Leading ERP software for growing manufacturers

Categories: Process Improvement
Understanding and Applying Statistical Process Control in Manufacturing, Part 4

Understanding and Applying Statistical Process Control in Manufacturing, Part 4

By Bob Sproull

Review of Understanding and Applying Statistical Process Control in Manufacturing, Part 3

In my last post, I presented the steps in conducting a gage repeatability and reproducibility study and explained the difference between the two concepts. I also explained how to conduct a process potential study, which provides a projection of the process capability, as well as a process capability study, which uses sample sizes greater than one.

In Part 4, I will continue this discussion on implementing SPC by discussing control charts in much more detail.  This post deals with the actions necessary for implementing control charts based upon the results of the completed process capability study.

The fundamental definitions for control charts

A control chart is a basic tool used in SPC. Its purpose is to provide a picture of just what the process is doing. That is, the control chart is used to judge whether the process is operating normally or whether action is required to correct a potential problem.  The results of the process capability study will serve as the basis for the creation of your control chart.

The following are definitions that must be developed and followed to successfully implement your control chart.

  1. Define your sampling plan. Many times, the same sampling plan used during the process capability study will be used for your control chart.
  2. Define the centerline for your X-bar chart. What is recommended is that the centerline for the X-bar chart be the same as the center of the specification for the control characteristic, so that Cp will equal Cpk.
  3. Define the centerline for the range chart and the control limits for the X-bar and range chart. If the subgroup size is the same as used in the process capability study, then the R-bar and control limits can be taken directly from the process capability study.
  4. Define the calculations to be used by the person implementing the control chart, which will be the sample average (X-bar) and the range.
  1. Define the instructions for use of the control chart. These should include how and when the samples should be taken, the required calculations, and any special instructions.
  2. Define the criteria for out-of-control conditions. Examples include any single point outside the control limits for both the X-bar and range charts, any run of eight consecutive points above or below the centerline of the X-bar chart, and any run of eight consecutive points above the centerline of the range chart.
  1. Define the rules of action to be taken when an out-of-control condition exists. The rules of action should state the steps to be followed in detail so there is no question about what should be done. One way to do this is to create an out-of-control checklist for the machine being monitored.

Audit the control charts

Once the control chart has been implemented, it’s important that an audit of the chart be completed on a regular basis. The audit is intended to answer the question, “Are the rules of action being followed as defined?” An audit is intended to identify specific and objectively recorded examples of non-compliance and should be performed by a group outside the production unit, such as the quality group. It’s important to understand that the purpose of the audit is not to determine the cause of the non-compliance, but rather that the non-compliance was recognized and acted upon.

Evaluate process capability

Process capability is expressed in terms of the spread of process data with respect to the specifications which translates into the capability of the process to produce acceptable product.  The measure of process capability is referred to as the capability index and is presented as Cp and Cpk. Cpk is the actual capability as the process is running, while Cp is the projected capability if the process is centered between the upper and lower specification limits. The following is the interpretation of Cpk:

  • Cpk less than 1.0: Process is not capable of producing product consistently within specification limits.
  • Cpk between 1.0 and 1.3: Process is marginally capable of producing product within specification limits.
  • Cpk between 1.3 and 2.0: Process is capable of consistently producing product within specification limits.
  • Cpk greater than 2.0: Process is highly capable and should never produce product outside specification limits.

It is critical that Cpk values be evaluated on a periodic basis to assure that the process remains stable and consistent over time.

Coming in the next post

In the final installment of this series, I will complete our discussion on statistical process control by looking at a way to further reduce the variability of processes and further improve process capability. I will do so by briefly discussing a very important tool known as a designed experiment. In the meantime, if you would like to learn more about this topic, check out my recent series, A Practical Guide for Manufacturing Process Improvement.

Until next time,

Bob Sproull

Bob Sproull

About the author

Bob Sproull has helped businesses across the manufacturing spectrum improve their operations for more than 40 years.

facebook-icon facebook-icon linkedin-icon linkedin-icon twitter-icon twitter-icon blog-icon blog-icon youtube-icon youtube-icon instagram-icon instagram-icon Bookmark this page Google +