International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 09 | Sep 2024
p-ISSN: 2395-0072
www.irjet.net
ANALAZTION OF BOILER PERFORMANCE WITH RESPECTIVE CHEMICAL SCALE FORMATION BY USING AI TECHNOLOGY 1Sanjay Thangamalar,2Santhosh Anbalagan,3A C Mariappan,4G Peter pakiyaraj 1Final year B.E Marine Cadet, Department Of Marine Engineering, PSNCET , Tirunelveli , Tamilnadu 2Final year B.E Marine Cadet, , Department Of Marine Engineering, PSNCET, Tirunelveli ,Tamilnadu 3Assistant Professor, Deptment Of Marine Engineering, PSNCET, Tirunelveli ,Tamilnadu
4Assistant Professor, Department Of Marine Engineering, PSNCET, Tirunelveli ,Tamilnadu
-------------------------------------------------------------***-------------------------------------------------------------ABSTRACT: 1.4 Predictive Analytics: Predicting when a boiler Boiler water treatment uses chemicals to condition and treat boiler feed water. Some common chemicals used in boiler water treatment include:
component is likely to Fail, allowing for proactive maintenance. 1.5 Real-time Monitoring: Real-time monitoring on boilers involves continuously tracking and analyzing data from various sensors and systems to ensure safe, efficient, and reliable operation.
Oxygen scavengers: Remove dissolved oxygen from boiler water to prevent corrosion.
Alkalinity builders: Raise the pH of boiler water to protect
1.6 Optimization: achieve maximum efficiency, reliability, and safety while minimizing energy consumption, emissions, and maintenance costs.
the boiler from corrosion and scale buildup.
Scale inhibitors: Prevent scale from forming on the inside of the boiler by coating the metal surfaces.
2. AI technologies used:
Corrosion inhibitors: Protect the boiler from corrosion.
2.1 Neural Networks: A neural network on a boiler is a machine learning model that uses artificial neural networks to predict, monitor, and optimize boiler performance.
Phosphates-dispersants: Neutralize the hardness of water by forming tri calcium phosphate.
Natural and synthetic dispersants: Increase the dispersive
properties
of
the
conditioning
2.2 Decision Trees: Decision Trees on a boiler are a machine learning model that uses a tree-like structure to predict, classify, or optimize boiler performance.
products.
Sequestering agents: Act as inhibitors and implement a threshold effect
2.3 Clustering: Clustering on a boiler is a machine learning technique that groups similar data points or operating conditions into clusters
Keywords: ACCDM,WSB,ML,RTM.
1.INTROTUCTION:
Regression Analysis: For predicting scale formation and boiler performance.
Scale formation using AI technology involves: 1.1 Data Collection: Gathering data on boiler operating conditions, water quality, and performance metrics.
2.4 Benefits: 1.Improved Boiler Efficiency
1.2 Machine Learning (ML) Model Development: Machine learning in boilers refers to the application of advanced data analysis and modeling techniques to predict, detect, and optimize boiler operations.
2.Reduced Maintenance Costs 3. Extended Equipment Life 4. Enhanced Safety
1.3 Pattern Recognition: Pattern recognition in boilers involves using algorithms to identify and interpret meaningful patterns in data generated by various sensors and monitoring systems.
© 2024, IRJET
|
Impact Factor value: 8.315
By leveraging AI technology, boiler operators can proactively address chemical scale formation, ensuring optimal performance and minimizing downtime.
|
ISO 9001:2008 Certified Journal
|
Page 542