The Basic EMP Study and Gage R&R [video]

This is the final blog in a four-part series on Gage R&R studies. The first blog addressed what a gage R&R study is. The second blog addressed Gage R&R studies and process variation and determine the % of total variance due to the measurement system. The third blog examined how good your measurement system is using an Evaluating the Measurement Process (EMP) classification developed by Dr. Donald Wheeler. This blog provides a general overview of the Basic EMP Study. The Basic EMP Study provides much more information than the usual Gage R&R analysis.

A general overview of the basic EMP study is given below. Details can be found in Dr. Wheeler’s book "EMP III, Evaluating the Measurement System" or in the EMP articles in our SPC Knowledge Base. The accompanying video uses an example for the overview of the technique. The actual equations used can be found in the book or on our website. Look through these steps – they show how much more information the basic EMP study gives you about your measurement process.

  • Have “o” operators measure each of “p” parts “n” times.
  • Construct the X chart based on operator-part averages.
    • The area between the lower and upper control limits (LCL and UCL) represents measurement error.
    • Examine the out of control points to see if there are any interaction effects.
  • Construct the R chart based on operator-part ranges.
    • The R chart must be in statistical control; if so, this means that the measurement process is consistent between operators.
  • Construct the Analysis of Main Effects Chart (ANOME).
    • This chart determines if there are differences in the operator averages (bias); differences should be investigated.
  • Construct the Analysis of Mean Range Chart (ANOMR).
    • This chart determines if there are differences in the average range between operators; there should be no differences.
  • Calculate the pure error or repeatability (σpe2) from the average range.
  • Calculate the probable error (PE).
    • The probable error is 0.675 (σpe2); half of repeated measurements should fall between the average and +/- one PE.
  • The measurement increment (resolution) should be between 0.2PE and 2PE; if it is not, you need to change your measurement increment.
  • Calculate the variances of the operators and parts, and then determine the various % of total variance due to:
    • Repeatability.
    • Reproducibility
    • R&R.
    • Parts.
  • Use the % of total variance due to the parts to classify the measurement system as a Class One, Class Two, Class Three or Class Four measurement system (see our previous blog).
  • Calculate the manufacturing specifications to determine the impact of the probable error on the product measurements versus specifications.
  • Calculate the precision to tolerance ratio, which measures how much of the specification range (tolerance) is consumed by the probable error.

It is impossible to show the power of the basic EMP study in a short blog. The reality is that the Basic EMP Study should be used in place of the average/range Gage R&R method and the ANOVA Gage R&R method. It provides much more information.

Comments (1)

  • anon

    Excellent Bill, thanks  

    Apr 23, 2019

Leave a comment

Filtered HTML

  • Web page addresses and e-mail addresses turn into links automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <h1> <h2> <h3> <h4> <h5> <h6> <img> <hr> <div> <span> <strike> <b> <i> <u> <table> <tbody> <tr> <td> <th>
  • Lines and paragraphs break automatically.

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
CAPTCHA
This question is for testing whether you are a human visitor and to prevent automated spam submissions.

Connect with Us

     

SPC Knowledge Base Sign-up

Click here to sign up for our FREE monthly publication, featuring SPC and other statistical topics, case studies and more!

SPC Around the World

SPC for Excel is used in over 60 countries internationally.  Click here for a list of those countries.