The document discusses measurement system analysis (MSA) which is used to evaluate measurement systems and understand sources of variation. Key points:
- MSA assesses measurement quality and identifies sources of error like bias, repeatability, reproducibility, stability, and linearity.
- It is required to make informed process adjustments and avoid wrong decisions from low quality measurement data.
- MSA studies involve multiple appraisers measuring multiple parts multiple times to calculate variation percentages.
- A sample MSA study shows data collection, calculations for repeatability, reproducibility, and overall variation to evaluate the measurement system.
2. MEASUREMENT PROCESS
‘Measurement ‘ is defined as the assignment of
numbers to Material things to represent the
relation ship with respect to particular properties.
Measurement system is the collection of
operations ,gages,personnel used to assign a
number to the characteristic being measured.
Measurement process should be viewed as
manufacturing process that produces numbers
(data) for its output
2
3. WHY MSA IS REQUIRED
• The decision to adjust a manufacturing
process or not based on measurement
data.If quality the of the measured data is
low then wrong judgment can be made.
• Example: 1.Allowing the process without
adjustment or premature adjustment
3
4. To better understand the sources of
variation that can influence the result
produced by the system.
To assess the Quality of
Measurement system
PURPOSE
4
5. MSA CAN BE USED
To assess(accept/reject/improve) new
measuring equipment/measuring process.
A comparison of one measuring device
with other
A comparison for measuring equipment
before and after repair
5
7. Bias
Bias = Observed Average – Reference value.
(Reference value can be determined by averaging
several Measurements with a higher level of
measuring equipment)
eg.,– Metrology lab or Layout equipment
Reference Value
Observed average value
BIAS
7
8. If the Bias is relatively large,
Look for these possible causes.
1. Error in the master.
2. Worn master.
3. Instrument made to the wrong
dimension.
4. Instrument measuring the wrong
characteristics.
5. Instrument not calibrate properly.
6. Instrument used improperly by
appraiser.
8
9. REPEATABILITY
(EQUIPMENT VARIATION)
Repeatability is the variation in measurements
Obtained with one measurement instrument
When used several times by an appraiser while
Measuring the identical characteristics on the
Same part.
Repeatability
9
10. REPRODUCIBILITY
(APPRAISER VARIATION)
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
Operator B
Operator A
Operator C
10
11. STABILITY
Stability ( or drift ) is the total variation in the
Measurement obtained with a measurement
System on the same master or parts when measuring a
single characteristics over an extended time period.
Stability
Time 2
Time 1
11
12. LINEARITY
Linearity is the difference in the bias values through the
expected operating range.
Reference Value
Observed average
value
Smaller
Bias
( Lower part of range )
Reference Value
Observed average value
Larger
Bias
( Higher part of range )
12
14. PREPARATION FOR THE STUDY TO ESTIMATE R&R
1.Optimum condition for MSA – 3Appraiser,3Trails,10Parts
(Condition for MSA (no.of appraisers) * (no.of parts) > 15)
2.The no.of parts chosen must represent the entire operating
Range
3.Appraisers are those who normally operate the gage
4.One observer should appointed to record the measurements
5.Each must be identified .
6.Instrument should have the L.C of 1/10th of the expected
process variation or the Tolerance
14
15. Important points during the study
1.Measurement should be done in random
order
2.The appraiser should be unaware which
numbered part is being checked to avoid
any Knowledge Bias.
3.Each appraiser must use the same method
to obtain the measurements.
