Measurement System Analysis (MSA)

What is It?
An MSA is a statistical tool used to determine if a measurement
system is capable of precise measurement.
 Measurement System Analysis (MSA)
What is It?
An MSA is a statistical tool used to
determine if a measurement system
is capable of precise measurement.
Objective or Purpose
• To determine how much error is in
the measurement due to the
When to Use It measurement process itself.
• On systems measuring critical inputs • Quantifies the variability added by
and outputs prior to collecting data the measurement system.
for analysis. • Applicable to attribute data and
• For any new or modified process in variable data.
order to ensure the quality of the IMPORTANT!
data.
Who Should be Involved Measurement System Analysis is
an analysis of the measurement
Everyone that measures and makes process, not an analysis of the
decisions about these measurements
should be involved in the MSA. people!!
MSA
MSA
MSA
 Measurement System Analysis (MSA)
Objective or Purpose

• To determine how much error is in the measurement due to the

measurement process itself.
• Quantifies the variability added by the measurement system.
• Applicable to attribute data and variable data.
MSA
MSA
MSA
MSA
 MSA
• 1. Item of Interest :-Product which is being measured
for a characteristics (Mass, Volume, Temp, Length,
Width etc.)
• 2.Man :- The person who will check/ verify the
product called Appraiser in this study.
• 3.Instruments :-The device by which we assign a
numerical value for a product characteristics.
• 4. Method :- The procedure by which we check the
product characteristics , Handling of Instrument,
Specific place where Verification will be Done
 MSA
• 5. Environment :- The conditions in which we
conduct the measurement process may be :
• a) Temperature & Humidity level of
environment where measurement is being
conduct.
• b) Lightening
• c) Vibrations
 MSA
The parameters of the measurement process are
• Input : Component to be measured
• Process factors : Equipment, Inspector etc.
• Output : Measured value
2 Main Points:
• Repeatability
• Reproducibility
 MSA
REPEATABILITY
• The variation in measurements obtained
• With one measuring instrument
• When used several times
• By one appraiser
• While measuring the identical characteristics
• On the same part
 MSA
REPRODUCIBILITY
• The variation in the average of the measurements made
• By different appraisers
• Using the same measuring equipment.
• While measuring the identical characteristics
• On the same part
MSA
MSA
MSA
MSA
MSA
Inspection – what do you really see?
Measurement System Analysis (MSA)
Observed Variation
Resolution

Precision Repeatability
(Variability)
Reproducibility
Measurement
System
Variation
Linearity
Observed Accuracy
(Central Bias
Variation Location)
Stability

Process
Variation Calibration helps address accuracy
MSA
Measurement System Analysis (MSA)

Resolution
Error in Resolution
The inability to detect small
changes.

Possible Cause
Wrong measurement device
selected - divisions on scale
not fine enough to detect
changes.
Resolution
MSA
Resolution
MSA
Resolution
MSA
Measurement System Analysis (MSA)
Repeatability
Error in Repeatability
The inability to get the same
answer from repeated
measurements made of the
same item under absolutely
identical conditions.

Possible Cause
Lack of standard operating
procedures (SOP), lack of
training, measuring system
variablilty.
Equipment Variation
 Repeatability – Measuring Instrument Va

Same Inspector Same Instruments Same Environment Same Method

10 Readings:
8.1; 8.3; 7.9; 8.0; 8.3; 8.1; 8.2
8±0.5 8.3; 8.4; 8.0;
There is error in repeatability
Same Part; Same Dimension
 Measurement System Analysis (MSA)
Reproducibility
Error in Reproducibility
The inability to get the same
answer from repeated
measurements made under
various conditions from
different inspectors.

Possible Cause
Lack of SOP, lack of training.

Appraiser Variation
 Reproducibility – Appraiser Variation

8±0.5

Same Part Same Instruments Same Environment Same Method

Same dimension
Inspector1:
8.5; 8.5; 8.4; 8.3; 8.3;
Inspector 2:
8.3; 8.4; 8.2; 8.1’ 8.1
There is error in reproducibility
Different Inspectors
 Variable MSA – Gage R&R Study

• Gage R&R is the combined estimate of

measurement system Repeatability and
Reproducibility
• Typically, a 3-person study is performed
 Each person randomly measures 10 marked parts per trial
 Each person can perform up to 3 trials

