write an article on one of the topics below? If so, please submit an idea to: www.plantengineering.com/contribute-to-plant-engineering
• Asset management
• Compressed air systems
• Environmental health
• Expert Q&A: VFDs and VSDs
• Expert Q&A: Plant automation
• Fall protection guidelines
• Lubrication and grease
• Preventive maintenance
• Remote monitoring
• Safety and PPE
• System integration
WTWH Media Contributor Guidelines Overview
Content For Engineers. WTWH Media focuses on engineers sharing with their peers. We welcome content submissions for all interested parties in engineering. We will use those materials online, on our website, in print and in newsletters to keep engineers informed about the products, solutions and industry trends.
The link below gives an overview of how to submit press releases, products, images and graphics, bylined feature articles, case studies, white papers and other media.
* Content should focus on helping engineers solve problems. Articles that are commercial in nature or that are critical of other products or organizations will be rejected. (Technology discussions and comparative tables may be accepted if nonpromotional and if contributor corroborates information with sources cited.)
* If the content meets criteria noted in guidelines, expect to see it first on the website. Content for enewsletters comes from content already available on the website. All content for print also will be online. All content that appears in the print magazine will appear as space permits, and we will indicate in print if more content from that article is available online.
* Deadlines for feature articles vary based on where it appears. Print-related content is due at least three months in advance of the publication date. Again, it is best to discuss all feature articles with the content manager prior to submission.
LEARN MORE AT: www.plantengineering.com/contributeto-plant-engineering
How in-person learning can beat AI every time
In a head-to-head comparison of in-person events and using AI, the in-person meetings are unbeatable.
News stories about individuals having deep, meaningful conversations and relationships with artificial intelligence (AI) became a topic at my book club recently. Does AI have emotions? Are human participants in an echo chamber when chatting with AI? Could AI fully replace human interaction?
In our industry, AI has rapidly become a powerful tool in the engineer’s toolkit. From predictive maintenance insights to quick answers on troubleshooting and standards, AI can distill vast amounts of information into digestible, actionable guidance quickly. For busy plant engineers balancing uptime, safety and efficiency, that kind of speed is invaluable.
failed despite best practices and how they adapted in real time. These are insights rarely captured in manuals or databases — and certainly not through AI tools.
Amara Rozgus, Editor-in-Chief
In-person conversations allow for depth. A presentation might spark a question, which leads to a hallway conversation, which evolves into a collaborative exchange of ideas. That back-and-forth, shaped by context, tone and shared challenges, builds a better understanding than any standalone answer can provide.
But while AI excels at delivering “quick-hit” information, it operates within a box: it aggregates and synthesizes what already exists — an echo chamber. It does not replace the nuanced understanding that comes from shared experience, nor does it replicate the trust built through human interaction. That’s where in-person events, conferences and peer discussions continue to play an irreplaceable role for engineers.
Walk into any conference or summit and you’ll notice something immediately: the conversations happening between sessions are often just as valuable as the presentations themselves. Engineers swap stories about what worked on the plant floor, what
Equally important is the relationship-building that happens face-to-face. Trust is foundational in engineering collaboration — whether you’re evaluating a technology, selecting a vendor or benchmarking processes.
This is not an either/or equation. AI and in-person engagement serve different, complementary purposes. AI can accelerate learning, provide immediate answers and help prepare for deeper discussions. Conferences and live events, in turn, expand that knowledge, challenge assumptions and create human connections that drive innovation.
As the industry continues to evolve, the most effective plant engineers will be those who leverage both. Use AI to get smart quickly — but step into the room, join the conversation and build the relationships that turn information into lasting impact. PE
Modernize Safety I/O Without Adding Complexity
RSio Remote Safe I/O reduces home-run wiring by moving safety I/O out of the cabinet and onto the machine, while integrating seamlessly into Studio 5000®.
With hybrid I/O flexibility and support for up to 192 In-Series Diagnostics devices , RSio simplifies installation without complicating configuration.
Remote Safe I/O works with the software you already use.
In-Series Diagnostics
More Devices, Less Wiring, and Faster Diagnostics
ISD allows multiple safety devices to be wired in series while maintaining individual device visibility.
Diagnostic data travels alongside the safety signal over the same OSSD wiring, reducing cabling at the machine while preserving full device-level reporting to the safety controller over CIP Safety™.
When a stop occurs, you know exactly which device initiated it, not just which zone opened.
Seamless integration into CIP Safety™ applications
Easy scalability with Ethernet passthrough
Familiar setup using Rockwell's Studio 5000®
No new software to learn
Six inputs compatible with most industrial safety devices, including light curtains, e-stops, door switches, and scanners
Simplify wiring, reduce cost, and gain valuable insights into your safety devices with In-Series Diagnostics (ISD)
Two configurable safety outputs provide single- or dual-channel control at 1 A per channel
Bright LEDs for easy status indication and troubleshooting
IP67-rated for flexible, out-of-cabinet installations
Available with either M12 L-Code or Mini pass-through power connections
Our maintenance expert offers can’t-miss advice
When it comes to maintenance, there are many approaches and philosophies. But which maintenance advice should plant managers follow to avoid downtime and keep equipment running optimally? Our expert shares some advice.
Maintenance is a critical function in any plant. But what are the best approaches? Javier Martinez, sales engineering with Teadit, shared some valuable insights to help plant managers better prioritize maintenance.
Question: What assets in your plant have benefited most from condition-based maintenance?
Answer: Heat exchangers have realized significant benefits from implementing condition-based maintenance strategies. Given the substantial capital investment required to replace this equipment, proactive monitoring and predictive maintenance practices are essential. By identifying performance degradation early, these approaches help maintain optimal operating efficiency, reduce unplanned downtime and minimize the risk of costly repairs or premature replacement.
Objectives
• Understand the best practices for maintenance strategies.
• Learn how to implement condition-based maintenance strategies.
• Determine how databased insights are impacting maintenance strategies.
Q: How has the skilled labor shortage changed the way you approach maintenance planning?
A: The skilled labor shortage has prompted organizations to adopt a more collaborative and strategic approach to maintenance planning. Many now place greater reliance on experienced vendors who can provide hands-on training, onsite consultations and ongoing technical support. This partnership model helps bridge internal resource gaps while ensuring that maintenance activities are
executed safely, efficiently and in alignment with best practices.
Q: What types of equipment are you most comfortable monitoring or diagnosing remotely?
A: I am most comfortable with remotely monitoring and diagnosing heat exchangers. These assets have become increasingly predictable in recent years, largely due to advancements in gasket technology and a deeper understanding of bolt relaxation behavior during high temperature service. Enhanced material performance data and improved analytical methods have strengthened our ability to assess joint integrity, anticipate performance trends and identify potential issues before they escalate.
Q: Are original equipment manufacturers (OEMs) doing enough to design equipment with maintenance teams in mind?
A: From my experience, there has been a noticeable reduction in the volume and complexity of technical inquiries about newer equipment compared to legacy systems. This suggests that OEMs are placing greater emphasis on design standardization and documentation quality. The consistency in equipment construction, along with the improved precision and clarity of engineering drawings, reflects a more structured and maintenance-conscious design approach.
Q: How has reliability centered maintenance evolved with modern data and analytics?
A: Reliability centered maintenance has evolved significantly with the integration of modern data collection and analytics tools. As a new generation of professionals enters the industry, there is an increased emphasis on leveraging data-driven insights to support maintenance decision-making and long-term asset performance strategies. From a manufacturer’s perspective, we have made substantial investments in collecting, analyzing and
validating performance data across a wide range of applications. This information is shared with our customers to help them make informed, reliability centered maintenance upgrades to existing equipment. By combining field experience with empirical data, organizations are better positioned to optimize maintenance intervals, reduce unplanned downtime, and improve overall operational efficiency.
Q: What challenges have you faced in standardizing maintenance procedures across shifts or sites?
A: There is definite pushback when implementing any change in this industry. The industry is making strides toward standardizing procedures. For example, we have customers who ask us to help them implement and standardize their bolt-up procedure.
Q: What does it realistically take to move a plant from reactive to proactive maintenance?
A: Shifting from reactive to proactive maintenance often requires a significant catalyst, frequently an adverse event that highlights weaknesses in existing practices. In response, organizations reassess safety standards and maintenance procedures, leading to sitewide improvements.
Q: What tools have had the biggest impact on maintenance planning and scheduling?
A: As a vendor, I try to be as involved as possible with maintenance groups. Especially when large turnaround events are being planned years in advance. A clear, effective line of communication between the site and its vendors is crucial to the site's operations.
Q: What strategies are working to capture tribal knowledge before experienced workers retire?
A: I have noticed an increase in technical training courses offered by manufacturers and in mentorships at end user sites. In addition to investing in local community colleges, colleges have partnered with OEMs to incorporate their specialized knowledge into these courses, so students gain some hands-on experience before joining the workforce.
Q: What’s the biggest challenge in optimizing spare parts inventory without increasing downtime risk?
‘ Reliability centered maintenance has evolved significantly with the integration of modern data collection and analytics tools. ’
A: The primary challenge is striking the right balance between reducing inventory costs and maintaining operational readiness. While lowering stock levels can improve working capital, it can also increase exposure to unplanned downtime if critical components are not immediately available. One practical approach is to partner with suppliers that offer consignment inventory programs. This allows essential spare parts to remain on site while payment is deferred until the parts are used. Consignment arrangements are especially valuable during turnarounds and capital projects, where timely access to critical components directly impacts schedule and uptime.
Q: How are increasing compliance and documentation requirements affecting maintenance teams?
A: From my experience, maintenance teams are almost always short-staffed, so when new documentation requirements arise, this strains the team's effectiveness. As a vendor, I proactively provide my customers with all the necessary documentation I know they will need, and I retain a record if they request it years later. PE
Insightsu
Maintenance insights
uData-backed insights have opened a new world for reliability centered maintenance upgrades, requiring up-and-coming engineers to have a keen knowledge of this data.
uDocumentation is critical, especially given the manufacturing skill and labor shortage.
uThe manufacturing industry is making strides toward standardizing maintenance procedures.
Are
you ready
SECURE YOUR DOMESTIC NOW!
ENGINEERING SOLUTIONS
LUBRICATION
Frank J. Hayes, CLGS, CLS, MLA-I, MLT-I, OMA-I, CITGO Petroleum Corporation, Houston
How to sustain valve operation through proper lubrication
Proper lubrication is essential to maintaining reliable valve operation, extending service life and preventing leaks, spills and unplanned downtime. This guide outlines best practices for selecting and applying lubricants across a variety of industrial valves and actuators in plant settings.
Valves are critical for controlling fluid or pneumatic processes, and when they are not properly maintained, failures are most likely to occur at the worst possible time. The inner workings of a valve, such as stems, O-rings, lip seals, seats packing and actuators, rely on lubricants for sealing, corrosion protection and wear control. Without proper lubrication and compatible seal materials, valves lose effectiveness and longevity, increasing operational downtime and repair costs.
But proper lubricant selection and best lubrication practices can ensure a variety of industrial valves in plant and industrial settings are well-maintained to prevent unplanned downtime. It is important to note that lubricants are not used to support process fluid flow restriction in most valves, because prolonged exposure of a lubricant to a process fluid (including water) would result in dissolved lubricant and a compromised seal. Flow blockage is usually mechanical and based on the valve internals positioning and the surface roughness of the valve seat and internal interfaces.
