STM Quality
Limited
Measurement Systems
Analysis
TOTAL QUALITY MANAGEMENT
M.S.A.
©©ABSL
Power Solutions
STM Quality
Limited 2007
Outline and Objectives
STM Quality
Limited
 Introduce Measurement Systems
 Assess Measurement Systems Performance
 Understand Measurement System Variation
© STM Quality Limited
Requirements for M.S.A.
STM Quality
Limited
• TS16949 Clause 7.6.1. states:
• Statistical studies shall be conducted to analyse the
variation present in the results of each type of measuring
and test equipment system. This requirement shall apply to
measurement systems referenced in the control plan. The
analytical methods and acceptance criteria used shall
conform to those in customer reference manuals on
measurement systems analysis. Other analytical methods
and acceptance criteria may be used if approved by the
customer.
© STM Quality Limited
STM Quality
Limited
Process Control
A Typical Process
People
Methods
Material
Equipment
Environment
Input
PROCESS
Product
Process / System
Output
Identifying
Improvement
Opportunities
Accurate Measurement
using Measurement System Analysis
© STM Quality Limited
New Process Acceptance
 Observed Process
Variation
STM Quality
Limited
 Production Gauge
Variation
 Actual Process
Variation
© STM Quality Limited
Assessing
Measurement Systems
STM Quality
Limited
 Location variation
– Bias
– Stability
 Width variation
– Linearity
– Repeatability, Reproducibility
© STM Quality Limited
Determining and Assessing Bias
 Bias is the difference between
the observed average of
measurement and the reference
value.
Bias
 The reference value, also
known as the accepted
reference value or master value,
is a value that serves as an
agreed-upon reference for the
Reference
measured values. A reference
Value
value can be determined by
averaging several
measurements with a higher
level of measuring equipment.
STM Quality
Limited
Observed
Average Value
© STM Quality Limited
Determining and Assessing Stability
 Stability (or drift) is the total
STM Quality
Limited
Time
variation in the measurements
obtained with a measurement
system
• on the same master or part
when measuring a single
characteristic
• over an extended
time period
Reference Value
© STM Quality Limited
STM Quality
Limited
Determining and Assessing Linearity
 Linearity is the difference in the bias values through the
expected operating range of the gauge.
Reference
Value
Observed
Average Value
Smaller
Bias
Reference
Value
Observed
Average Value
Larger
Bias
50mm
200mm
© STM Quality Limited
Determining Repeatability
STM Quality
Limited
 Repeatability is the variation in
measurements obtained
• By one appraiser
• with one measurement
instrument
• when used several times
• while measuring the
identical characteristic
• on the same part
Repeatability
© STM Quality Limited
Determining Reproducibility
STM Quality
Limited
 Reproducibility is the variation in
the average of the measurements
made
• by different appraisers
• using the same measuring
instrument
• when measuring the
identical characteristic
• on the same part
Reproducibility
© STM Quality Limited
Preparing For A
Measurement System Study
STM Quality
Limited
 Variable Gauge Study (Average and Range Method)
The average and range method of gauge study breaks the gauge error
into repeatability and reproducibility.
Optimum conditions:
• 3 operators;
• 3 trials;
• 10 parts.
Study of the results can provide information concerning the causes of the
measurement error.
 If reproducibility is large compared to repeatability then;
• The operator is not properly trained in how to use and read the gauge;
• Graduations on the gauge are not clear.
© STM Quality Limited
Determining and Assessing
Repeatability and Reproducibility
STM Quality
Limited
 There are three methods:
 Range Method;
 Average and Range Method;
 Analysis of Variation Method (ANOVA).
© STM Quality Limited
Determining and Assessing
Repeatability and Reproducibility
STM Quality
Limited
Range Method
 Gives a quick approximation of measurement variability. It does not





decompose the variability into repeatability and reproducability.
Conducted with 2 appraisers and 5 parts;
Each appraiser measures each part once;
Evaluate the range at each part;
Estimate the variation between the measurement results over the average
Range (R/d2);
Gauge R&R = 99%-area under the normal distribution curve
(2*2,576*variation).
(not sufficient for PPAP and QS-9000 clause 4.11.4)
© STM Quality Limited
Determining and Assessing
Repeatability and Reproducibility
STM Quality
Limited
Average and Range Method
 Evaluates Repeatability and Reproducibility separately;
 Conducted typically with three appraisers and 10 parts;
 Each appraiser measures each part three time in a random order;
 Evaluation graphical or numerical;
 EV (equipment variation)
 AV (appraiser variation)
 R&R (R&R)² = EV² + AV²
 Part Variation PV
 Total VariationTV² = (R&R)² + PV²
(99%- norm. distr.)
(99%- norm. distr.)
(99%- norm. distr.)
(99%- norm. distr.)
(99%- norm. distr.)
© STM Quality Limited
STM Quality
Limited
Determining and Assessing
Repeatability and Reproducibility
Analysis of Variation Method
 Evaluates Repeatability and Reproducibility separately;
 Evaluates Interaction between appraiser and part;
 Conducted typically with three appraisers and 10 parts;
 Each appraiser measures each part three time in a random order;
 Evaluation graphical or numerical;
 EV (equipment variation)
 AV (appraiser variation)
(99%- norm. distr.)
(99%- norm. distr.)
 R&R (repeatability, reproducibility and interaction (I)
 R&R (R&R)² = EV² + AV²+I²
 Part Variation PV
 Total Variation TV² = (R&R)² + PV²
(99%- norm. distr.)
(99%- norm. distr.)
(99%- norm. distr.)
© STM Quality Limited
Determining and Assessing
Repeatability and Reproducibility
STM Quality
Limited
 If repeatability is large compared to reproducibility, the reasons may be:
 The instrument needs maintenance;
 The gauge should be redesigned to be more rigid;
 The clamping or location for gauging needs to be improved;
 There is excessive part variation.
 If reproducibility is large compared to repeatability, then possible causes
could be:
 The appraiser needs to be better trained in how to use and read the
gauge instrument;
 Calibrations on the gauge dial are not clear;
 A fixture of some sort may be needed to help the appraiser use the gauge
more consistently.
© STM Quality Limited