• There are 3 key indicators

 % P/T or measurement variation compared to tolerance
 % R&R or measurement variation compared to process variation
 Number of distinct categories (ndc) or measure of resolution
 Gage R & R Study
• Appraisers should be selected from those who normally
operate the instrument.
• Sample parts must be selected from the process and they
should represent its entire operating range.
• Instrument must have a discrimination (resolution) that allows
at least one-tenth of the expected process variation of the
characteristic. The measurement method is well defined.
• Measurements should be made in a random order.
 MSA
• Conducting the R & R Study
• Select ten parts from the process at random, preferably one
part from every days production.
• Identify them with a serial number that cannot be observed
by the appraisers.
• Select tow or three appraisers, who normally operate the
measuring system.
• Measure the parts randomly so that all the appraisers
measure all the parts for two or three times (trial).
 Gage R&R Steps
1. Select two or three appraisers who use the measurement
system. 2. Obtain a sample of 10 parts that represent actual or
expected range of process variation.
3. Number parts 1 through 10 so that numbers are not visible
to appraisers. 4. Identify and Mark the place where
measurement to be taken to eliminate within part variation
5. Measure 10 parts in random order by appraiser A, with an
observer recording results.
6. Repeat step 5 with other appraisers conceal other
appraisers readings. 7. Repeat step 5 and 6 using a different
random order of measurement. 8. Calculate the average and
ranges for all readings for each appraiser. 9 Using attached
GR&R report, enter part averages and range averages.
10. Calculate repeatability - equipment variation.
11. Calculate reproducibility - appraiser variation.
 Gage R&R Steps
12.Calculate GR&R and convert to percentage.
13. Calculate part variation and convert to percentage.
14. Calculate total variation.
 MSA
• Calculate the variations due to different factors, according to
the formulae given.
• A measurement system with R & R % of 10% or less is
considered good.
• A measurement system with R & R % between 10% to 30%
may have to be evaluated for acceptance, considering the
criticality of the part.
 MSA
• FORMULAE
• Xa bar, Xb bar, Xc bar = Average of all the measurements
made by A, B &C respectively
• Ra bar, Rb bar, Rc bar = Average of the range of the trails
made on 10 parts by A, B & C respectively • Rp = Maximum
part average – Minimum part average
• R- bar = (Ra bar + Rb bar + Rc bar ) / No. of Operators
• X-bar Diff = Max X-bar – Min X-bar
• UC LR = R-bar * D4 D4 = 3.27 for 2 trails
= 2.58 for 3 trails
• LC LR = R-bar * D3 D3 = 0 for 2 & 3 trails
 MSA
• Homogenize the data for Range
• Calculate R-bar, X-bar Diff and Rp only after homogenizing
• Equipment Variation (EV) = R-bar * K1 (K1 = 4.56 for 2 trails
= 3.05 for 3 trails)
• Appraiser Variation (AV) = SQRT { (X-bar Diff * K2 )2 – [ EV2 /
(nr)]} (K2 = 3.65 for 2 operators = 2.70 for 3 operators)
 MSA
• (n : No. of parts r : No. of trails)
• Repeatability & Reproducibility ( R &R) = SQRT { (EV2 + A V2 ) }
• Part Variation (PV) = Rp * K3
Value of K3 can be taken from Table velow
n K3
2 3.65
3 2.70
4 2.30
5 2.08
6 1.93
7 1.82
8 1.74
9 1.67
10 1.62
 MSA
• Total Variation (TV) = SQRT { (R&R2 + PV2) }
• %EV = (EV/TV)* 100
• %AV = (AV/TV) * 100
• %R&R = (R&R/TV) * 100
• %PV = (PV/TV) * 100
 MSA
Attribute Gage Study (Alternate) Method
a. Method of conducting Study
1.Obtain 50 components which are 50% OK, 25% marginally ok a
nd 25% marginally not OK.
2.Identify the components with numbers and note master readin
gs in the Attribute Study data sheet.
3. Select the appraisers for giving the decision (A,B & C)
4.Using the appraiser ‘A’, carryout the trial ‘A1’ and carryout the s
ame with appraiser ‘B’ & ‘C’ for the trials ‘B1’ & ‘C1’
5. Repeat the step 4 for the trials A2,A3,B2,B3,C2&C3 for the
appraiser’s A,B & C.
 Variable MSA – AIAG GR&R VAR(Tol)
GAGE REPEATABILITY AND REPRODUCIBILITY DATA SHEET GAGE REPEATABILITY AND REPRODUCIBILITY DATA SHEET
VARIABLE DATA RESULTS VARIABLE DATA RESULTS
Part Number Gage Name Appraiser A Part Number Gage Name Appraiser A
NUMBER NUMBER
Part Name Gage Number Appraiser B Part Name Gage Number Appraiser B
NAME NAME
Characteristic Specification Gage Type Appraiser C Characteristic Gage Type Appraiser C
Lower Upper
Characteristic Classification Trials Parts Appraisers Date Performed Characteristic Classification Trials Parts Appraisers Date Performed

