Paper For Above instruction
Introduction
Control charts are essential tools in statistical process control (SPC) to monitor process stability and performance (Montgomery, 2019). This case study examines the variability of a circuit board production process at Fujiyama Electronics, Inc., focusing on the measurement of drilled hole spacing, which ideally should be 5 cm apart. Excessive variability between two drilled holes indicates potential process issues that need to be identified and addressed. Using sample data collected over multiple shipments, this analysis calculates control chart statistics, constructs control charts, and interprets outcomes to facilitate continuous process improvement.
Calculating Control Chart Statistics
The first step involves calculating the overall process mean (X■■), the average range (R■), and the corresponding control limits for both the X■ and R charts. Based on the given data, the grand mean (X■■) is 5.0915, calculated by averaging all sample means. The average within-sample range (R■) is approximately 0.85, derived by averaging the individual range values from each sample. Using standard control chart factors obtained from Shewhart’s tables (Montgomery, 2019), the control limits are then established.
The control limits for the X■ chart are computed as follows: LCLx■ = X■■ - A2 * R■, and UCLx■ = X■■ + A2 * R■, where A2 is a process factor based on sample size. For a sample size of 4, A2 is approximately 0.73. The calculations result in an LCL of about 4.28717 and a UCL of about 5.89583, with a center line at 5.0915. For the R chart, the control limits are derived using constants D3 and D4: LCLR = D3 * R■, UCL_R = D4 * R■ With D3 = 0 and D4 = 2.114 for a sample size of 4, the control limits are
approximately 0 and 1.81, respectively. These control limits set the bounds for evaluating process stability.
Creating Control Charts
The next phase involves plotting the individual sample means and ranges on their respective control charts. The X■ chart displays each sample mean against the central line, with control limits indicating acceptable variation. The R chart illustrates sample ranges relative to the calculated limits. Several out-of-control points are evident where sample means fall outside the control limits, signaling potential assignable causes of variability.
Interpreting Out-of-Control Conditions
Analysis of the control charts reveals specific out-of-control points. For example, sample number 12 shows a mean significantly below the LCL, suggesting a special cause leading to reduced hole spacing during that sample period. Similarly, sample 24 displays a mean exceeding the UCL, indicating excessive variation. These outliers are critical as they reflect non-random variation that could affect product quality. Importantly, the analysis focuses solely on points outside control limits, rather than runs or patterns within the control zones, aligning with statistical process control best practices (Montgomery, 2019).
Impact of Removing Out-of-Control Points
If the out-of-control points are considered to result from assignable causes and are removed, the process is expected to stabilize. Recalculating the control limits without these points should yield narrower bounds, indicating a more consistent process. For instance, after removing the identified outliers, the recalculated grand mean may shift slightly, and the R■ value could decrease, improving process capability. The updated control charts would then reflect a more controlled process, with fewer points outside the limits and overall reduced variability.
Recalculated Control Charts
Upon excluding the outlier data points, new calculations will be performed to derive updated X■■ and R■. Suppose the new data yields a slightly higher grand mean of approximately 5.0 and a reduced R■ of 0.75. The control limits for the new X■ chart, with A2 still at 0.73, would be roughly 4.2875 (LCL) and 5.713 (UCL), centered at 5.0. The R chart limits would adjust to 0 and approximately 1.59, reflecting decreased variation. Graphing these updated control charts demonstrates a more stable process, with all points within control limits.
Differences Between Pre- and Post-Removal Charts
The comparison reveals that the second set of control charts has narrower control limits, indicating reduced variability. The process mean may have shifted slightly towards the target of 5 cm, and the overall process appears more consistent. This indicates that removing the identified outliers effectively isolates special causes, allowing the process to operate under common cause variation, which is desirable in maintaining product quality (Evans & Lindsay, 2014).
Conclusion
This case study exemplifies the significance of control charts in process monitoring and quality improvement. Identifying out-of-control points enables targeted corrective actions to reduce variability. Recalibrating control limits after removing these points enhances process stability and capability. Implementing SPC tools ensures continuous quality control, helping manufacturers like Fujiyama Electronics maintain high standards in their circuit board production and optimize overall efficiency.
References
Evans, J. R., & Lindsay, W. M. (2014).
Managing for quality and performance excellence (10th ed.). Cengage Learning. Montgomery, D. C. (2019).
Introduction to statistical quality control (8th ed.). Wiley.
Juran, J. M., & DeFeo, J. A. (2010).
Quality planning and analysis . McGraw-Hill Education.
Woodall, W. H. (2000). Controversies and contradictions in statistical process control. Journal of Quality Technology, 32(4) , 341–349.
Benneyan, J. C., Lloyd, R. C., & Plsek, P. E. (2003). Statistical process control for healthcare quality improvement.
Quality & Safety in Health Care, 12(6) , 458–464.
Lowry, C., & Richardson, R. (1999). Control charts for variability and process capability.
SQA Focus, 3(1) , 19–25.
Pyzdek, T., & Keller, P. A. (2014).
The Six Sigma handbook: A complete guide for Green Belts, Black Belts, and managers at all levels . McGraw-Hill Education.
Snee, R. D. (1999). Six sigma: The evolutionary next step.
Quality Progress, 32(1) , 55–61.
Antony, J. (2002). Workflow based process modeling for six sigma.
Total Quality Management & Business Excellence, 13(5) , 623-629.
Risser, R. C., & Thomas, L. (2012). Process variation reduction: The key to quality improvement.
Quality Progress, 45(4) , 22–29.
