18.04.MSA NonReplicableGRR Nested

Measurement
System Analysis –
Non-Replicable
Gage R&R
(Nested)
Advance Topic
Global LSS
Aug 2020
Measurement System Analysis
Objective
• Share the approach to handle non-replicated measurement system GR&R.
Key Topics
• GR&R (Nested)
Non-Replicable
Measurement
System - Gage
R&R (Nested)
Destructive Testing
• Destructive testing are defined as tests that

are made to a material through the use of
tools or machines, which produce an
irreversible alteration of their chemical
composition or dimensional geometry.
• These parts or products where what we wish
to measure (characteristic) will either alter or
in some cases even destroy by the act of Pull Test on Wire Bond
measuring the process is known as
destructive measurement.
• How can we then do a Gage R&R where get

meaningful results regarding repeatability?
Bond Adhesion Test

Gage R&R (Nested)
• Since parts are destroyed during test and test-retest on the same part by
the same operator is no longer possible, this is also known as Non-
replicable measurement system
• GR&R (Nested) analysis is used when parts cannot be measured multiple

times by multiple appraisers
For replicable measurement system, similar
• Example: destructive weld testing, destructive plating testing, salt parts will be cross examined by different
appraisals
spray/humidity booth testing, impact testing or mass spectroscopy
and other material characteristic testing processes.
• There are special situation whereby GR&R (Nested) can be utilized as

long as the parts cannot be measured repeatedly by the same
operator.
• Important:
• This analysis requires that you choose groups of parts with

For non-replicable measurement system, parts
characteristic similar enough so they can be considered the same will be damage and will not be able to be re-
examined by different appraisals
part; otherwise, the part variation will mask the measurement
T-Map for MSA Success (Process Overview)
1. Select Measurement
System
2. Develop Measurement • # of operators

Strategy Outputs • # of measurements
• # dependent on type
3. Collect Samples Outputs of test
4. Prepare Measurement
Data Sheet
5. Perform MSA
Study
6. Analyze MSA • R chart

Results
Outputs • X bar chart
• Stability
7. Interpret MSA • Discrimination
Results
Outputs • Operator Bias
• Reproducibility
• Measurement Variation
8. Outline Next Steps Outputs • Optimization Plan
Nested GR&R - Example
An engineer wants to monitor the impact strength of ceramic components. The engineer selects 10
groups of samples that represent the expected range of the process variation with 6 samples from
each group (close enough property) and gives 10X2 samples to each operators. The 3 operators
measure a total of 60 measurements.
Note: Each part (sample) is unique to operator; no 2 operators measured the same part.
Because the measurements are nested within operator, the engineer performs a nested gage R&R
study to assess the variability in measurements that may be due to the measurement system.
1.Open the sample data, 18.4.1 CeramicComponent.MTW.

2.Choose Stat > Quality Tools > Gage Study > Gage R&R Study (Nested).
3.In Part or batch numbers, enter Part.
4.In Operators, enter Operator.
5.In Measurement data, enter Response.
6.Click OK.
Adopted from Minitab Help
Nested GR&R – Example (Statistical Analysis)
Interpret the results
• P-value for Part (Operator) is 0.000 and is less than 0.05.

The average measurements of different parts nested within
each operator are significantly different.
• Total Gage R&R = 23.71% (Marginal)

• All from repeatability issue
• NDC = 5 (Acceptable)
Nested GR&R – Example (Graphical Analysis)
• In the R Chart by Operator, all the data

are in control, which indicates that the
three operators measure consistently.
• In the Xbar Chart by Operator, several
points are beyond the control limits. Thus,
much of the variation is due to
differences between parts.
• The By Part graph shows that the
differences between parts are large.
• In the By Operator graph, the
measurements for each operator vary by
approximately the same amount. Also,
the part averages vary by a small
amount. While some variation is always
present, the data indicate that the
operators measure parts similarly.
GR&R (Nested) - Exercise
Three operators each measured 10 different parts from 5 different groups which cover the
range of measurement interest), a total of 30 measurements. Each part is unique to each
operator; no two operators measured the same part. A gage R&R study (nested) is conducted
to determine how much of your observed process variation is due to measurement system
variation .
1. Open the worksheet 18.4.2 GAGENEST.MTW.

2. Choose Stat > Quality Tools > Gage Study > Gage
R&R Study (Nested).
3. In Part or batch numbers, enter Part.
4. In Operators, enter Operator.
5. In Measurement data, enter Response.
6. Click Options. Under Process tolerance, choose Upper
spec - Lower spec, and enter 10.
7. Click OK in each dialog box.
THANK YOU
BUSINESS CONFIDENTIAL | ©Jabil Inc. 2019. All Rights Reserved.

Version Log
User Date Version # Changes
Joseph Ang 8th Aug 2020 1.0

18.04.MSA NonReplicableGRR Nested

Uploaded by

Copyright:

Available Formats

18.04.MSA NonReplicableGRR Nested

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

18.04.MSA NonReplicableGRR Nested

Uploaded by

Copyright:

Available Formats

Measurement

• Share the approach to handle non-replicated measurement system GR&R.

• Destructive testing are defined as tests that

• How can we then do a Gage R&R where get

Bond Adhesion Test

• GR&R (Nested) analysis is used when parts cannot be measured multiple

• There are special situation whereby GR&R (Nested) can be utilized as

• This analysis requires that you choose groups of parts with

2. Develop Measurement • # of operators

6. Analyze MSA • R chart

1.Open the sample data, 18.4.1 CeramicComponent.MTW.

Interpret the results

• P-value for Part (Operator) is 0.000 and is less than 0.05.

• Total Gage R&R = 23.71% (Marginal)

• In the R Chart by Operator, all the data

1. Open the worksheet 18.4.2 GAGENEST.MTW.

BUSINESS CONFIDENTIAL | ©Jabil Inc. 2019. All Rights Reserved.

Joseph Ang 8th Aug 2020 1.0

You might also like