MEASUREMENT SYSTEM ANALYSIS

Presented by:

United Registrar of Systems-Middle East

19/04/12

URS/MSA

AGENDA

19/04/12

Why MSA ? Normal Distribution Definitions R&R Calculation R&R Analysis Gauge R&R (Attribute) Plotting of Charts Work shops
URS/MSA 2

MEASUREMENT SYSTEM ERRORS

Bias Repeatability Reproducibility Stability Linearity

19/04/12

URS/MSA

BIAS
The difference between the observed average of measurements and the reference value. The reference value or master value, is a value determined by averaging several measurements with a higher level (e.g., metrology lab or layout equipment) of measuring equipment.
Reference Value
Bias

Observed Average Value

Bias
19/04/12 URS/MSA 4

BIAS
BIAS = Observed Value Reference Value % BIAS = {Bias / Process Variation} 100 Tolerance can take as process variation
BIAS
OBSERVED BIAS REFERENCE VALUE

19/04/12

URS/MSA

REPEATABILITY
Variation in measurements obtained with one measurement instrument used several times by one appraiser and measuring the identical characteristic on the same part

Range Repeatability

19/04/12

URS/MSA

REPRODUCIBILITY
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.
19/04/12 URS/MSA

Operator B

Operator C

Operator A
Diff. Reproducibility
7

STABILITY
Stability (or drift) is the total variation in the measurements obtained with a measurement system on the same master or parts when measuring a single characteristic over an extended time period
19/04/12 URS/MSA

Stability

Time 2

Time 1

Stability

LINEARITY
Linearity is the difference in the bias values through the expected operating Range of the gage
REFERENCE VALUE
BI AS

OBSERVED AVERAGE VALUE

NO BIAS

19/04/12

URS/MSA

DEFINITIONS
Measurement Assignment of numbers to material things to represent the relations among them with respect to particular properties. Measurement System The collection of operations, procedures, gauges and other equipments, software and personnel used to assign a number to the complete process used to obtain measurements.

19/04/12

URS/MSA

10

DEFINITIONS
Accuracy (Location) Closeness to the true value or to an accepted reference value Precision (width) Closeness of repeated readings to each other Measurement System Capability (width) A short term estimate of measurement system variation Measurement System Performance (width) A long term estimate of measurement system variation Measurement System Uncertainty An estimated range of values about the measured value in which the true value is believed to be contained
19/04/12 URS/MSA 11

DEFINITIONS
Sensitivity: Smallest input that results in a detectable output signal or responsiveness of the measurement system to change in measured feature Consistency: The degree of change of repeatability over time or a consistent measurement process is in statistical control with respect to width Uniformity: The change in repeatability over the normal operating range or homogeneity or repeatability
19/04/12 URS/MSA 12

PREPARATION FOR MSA

Criticality of dimension - critical dimensions need more trials Part configuration - bulky / heavy Sample must represent its entire operating range Instrument must have discrimination power - 1/10 of process variation Follow defined / standard measurement method Measurement in random order
19/04/12 URS/MSA 13

PROPERTIES OF MEASUREMENT SYSTEM (MS)

1. MS should be in statistical control common cause variations only
no special cause variation

2. Variability of MS Process Variability 3. Process Variability Specification Limits 4. Resl. of Equp. Process Variability

19/04/12

Resl. is preferably 1/10 of Process Variability(6)

URS/MSA 14

ANALYSIS OF RESULT
% GRR
Error < 10% 10% Error < 30% Error 30% MS is acceptable May be acceptable MS needs improvement

19/04/12

URS/MSA

15

ANALYSIS OF RESULT
Part-to-Part Variation: More than 90% part averages outside the limit - MS is acceptable No. of Distinct Categories: ndc 5 Linearity: Lower the slop, the better the gage linearity

19/04/12

URS/MSA

16

POSSIBLE CAUSES
Error in the master Worn components Instrument made to the wrong dimension Instrument measuring the wrong characteristics Instrument not calibrated properly Instrument used improperly by appraiser
19/04/12 URS/MSA 17

19/04/12

URS/MSA

18

19/04/12

URS/MSA

19