How to identify lubricated valve types by application
The internal geometry and operating components of industrial valves are designed to control fluid flow in specific ways. Each valve type has unique lubrication requirements. Here is a summary of valves for which lubricants are required:
• Gate valves: Primarily used for on/off service
• Outside screw and yoke (OS&Y) valves: Usually gate valves; stem movement is visible and easier to lubricate and maintain
• Ball valves: Use a rotating ball to control flow, providing quick operation and tight shutoff
• Globe valves: Use a movable disc for throttling and flow regulation
• Butterfly valves: Rotate a disc on a shaft to regulate flow; lightweight and common in large-diameter piping
• Plug valves: Rotate a cylindrical or tapered plug to control flow; suited for on/off or limited throttling applications
• Needle valves: Provide precise control with a slender, tapered needle; common in instrumentation or low-flow applications
• Diaphragm valves: Use a flexible diaphragm to control flow while isolating the mechanism from the process fluid; ideal for corrosive or sanitary service
• Actuators: Devices that open, close or position valves using mechanical force; may be manual, pneumatic, electric or hydraulic and are key for automated or remote operation
All valve types and their actuators contain moving components such as stems, threads and packing. Proper lubrication ensures:
• Reduced wear and friction
• Lower operating torque
• Longer service life
How to select a valve grease
Process fluid compatibility is critical to grease longevity. For high-pH fluids, alkaline calcium sulfonate complex greases are commonly used. Calcium-based, calcium sulfonate and calcium sulfonate complex greases are also suitable for water service, remaining stable in wet environments and providing corrosion protection. For low-pH fluids, slightly acidic lithium complex greases are preferred. Greases with highly refined mineral oils or polyal-
phaolefin (PAO) synthetic base oils are generally compatible across both acidic and basic pH ranges. Temperature is another key factor. PAO-based greases remain mobile in arctic conditions, ensuring valve internals move freely. They are suitable for service up to approximately 350°F. For higher temperatures, sealing may rely on the process fluid or specialty greases that leave behind solid lubricants like graphite or molybdenum disulfide.
What to consider when relubricating a valve
Always follow manufacturer-recommended regreasing procedures. Frequency and quantity depend on valve type, cycle count, process fluid chemistry, ambient and operating temperatures and pressure.
Most large valves include a stem thread lubricator and a packing gland, which is the primary seal against fluid leaks. Inspect packing gland regularly; tighten to stop leaks and replace when necessary.
Valve stem and body lubrication often involves purging old grease with fresh grease. For manually actuated valves, stem grease points can usually be serviced while the valve remains in operation, but a proper work permit should always be obtained.
Whenever possible, isolate, depressurize and drain the valve before replacing packing or purging grease to minimize exposure to process fluids or high-pressure water.
More specific relubrication practices are addressed in each valve description below.
Gate valves
In OS&Y gate valves, the upper portion of the stem is threaded and moves through the handwheel, while the lower, non-threaded portion passes through lubricated packing and connects to the gate that controls flow. The actuating handle on standard gate valves is affixed to the top of the stem and away from the valve body with the stem.
‘Most large valves include a stem thread lubricator and a packing gland, which is the primary seal against fluid leaks.’
Objectives Learningu
• Identify the different types of industrial valves and their key components that require lubrication.
• Select appropriate lubricants based on valve type, process fluid compatibility and operating conditions.
• Apply maintenance and lubrication best practices to extend valve life, reduce wear and ensure safe, reliable plant operation.
Always follow manufacturerrecommended regreasing procedures. Frequency and quantity depend on valve type, cycle count, process fluid chemistry, ambient and operating temperatures and pressure.’
Gate valves are typically serviced every 60 operating cycles or quarterly. In applications with highly caustic or acidic process fluids, valves should be inspected daily and serviced weekly. For most services, the packing is impregnated with a silicone-based lubricant to resist washout from process fluids or water. Valves with long stems may include a grease zerk at the top of the yoke to reduce operating torque.
When maintenance is required, lubricated packing should be replaced, often after back-seating the valve where applicable. Stem threads should be lubricated through the grease fitting at the actuator. If no grease fitting is provided, the valve should be cycled and the stem hand-lubricated until the threaded portion is fully coated.
High-pressure valves
Depending on service temperature, high-pressure flanged valves used in plant process and industrial steam service, as defined by American Society of Mechanical Engineers (ASME) B16.34, may operate at maximum allowable working pressures up to approximately 500 psi. As operating pressure increases, tackified greases are often required to limit grease displacement caused by high internal contact pressures.
Extreme-pressure valves, such as ASME B16.34 Class 4500 designs, can operate at pressures up to 7,500 psi and feature thicker bodies and welded connections. Valves designed for oil and gas service may operate at pressures up to 15,000 psi and are constructed with heavy-wall bodies, robust flanged connections and grease-filled cavities to allow internal components to move under extreme contact loads.
Routine lubrication practices for high-pressure valves generally follow the same procedures used for lower-pressure valves of similar design, with grease selection adjusted to accommodate higher contact pressures.
Ball valves
Ball valves are commonly used in gas service because they provide positive shutoff when closed. Unlike gate valves, ball valves rely on lubricated seats to accommodate the sliding motion required to rotate the ball between open and closed positions. When ball valves are used in liquid service, seat grease compatibility becomes especially important, as the lubricant is continuously exposed to the process fluid and may be subject to washout. In general, liquid service is more demanding on seat grease than natural gas service.
Service intervals for ball valves vary with operating conditions and may range from daily to monthly. When maintenance is required, both the valve body and stem should be purged with fresh grease. Ball valves should be placed in the fully open position during servicing to ensure proper grease distribution.
Plug valves
Plug valves (see Figure 2) are designed for quick on/off service and high flow capacity, using a quarter-turn motion. The stem is lubricated through a grease fitting, while a lubricated packing assembly is compressed to provide process fluid containment.
Service intervals for plug valves depend on operating conditions and may range from daily to monthly. When maintenance is required, both the valve body and stem should be purged with fresh grease. The valve should be in the fully open position during servicing to ensure proper grease distribution. Plug valve lubrication practices are like those used for ball valves.
Needle valves are used for precise metering and fine control of very low flow rates and require multiple turns to position the tapered needle relative to the seat. Needle valve lubrication and sealing practices are like those used for gate valves, with lubricated stem threads and packing providing smooth operation and effective sealing.
Globe valves
Globe valves use a circular disc or plug that seals against a beveled orifice in the valve body to control or throttle flow. They can also function as check valves when a spring-loaded shaft closes the disc against the orifice during reverse flow.
Lubrication is required for the stem packing and actuator, whether the valve uses a manual handwheel or a hydraulic actuator with a gearbox. Globe valve lubrication practices are like those for gate valves, focusing on maintaining the packing gland and valve stem threads.
Diaphragm valve
Diaphragm valves isolate moving components or the valve from the process fluid, making them well suited for caustic or acidic service where metal components are prone to corrosion. In these applications, the valve body internal fluid passage and system piping will be coated or lined for additional protection.
The valve stem is driven by an actuator and pushes a disc that transmits force to the diaphragm, which seals against a raised surface at the inlet and outlet junction. While diaphragm valves can provide flow control and throttling, doing so may reduce diaphragm life due to erosion.
Diaphragm valves do not use stem packing, but a grease point may be present at the actuator base for stem thread lubrication, when required. Diaphragm valve stem thread lubrication requirements are like gate valve stem thread lubrication.
Special lubricants for valve actuators and gear boxes
An actuator is any device that opens or closes a valve by applying kinetic energy. Actuators can be manual, electric, pneumatic or hydraulic (see Figure 3). Unlike solenoids, which send an electric signal to start an actuator, actuators perform the
actual movement. Lubrication is typically applied to manual and hydraulic actuators.
Pneumatic actuators operate within an air-line system that includes a lubricator containing low-viscosity, arctic-stable fluids with good oxidation resistance. Hydraulic actuators are usually powered with International Organization for Standardization (ISO) 15–32 arctic-grade fluids or, in some systems, water-glycol emulsions, providing wear protection and oxidation stability.
Aside from maintaining fluid performance in extreme temperatures or sunlight, actuator lubrication is generally not severe duty. Systems should be inspected and serviced at least quarterly, with more frequent attention for valves in critical service. Hydraulic and air-line fluids should be replaced at least annually to prevent degradation from moisture or contamination.
Worm gearboxes (see Figure 4) are commonly used on large, high-pressure valves as part of a manual or remote-controlled actuator. They provide slow, controlled movement of valve internals, which is useful for precise flow control. Gearboxes are typically lubricated with grease due to high loads and slow operation.
Gearboxes should be inspected at least quarterly to check for leaks. Grease should be purged annually to maintain a uniform and effective lubrication layer.
Thoughts for developing a valve maintenance schedule
When developing valve maintenance schedules, plant operators should consult valve manufacturers to ensure recommended practices are followed for the expected operating conditions. Using the correct grease for the service, applying the proper amount and performing maintenance at the appropriate intervals helps extend valve life and prevents leaks, process fluid spills, gas releases and other safety hazards. PE
Frank J. Hayes is a senior product specialist for lubricants with CITGO Petroleum Corporation.
Insightsu
Valve operation insights
uValves are a critical component, and they need to be properly maintained with lubrication.
uIndustrial valves control fluid flow, but there are many different types — and each type has special lubrication considerations.
u A valve maintenance schedule can help plants avoid unplanned downtime and keep equipment running at maximum efficiency.
FIGURE 4: Top-entry bolted body valve with worm gear actuator. Courtesy: CITGO Petroleum Corporation
ASSET MANAGEMENT
Julie Holmquist, Cortec Corp., St. Paul, Minnesota
How to save money by avoiding the what-ifs of valve corrosion
Corrosion on valves can inflict serious costs that take plants by surprise.
It is more difficult to calculate the cost of “what-if” than “what-is” in any industry, no less those that make or use valves. What if the next valve shipment rusts on the way to the customer and must be scrapped and replaced? What if that spare backup valve is corroded when the critical bypass valve needs to be switched out? What if the entire warehouse of spares rusts due to inadequate preservation?
The challenge of predicting the full cost of corrosion and its domino effect at any stage in a valve’s life cycle does not mean the exercise should not be
done. A little upfront calculation of potential losses from rusty valves quickly shows that even small initial investments can add up to incredible savings that are worth the effort — even if one never fully discovers the value of the time and money saved from emergencies avoided. In short, corrosion control at every stage from manufacturing to maintenance can have a significant return on investment for practically any plant that makes or uses valves.
Understanding valve hydrotesting and shipment
Valves are inherently critical components that must be manufactured with precision and reliability. Part of that process is hydrostatic testing to ensure valves can withstand the pressure of the fluids or gases that they will handle. The irony is that in seeking to confirm integrity, hydrotesting can undermine integrity by introducing corrosion-inciting moisture. Residual water must be completely dried to avoid flash rusting. Unfortunately, the intricacy of valves can make this step difficult.
Even without the threat of residual water, valves — like any other metal component — face corrosion risks on the journey to the end user. Shipping conditions can be unpredictable and uncontrollable, especially during several months of sea export through changing climates. Fluctuating temperatures and humidity can easily lead to condensation and corrosion that compromises the valve by the time the end user opens the package.
The natural response is to reject the components that no longer look new, forcing the manufacturer to incur time and labor costs to restore or replace the valves, while the customer may lose valuable time from project delays.
What-ifs of critical and operational spares
The cost of rust on critical and operational spares can also add up quickly. First, the plant loses
FIGURE 1: Three jars show the typical three fluids needed for a rust removal station, left to right: biobased rust remover, rinse water and alkaline cleaner with flash corrosion protection. Courtesy: Cortec
Table 1: Understanding corrosion and rust what-ifs
What if It could cost Solution
Valves corrode in shipment?
Time and money to restore valves.
Time and money to replace valves.
Time and money to handle rust complaints.
Time to wait for the end user project to proceed.
Spare valves corrode?
