2.6.3T Statistical Process Control

(2.6.3T.P1)

Statistical Process Control (SPC) techniques provide a data-based, objective way to determine whether your project is producing products within acceptable levels of quality. These techniques rely on testing or quality inspections on many products being produced by the project team. If your project is creating a small number of highly-customized deliverables, SPC techniques may not work for you. However, if your project will result in the creation of many similar products, SPC may be a good way for you to determine if your processes are sufficient to produce high-quality products.

SPC also helps you determine if your processes are “in control”. That is, you can determine if your processes are adequate to produce products with an acceptable level of quality on an ongoing basis. When the process starts to falter and produce products that do not conform to quality standards, the processes are designated as “out of control”. SPC techniques will tell you as soon as possible when your processes are “out of control”.

The philosophy behind SPC is that process output can be statistically controlled through process engineering and management actions. This approach helps project teams and companies to:

  • Identify critical problem areas early in a process

  • Reduce product variability

  • Determine the capability of a process

  • Optimize a process

  • Determine the reliability of the product

Although SPC appears to be an easy and straightforward technique, its implementation can be complicated. It requires a common and consistent way to test products being produced, a way to measure the results of the tests and a way to interpret the results to understand what is happening.

Control Charts (2.6.3T.P2)

The use of control charts is a critical aspect of SPC, but it is not the only way SPC can be implemented. A control chart is a graph with a horizontal axis that represents sample numbers or points in time, and a vertical axis that represents measurements made from these samples. The chart has one central line denoting the process target and both upper and lower control limits representing the acceptable limits around the process target line.

A control chart relies on the data collected during the sampling process. Sufficient data must be collected and plotted on a graph. When all the points in the graph are within the control limits, the process is labeled as “in control”. If there are points outside the upper and lower control limits, the process is considered uncontrolled or “out of control”.

 

 

 On the control chart, the horizontal axis lists the samples or points in time. The vertical axis contains measurements from these samples. The control line (CL) denotes the process target. The upper and lower acceptable control limits are represented by lines Upper Control Limit (UCL) and Lower Control Limit (LCL).

 

A process in control is one where all measurements over time fall within the upper control limits and the lower control limits.

 

A process is considered “out of control” when one or more of the following events occur.

  • One or more points are outside of the control limits

  • A run of eight points on one side of the center line (more than what would be considered “random”)

  • An unusual or nonrandom pattern in the data

  • A trend of seven points in a row upward or downward

  • Pattern of over and under CL, but within limits

  • Several points near a control limit (but not outside the limits)

If any of these situations occurs, the project team needs to investigate the cause of the problem and determine the changes required to get the process back “in control”.

It is often argued that SPC techniques are objective, but their use in decision-making is more subjective. It is up to individual managers and team members to interpret the results and take further actions. Simply plotting a control chart cannot improve quality or prevent process problems. The benefits of SPC depend on how the results are interpreted and used.

It is important to note that although you may strive for process perfection, you can never reach this state. Human factors, imperfect machinery and tools, equipment wear-and-tear and process exceptions will always result in some variability. You can shrink the UCL and LCL to a smaller and smaller range, if you continue to improve your processes (and tools). However, the variability will never reach zero.