MSA测量系统分析(英文版)培训讲学课件.ppt

《MSA测量系统分析(英文版)培训讲学课件.ppt》由会员分享，可在线阅读，更多相关《MSA测量系统分析(英文版)培训讲学课件.ppt（53页珍藏版）》请在三一办公上搜索。

1、SPC for Test System,Gauge R&R,2,有多少個黑點？,3,這些橫線是不是平行的？,4,是靜的還是動的？,5,三個正方形,6,幾何謎題,7,沒有適當的量測工具就無法管理品質!,8,比較式絕對式,顯示,量測之種類,顯示,9,Basic Concepts,Every Process produce a“Product”.Every product possesses Qualities(Features)Every Quality Feature Can be measuredTotal Variation=Product Variation+Measurement Var

2、iationSome Variation Inherent in System Design.Some Variation is due to a Faulty performance of the System(s).,10,Components of Measurement System,Equipment or GageType of Gage:Attribute:go-no go,vision systems Variable:calipers,probe,coordinate measurement machinesUnit of Measurement-discrimination

3、At least 1/10 of 6*process standard deviation(6s)Other rules:at least 1/10 of toleranceOperator&Operating InstructionsPart locating or orientation schemea gage must be able to consistently locate the part being measured.,11,Terms You Should Know,Measurement system:The collection of operations,proced

4、ures,gages and personnel use to obtain measurements of work piece characteristics Gage:A device used to obtain measurements Repeatability:Repeatability(Precision)The variation in measurement obtained with one measurement instrument when used by one operator to measure.)an identical characteristic on

5、 the same part.(EV:Equipment Variation Reproducibility:The variation in the average of the measurements made by different operators using the same measurement instrument when measuring identical characteristics on the same part.(AV:Appraiser Variation),12,Terms You Should Know,Bias:The difference be

6、tween the observed average of measurements and the reference value.Percent R&R:The percentage of process variation related to the measurement system for repeatability and reproducibility Stability:The total variation in the measurements obtained with a measurement system on the same master or parts

7、when measuring single characteristics over an extended timeperiod.Linearity:The difference in the bias values through the expected operating range of the gage.,13,1.Accuracy,Difference between the true average and the observed average(true average may be obtained using a more precise measuring tool)

8、,14,2.Reproducibility,Variation in average of measurements made by different operators using the same gage measuring the same part.Appraiser Variation(AV),15,3.Repeatability(Precision),Random variation in measurements when one operator uses the same gage to measure the same part several times.Equipm

9、ent Variation(EV),16,4.Stability,Difference in the average of at least 2 sets of measurements obtained with a gage as a result of time.,17,Precision and Accuracy,18,Accuracy and Stability,Measure same parts using a more precise instrument(Accuracy).,Measure same parts using the same gage at a later

10、date(Stability or Drift).,19,Measurement System Variables,20,Possible Sources of ProcessVariation,21,Sources of Measurement Error,Systematic Variations1.accuracy:improper calibration of equipment2.reproducibility:different operators using same equipment with different techniquesRandom Variations3.re

11、peatability:(for example,inconsistent part locating)Periodic Variations4.stability:wear,deterioration,environmental conditions,22,The GR&R Design Model,Suppose multiple operators,measure multiple parts several times each.Then:,In terms of the gage performance,between-operator reproducibility is due

12、to the operator effect and the operator*part interaction.Within-operator repeatability is from the pure error term.,23,The Components of Variance,24,Measurement Error Gage R&R,25,Averages,ANOVA analysis begins with the calculation of all relevant averages.Heres an example:,26,Types of Gage Error and

13、 AnalysisMethods:,Accuracy Gage Accuracy(Bias)StudyGage Linearity Study.Repeatability&ReproducibilityGage R&R(Methods:X-bar/Range or ANOVA)Repeated Measurement StudyRepeatability Static&Dynamic StudyStability Repeated Measurements,27,Variance Partitioning,The total variance of the GR&R data is parti

14、tioned into components according to the model.Variances add,so all partitioned pieces sum to the total data variance!,28,Two Way Anova Table,29,Gage R&R Acceptance,To determine acceptability,a ratio is typically formed comparing gage variation to either:Gage R&R%of Tolerance WidthGage R&R%of Total V