Warehoused valves have already rusted?
Thousands of dollars for replacement.
Thousands to millions of dollars of lost profit from downtime.
The base value of the valves. The time needed to restore or replace the valves.
Valves corrode during mothballing? Resale value of valves.
Hydrotest with corrosion inhibitors and apply additional vapor corrosion inhibitor (VCI) fogging fluid, emitters and packaging as needed.
Preserve spare valves with VCI materials.
Set up a rust removal station to restore rusted valves. Follow with preservation.
Preserve spare valves with VCI materials.
TABLE 1: By following this cause-and-effect path, end users can learn to handle valve corrosion. Courtesy: Cortec
the baseline value of the spares themselves, reflected in the amount of money spent to replace those spares (if not restored). This can quickly reach tens of thousands of dollars. For example, one water treatment plant in Canada spends approximately $6,500 (CAD) to purchase spare pumps. Losing a few of these to rust could quickly leave them with a price tag of close to $20,000 to replace these spares. A more intangible but potentially much higher loss is the cost of plant downtime. If a major valve needs to be replaced but the backup cannot be installed because it is rusty, some or all of plant operations will be suspended until the valve can be restored or replaced.
Oil and gas facilities face some of the greatest potential losses. According to Siemens, the cost of one hour of unplanned plant downtime in the oil and gas industry was approximately $200,000 to $600,000 per hour over the 2019 to 2023 fiscal year period, fluctuating with the price of a barrel of oil. This could easily add up to $5 million in a 24 hour period, underscoring the importance of minimizing downtime.
The long and short of the equation is that when a plant cannot function due to rust, it cannot produce; when it cannot produce, it cannot generate revenue. The key then is to be able to return a facility to service as quickly as possible to minimize lost productivity and revenue. This makes storing critical and operational spares rust-free, in a manner that allows for immediate installation, even more important, not only for oil and gas facilities but for any manufacturing facility that can suffer from lost production while waiting for a replacement part.
Understanding the what-ifs of mothballing
Mothballing holds value like the layup of spares, but with a slightly different purpose. This term is typically reserved for plants that will be shut down temporarily or permanently. In the oil and gas industry, it is not uncommon to shut down operations for a couple of years.
In the meantime, idle equipment — both spares and installed assets — must be preserved or face the potential of gradual deterioration over time, especially if stored in harsh climate regions where warehousing is minimal or not climate-controlled. Without proper preservation, assets could lose their integrity and value by the time the plant restarts or the organization decides to sell them.
How to ship valves rust-free
Ideally, rust prevention should start with the manufacturer. Through proper foresight, the manufacturer can not only save the end user from unexpected delays and setbacks from rusted materials but can also spare themselves the serious headaches that would come from their liability to refund or replace rusty valves.
Hydrotesting is a prime time to add corrosion protection, especially when hydrotest additives include corrosion inhibitors that leave a protective layer behind. The higher the corrosion inhibitor dose, the longer the protection period will be (as much as two years after hydrotesting). This protects internal valve intricacies and eliminates the urgency of drying hard-to-reach valve internals.
‘The cost of rust on critical and operational spares can also add up quickly.’
u
• Understand how corrosion on valves can create serious losses for manufacturers and end users.
• See how corrosion prevention can be easily incorporated into the hydrotesting, shipping and storage process.
• Learn how to create a rust removal station for rusty valve restoration.
ENGINEERING SOLUTIONS
FIGURE 2: To preserve against further corrosion, follow these six steps.
Courtesy: Cortec
Another great option for internal protection is the use of vapor corrosion inhibitors (VCI) that diffuse throughout an enclosed space, forming a protective molecular layer on metal surfaces. VCIs can be applied by fogging a valve internal or placing a VCI emitting material (e.g., a breathable pouch containing VCI) inside the valve and closing all openings. VCI bags or shrink film work well for this purpose while adding an additional dose of VCI to the package. All materials are relatively easy to remove before installation.
‘With traceable preservation, one team can hand off the valves to another team with greater confidence in and confirmation of their reliability and integrity.’
Steps to reclaim rusty valves
Valves that have already rusted — whether just during the trip overseas or after years of deficient storage — can often be reclaimed through a simple rust removal process if the rust is not deep enough to compromise valve integrity. Setting up a rust removal station is a great way to restore multiple parts over a brief or extended period (see Figure 2).
STEP 1: Select three containers large enough to hold the valves or components that need to be cleaned. These could be anything from small pails or dishpans to large tubs or tanks. Using portable containers is a great idea for large facilities that might have rusty parts on opposite ends of the warehouse.
STEP 2: Choose rust removal materials. A biobased rust remover can be a great way to introduce sustainability into the project, although stronger chemistries often act more quickly. Still, large preservation projects have found biobased rust removers to work well for hundreds of parts.
STEP 3: Clean the valves. It is important to remove any existing grease or rust preventatives to
avoid contaminating the rust removal solution and to allow direct contact with the metal.
STEP 4: Soak the valves in the rust remover solution. This may take 20 minutes to 24 hours depending on the severity of the rust. The best strategy is to check the part periodically to see how rust removal is progressing. If needed, workers can speed the process by warming or agitating the solution. (A scrub pad and gloves can also be used for extra abrasion if needed.)
STEP 5: Rinse valves in clean water. This helps remove corrosion products and avoid contaminating the final rinse solution.
STEP 6: Rinse valves in an alkaline cleaner that offers flash corrosion protection. In addition to providing temporary protection from re-rusting, this also neutralizes the acidity of the rust removal solution.
The same rust removal solutions can often be reused many times before they need to be topped off or replaced.
One manufacturer in India used a process like this to restore valve inserts that had been rejected by the customer due to rust, despite previous application of a moisture-displacing rust preventive. Short on time, the manufacturer set up a rust removal station with three tubs: one for the rust remover solution, one for water and one for the alkaline cleaner/ neutralizer/flash corrosion inhibitor. (A fourth tub was added to dip the parts into a wet film corrosion inhibitor for the preservation stage.) After going through this assembly-line process, the components were like-new and arrived rust-free at the customer’s location. The whole restoration process was completed in three days, with some parts taking as little as two minutes to clean.
How to preserve valves
Restoration and preservation often go hand in hand. Restoring valves without preserving them can leave them rusty again. Preserving valves without restoring them does not eliminate the rust that
42-inch ANSI 600 class trunnion ball valves) that they must store them outside in UV resistant VCI bags that are 36x600 inches. Due to their critical need for integrity, the company practices careful documentation — both for valves themselves and for the preservation process. This underscores an important practice among preservation crews: providing quality assurance to the next project owner by providing evidence of proper preservation. With traceable preservation, one team can hand off the valves to another team with greater confidence in and confirmation of their reliability and integrity.
The valve life cycle is full of what-ifs — many possible points at which rust could enter the picture and send the entire plant reeling with hundreds to millions of dollars of loss. Fortunately, preventing those what-ifs from happening is relatively easy with a little foresight and good restoration and preservation habits. The key is to think about these what-ifs before they become “what is” to save significant time and money. PE
Julie Holmquist is Marketing Content Writer at Cortec Corp.
Insights
Valve corrosion insights
uThinking ahead about potential valve corrosion concerns and losses and taking simple steps to avoid them offers a significant return on investment.
uFortunately, a few basic rust removal and prevention techniques can stop deterioration and loss of value at many steps along the way, at any point from the manufacturer to the end user.
Zero weep holes
Double seals on motor cover and all connection points
Designed to EHEDG Standards and IP68 and IP69K Certified
COMPRESSED AIR
Spencer Hall, Hitachi Global Air Power, Michigan City, Indiana
Why valves and seals are important in compressed air systems
Manufacturing maintenance professionals should understand valves
and
seals
within
compressed air systems.
Compressed air systems are getting more complex as technology advances. However, new technology still requires a basic service and maintenance routine. Learn to effectively and efficiently control these systems, specifically valves.
There are many types of valves in compressed air systems: solenoid valves, blow-down valve (BDV), pressure regulators, pressure relief valves (PRV), minimum pressure control valves (MPCV), inlet valves, shuttle valves, check valves, thermal valves and more. Each of these components serves a specific function to ensure the equipment runs as designed.
Inlet modulation can provide significant energy savings over time. Failed and/or neglected compressor control valves can lead to high energy costs.
Important valves in compressed air systems
The MPCV in a compressor system is no doubt one of the most important control valves on a compressor. All of the control valves play an important role, but this one can make or break the operation like no other. Due to its location, the MPCV is exposed to the worst conditions in the control system.
Every cubic foot of air per minute that feeds a process passes through this valve. The compressed air in this location of the discharge system is hot and humid. The valves, seals and related components in this area are susceptible to scale and corrosion. Depending on the application, the condition of the MPCV can deteriorate at an alarming rate. A good maintenance routine to service this MPCV will provide years of reliable control. An MPCV serves two purposes:
Learningu
Objectives
• Learn about the various types of valves and seals used in a compressed air system.
• Review predictive maintenance programs for valves and seals within a manufacturing facility.
• Understand the potential consequences of component neglect and improper form, fit and function.
One of the most common issues with compressed air systems is proper sizing of the air compressor, air piping and receiver. All the valves listed above are subject to premature failure due to high load/unload cycle counts or running unloaded for an extended amount of time.
In terms of modulation, lack of inlet modulation is a common service call. We find one valve failure can cause other valves to fail — usually seal and diaphragm failures in the control system are the culprit. A pressure regulator out of adjustment or worn diaphragm can cause control components to wear prematurely due to high load/unload cycle count. The results are often expensive repair costs along with efficiency decline.
• Prevents sump tank pressure from dropping below the minimum required to maintain safe cooling and lubrication flow.
• Prevents back flow of plant air to the sump.
The BDV is probably the second most important valve on the compressor package for system control. With each load cycle, there is a chain of events that occurs: when a load signal is initiated, load solenoid changes state, inlet valve opens, BDV closes, MPCV opens, flow and pressure increases. As pressure reaches the unload setpoint, inlet valve modulation has reached its maximum and the reverse occurs: load signal drops off, control solenoid changes state,
inlet valve closes, MPCV closes and the BDV dumps all the hot humid air to the atmosphere. Without a properly functioning BDV, there is risk of over loading the drive motor, over pressurizing the plant and lifting the PRV (see Figure 2).
Controlling a compressed air system
Advancements in control and monitoring technology of compressed air systems can greatly improve efficiencies. These advanced systems can provide early warnings of control issues that can be addressed quickly.
Compressed air is considered the fourth utility, behind electricity, water and gas. However, compressed air is completely in control of the manufacturing facility, unlike the other three. How you control compressed air systems can make a huge difference in cost of operation. Start by doing some basic evaluations:
• For new compressor applications, evaluate projected demand. Determine the production equipment required cubic feet per minute to operate, determine compressor type and size and determine receiver tank size. Downstream filtration should also be factored in.
• Have an air audit performed on an existing system. Processes likely have changed over the years or leaks have developed in the system. Air audits will reveal how the compressor is running over a period of time. The return on investment of an air audit can be quick.
• Control valves, such as inlet, blow down, MPCV and load solenoid should be maintained periodically to ensure the most robust, efficient and reliable system as possible.
• Compressors with inlet valve modulation and variable displacement should be considered if demand fluctuates drastically from shift to shift. Variable speed drives are also options along with the above control methods.
Paying attention to a manufacturing process changes and compressed air demand is key. Plant
FIGURE 1: Air flow and the inner workings of a minimum pressure control valve, one of the most critical control valves of an air compressor. Courtesy: Hitachi Global Air Power
air demands come and go as production changes. For new compressor sizing, contact a local distributor for an air audit to find the best compressor for an application.
