Leading ERP software for growing manufacturers

Categories: Problem Solving
A Practical Guide for Manufacturing Process Improvement, Part 4

A Practical Guide for Manufacturing Process Improvement, Part 4

By Bob Sproull

Review of A Practical Guide for Manufacturing Process Improvement, Part 3

In Part 3 of this series, I walked you through the basics of a measurement system evaluation (MSE) and process potential and process capability studies. I explained that one of the keys to successful improvement initiatives is to assure that all measurements are both accurate and repeatable. I also explained that the primary difference between the process potential study and the process capability study is the length of time required by each. Further, I expounded on how the process potential study is intended to lay the foundation for the process capability study. When the data collection is complete, there are several key questions which must be answered:

  1. Is the data normally distributed?
  2. Is the process in statistical control?
  3. Does the Cp equal the Cpk, or are they at least close to each other?

In Part 4, I will discuss how best to implement control charts. Then I’ll complete this exploration of process improvement with a more detailed discussion on Cp and Cpk. As stated in previous posts, due to limited space, I will not provide details of key calculations, but rather refer you to other sources of information on these subjects.

Implementing control charts

A control chart is the natural outgrowth of your process potential and process capability studies. Its purpose is to provide a graphic illustration of what is actually happening within your process. The results of the process capability study serve as the basis for construction of the control chart. In constructing control chart, there are logical steps which should be followed:

  1. Define the sampling plan: Often, the sampling plan used during the process capability study will be used with the first iteration of the control chart.
  2. Define the centerline and control limits for the X-bar chart: Typically, you will set the centerline equal to the center of the specification associated with the control characteristic and the control limits of the process being controlled.
  3. Define the centerline for the range chart and the associated control limits: If the subgroup size is the same as used in the process capability study, then the R-bar control limits can be taken directly from these results.
  4. Define the necessary calculations: The basic calculations to be used will be for the average (X-bar) and fange (high value minus low value).
  5. Define the control chart format: The basic format for the control chart should permit easy presentation of data and corresponding data patterns.
  6. Define “out-of-control” conditions: The control chart instructions should clearly state what is being controlled, what should be done, and by whom in the event data points fall outside the control limits (i.e., rules of actions).

Evaluation of Cpk

Process capability is expressed in terms of the spread of the process (i.e., +/- 3 sigma) relative to the product specifications. In reality, it represents the capability of a process to make acceptable products. This index is expressed as Cpk, which represents the actual process capability, and Cp which represents the capability of the process if it were centered within the tolerance band.

In general, the following interpretations can be made from Cpk values:

  • Cpk < 1.0 (process is not capable)
  • 0 < Cpk < 1.33 (process is marginally capable)
  • 33 < Cpk < 2.0 (process is capable)
  • Cpk > 2.0 (process is highly capable)

Cp is simply what the capability of the process would be if the average (X-bar) was equal to the center of the process specifications. In other words, Cp (process potential) is a measure of how good the capability of the process could be if the process were centered.

Coming in the next post

The next post will be the first in a new series on a new improvement subject.  

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 +