15、ariation 6s-represents 99.73%of values if normal distribution 5.15 s-represents 99%of values if normal distribution,30,Criteria for Evaluating Gage R&R,Gage R&R%-TV or R&R%-Toleranceif R&R%is:30%=measurement system needs improvement,31,Conducting a Gage R&R Study,1.Plan the approach What is nature o

16、f operator and measurement interaction?Reproducibility can be negligible sometimes.2.Select 3 well trained operators3.Select 10 parts for test,Select sample parts should represent entire normal production range.(Prefer cover the distribution of+/-4 sigma)4.Repeat measure each parts 3 times.5.Take me

17、asurements in random order.6.Take blind measurement Person measuring doesnt know which piece is being measured,what previous measurements were,or what other appraisers found.,32,Conducting a Gage R&R Study,7.Record all measurements on worksheet.8.Calculate trial range for each piece for each operato

18、r and record values,calculate R&R(square root of the sum of the squares of the repeatability and reproducibility).9.Keep the standard parts&its reading for“Equipment Correlation“purpose,33,Guidelines For Gauge R&R Acceptance,Under 10%Error:Acceptable10%30%Error:May be Acceptable depending on the imp

19、ortance of the application.Over 30%error:Improvement is needed,34,Gauge R&R Study,35,Gauge R&R Study,36,Gauge R&R Study,37,Gauge R&R Study,38,Gauge R&R Study,39,Anova Method Example,Equipment Calibration By Simple Linearity Model(Y=mX+b),41,Selection of Standard Units,Set up about 10 pcs standard un

20、its which can cover the overall spread of normal production.Prefer 2 reject unit beyond upper/lower spec.Aging all units Find standard reading,42,Regression Analysis:Equipment vs Standard,Measure Standard unit on each individual test equipment several times.Take the average of measurement data for e

21、ach unitRegression Analysis;Equipment Reading vs Standard Reading.If correlation coefficient 90%,then calculate the slope and off-set per test m/c.If correlation coefficient 90%,find the reason.Test Result=Actual Reading X Slope+Offset,43,Measurement Data of Standard Sets each Test Machine,44,Regres

22、sion Analysis,45,Add Translation Key,After Correction=Reading X Slope+OffsetTest result become closer among test machines.,Slope/Offset per Test Equipment,46,Equipment Long Term Stability Test,Equipment long term stability can be checked by testing 13 working standard units per each time before oper

23、ator use that test machine and plot the test results on a SPC chart.,47,Computing Kappa(GR&R Test For visual inspector),48,Kappa Coefficient(Cohen,1960),Rater 2,Rater 1,pi.x p.i.39.075.01,High reliability requires that the frequencies along the diagonal should be chance and off diagonal frequencies

24、should be chance.Use marginal frequencies/probabilities to estimate chance agreement.,Proportion agreement observed,po=ipii=1/n inii,Proportion agreement expected by chance,pc=ipi.x p.i,49,Kappa Coefficient(Cohen,1960),Proportion agreement observed,po=ipii=1/n inii,Proportion agreement expected by c

25、hance,pc=ipi.x p.i,50,Select 20 good and 20 bad partsHave each inspector inspect each of the parts and record whether it“Passed”or“Failed”;capture data in a“Kappa Study Data Table”.Perform the study such that each inspector does not know what the other inspectors results are.Convert the data into pr

26、oportions and populate a“Kappa Contingency Table(a)Compute Kappa=(Pobserved-Pchance)/(1-Pchance)(b)Pobserved is the proportion of units on which both inspections agree(c)Pchance is the proportion of agreements expected by chanced.Kappa shall be 0.75.If Kappa is 0.75,the measurement system must be im

27、proved before accepting or rejecting parts.,Computing Kappa(GR&R Test For visual inspector),51,Example of Computing Kappa,52,Example of Computing Kappa,Proportion agreement observed,Proportion agreement expected by chance,K=P(agreement|no agreement by chance)1-pc=1-0.503=0.497 of cases where no agreement by chancepo-pc=0.825 0.503=0.322 of cases are those non-chance agreement cases where observers agreed.,&,