Understand seal materials
Knowing the difference in available seal materials is crucial when selecting a replacement component. The manufacturer has already completed the homework for you in selecting a component with the proper seal material. Therefore, pay attention when selecting original equipment manufacturer (OEM) versus non-OEM replacement parts. Cheaper is almost never better.
Buna is a popular seal material in the compressed air industry. One question that comes up regularly: is it Buna or Buna-N? Which is it?
Manufacturers of components sometimes drop the -N when adding descriptions to their component seal material. Buna and Buna-N are often used interchangeably to indicate the material used is a synthetic rubber.
However, there is a name distinction within the Buna family:
• Buna-N (Nitrile rubber) is made from butadiene and acrylonitrile. Buna-N is known for its excellent chemical resistance properties used in seal, gasket and hose applications.
‘The BDV is probably the second most important valve on the compressor package for system control.’
ENGINEERING SOLUTIONS
• Buna-S (styrene butadiene rubber) is made from butadiene and styrene. Buna-S is known for its abrasion-resistant properties such as tires, conveyor belts and use in high-temperature applications.
Other common seal materials found in the compressed air industry are ethylene propylene diene monomer (EPDM) and Viton.
• EPDM is also a synthetic rubber made from a specific combination of polymers. This material offers strong outdoor-element and ultraviolet resistance, making it useful for roofing materials and automotive parts.
• Viton is a high-performance synthetic rubber called Fluoroelastomer (FKM). Viton is available in three grades: Viton A, B and F. These different grades of Viton indicate the difference in fluorine content. The higher the fluorine content, the greater the resistance to harsh chemicals such as acids and solvents. Viton is a great material for valves and seals exposed to chemicals, oils and high temperatures up to 400°F.
Seals have a finite lifespan in any application. Seals are often referred to as “soft goods” and can be in the form of O-rings, gaskets, lip seal, U-cup, V-ring, mechanical, labyrinth and carbon ring seals, just to name a few. Typically, seals are used to contain process air, oil or gas to a certain design specification.
related valves, components, lubrication and cooling systems.
FIGURE 2: A flow diagram that shows a basic oil flooded compressor discharge system. This includes control
Courtesy: Hitachi Global Air Power
Compressed air predictive maintenance
Seal and valve failures are most often caused by normal wear and tear. Seal degradation can be detected by oil visibly leaking at the compressor package or fouling downstream production equipment.
To prevent failures, a maintenance program should be proactive and predictive. Take the following measures to help avoid any potential seal/ component failures:
• Oil sampling: This will help provide early warning signs of caustic, contaminated conditions. These conditions can cause seals to swell, crack and wear.
• Vibration measurements: This predictive maintenance tool can detect issues far in advance and may provide insight into other component failures.
• Following manufacturers’ maintenance recommendations: This is key to a reliable compressor system. Typically, the “soft goods” can be replaced during routine maintenance service calls. Scheduled maintenance downtime is far less expensive than in-service downtime.
There really are no definitive cut-in-stone maintenance procedures. Each compressor application has its own unique maintenance challenges. Yes, timers can indicate when to change fluid and filters, but there are so many other opportunities to increase the reliability of your compressor system.
The state of a compressor room makes a difference too. There are consequences for installing an investment in adverse conditions. Dirt-clogged heat exchangers will increase compressor discharge temperatures and initiate fluid degradation. These conditions can shorten the life of valves and seals in your compressor control system. Fluid degradation and increased acid levels will attack seals and sealing surfaces, bearings and heat exchangers.
OEM versus non-OEM parts
The topic of OEM versus non-OEM parts includes both valves and seals. The equipment manufacturer designs compressor packages to meet certain specifications. Flows, pressures and
temperatures are taken into consideration when components are selected for the package design. Changing the design specifications of equipment can be detrimental.
Valves are typically actuated with an air signal or electric input from a control device, pressure switch, controller or a programmable logic controller. Installing a non-OEM valve can lead to performance and reliability issues. Many service calls are generated when someone has cut corners and ordered components online and they just didn’t work out.
For example, in BDVs, these valves are selected by temperature, pressure and flow by the manufacturer’s specification. There are many suppliers that will sell a valve with similar form and fit but that does not function as it’s intended. Installing a BDV that has the incorrect flow can cause control issues, create a short-cycle condition or create an over-pressure condition during unload. This can cause components such as inlet valves, control solenoids, pressure switches and minimum pressure valves to have excessive wear.
Oil condition and sampling are also a part of the OEM conversation. Contaminated oil can create havoc in a compressor system. Oil foaming and carry-over can damage downstream equipment, and high particle counts can wear out seals and damage bearings. Additionally, there are many pirate parts being sold online. Oil filters are easy to duplicate but may not perform to the same standard. A valve or seal manufacturer might ask, “Are you using OEM parts and fluids?”
Understanding the roles of various valves and seals and the consequences of neglecting them can reveal opportunities to optimize the reliability and lifespan of a compressed air system. With proper maintenance, correct component selection, and attention to routine service requirements, these critical parts can perform as designed and help maintain system efficiency. Take a moment to look over a compressor system with fresh eyes — maintenance teams may spot an opportunity to boost performance before small issues become big ones. PE
Spencer Hall is the OEM Application Engineer at Hitachi Global Air Power.
‘The equipment manufacturer designs compressor packages to meet certain specifications.’
Insightsu
Compressed air insights
u As compressed air systems become more complex, proper sizing, valve selection and routine maintenance remain critical to controlling efficiency, reliability and energy costs in compressed air operations.
uEffective compressed air management depends on understanding valve functions, seal materials, predictive maintenance and the risks of improper control or non-OEM components, all of which can significantly impact performance and life cycle costs.
ENGINEERING SOLUTIONS
Claudio Fayad and Sean Saul, Emerson, Austin, Texas
How to ready operational technology for intelligent AI orchestration
The adoption of artificial intelligence (AI) is accelerating and forward-looking teams must strengthen their data ecosystem and operational alignment today to prepare for the shift toward orchestrated, AI-enabled automation.
Artificial intelligence (AI) is one of the primary areas of focus in process manufacturing and for good reason. Many organizations are already implementing AI models and frameworks in their workflows.
In fact, a recent Massachusetts Institute of Technology’s Technology Review survey reported that
64% of manufacturers have already begun working with AI and of that group, approximately 35% have begun to put AI into production. Such a shift is hardly surprising given the challenges of competing in the modern marketplace.
Increased globalization, market fluctuations and regulatory uncertainty are combining with increasing demand and growing experienced workforce shortages to create a perfect storm of complexity. Maintaining competitive advantage means teams must not only achieve operational excellence but also maintain and evolve it.
As this complexity has grown, the maturity of consumer-grade AI has evolved in parallel. Large language models (LLMs) are significantly more powerful today than they were just a few years ago. Where once consumer-grade AI advisors were limited to data from 2021 and before, today’s LLMs and AI agents can orchestrate tasks, provide complex responses and search the web for updated content, feed that information into their models and generate a far more complex and reliable outcome. With this improvement, the number of use cases for AI has grown exponentially.
Like consumer-grade AI, industrial AI is also continually improving. However, operational technology’s (OT) need for uncompromising safety and availability create additional complexities for the use of AI. Despite these challenges, new industrial AI solutions — enhanced by contextualized data and protected by first principles models — will rapidly evolve, continuing to provide new opportunities for OT and driving the world toward an unimagined era of safety, reliability and autonomy.
Orchestration: pivotal for productivity and scale
Today, much of the popular AI software in use consists of isolated point solutions developed for specific tasks. In coming years, those solutions will
FIGURE 1: Reliability tools working with local AI models will improve outcomes. Courtesy: Emerson
become increasingly interconnected as multiple AI agents are applied in an OT context. To deliver peak value, however, these solutions will need orchestration, which will reduce the complexity exposed to users by providing coordinated workflow and task routing.
In OT, teams will have many different types of AI models, data sources and agents and they will need to deploy them in the right places and orchestrate them seamlessly to create as much value as possible. Orchestration will bring together otherwise fragmented AI capabilities, elevating operational intelligence to achieve autonomous operations.
Ultimately, this strategy is an evolution of something OT teams and their parent organizations have been trying to achieve for decades. Even before AI in the plant was a consideration, OT teams looked for ways to optimize the entire operation by first optimizing smaller units or pieces of equipment. Teams know they need each plant to operate as efficiently as possible independently, but also coordinated as part of a holistic, global enterprise.
This need has driven the digital transformation initiatives of the last 10 years as teams looked for a way to build connectors and integrate disparate systems via a supervisory control and data acquisition (SCADA) system. However, accomplishing that goal was complex, requiring development of the right systems and extensive custom engineering.
‘Orchestration will bring together otherwise fragmented AI capabilities, elevating operational intelligence to achieve autonomous operations.’
In the years ahead, to take that interconnectivity to the next level, AI will evolve from disparate software implementations to a core integration engine. This engine will be the ultimate connector of different processes, applications and plants — converging point solutions into a holistic ecosystem that can make better use of the whole. Soon, organizations will rely on plant-level AI advisors as local orchestrators, bringing the plant information together and coordinating tasks and analysis, while enterprise-level AI advisors will coordinate with those plant-level advisors to provide end-to-end, holistic optimization.
The data foundation: generators, transformers and context
Free-flowing data across the OT space is a critical enabler of successful AI implementation. AI consumes tremendous amounts of data and that data is the primary driver to ensure accurate results
Objectives Learningu
• Understand the role of artificial intelligence (AI) in process manufacturing.
• Learn how data impacts the use of AI in process manufacturing.
• Discover the many types of AI models, data sources and agents and how they orchestrate to bring together otherwise fragmented AI capabilities.
FIGURE 2: Well-orchestrated systems will provide improved predictive insight. Courtesy: Emerson
ENGINEERING SOLUTIONS
and guidance are generated by AI models. Therefore, a robust and trustworthy data-generating infrastructure is needed to feed and support AI initiatives.
formers, in turn, work closely with local AI models to perform and enrich operational outcomes (see Figure 1).
However, raw data is not enough. To truly create a transformative AI architecture, each layer of the data foundation must also preserve context. AI models will need to work with diverse, multimodal streaming and event-based operational data, so it is critical that context — the associated relationships between different pieces of data — be inherently preserved in the system, rather than requiring manual effort to generate. Contextualized, relevant, real-time data is essential for industrial AI effectiveness.
Building the AI ecosystem: layers of intelligence
Once teams have their data foundation in place, they can leverage that data to inform AI models for greater insight. And once those models are built out orchestration across disparate agents will be needed to deliver the next level of value across the wide spectrum of OT systems (see Figure 2).
‘To truly create a transformative AI architecture, each layer of the data foundation must also preserve context.’
Smart instruments are the primary data generators, the location where the data is born in operating facilities. Flow computers, gas chromatographs, valve controllers and other field devices also play a key role as data generators by providing data about themselves and by collecting and exposing data about the process to provide insight.
There is incredible value in the highly trustworthy, highly sophisticated diagnostics and intelligence delivered by these devices. Moreover, as emerging technologies like Ethernet Advanced Physical Layer expand both the bandwidth and capabilities of these devices, the value they provide to AI solutions will only continue to increase, delivering more powerful, faster diagnostic insights into the underlying process dynamics.
Domain-specific software applications are also critical to a strong data foundation, acting as data transformers. Modern software applications like advanced process control (APC), alarm management, real-time scheduling, historians, reliability predictive analytics and other software gather data and enrich it to create information. The data trans-
For example, consider a boiler control system. The boiler operation is broken down into many control loops: pressure control, level control, steam flow and more. Once those individual loops are optimized at the local level, the OT team can implement AI-enabled adaptive process control software to automatically adapt and optimize operations to manage ever-changing plant conditions — optimizing the whole boiler system.
