MSA Training.ppt

WELCOME TO TRAINING PROGRAM ON : 

Chintamani Kulkarni Rev. 0.0 1 WELCOME TO TRAINING PROGRAM ON MEASUREMENT SYSTEM ANALYSIS (MSA) BY CHINTAMANI KULKARNI

What is Measurement system : 

Chintamani Kulkarni Rev. 0.0 2 What is Measurement system A measurement system is a process by which we assign a number to a characteristic of a product / service. A measurement system includes Standard Item of interest (Work piece) Measurement equipment (Instrument) Personnel / Procedure to use the equipment Environment under which to conduct the measurement i.e. SWIPE

Slide 3: 

Chintamani Kulkarni Rev. 0.0 3

Effect of Measurement system error on Product Decisions : 

Chintamani Kulkarni Rev. 0.0 4 Effect of Measurement system error on Product Decisions A wrong decision may be taken whenever any part of the measurement distribution overlaps a specification limit. A “Good” part will sometimes be called as “Bad” (type I error, producer’s risk or false alarm)

Effect of Measurement system error on Product Decisions : 

Chintamani Kulkarni Rev. 0.0 5 Effect of Measurement system error on Product Decisions A “Bad” part will sometimes be called as “Good” (type II error, consumer’s risk or miss rate) This is most risky as Consumer will be suffering as “Bad” part will be delivered to him as “Good” part.

What is MSA? : 

Chintamani Kulkarni Rev. 0.0 6 What is MSA? Measurement System Analysis (MSA) Deals with analyzing the effect of the Measurement system on the measured value Emphasis is on the effect due to equipment & personnel We test the system to determine numerical values of its statistical properties and compare them to Accepted Standards

Measurement is not ALWAYS Exact : 

Chintamani Kulkarni Rev. 0.0 7 Measurement is not ALWAYS Exact Measurement system variation affects Individual measurements Decisions based on data

Attribute measurement system exampleCould this ball hit the stumps? (Decision for LBW) : 

Chintamani Kulkarni Rev. 0.0 8 Attribute measurement system exampleCould this ball hit the stumps? (Decision for LBW)

You require measurement system which will give enlarged view : 

Chintamani Kulkarni Rev. 0.0 9 You require measurement system which will give enlarged view

Ball just misses the stump. But will player will be given out or not? (OK or NOT OK) Can umpire give repeatedly CORRECT decisions? : 

Chintamani Kulkarni Rev. 0.0 10 Ball just misses the stump. But will player will be given out or not? (OK or NOT OK) Can umpire give repeatedly CORRECT decisions?

Repeatability : 

Chintamani Kulkarni Rev. 0.0 11 Repeatability Variation in measurements obtained with one measurement instrument when used several times by one assessor while measuring identical characteristic on same part.

Reproducibility : 

Chintamani Kulkarni Rev. 0.0 12 Reproducibility Reproducibility is variation in average of measurements made by different assessors using same measuring instrument when measuring identical characteristic on same part.

Stability : 

Chintamani Kulkarni Rev. 0.0 13 Stability Stability (or drift) is total variation in measurements obtained with a measurement system on same master or parts when measuring a single characteristic over an extended time period. (a time period is days, not hours)

Linearity : 

Chintamani Kulkarni Rev. 0.0 14 Linearity Difference in bias values through expected operating range of gage.

Bias : 

Chintamani Kulkarni Rev. 0.0 15 Bias Difference between observed average of measurements and reference value. Reference value, also known as accepted reference value or master value, is a value that serves as an agreed‑upon reference for measured values. A reference value can be determined by averaging several measurements with a higher level of measuring equipment.

