Measurement Systems Analysis

Define

Measure

Analyze

Improve

By: Mahender Kumar Control1

 Learning Objectives

• Understand the language of Measurement.

• Show the importance of Measurement.
Measurement
• Walk away knowing how to perform a Gage
R&R and how to interpret results.
results
• Share some lessons learned.

2
Since Measurement systems
y represent
p
a sub-process within a process...

• They are subject to Variation.

• What could be the source of this variation?

• Why do Measurements Vary?

3
Sources of Measurement Variation

•Equipment
q p
•Part
•Operator
•Environment
•Procedure

4
Sources of Measurement Variation

Measurement System C&E Matrix

Measurements Materials Men

Cleanliness Procedure
P d
Mechanical Integrety Fatigue
Temperature
Attention
Dimension
Wear Calibration Error
Weight Interpretation
Corrosion Speed
Electrical Instability
Coordination
Hardness
Know ledge
Conductivity Dexterity
Algorithm Instability
Density Vision
Measurement System Error

Temp Fluxctuation Operator Technique Wear

Standard Procedure Stability

Line Voltage Variation Resolution
Sufficient Work time
Calibration
Vibration Maintenance Standard
Precision
Calibration Frequency
Cleanliness Design
Operator Training Temperature
Humidity Ease of use Cleanliness

Environment Methods Machines

Six Sigma Champion Training 5
Possible Sources of Process Variation
Observed Process Variation

Actual Process Variation Measurement Variation

Long-term Short-term Variation Variation due Variation due

Process Variation Process Variation w/i sample to gage to operators

Repeatability Accuracy Stability Linearity Reproducibility

We will look at “repeatability” and “reproducibility” as

these
ese aree thee primary
p y contributors
co bu o s too measurement
e su e e error.
e o.

6
Why MSA
 U : UNCERTAINITY
RU = U=
0.0001 0.0001 RANDOM UNCERTAINITY –
NATIONAL
STANDARD
FOUND THRU
CALIBRATION
RU = U= LABORATORY
0.001 0.001005 STANDARD
SYSTEM UNCERTAINITY – OF
MASTER
TOTAL UNCERTAINITY –
SQRT( RU*RU + SU*SU)
WORK
RU = 0.01 U=
STANDARD
0.01005

GAUGE FOR
RU = 0.05 U= INSPECTION /
0.05099 TESTING
Process Capability

Lower Spec. Limit Upper Spec. Limit

6σ
Tolerance = T

Process Capability = T / 6 σ > 1.33

Means, 6 σ < (0.75*T)
 Impact of Uncertainty ERROR identified through
Calibration Process

Lower Spec. Limit Upper Spec. Limit

Uncertainty

6 σ Process
P
Tolerance = T
 Knowledge to be obtained

• How big is the measurement error?

• What are the sources of measurement
error?
• Is the gage stable over time?
• Is the gage capable for this process?
• How do we improve the measurement
system?
11
 Sources of Variation
P d t Variability
Product V i bilit
(Actual variability)

Measurement
Variability

Total Variability
(Observed variability)

12
Effects of Measurement Error
Measurement
System Bias —
Averages Determined through
“Accuracy Study”

µ total = µ product + µ measurement

Measurement System
Variability Variability —
Determined through
“R&R Study” y

σ 2total = σ 2product + σ measurement

2

13
 Terminology

• Location related terms:

– True value
– Bias
– Linearity
• Stability (over time)
• Variation related terms
– Repeatability
– Reproducibility

14
 Definition of Terms

• Reference Value
– The theoretically or agreed upon correct
value of the characteristic being
measured, traceable to some standard

• Resolution
– The smallest increment,, or unit of
measure, available from a measurement
process
– Generally at least 1/10th of the specification
range
 Definition of Terms

• Precision
– The degree of agreement (or variability)
between individual measurements or test
results from measuring the same
specimen(s)

• Accuracy
y (Bias)
( )
– The difference between the average of the
measurement error distribution and the
reference value of the specimen measured
 The Nature of Process Variation

1 2 3 4 5

Precise but not Accurate

1 2 3 4

Accurate but not Precise

Rule
R l off th thumb:b
. . . . . .Test equipment MUST be a least 10 times
more accurate t & precise
i then
th what’s
h t’ bbeing
i ttested
t d
17
 Measurement System Error

Precise but Accurate but Not accurate Accurate

not accurate not precise or precise and
precise
Prrecision
Precision vs.
vs Accuracy

Accuracy
 Definition of Terms

• Repeatability
p y
– The variation in repeated measurements of the
same items with a single measurement system
– Within appraiser/system variation

• Reproducibility
R d ibilit
– The variation in the average measurements by
diff
different
t appraisers
i or systems
t measuring
i ththe
same items
– Between appraiser/system variation
 Terms

• Linearity
– The degree to which bias changes with
changes in the magnitude of the characteristic
measured

• Stability
y
– The dependability, or consistency of the
measurement p
process over time
 Measurement
Systems Capability
• The variability resulting from measurement error
must not exceed a significant proportion of the
intended specifications said to be capable
• In addition, it is not desirable for measurement
error to exceed a significant proportion of the
total process variability
• Capability is not the same as
acceptability, acceptability must be determined
on a case by
b case b basis
i
 Measurement System Studies

• Potential Studies
– Assess potential of a measurement system to
be capable over the long term
– 10 p
parts measured 2–3 times byy one or more
appraisers
– A “quick and dirty”
y studyy to find out if you
y are in
the ballpark
– Assesses repeatability and reproducibility
– Often called an R&R study
• True value:
– Theoreticallyy correct value – unknown and unknowable
– Reference standards
– NIST standards
• Bias
– Distance between average value of all measurements
and true value
– Amount gage is consistently off target
– Systematic error or offset
24
 BIAS Definition

BIAS — Is the difference between the

observed average of the measurement
and the reference value. The reference- Reference
value is the value that serves as an Value
agreed-upon reference. The reference
value can be determined by averaging
several measurements with a higher level
(e.g., metrology lab) of measuring
equipment.