Ideally the same control software will be used on other assets across the plant, creating many optimized individual systems. At that point, the team can implement AI-enabled planning, scheduling and advanced process control software to tell each facet of the control system what to do, driving plant-level orchestration.
Once each plant is optimized, organizations will continue improvement with enterprise-level orchestration tools to integrate scheduling, optimization and global coordination. Such systems will be connected through seamless mobility of contextualized data, empowering AI agents at each level to communicate and automate workflows effectively and providing OT users with a single, intuitive natural language interface to manage the system from the top down.
FIGURE 3: AI engineering tools augment workflows for OT teams. Courtesy: Emerson
The AI advisor: From augmentation to autonomy
Much of the future of industrial AI for OT applications might seem like science fiction. The AI advisors used in process manufacturing today are powerful — providing guidance, decision support and insight to augment operators’, engineers’ and system architects’ existing workflows –– but they are not yet ready to deliver a holistic orchestrated AI ecosystem (see Figure 3).
For example, modern AI advisors can provide control room operators experiencing a transient state or unknown condition an easy way to ask, “Current operations are abnormal, what is going on?” Instead of having to flip through manuals and try to determine a corrective action, operators have a natural language prompt that can guide them to action in real time — augmenting their expertise to make them the best, most knowledgeable person they can be for any given task. This capability provides powerful functionality, but it is not yet proven to orchestrate enterprise operation.
It would be a mistake, however, to assume that those orchestration capabilities are many years away. Today’s OT AI advisors are early-stage tools, akin to consumer generative AI tools in their infancy. It is easy to see how those same AI advisors will soon be able to start coordinating individual AI
deployments and integrating them with knowledge in the form of a fine-tuned, multi-agent network. As they are further trained on facility-specific details, they can continue to leverage all their collected data to monitor, interpret and coordinate across models. This vision — one of a software-defined, AI-driven enterprise operations platform (EOP) — is on the horizon (see Figure 4).
Manufacturing often follows a prescriptive deployment of technology because OT solutions must always be ruggedized, both for use in challenging environments and, more importantly, to eliminate the possibility of mistakes and fabrications. Industrial AI will always need to be more predictable and deterministic than generic AI.
A good predictor of when a technology will find its way into industrial applications is when it becomes ubiquitous in normal life — and AI is ubiquitous today. People experience AI interactions every day, whether it is in auto translation, software that can predict the next words a user will type or search engines providing summaries of the most useful content. These capabilities are integrated into the tools people already use
FIGURE 4: An AI-driven, software-defined enterprise operations platform will help organizations orchestrate their AI capabilities. Courtesy: Emerson
ENGINEERING SOLUTIONS
‘Ultimately, teams will likely need AI-driven data validation layers to compare the data against the context. This, in turn, will require seamless interconnectivity provided by orchestrated AI across the plant and enterprise.’
and sometimes it is not obvious they have been added. They just become a normal part of everyday products.
The same thing is happening with manufacturing tools. Not every AI application — perhaps not even most AI applications — will be something OT teams overlay on existing solutions and must train people to use. Instead, many of these applications are now being delivered as feature advancements in the software users already trust and will appear incrementally, making them easier to adopt and leverage to drive increased operational excellence.
Preparing for tomorrow's AI ecosystem today
Preparing for the paradigm shift of AI-empowered operation via an EOP means ensuring support for the three critical elements that drive industrial AI: data, context and first principles. Organizations first must ensure they have the right data, have efficient data architectures in place to keep it moving seamlessly to the people and applications that need it and can keep it contextualized at every step of that process.
These needs will become even more critical as AI begins to evaluate data in real time. For example, if data in one part of the process reports a significant temperature drop, but data from another area does not support that information, OT teams will need a way to validate their data. Today, validation can be performed manually by human analysts, but it will need to happen much faster than humans can handle if the data is to be used by AI to support real-time operations.
Ultimately, teams will likely need AI-driven data validation layers to compare the data against the context. This, in turn, will require seamless interconnectivity provided by orchestrated AI across the plant and enterprise.
In addition, OT-specific AI also needs first principles grounding — fundamental physics and chemistry constraints — built in to keep it from making mistakes or fabrications. First and foremost, OT teams should select models from automation solution providers with decades of experience in their industry. Those providers will have industrial AI solutions that can be deployed either on the cloud or on premises using an automation tuned LLM as a general framework. That LLM can then be fed specific OT data to customize it to a given use case.
When that industry-specific, local LLM is deployed at the facility, it can be further trained with organization-specific systems and procedures, so the OT team has a model fully customized to their unique operations — trained on two layers of proprietary data from automation systems and users.
The orchestrated AI future is just over the horizon
Pervasive AI in process manufacturing is not only inevitable, but also closer than most would think. The consumer-grade AI models once limited by expired data and a strong tendency to hallucinate have grown in power, capability, flexibility and reliability as frontier models are released in weeks rather than years apart. They have also increasingly become ubiquitous parts of everyday life.
The same will happen in the OT space and, once again, on a much shorter timeline than anticipated. Now is the time to begin building a data foundation, as well as training, learning and building trust for the new tools that will shape the future of manufacturing. PE
Claudio Fayad is the chief technology officer of Emerson’s Aspen Technology business. Sean Saul is the vice president of the DeltaV™ platform at Emerson.
Insightsu
AI orchestration insights
uArtificial intelligence (AI) will continue to proliferate in process manufacturing.
u AI will evolve from disparate software implementations to a core integration engine. This engine will connect different processes, applications and plants — converging point solutions into a holistic ecosystem that can make better use of the whole.
uOrganizations must ensure they have the right data, efficient data architectures in place to keep it moving seamlessly to the people and applications that need it and contextualized it at every step of that process.
Subrat Tripathy, L&T Technology Services (LTTS), Edison, New Jersey
Reengineering the future of process industries with automation
Plant operators worldwide are struggling to cope with a growing mismatch between factory capabilities and evolving market expectations. As global manufacturing demand volatility continues, there is a rising need for flexible and digitally augmented operations.
Learningu
Objectives
• Understand why process manufacturers are shifting from incremental upgrades to artificial intelligence (AI)led, scalable automation as a response to volatility, legacy systems and skills shortages.
• Learn how AI-enabled automation, such as predictive maintenance, digital workflows, digital twins and real-time asset health, directly improves uptime, quality, throughput and time to market.
• Recognize the strategic value of integrated onestop engineering and digital delivery models in modernizing plants consistently across multiple sites with measurable business outcomes.
Plant operators worldwide are struggling to cope with a growing mismatch between their factory capabilities and evolving market expectations. As global manufacturing demand volatility continues unabated, there is a corresponding rise in the need for flexible and digitally augmented operations. Legacy control systems, placed on top of aging assets, further intensify the challenge. And consequently, manufacturers are increasingly prioritizing three pillars.
Legacy system upgrades
Existing equipment, obsolete control technologies and standalone operational technology (OT) networks create blind spots in plant performance. Modernization, therefore, involves migrating aging programmable logic controllers (PLCs) and human-machine interface architectures to contemporary, secure and more scalable platforms leveraging any-to-any technology synergies. This helps create unified data pipelines across PLCs, Supervisory Control and Data Acquisition (SCADA), historian, Manufacturing Execution System (MES), Enterprise Resource Planning (ERP) in adopting interoperable communication standards.
High-speed, high-mix manufacturing
Consumer demand is shifting toward more rapidly available alternatives, based on increasingly localized supply chains. With shortening product life cycles, this has increased the focus on more agile manufacturing lines that can support greater Stock Keeping Units’ (SKUs) variability and availability with resilience, enhanced energy-responsiveness and utility aware market adaptive operational controls.
Automation at scale across global plants
From modernizing individual assets, the focus is shifting toward scalable automation architectures that can be replicated across dozens or even hundreds of plants, with multisite, connected plant rollouts at the center.
Artificial intelligence (AI)-enabled automation as a response to the skills gap
Unfilled manufacturing roles could surpass 1.9 million workers by as early as 2033. This persistent shortage of skilled shop floor operators and plant technicians could have a significant adverse impact on asset availability, maintenance practices, safety and overall throughput.
Artificial intelligence (AI)-enabled knowledge management, automation and other breakthroughs multiply human capabilities and enhance plant resilience in this scenario. This includes leveraging sustained advances in AI- driven spatial computing from design to commissioning, robotics, expansion of low-cost edge computing, agentic operations and the availability of new-age cloud architecture that helps deployments become more affordable and modular.
Combined with AI-assisted operator, anomaly prediction, adaptive production control and remote troubleshooting, a growing momentum in favor of
‘Artificial intelligence (AI)enabled knowledge management, automation and other breakthroughs multiply human capabilities and enhance plant resilience in this scenario.’
AI-enabled automation can also help significantly reduce the continued need for deep tribal knowledge on the shop floor.
Key technology trends shape plant automation
Several converging technology trends are redefining how plants worldwide operate, optimize and scale.
AI-driven productivity gains
AI models are increasingly embedded into production lines, packaging systems and maintenance workflows. This could contribute up to $15 trillion to the global GDP by 2030, with manufacturing among the largest beneficiaries. This movement is already evident across applications spanning machine vision for defect detection, real-time optimization of set points and automated cycle time improvements.
1. Digital workflows replacing manual processes
Digital workflows today go far beyond reporting or recipe control and coordinate the entire value chain from market demand to maintenance execution. Connected plants integrate demand signals, planning, scheduling, operations, quality, energy use, asset health and maintenance into a unified, autonomous workflow layer, replacing functional silos with continuous, real time, cross process orchestration.
2. Predictive and prescriptive maintenance
AI/ML models are being leveraged for routine forecasts of potential asset failures long before they occur. This enhances equipment reliability and reduces unplanned downtime, which can cost manufacturers upwards of $20,000 per minute in some industries.
FIGURE 1: AI-led plant automation turns predictive intelligence into measurable gains across uptime, quality, efficiency, margins and speed.
Courtesy: L&T Technology Services
ENGINEERING SOLUTIONS
‘
The AI-automation revolution can be characterized by the consolidation of plant engineering, automation and digital services into integrated delivery models.
’
3. Digital twins
A digital twin is a virtual representation of a process, machine, line or entire plant and field-operations that mirror real time and simulated performance. It enables a more rapid assessment of layout and equipment changes, stress analysis, process and throughput forecasting and optimization of energy consumption and batch performance. With market trends estimating a global demand to the tune of $150 billion by 2030, the growing adoption of digital twins appears set to redefine the plant ecosystem.
4. Real-time asset health monitoring
The combination of edge AI devices installed on factory equipment with OT data pipelines and embedded AI models drive the creation of reliable and continuously monitored equipment ecosystems. And the consequent early anomaly detection enables corrective actions before machinery failures escalate, helping promote a transformed asset behavior that was reactive to a more predictive and strategic outlook.
What AI in plant automation delivers
An accelerated, AI-led automation journey across the global process industry landscape is being increasingly characterized by:
• Marked reductions in unplanned downtime, with predictive maintenance and real-time monitoring significantly reducing sudden line stoppages,
• Sustained enhancements in quality, consistency and yield, leveraging machine vision systems, digital quality checks and automated parameter adjustments to minimize variation and improve first pass yields,
• Overall higher equipment effectiveness, with AI-driven cycle time optimization, automated changeovers and advanced controls to increase both throughput and asset availability,
FIGURE 2: AI acts as the multiplier that unifies systems, accelerates agility and scales automation across modern plants. Courtesy: L&T Technology Services
• Enhanced margins, from better uptime, improved quality of output and greater equipment utilization and
• Faster time to market, with digitally simulated commissioning, modular automation and accelerated recipe changeover compressing production readiness timelines.