MSA Plan : 

Chintamani Kulkarni Rev. 0.0 16 MSA Plan

Gage R&R : 

Chintamani Kulkarni Rev. 0.0 17 Gage R&R Gage R&R is conducted for Variable measurements Attribute measurements

Conducting Gage R&R study (variable) : 

Chintamani Kulkarni Rev. 0.0 18 Conducting Gage R&R study (variable) Sample of Ten units are selected from manufacturing process. Three assessors who usually do measurements are selected to conduct study. Each part is measured Two / Three times at random by three assessors and results are collected & tabulated. Equipment variation & Appraiser variation is calculated

Conducting Gage R&R study (variable) : 

Chintamani Kulkarni Rev. 0.0 19 Conducting Gage R&R study (variable) Calculations R = 0.3417, n = 10, r = 3, Xdiff = 0.4446, Rp = 3.511 Repeatability = Equipment variation (EV) = R * K1 = 0.3417*0.5908 = 0.20188 Reproducibility = Appraiser variation (AV) = Sq. root {(Xdiff * K2) – (EV*EV / nr)} = 0.22963 n = parts, r = trials

Conducting Gage R&R study (variable) : 

Chintamani Kulkarni Rev. 0.0 20 Conducting Gage R&R study (variable) Repeatability & Reproducibility (GRR) = Sq. root (EV*EV + AV*AV) GRR = 0.30375 Part variation (PV) = Rp*K3 = 1.10456 Total variation (TV) = Sq. root (GRR*GRR + PV*PV) = 1.14610 % EV = 100 [EV / TV] = 17.62 % % AV = 100 [AV / TV] = 20.04 % % GRR = 100 [GRR / TV] = 26.68 % % PV = 100 [PV / TV] = 96.38 %

Attribute Gage Study : 

Chintamani Kulkarni Rev. 0.0 21 Attribute Gage Study Select 20 parts Include some parts that are marginal on upper & lower specification limits Select two / three assessors who regularly use the gage as part of their daily work Take two / three measurements by each assessor on each part at random

Parts in Gray areas : 

Chintamani Kulkarni Rev. 0.0 22 Parts in Gray areas

Analysis of GRR studies : 

Chintamani Kulkarni Rev. 0.0 23 Analysis of GRR studies If Repeatability is large compared to Reproducibility The instrument needs maintenance The gage may need to be redesigned to be more rigid The clamping or location for gaging needs to be improved There is excess within part variation

Analysis of GRR studies : 

Chintamani Kulkarni Rev. 0.0 24 Analysis of GRR studies If Reproducibility is large compared to Repeatability The Appraiser needs to be better trained in how to use & read gage instrument Calibrations on the gage dial are not clear A fixture of some sort may be needed to help the Appraiser use the gage more consistently

Gage stability study : 

Chintamani Kulkarni Rev. 0.0 25 Gage stability study Obtain sample & establish its reference value relative to traceable standard, identify as master sample for stability analysis If not possible select production part in mid range of process / tolerance Measure master(s) three to five times (based on knowledge of measurement system) at different times of the day for a week Plot data on X bar & R chart Compare standard deviation for measurements with process to determine suitability for the application

Bias study : 

Chintamani Kulkarni Rev. 0.0 26 Bias study Obtain accepted reference value for part Use tool room or layout inspection equipment Measure same part minimum 10 times using gage under evaluation Calculate average of readings Bias = observed average – reference value % Bias = 100 [Bias / Process variation (or tolerance)]

Gage Linearity Study : 

Chintamani Kulkarni Rev. 0.0 27 Gage Linearity Study Select 5-8 parts that can be measured at different operating ranges of measurement system Determine reference value for each part using layout inspection Use one appraiser to measure parts Take 10-12 repeated measurements on each part Calculate part’s bias Bias = observed average – reference value

Gage Linearity Study : 

Chintamani Kulkarni Rev. 0.0 28 Gage Linearity Study Plot bias average against reference values Linearity represented by slope of best fit line of these points Gage linearity index = Slope X Process variation or Tolerance % Linearity = 100 [Linearity / Process variation or Tolerance]

Charting Linearity : 

Chintamani Kulkarni Rev. 0.0 29 Charting Linearity

Slide 30: 

Chintamani Kulkarni Rev. 0.0 30 Thank You