Observed
A
Average V
Value
l
ACCURACY IS THE SAME AS BIAS
25
 Linearity
Difference in the accuracy values of a gage
through the expected operating range of the gage

Good Linearity Bad Linearity

Regression Plot Linearity is Not Good

55 55

45 45

35 35
Trials

Trials
Y=0.934227+0.994959X Y=0.245295+0.99505X
25 25
R-Squared=0.981 R-Squared=0.982

15 15

5 5

10 20 30 40 50 10 20 30 40 50

Standard Standard

26
 Stability

• The distribution of measurements remains

constant and predictable over time for both mean
and standard deviation
• Total variation in the measurements obtained with
a gage, on the
th same mastert or master
t parts,
t
when measuring a single characteristic over an
extended time period
period.
• Evaluated using a trend chart or multiple
measurement analysis studies over time
27
 Stability (drift) Definition

Time-2
Stability — Is the total variation in
the measurement obtained with a
measurement system (test / gage ) on
the same master pparts when measuringg
a single characteristic over an
extended time period.
Magnitude
g
Ti
Time-1
1

time
Points to the frequency of Mean center Calibration Stability

28
• Total variation in the measurement system
p
• Measure of natural variation of repeated
measurements
• Terms: Random Error, Spread, Test/Retest
error
• Repeatability and Reproducibility

σ 2
MS =σ +σ
2
G
2
O

29
 Repeatability
p y
σG
• The inherent variability of the measurement system
• Variation in measurements obtained with a gage when
usedd severall titimes b
by one operator
t while
hil measuring
i a
characteristic on one part.
• Estimated by the pooled standard deviation of the
distribution of repeated measurements R
σG =
d 2*
• Repeatability is less than the total variation of the
measurement system

30
 R
Repeatability
t bilit Definition
D fi iti

Repeatability — The variation in measurements

obtained with one measurement instrument
when used several times by one appraiser while
measuring the identical characteristic on
same part.

REPEATABILITY

31
 Reproducibility
p y σO

• Operator variability of the measurement system

• Variation in the average of the measurements
made
d b by diff
different operators using
i the
h same gage
when measuring a characteristic on one part
• Must
M t be
b adjusted
dj t d ffor gage variation
i ti
• Reproducibility is less than the total variation of
the measurement system

R
σ O = *
d2
32
 Reproducibility Definition
Operator-B
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 Operator-C
Ope ato C
part.

Operator-A

Reproducibility
d ibili
33
 Accuracy of Measurement

• Broken down into three components:

1. Stability:
y the consistency
y of
measurements over time.
2. Accuracy: y a measure of the amount of
bias in the system.
3. Linearity:
y a measure of the bias values
through the expected range of
measurements.
 Precision of Measurement

• Precision, Measurement Variation, can be

broken down into two components:
p
1. Repeatability (Equipment variation): variation in
measurements under exact conditions.
2. Reproducibility (Appraiser variation): variation
in the average of measurements when different
operators measure the same part.
Measurement System
y Discrimination
zLeast count should be at most one-tenth of the total
process capability or tolerance (6 sigma)
– Process capability 10 Max Least count 1
zPart to Part variation must be greater than the smallest
unit
it off measure

36
 Types of R&R Studies

• Variable Gage R&R

– Numbers
– Units of measure
• Attribute Gage R&R
– Subjective (cosmetic defects)
– Scatter of defects
– feel/visual

37
 Basic Terms

zEV= Equipment Variation (Repeatability)

zAV= Appraiser Variation (Reproducibility)

zAV

zR&R= Repeatability & Reproducibility

zPV= Part Variation

zTV= Total Variation of R&R and PV

zK1-Trial, K2-Operator, & K3-Part Constants

38
 Gage R&R study

z Generally two or three operators

z Generally 10 units to measure

z Each unit is measured 2-3 times by each

operator

39
 Preparation
p for a Measurement
Study
• Determine if reproducibility is an issue. If it is, select the
number of operators to participate.
• Operators selected should normally use the measurement
system.
• Select samples that represent the entire operating range.
• Gage must have graduations that allow at least one-tenth
of the expected process variation.
• Insure defined gaging procedures are followed
followed.
• Measurements should be made in random order.
• Study must be observed by someone who recognizes the
importance of conducting a reliable study.
40
 Procedure for Performing
g R&R
Study
• Calibrate the gage, or assure that it has been calibrated.
• Have the first operator measure all the samples once in random
order.
• Have the second operator measure all the samples once in
random order.
• Continue until all operators
p have measured the samples
p once
(this is Trial 1).
• Repeat above steps for the required number of trials.
• Use GR&R form to determine the statistics of the study.y
– Repeatability, Reproducibility & %GR&R
– Standard deviations of each of the above
– % Tolerance analysis
• Analyze results and determine action, if any.
41
 Variable Gage
g R&R

Guidelines
% R&R Results
≤ 10% Gage is OK
10% – 30% Maybe acceptable based upon importance
of application, and cost factor
Over 30% Gage system needs improvement/corrective
action

42
 Xbar Chart by Operator Operator*Part No. Interaction

A- B- C-
40
40
35
35
30
30
Sample Mean
n

Average
25 25

20 20

15 15

10
10
5
5
0
0 1 2 3 4 5 6 7 8 9 10

Part No.

43
 Thanks

For any query pl.

pl mail me at mahender.kumar@yahoo.co.in
mahender kumar@yahoo co in

44