One-stop engineering and digital model
The AI-automation revolution can be characterized by the consolidation of plant engineering, automation and digital services into integrated delivery models. Manufacturers increasingly prefer unified partners who can address mechanical, electrical, controls, digital, operational technology security and data engineering requirements through a single framework. This model relies on:
• Cross-functional engineering depth
• Automation expertise across platforms and vendors
• AI and digital platform integration capabilities
• Pre-engineered templates and solution blocks for rapid deployment
FIGURE 3: AI-driven automation stacks unify engineering, platforms and digital intelligence to scale plant performance.
Courtesy: L&T Technology Services
Reengineering the future
The reengineering of modern factories is underway, powered by a synergy of AI technologies, digital engineering and automation paradigms. And manufacturers worldwide are no longer asking whether to modernize but how to modernize at scale, across plants and with measurable business outcomes.
In the ongoing transformation, companies that embrace modernization not just as a technology upgrade but as a complete reinvention of the plant — combining engineering discipline, domain knowledge, digital fluency and AI — stand to lead the curve. They will drive the creation of factories that are not only efficient but also future ready and are at the forefront of the AI-automation revolution. PE
Subrat Tripathy is the chief segment officer of process industries at L&T Technology Services (LTTS).
Insightsu
Automation insights
uAutomation can assist process industries meet demands even as volatility continues.
uAI-led technologies can help fill skill gaps in process industries.
uCompanies that embrace modernization not just as a technology upgrade but as a complete reinvention of the plant will be at the forefront of the AI-automation revolution.
Configure a workbench to meet your needs. Configure a work bench to meet your requirements.
•Proline’s 3D configurator allows you to choose from four models, eight work surface choices and three frame colors.
•Choose from a heavy duty four leg design, cantilever design , hand crank adjustable or electric height adjustable.
•We have the workbench you need in stock and ready to ship in five days or less.
•With a vast array of modular accessories and options available, you design the bench you need.
Try it today ! www.1proline.com
ENGINEERING SOLUTIONS
ARTIFICIAL INTELLIGENCE
Buddy Lee, MBA, CRL, CMRP, Dandridge Tennessee
Incorporating artificial intelligence and machine learning into heavy-asset industry
Artificial intelligence (AI) and machine learning (ML) are integral to industrial plant engineering, particularly in asset-intensive sectors such as power generation, chemical processing, refining and advanced manufacturing.
Industr ial plant engineering has historically relied on deterministic models, first-principles analysis and human expertise to design, operate and maintain complex production systems. But these foundational approaches are being outpaced by the scale, complexity and data intensity of modern industrial facilities.
Learningu
Objectives
• Attain a basic understanding of industrial artificial intelligence/machine learning (AI/ML) core concepts such as ML types and algorithms/models.
• Learn about common data sources and applications for ML.
• Understand a case study ML model application for vibration monitoring bearing failure prediction on paper machine rolls as compared with a human analyst for a seven-year vibration database with multiple recorded failures.
The data volume from wireless vibration sensing has exceeded the limits of manual and rule-based data analysis for decision-making. Large volumes of operational and maintenance data are generated from sensors embedded in rotating equipment, distributed control systems (DCS), process historians, computerized maintenance management systems (CMMS) and enterprise resource planning platforms. Artificial intelligence (AI) and machine learning (ML) offer mechanisms to digest and transform this data into actionable insight.
ML models are applied tools in narrow use cases that support asset reliability, process stability, energy efficiency and safety. True AI has not yet achieved the same acceptance for engineering uses, but generative AI applications in nuclear plant relicensing documentation are growing rapidly and others will follow. When properly implemented, AI and ML will augment engineer-
ing judgment, advising users through agentic AI advisors using causal analysis products that enable earlier fault detection, improved root-cause analysis and optimized operational strategies.
Integrating AI and ML into an industrial engineering setting requires practical application. Plant managers will need to understand key concepts and common algorithms to address the organizational and technical considerations required for sustainable adoption of AI and ML in heavy-asset industries.
Artificial intelligence in an industrial context
AI refers to computer systems capable of performing tasks that normally require human intelligence and is often confused with machine learning. But they have separate meanings. AI concerns reasoning, learning and autonomous decision-making, while ML is usually concerned with pattern recognition and learning. In industrial environments, AI systems typically operate within defined boundaries called guardrails and support specific engineering or operational objectives rather than exhibiting generalized intelligence.
Examples of AI capabilities in plant engineering include:
• Automated fault detection and diagnosis
• Anomaly detection in process variables
• Decision support for maintenance planning
• Optimization of control setpoints
These systems are often embedded within existing operational technology platforms, such as advanced process controllers and condition monitoring systems. Digital twins are configured from
available data models of existing physical systems and may be used in design engineering or operational analysis exercises.
Machine learning as a subset of AI
Machine learning is a subset of AI focused on algorithms that learn patterns from data rather than relying solely on programming. In industrial plant engineering, ML models learn relationships between inputs such as vibration, temperature and pressure and outputs such as equipment health, product quality and energy consumption.
ML is particularly valuable in environments where:
• Physical models are incomplete or complex
• Equipment behavior changes over time due to wear or fouling
• Multivariate interactions obscure root causes
Machine learning paradigms: Supervised, unsupervised and reinforcement learning
ML can be trained under three different paradigms — supervised learning, unsupervised learning and reinforcement learning.
Supervised learning
Supervised learning uses labeled data with historical examples (where outcomes are known) to train predictive models. In industrial settings, this often includes failure histories, maintenance records or quality outcomes.
Common applications:
• Remaining useful life estimation
• Failure mode classification
• Quality prediction
Typical algorithms:
• Linear and logistic regression
• Random forests
• Support vector machines
• Neural networks
Unsupervised learning
Unsupervised learning identifies patterns in unlabeled data. This is particularly useful in industrial environments where failure events are rare, but large volumes of normal operating data exist.
Common applications:
• Anomaly detection
• Process state clustering
• Baseline behavior modeling
Typical algorithms:
• k-means clustering
• Principal component analysis (PCA)
• Autoencoders
Reinforcement learning
Reinforcement learning involves agents that learn optimal actions through interaction with an environment, receiving rewards or penalties based on performance. While still emerging in heavy industry, RL shows promise in control and optimization problems.
Potential applications:
• Advanced process control optimization
• Energy management
• Autonomous operational decision-making
Data foundations for AI and ML in industrial plants
AI and ML performance is fundamentally constrained by data quality and contextual integrity. Industrial plants typically draw from multiple data sources:
‘ML models learn relationships between inputs such as vibration, temperature and pressure and outputs such as equipment health, product quality and energy consumption.’
FIGURE 1: Waveform, Fast Fourier Transform and Trend Graphics.
Courtesy: Buddy Lee
ENGINEERING SOLUTIONS
• Improved spare parts planning
• Enhanced safety
• Sensors and instrumentation (vibration, temperature, flow, pressure, PH,)
• Control systems (DCS, PLC)
• Asset systems (CMMS, EAM)
• Laboratory reports and quality testing documents
• Operator logs and narratives
For ML models to be effective, data must be contextualized or linked to assets, operating states, process conditions and maintenance events.
Key ML applications in plant engineering
There are core areas in which ML is particularly effective in plant engineering. These include:
Predictive maintenance and asset reliability
Predictive maintenance is one of the most mature and impactful applications of ML in industrial engineering. By analyzing condition monitoring data, ML models can detect early degradation patterns long before functional failure occurs.
Benefits include:
• Reduced unplanned downtime
• Optimized maintenance intervals
ML complements traditional reliability tools such as vibration analysis, oil analysis and thermography by identifying subtle multivariate patterns that may be invisible to single-parameter thresholds.
Process optimization and control
AI and ML models can analyze thousands of process variables simultaneously to identify optimal operating regions. Unlike static control strategies such as setpoint alarms, ML-based systems adapt to changing feedstocks, environmental conditions and equipment states.
Applications include:
• Yield optimization
• Energy efficiency improvement
• Throughput maximization
• Emissions reduction
These systems often function as advisory layers, providing recommended setpoints that operators or control systems validate before implementation.
Energy management and sustainability
Energy costs represent a significant portion of operating expenses in industrial plants. ML models
FIGURE 2: Receiver Operating Characteristic and Area Under the Curve Graphics for Operational, Degraded and Failed Bearing Classifications.
Courtesy: Buddy Lee
can forecast energy demand, optimize load distribution and identify inefficiencies across equipment and processes.
Applications include:
• Boilers, heat recovery steam generators and turbine optimization
• Demand response strategies
• Carbon intensity tracking
Such capabilities align AI adoption with broader sustainability and decarbonization objectives.
Safety, risk and abnormal situation management
ML-based anomaly detection can identify deviations from normal operating conditions that precede safety incidents. When integrated with alarm management and operator decision support systems, AI can enhance situational awareness without overwhelming personnel with nuisance alarms.
Human–machine collaboration in engineering practice
Industrial AI models should support human engineering judgment. Subject matter expert (SME) Engineers provide contextual understanding, failure mode knowledge and ethical oversight that AI algorithms lack.
Effective AI systems:
• Provide explainable outputs
• Integrate with existing workflows
• Enable engineers to validate recommendations
Explainable AI techniques are particularly important in regulated industries, where transparency and auditability are essential.
ML implementation challenges and best practices
ML is only as good as the data provided. Therefore, it’s critical to consider certain challenges and best practices when implementing ML in industrial applications.
Data quality and governance
Poor data quality remains the primary barrier to successful AI initiatives. Sensor drift, missing data and inconsistent asset hierarchies can significantly degrade model performance.
Best practices include:
• Standardized asset taxonomies
• Robust data validation processes
• Clear ownership of data stewardship
Organizational readiness
AI adoption is as much a cultural transformation as a technical one. Engineering teams must trust the models, understand their limitations and be trained to use them effectively. Therefore, Leadership plays a critical role in:
• Setting realistic expectations
• Aligning AI initiatives with business objectives
• Investing in workforce capability development
Model life cycle management
Industrial ML models require ongoing monitoring, retraining and validation as equipment and processes evolve. Without governance, models may silently degrade, leading to inaccurate recommendations.
Generating value
Advanced industrial users refine data with machine learning to segment, classify or predict results. The idea is to have the system use automated statistics to do the things that humans do not have the bandwidth to do, but at which computers excel. The overall process consists of six steps: Load data, build the model,
922 - 4336
ENGINEERING SOLUTIONS
‘
By leveraging existing facility operations and maintenance
data, AI and ML can enhance reliability, optimize processes, improve energy efficiency and strengthen safety performance.’
register the model, deploy it, monitor alerts and then retrain and run new experiments.
One way to gain insight to data is to query it and today’s AI/ML systems can be trained using models that use a large language database. These models are typically trained on very large datasets, such as the entire content of the internet. These models can and do generate errors, so in our industrial case the large-language model (LLM) used is limited to the information available for the asset or system, including the failure modes and effects analysis history and documented functional failures.
By using a copilot, an AI-generated agent, one can query the model and ask for predictions and can pin the results into dashboards with real-time data updates. This allows predictive analysis on the fly with information previously unavailable in real-time. Where uses previously had to find, discover, analyze and document on their own, (a slow process) they can now use the power of pretrained generative models constrained to a known body of knowledge about equipment, systems and processes.
ChatGPT is notation for a generative pretrained transformer, which can be queried and used by simply typing a
question or statement to prompt some response from the LLM. The chat portion comes from the use of text chat style boxes for the prompt.
Imagine how efficiently the system can be implemented using piping and instrumentation diagram and other information sources for the system and how much knowledge capture can be accomplished and made available to future engineers and maintenance folks. Today’s AI/ML systems are just beginning to scratch the surface of using tools like knowledge graphs and LLMs to guide and inform people to make the right decisions at the right time.