APPRAISER/ PART AVERAGE Measurement Unit Analysis % Tolerance (Tol)

Included in PPAP Workbook

TRIAL #
1. A 1
1 2 3 4 5 6 7 8 9 10 Repeatability - Equipment Variation (EV)
EV = R x K1 Trials K1 % EV = 100 (EV/Tol)

2. 2 = 2 0.8862 =
3. 3 = 3 0.5908 =
4. AVE xa= Reproducibility - Appraiser Variation (AV)
5. R ra= AV = {(xDIFF x K 2)2 - (EV 2/nr)}1/2 % AV = 100 (AV/Tol)

6. B 1 = =
7. 2 = =

Automatically calculates x
8. 3 A p p r aiser s 2 3
9. AVE b= n = parts r = trials K2 0.7071 0.5231
10.

11. C
R

1
%GRR, %PV, ndc r b= Repeatability & Reproducibility (GRR)

GRR = {(EV2 + AV 2)}1/2 Parts K3

% GRR =

=
100 (GRR/Tol)

12. 2 = 2 0.7071 =
13. 3 = 3 0.5231
14. AVE xc = Part Variation (PV) 4 0.4467
15. R rc = PV = RP x K3 5 0.4030 % PV = 100 (PV/Tol)

16. PART X= = 6 0.3742 =

AVERAGE Rp= = 7 0.3534 =
17. (ra + rb + rc ) / (# OF APPRAISERS) = R= Tolerance (Tol) 8 0.3375
18. x DIFF = (Max x - Min x) = xDIFF = Tol = Upper - Lower / 6 9 0.3249 ndc = 1.41(PV/GRR)
19. * UCLR = R x D4 = UCLR = = ( Upper - Lower ) / 6 10 0.3146 =

= =
* D4 =3.27 for 2 trials and 2.58 for 3 trials. UCLR represents the limit of individual R's. Circle those that are
beyond this limit. Identify the cause and correct. Repeat these readings using the same appraiser and unit as originally used or
discard values and re-average and recompute R and the limiting value from the remaining observations. For information on the theory and constants used in the form see MSA Reference Manual , Fourth edition.

Notes:
 Variable MSA – Gage R&R Steps
Step 1 Step 2 Step 3 Step 4 Step 5 Step 6 Step 7 Step 8 Step 9

1. Select 10 items that represent the full range of long-term process variation

2. Identify the appraisers – they should be operator who normally use the gage

3. If appropriate, calibrate the gage or verify that the last calibration date is valid

4. Open the GR&R VAR(Tol) worksheet in the AIAG Core Tools file to record data, or use MiniTab

5. Have each appraiser assess each part 3 times preferably in random order (Minitab can generate a random
run order)

6. Input data into the GR&R VAR(Tol) worksheet or MiniTab

7. Enter the number of operators, trials, samples and specification limits

8. Analyze data and review GR&R and PV values

9. Take actions for improvement if necessary.

 Measurements Systems Analysis MSA
Tips and Lessons Learned
 Important: An MSA is an analysis of the process, not an analysis of the people. If an
MSA fails, the process failed.
 A Variable MSA provides more analysis capability than an Attribute MSA. For this
and other reasons, always use variable data if possible.
 The involvement of people is the key to success.
 Involve the people that actually work the process
 Involve the supervision
 Involve the suppliers and customers of the process
 An MSA primarily addresses precision with limited accuracy information.
 MSA: Reviewer’s Checklist
 If the gage/inspection measures a special characteristic
or other important feature, then conduct a Gage R&R
 Make sure the study is recent - less than 1 year
 Compare the control plan gages against the Gage R&Rs
 % R&R and %P/T should be less than 10%
 Values greater than 10% should be reviewed with Eaton
 Number of distinct categories should be >5
 If you question that gage, then
• Question the technique and part sampling
• Ask for additional studies
 MSA Summary
• Measurement systems must be analyzed BEFORE
embarking on process improvement activities
• MSA helps understand how much observed variation is
from the measurement system
• MSA will tell you about the repeatability,
reproducibility and discrimination
• Sample selection is very important – sample during
normal production to capture total range of process
variation
• MSA assessors should be operators that would
normally use the measurement system
• MSA should be done on a regular basis
MSA
MSA