15
17. A
B
C
PART
1 2 3 4 5 6 7 8 9 10
1 9.490 9.490 9.490 9.480 9.480 9.470 9.480 9.470 9.490 9.480 9.482
2 9.490 9.480 9.490 9.490 9.480 9.480 9.490 9.490 9.490 9.490 9.487
3 9.490 9.480 9.490 9.490 9.480 9.480 9.490 9.490 9.490 9.490 9.487
9.490 9.483 9.490 9.487 9.480 9.477 9.487 9.483 9.490 9.487 Xa= 9.4853
0.000 0.010 0.000 0.010 0.000 0.010 0.010 0.020 0.000 0.010 Ra= 0.0070
1 9.470 9.470 9.480 9.470 9.460 9.480 9.490 9.480 9.480 9.470 9.475
2 9.490 9.470 9.470 9.490 9.480 9.490 9.480 9.480 9.480 9.480 9.481
3 9.470 9.470 9.490 9.470 9.480 9.480 9.490 9.470 9.480 9.490 9.479
9.477 9.470 9.480 9.477 9.473 9.483 9.487 9.477 9.480 9.480 Xb= 9.4783
0.020 0.000 0.020 0.020 0.020 0.010 0.010 0.010 0.000 0.020 Rb= 0.0130
1 9.470 9.470 9.480 9.480 9.470 9.480 9.470 9.470 9.470 9.460 9.472
2 9.480 9.460 9.470 9.470 9.470 9.480 9.470 9.470 9.480 9.480 9.473
3 9.480 9.480 9.470 9.480 9.470 9.470 9.480 9.480 9.470 9.470 9.475
AVERAGE 9.477 9.470 9.473 9.477 9.470 9.477 9.473 9.473 9.473 9.470 Xc= 9.4733
RANGE 0.010 0.020 0.010 0.010 0.000 0.010 0.010 0.010 0.010 0.020 Rc= 0.0110
PART AVERAGE (Xp) 9.481 9.474 9.481 9.480 9.474 9.479 9.482 9.478 9.481 9.479 Rp= 0.0078
Xp = 9.4790
R = 0.0103
X Diff = Max X - Min X X Diff= 0.0120
UCL (R) = D4 X R D4 = 2.575 0.0266
LCL (R) = D3 X R D3 = 0.000 0
UCL (x ) = [Xp + A2R] A2 = 1.023 9.4896
LCL (x ) = [Xp - A2R] 9.4684
AVERAGE
RANGE
C
Xp = [ Xa + Xb +Xc] / 3
A
AVERAGE
RANGE
B
OPERATOR TRIAL NO. AVERAGE
Specification Gauge Least Count 0.02mm
Characteristic Gauge Type -----
Part Name Fuel pump Gauge Name V.C
GAUGE REPEATABILITY AND REPRODUCIBILITY DATA SHEET
Part No. HA196100-3101 Gauge No. XXXXX Operator Name (s)
R = [ Ra + Rb +Rc] / 3
17
18. Doc. No. Written
Line Name
Date YYYY MM DD
No. of Trials 3 3 10
1
2
3
R
REPEATABILITY - EQUIPMENT VARIATION (EV)
R = 0.0103 % EV = 100 [EV/TV]
K1 = 3.05 Trials K1
EV = R X K1 2 4.56 = 68%
= 0.031517 3 3.05
REPRODUCIBILITY - APPRAISAR VARIATION (AV)
X Diff = 0.012 % AV = 100[AV/TV]
K2 = 2.70
= 68%
AV = SQRT OF [(X Diff X K2) - (EV / n x r) ]
= 0.032
Note: n = number of parts; r = no. of trials
2 3
3.65 2.70
REPRODUCIBILITY & REPEATABILITY (R&R)
%R&R = 100[R&R/TV]
R&R = SQRT OF ( EV + AV )
= 0.045 = 96%
PART VARIATION (PV) Parts (n) K 3
2 3.65 % PV = 100[PV/TV]
Rp = 0.008 3 2.70
K3 = 1.62 4 2.30 = 27%
5 2.08
PV = Rp X K3 6 1.93
= 0.0126 7 1.82
8 1.74
9 1.67
10 1.62
TOTAL VARIATION (TV)
TV = SQRT OF (R&R + PV )
= 0.0466
PERFORMED BY : DATE :
MEASUREMENT UNIT ANALYSIS % PROCESS VARIATION
No. of Operators
K 2
From Data Sheet:
0.0103 X diff 0.012 Rp 0.008
Specification 0.6 ~ 1.0mm
Characteristic Gauge Type
Operator Name (s)
Part Name Gauge Name
Part No. Gauge No.
No. of operators No. of Parts
GAUGE REPEATABILITY AND REPRODUCIBILITY ANALYSIS REPORT
Rev. No. Approved Checked
22
22
2 2
18
19. MSA STUDY FOR ATTRIBUTE STUDY
S.NO
1 G G G G
2 NG NG NG NG
3 G G G G
4 G G G G
5 G G G G
6 G G G G
7 G G G G
8 NG NG NG G
9 G G G G
10 G G G G
11 G G G G
12 G G G G
13 G G NG NG
14 G G G G
15 G G G G
16 G G G G
17 G G G G
18 NG NG NG NG
19 G G G G
20 G G G G
Appraiser A Appraiser B
19