A knowledge graph is an infinite network diagram canvas, used for rapid systems and equipment analysis and insights. Links to summary information, health scores, alerts, meta data and analytics are provided for end users.
Knowledge graphs allow users to
drill down to systems or assets of interest and query, using a chat-style interface, the underlying data structures. For the example shown here the boiler feed pump (BFP) is reporting a health score of 74% based on the measurements from the instrumentation contextualized to the BFP asset. An alert has been thrown, and the next step would be to check which contributing factors are triggered, either singly or in combination, to provide an insight based on the failure mode. If a Failure Modes and Effects Analysis (FMEA) report exists, the KG can use it to generate an accurate alert with causal probability. This is a great way to capture existing tribal knowledge about the processes and machinery assets in a plant. After repairs, the health score should rise if the correct repairs were, in fact, done. Each system user can then have a personalized dashboard of the trended data pertinent to their responsibilities.
Paper machine roll
AI and ML can enable modern industrial plants
AI and ML are powerful enablers for modern industrial plant engineering, operations and maintenance. By leveraging existing facility operations and maintenance data, AI and ML can enhance reliability, optimize processes, improve energy efficiency and strengthen safety performance. The key to the successful application of AI and ML models demands high-quality data, contextual understanding, advanced algorithms, disciplined governance and strong human-machine collaboration. For plant engineers, operators, maintenance personnel and engineering leaders, the path forward is not to replace traditional engineering methods and operational paradigms, but to augment them. When AI and ML are integrated thoughtfully into existing
reliability, maintenance and operational frameworks, they become catalysts for sustained operational excellence and long-term asset value creation. PE
Buddy Lee provides companies improve performance through the application of artificial intelligence and machine learning technologies, as well as condition monitoring.
Insightsu
Industrial engineering insights
uArtificial intelligence (AI) and machine learning (ML) require special organizational and technical considerations.
u ML relies on high-quality data to perform at its best.
uML-based systems adapt to changing feedstocks, environmental conditions and equipment states.
25_000529_Plant_Engineering_APR Mod: February 7, 2025 10:20 AM Print: 02/20/25 page 1 v2.5
ENGINEERING SOLUTIONS
Dean Armistead and Sebastien Blais, Salas O’Brien Canada Inc., Quebec City
Ways to automate changeover for the era of mass customization
Frequent product changeovers are costing manufacturers valuable production time, but automation is changing the economics.
TObjectives Learningu
• Identify changeover bottlenecks: Understand where manual changeovers create the most delays, from repeatability issues to parts management and how these inefficiencies compound across production runs.
• Recognize automation tools that accelerate changeovers: Learn which technologies, from recipebased control systems to servo motors and MES integration, to deliver the fastest improvements in changeover speed and consistency.
• Assess return on investment through multiple lenses: Explore how automated changeovers generate value not just in time savings, but through improved OEE, reduced waste, better scheduling flexibility and planning and enhanced sustainability.
he manual changeover process remains one of manufacturing’s most persistent sources of inefficiency. But better planning and automation are changing that. By making changeovers faster, more consistent and less dependent on individual skill sets, automated systems are turning what was once a necessary drain on productivity into a competitive advantage.
To understand why this shift matters, consider what’s happening on the floor. A typical packaging facility during a format change reveals operators searching for change parts, mechanics adjusting guide rails by eye and production managers watching valuable runtime slip away. When the line restarts, there’s often a lengthy ramp-up period as operations staff fine-tune settings that weren’t quite right to reach the projected line overall equipment effectiveness (OEE).
The root of this inefficiency is repeatability. Even in well-managed facilities, without mechanical jigs or adjustment blocks to standardize guide rail openings and machine settings, each changeover becomes a new interpretation, leading to bridging or fallen containers or excessive pressure that could damage containers. Even with detailed procedures, the process remains prone to individual judgment.
Warehousing and market constraints are pushing manufacturers toward run-to-order production with smaller batches and more frequent format changes. Meanwhile, experienced operations personnel,
mechanics and electricians are retiring and new staff often lack the hands-on experience that once made manual changeovers manageable. These pressures make the cost of inefficiency impossible to ignore.
The high cost of inconsistent changeovers
Before exploring automation solutions, it’s important to understand what’s truly at risk during a changeover. In high-speed packaging operations, especially in breweries and beverage facilities, clearing an entire line from depalletizer to palletizer can take more than an hour of runtime. Many plants have adapted by inserting gaps in production — pausing the front of the line while the back end continues processing the previous product — reducing that window to about 20 minutes. However, even in the best-case scenario, significant capacity is lost when changeovers happen multiple times during a shift.
The less obvious cost occurs during the restart. After a manual changeover, lines rarely reach full target efficiency right away. Instead, there’s a rampup period where operators and maintenance staff find a missed adjustment, a guide rail that’s slightly misaligned or an inspection system or coder not configured for the new product. Overall line efficiency might start at a low level and take significant time to climb back to the targeted line efficiency. Every minute spent in that ramp-up phase is production capacity lost and it pushes scheduled runs later into shifts that are already short-staffed.
This efficiency drag becomes especially painful when manufacturing is driven by customer orders instead of building inventory. The global economy has prompted many manufacturers to produce in various countries or shift production between facil-
ities to control costs. This flexibility demands the ability to change formats quickly and confidently, knowing that the line will perform as expected from the moment it restarts.
Automation tools that make a difference
The most significant automation improvement for changeover comes from recipe-based conveyor control systems and machine configurations. These systems automatically adjust conveyor speeds and machine parameters based on the selected product format. Programmable logic controller (PLC)based conveyor speeds, using sensors and real-time speed data from upstream and downstream equipment, can be modulated to meet machine and conveyor requirements.
Instead of operators manually adjusting each section of the conveyor, the entire line synchronizes to the new format with a recipe selection. This prevents overpopulation and jams while guiding accumulation and mass conveyors to operate at optimal speeds for the product being run. Newer equipment (and some older equipment) can also be equipped with methods (both automated and manual) to achieve repeatable changeovers, greatly reducing the ramp-up time.
The engineering behind these systems involves calculating conveyor widths to find the optimal operating condition to satisfy all formats. This is a mechanical setup that works well across all format
variations, avoiding the need for constant physical adjustments. By maintaining fixed widths for mass conveyors and reserving manual guide adjustments for sensitive areas near single-file operations, plants can significantly reduce the number of points during a changeover.
Recipe systems also offer verification before production begins. By assigning the conveyor PLC as the master control, engineers can program the system to verify that all equipment on the line — fillers, packers, inspectors and coders — are set for the same format. This prestart check identifies mismatches that could lead to costly waste, reducing hours of production errors to just a few minutes of troubleshooting before any product is at risk.
Servo motors are a major advancement, especially in packaging equipment like case packers. Where manual changeovers once required operators or mechanics to physically adjust star wheels, guide rails and positioning devices, servo-driven systems now automate these adjustments according to the selected recipe. This eliminates variability caused by individual operators preference — and supports consistent changeovers.
The integration with manufacturing execution systems (MES) advances this process by directly sending recipes from production scheduling to line equipment. Instead of operators manually choosing formats and risking errors, the MES automatically configures the line based on the production order.
FIGURE 1: Automated changeovers with improved repeatability double starting overall equipment effectiveness from 30% to 60%, significantly reducing lost production capacity (shaded area) during ramp-up. Courtesy: Salas O’Brien.
‘Every minute spent in that ramp-up phase is production capacity lost and it pushes scheduled runs later into shifts that are already short-staffed. ’
ENGINEERING SOLUTIONS
reviews backup generation infrastructure, an area where automation is playing a growing role in improving monitoring, reliability and system readiness during changing operating conditions.
Courtesy:
This direct data transfer prevents manual entry mistakes that could be costly to fix.
Optimizing production through strategic changeovers
With faster, more reliable changeover mechanics in place, attention can shift to using that speed strategically to further reduce downtime. Automation does more than just make individual changeovers quicker; it enables smarter production scheduling that minimizes the number and complexity of changeovers needed.
In food and beverage production facilities handling multiple flavors or product types, the order of production runs can significantly influence cleaning requirements between products and, consequently, downtime. Additionally, planning more complex changeover tasks, such as a seamer format change during nonproduction time (e.g., on the weekend), although more costly per hour, could save valuable production time.
The principle is simple but often overlooked: organize changeovers to reduce cleaning and changeover times between products. For example, in facilities making rum or other spirits, this means starting with unflavored white products, then progressing through stronger flavors before switching to amber and finally dark varieties. Each step in that sequence requires minimal cleaning because the previous product will not affect the flavor of the new product. Running in reverse — starting with dark rum and switching to white — would need extensive cleaning of the filler and process equipment, causing additional loss of time and using considerable water, chemicals and energy.
This approach from the food and beverage industry applies to other industries. By grouping compatible products and planning changeover sequences that move from lighter to heavier flavors or from similar-size packages, plants can reduce many of the time-consuming cleaning cycles and changeovers that otherwise disrupt production. When automation enables quicker mechanical changeovers, this strategic sequencing becomes even more important because the main remaining delay — cleaning — can be minimized through better planning.
Considerations for changeover automation
Implementing automated changeover systems requires assessment of existing equipment and production needs. What skill level is currently required to perform a changeover and can automation reduce that requirement? The aim on older or difficult areas to changeover is to transfer changeover tasks from mechanics and electricians to operators who can work with color-coded change parts, mechanical jigs and servo-driven adjustments to simplify these tasks.
This doesn’t mean removing the need for skilled workers. Instead, it means freeing those valuable staff from repetitive changeover tasks so they can focus on troubleshooting, optimization and maintaining more complex automated systems. When operators can manage routine format changes with clearly marked parts and automated positioning systems, maintenance staff can devote their time to higher-value activities that truly require their expertise, which will pay off in higher OEEs.
Color coding and engraving of change parts act as a simple yet effective link between manual and automated systems. Parts that can be inserted in an incorrect orientation or position should have “positioning keys” or guiding pins to enable correct installation. By marking all change parts for a specific format with the same color and engraving them with format specifications, plants create visual cues that are accessible even for color-blind operators. This reduces the time spent searching for parts and makes sure the correct components are installed together.
Equally important is inspecting change parts as part of the changeover procedure. They should be
FIGURE 2: Salas O’Brien
Salas O’Brien
fully inspected at the completion of the changeover. Detecting damaged parts immediately after removal allows maintenance to repair or replace them before the next run on of that format, preventing costly discoveries of damaged parts during the next changeover.
For equipment that requires heavy or complex change parts, such as blow molder for plastic bottle production, robotics can manage the physical changeover of the heavy molds. These molds are large castings with water jackets for cooling, often weighing more than 50 pounds. Having operators lift and position these parts introduces safety hazards and risks damaging expensive, precision tooling. A robotic changeover system handles the weight, precisely positions the mold every time and removes ergonomic concerns associated with operators manipulating heavy equipment.
The appropriate level of automation depends on the specific application, but most successful implementations share common features: control over conveyor speeds, recipe-based setup, communication among all PLCs on the line and minimizing operator intervention to facilitate repeatability of changeovers. These core elements offer the flexibility to handle various products while supporting consistent performance that builds reliability.
Where ROI shows up
The return on investment from automated changeovers appears in several areas. The most obvious is time, as shorter changeover windows free up significant production capacity, especially in facilities that perform multiple format changes per shift. However, the financial benefits go far beyond just reducing downtime.
Improved efficiency: When each piece of equipment operates at high individual efficiency, but the line as a whole runs at a reduced efficiency due to induced faults between equipment and poor accumulation management, the bottleneck is in the system design and/or the controls. Properly designed accumulation with recipe-based control can increase line efficiency by masking individual machine faults with accumulation and controlling machine speeds to allow for accumulation regeneration, allowing the same equipment fleet to produce significantly more output per hour. This efficiency improvement directly reduces the cost per unit, making the operation more competitive.
Quality improvements: Automated verification systems identify recipe mismatches before any product reaches the equipment, preventing waste caused by running with incorrect settings. Reliable changeovers reduce the ramp-up time after format changes, enabling the line to return to target OEE more quickly. Additionally, by ensuring date coders and track-and-trace systems receive correct information directly from production scheduling, plants can avoid waste generated by incorrectly coded product.
Flexibility: Perhaps most importantly, automated changeovers allow manufacturers to accept smaller orders and more specialized products that manual changeover economics would otherwise make unprofitable. When format changes take an extended time and returning to the line’s normal OEE is difficult, plants naturally lean toward longer production runs of fewer formats. When changeovers occur at a predictable time and restart performance is consistent, the economics of smaller batches improve significantly. In markets where customers increasingly expect customization and variety, this flexibility can be the difference between winning and losing business.
Mass customization is already here
Manufacturers that can quickly adapt to diverse customer needs while keeping efficiency and quality will gain market share from those that can’t. Automated and predictable changeover systems and methods lay the groundwork for that agility, transforming what was once a necessary evil into a true competitive advantage.
The investment case is straightforward: identify where manual changeovers cause the most significant delays and quality issues, select the appropriate tools that address these specific problems and implement systems to enhance both speed and consistency. The plants that make this shift successfully will develop the flexibility to succeed in a market where customer demands are increasingly varied and traditional economies of scale matter less than the ability to switch formats quickly and confidently. PE
Dean Armistead is Principal, Technical Director at Salas O’Brien Canada Inc. Sebastien Blais is Vice-President, Group Director – Automation at Salas O’Brien Canada Inc.
‘The return on investment from automated changeovers appears in several areas. ’
Insightsu
Changeover insights
u By replacing inconsistent manual processes with recipe-driven automation and smarter planning, manufacturers are transforming the changeover from a costly source of downtime and variability into a faster, repeatable and strategic competitive advantage.
uRecipe-based control systems, servo motors and MES integration are cutting changeover times from hours to minutes, allowing plants to say yes to smaller orders and customized products that were once unprofitable.
ENGINEERING SOLUTIONS
SAFETY AND PPE
Philip Jacklin, Diversified Fall Protection, Virginia Beach, Virginia
Focus on these answers to fall protection equipment inspection questions
Fall protection equipment inspections ensure equipment is working properly and will keep workers safe.
It is very likely that the same workplace hazards will continue to harm workers all over the country. Each year, falls are one of the most common causes of injury and fatality, with steady increases in recent years, according to the U.S. Bureau of Labor Statistics. Additionally, fall protection general requirements have been the leading violation cited by the Occupational Safety and Health Administration (OSHA) for the past 15 consecutive years.
inspections on all pieces of fall protection equipment. California requires construction companies to conduct semiannual equipment inspections as well. Building owners and employers should refer to local OSHA authorities to confirm their inspection schedule is legally compliant.
Pre-use inspection: These are sometimes referred to as “daily” inspections but are actually required by OSHA each time a worker is about to use their fall protection equipment. The user of the equipment is responsible for conducting this inspection before donning the equipment. If equipment fails inspection, it must be immediately reported to the competent person and replaced before beginning elevated work again.
• Understand what inspections are legally required for fall protection equipment.
• Review who must perform equipment inspections.
• Know how frequently fall protection equipment must be inspected. Objectives
Many plants and facilities have committed to increasing worker safety and providing fall protection equipment to their workers. However, routine inspection and maintenance of the equipment is an essential part in ensuring the success of a fall protection program. Equipment inspections are straightforward, but many factors can affect a program’s efficiency or legal compliance. If inspections are not performed thoroughly or frequently enough, workers could be subject to faulty equipment that does not provide the anticipated safety factor.
Q: How often do I have to inspect my fall protection equipment?
A: Fall protection must be inspected by the authorized person before each use.
OSHA 29 CFR 1910 for general industry employers and OSHA 29 CFR 1926 for construction employers require daily “pre-use” and annual
Annual inspection: Annual inspections follow a similar process to the daily “pre-use” inspections performed on fall protection equipment. However, pre-use inspections are performed by the equipment user. When documenting the inspection, the organization’s competent person must notate the following information regarding the equipment:
Annual equipment inspection documents must be retained for the life of the equipment.
Q: What fall protection equipment must be inspected?
A: Every piece of fall protection equipment, except guardrail.
Anchors:
• Temporary anchorages: cross arm straps, beam gliders, etc.
• Permanent anchorages: anchor posts, d-ring anchors, etc.
• Noncertified anchorages: fall protection anchors purchased from a manufacturer, distributor, retailer, etc. and installed according to the manufacturer's specification.
• Certified anchorages: after initial installation, anchors that are “certified” by qualified person or engineer for special circumstances, like horizontal lifelines, suspended access systems and more.
Body harnesses: Users must also check for appropriate fit and dorsal d-ring placement according to manufacturer’s specifications.
Connection devices:
• Lanyards
• SRL
• Horizontal lifelines
• Vertical lifelines
• Ladder safety system shuttles
Climbing/rescue devices:
• Emergency rescue ladders
• Ladder safety systems
• Permanent ladders
• Portable ladders
Q: How do I perform an equipment inspection?
A: There are three main components for users to inspect:
Manufacturer tags are intact and legible: This OSHA requirement ensures the equipment can be identified if involved in a fall incident. It also contains the detailed product information required for annual inspections.
No signs of deployment: All pieces of fall protection equipment are rated to arrest only one fall.
After that, the equipment must be removed from service and replaced. ANSI Z359-compliant products will include a deployment indicator somewhere on the equipment assembly.
For example, harnesses have cross-over stitching on the rear straps that will tear to indicate a fall has occurred. Or many snaphook attachments on SRLs will reveal a red line if the equipment has arrested a fall. Employers must train their workers on how to properly perform this part of their inspection and should reference the product’s instruction manual to learn about the deployment indicators on their specific equipment.
Harnesses used with a “tripped” deployment indicator cannot be guaranteed to work properly and protect the worker from major injury.
Physical signs of damage, defect or dysfunction: The user must thoroughly inspect the webbing, d-rings, connectors and other components of the equipment for wear, tears, cuts, holes, frays or other damage that could cause the equipment to fail. Too much ultraviolet (UV) exposure (aka sunlight) on equipment such as harnesses, lanyards and ropes can damage the elasticity of the webbing, causing it to become brittle and frail. Discoloration is the most common sign of UV damage. Proper storage of the equipment in a locker, office or jobsite trailer can help prolong the life of the equipment and ensure safe operation for its user.
‘If equipment fails inspection, it must be immediately reported to the competent person and replaced before beginning elevated work again.’
FIGURE 1: Workers performing rooftop fall protection equipment inspection. Courtesy: Diversified Fall Protection
ENGINEERING SOLUTIONS
‘Equipment inspections are a pivotal part of any fall protection program.’
At this stage, users should confirm their harnesses fit correctly according to the manufacturer's specifications. Proper harness fit and dorsal d-ring placement can prevent more severe injury during a fall.
Q: Who can perform equipment inspections?
A: Pre-use inspections are conducted by the equipment’s end user and must have been trained by the organization’s competent person.
Each organization must have (at least) one employee designated as its competent person. This person is the facilitator of their organization’s fall protection program and is responsible for conducting annual equipment inspections, among other duties.
In larger organizations, it quickly becomes clear why multiple competent persons can help shoulder the many tasks required to maintain a comprehensive fall protection program. That is, one that operates in accordance with local OSHA jurisdictions and is also effective at preventing falls and protecting workers from injury. Compliance is fine, but injury prevention is the goal.
Each employee designated to be their organization’s competent person must have a valid certification from an ANSI-compliant training organization and that certification must be refreshed every two years. If an organization chooses to do so, their competent person can designate a third-party equipment inspector to conduct their annual inspections.
However, the inspector then assumes liability for the fall protection system's proper functioning. The workers, of course, must use the equipment according to the manufacturer’s instructions. Equipment inspectors must be trained at a competent person level, at a minimum.
rated at a minimum of a 2:1 safety factor for the anticipated fall forces.
Anchor posts and davit arms used for suspended access systems (window washing, rope descent, swing stage systems, etc.) must be recertified every 10 years. In this recertification process, the qualified person must, among other qualitative metrics, use a pull-testing device to confirm the anchorage is capable of withstanding static loads and dynamic loads that would be incurred from a fall.
Q:We recently performed annual inspections and failed many pieces of equipment. What could that teach us about our fall protection program?
A: In theory, if users are diligently performing pre-use inspections, there should be no failures during annual inspections. Because this equipment made it back to the competent person, it might indicate that the detail was overlooked or ignored by the worker. In those cases, we recommend employers retrain their workers and make an emphasis on the importance of pre-use inspections. While OSHA does not require these inspections to be recorded, many organizations require employees to document their daily inspections to increase accountability. Safety is everyone’s responsibility. The employer is responsible for providing the fall protection equipment and the authorized person is responsible for inspecting the equipment and using it properly every time.
Fall protection success
Fall protection insights
uThis article will answer some of the most common questions building owners and employers have regarding their fall protection equipment inspections.
uOSHA defines what fall protection equipment must be used and its inspection schedule.
Q: I have certified anchors in my facility. Is recertification part of the inspection process?
A: Anchor certifications are related, but not the same thing. Noncertified and certified anchors are both subject to typical annual inspections as described earlier.
Certified anchorages for active fall protection systems (horizontal lifelines, single-point systems, etc.) must be recertified every five years. Among other qualifications, an engineer or qualified person must confirm that the anchorage system is
Equipment inspections are a pivotal part of any fall protection program. Companies are more than empowered to maintain inspection schedules and records in-house and are also encouraged to reach out to their fall protection providers for assistance. When manufacturers, building owners, employers and end users work together to create more robust fall protection programs, workers everywhere will benefit from those efforts.
Falls are preventable, but only if organizations take the necessary time to plan, prepare and educate their workers. If we put in the effort today, we can potentially save lives tomorrow. PE
Philip Jacklin is Continuing Education Program Manager at Diversified Fall Protection.
From planned projects to last-minute needs, The Home Depot delivers on your schedule—same day, next day or any day you need to keep the job moving. When and Where You Need It.
Rick Ellis, Director, Audience Growth 303-246-1250, REllis@WTWHMedia.com
Custom reprints, print/electronic: Matt Claney, 216-860-5253, MClaney@WTWHMedia.com
Information: For a Media Kit or Editorial Calendar, go to https://www.plantengineering.com/advertise-with-us.
Letters to the editor: Please e-mail us your opinions to ARozgus@WTWHMedia.com. Letters should include name, company, and address, and may be edited.
Less energy costs. More performance.
Driving Efficiency: DR2C Permanent Magnet Motor
Engineered for ultra-premium efficiency, the DR2C Permanent Magnet Motor from SEW-EURODRIVE delivers the performance today’s operations require while reducing long-term energy costs. With up to 50% lower energy losses than standard IE3 motors, the DR2C reduces total cost of ownership (TCO) and enhances reliability. Built with Interior Permanent Magnet (IPM) technology, offering high torque density in a compact, space-saving design, enabling smaller motor sizes without sacrificing power. Optimized for continuous duty and high-cycle start/stop operation, the DR2C performs efficiently across a wide speed range. Ideal for conveyors, automated logistics, packaging lines, and manufacturing systems.
