MSA测量系统分析报告ppt .ppt

TrainingMaterialforMEASUREMENTSYSTEMANALYSIS Contents INTRODUCTIONFORMEASUREMENTSYSTEMANALYSISGENERALMETHODSILLUSTRATIONFORMEASUREMENTSYSTEMANALYSISVARIABLEGAGEANALYSISMETHOD1 THEAVERAGE RANGEMETHOD2 THEANOVAMETHODATTRIBUTEGAGEANALYSISMETHOD1 SHORTMETHOD2 HYPOTHESISTESTANALYSIS3 SIGNALDETECTIONTHEORY4 LONGMETHODACCEPTABILITYCRITERIACONCLUSIONFOURMETHODSCOMPARISON Introduction BasicrequirementsbyQS 9000 TS16949 BaseonQS9000 TS16949requirements allmeasurementsystemwhichwerementionedinQualityPlanshouldbeconductedMeasurementSystemAnalysis MSARequirement Introduction ThecategoryofMeasurementSystem Mostindustrialmeasurementsystemcanbedividedtwocategories oneisvariablemeasurementsystem anotherisattributemeasurementsystem Anattributegagecannotindicatehowgoodorhowbadapartis butonlyindicatesthatthepartisacceptedorrejected ThemostcommonoftheseisaGo No gogage VariableGage AttributeGage Go No goGage Introduction Whatisameasurementprocess GeneralProcess MeasurementProcess Measurement Theassignmentofanumericalvaluetomaterialthingstorepresenttherelationsamongthemwithrespecttoaparticularprocess MeasurementProcess Theprocessofassigningthenumericalvaluetomaterialthings Introduction Whatarethevariationsofmeasurementprocess Introduction Whatarethevariationsofmeasurementprocess Measurement Observed Value ActualValue VarianceofTheMeasurementSystem Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 1 LocationVariation Bias Stability LinearityBiasisthedifferencebetweentheobservedaverageofmeasurementsandareferencevalue Biasisoftenreferredtoasaccuracy Itisasystematicerrorcomponentofthemeasurementsystem Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 1 LocationVariation Bias Stability LinearityStability Alias Drift Stabilityisthetotalvariationinthemeasurementsobtainedwithameasurementsystemonthesamemasterorpartswhenmeasuringasinglecharacteristicoveranextendedtimeperiod Astablemeasurementprocessisinstatisticalcontrolwithrespecttolocation Stability Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 1 LocationVariation Bias Stability LinearityLinearityisthedifferenceinthebiasvaluesthroughtheexpectedoperatingrangeofthemeasurementinstrument Itisasystematicerrorcomponentofthemeasurementsystem Linearity Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 2 WidthVariation Repeatability Reproducibility GageR RRepeatabilityisthevariationinmeasurementsobtainedwithonemeasurementinstrumentwhenusedseveraltimeswhilemeasuringtheidenticalcharacteristiconthesamepartbyanappraiser ItisaWithin systemvariation commonlyreferredtoasE V EquipmentVariation Repeatability Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 2 WidthVariation Repeatability Reproducibility GageR RReproducibilityisthevariationintheaverageofthemeasurementsmadebydifferentappraisersusingthesamegagewhenmeasuringtheidenticalcharacteristicsofthesamepart Itisbetween systemvariation commonlyreferredtoasA V AppraiserVariation Reproducibility Introduction Wheredoesthevariationofmeasurementsystemcomefrom TheFiveCharacterizationsofMeasurementSystem 2 WidthVariation Repeatability Reproducibility GageR RGageR RmeansGagerepeatabilityandreproducibility whichcombinedestimateofmeasurementsystemrepeatabilityandreproducibility ThiscombinedmeasurementerrortheniscomparedwiththeprocessoutputvariabilitytocomputethegagepercentageR R R R The R Risthebasisformakingajudgmentofwhetherthemeasurementsystemisgoodenoughtomeasuretheprocess AnalysisTechniques CurrentlytherearethreetechniquesforvariablemeasurementsystemandfourtechniquesforattributemeasurementsystemanalysiswererecommendedbyAIAGMSAReferenceManual RangeMethod Average RangeMethod ANOVA ShortMethod LongMethod HypothesisTestAnalyses SignalDetectionTheory Followingsaresomepracticalexamplestoillustratehowtoperformfourmethodsrespectively VariableGage AttributeGage AnalysisTechniques PreparationbeforeMSA Theapproachtobeusedshouldbeplanned Thenumberofappraisers numberofsampleparts andnumberofrepeatreadingsshouldbedeterminedinadvance Theappraisersshouldbeselectedformthosewhonormallyoperatetheinstrument Thesamplepartsmustbeselectedfromtheprocessandrepresentitsentireoperatingrange Theinstrumentmusthaveadiscriminationthatallowsatleastone tenthoftheexpectedprocessvariationofthecharacteristictobereaddirectly Themeasurementprocedureshouldbedefinedinadvancetoensuretheconsistentmeasuringmethod AnalysisTechniques VariableGageAnalysis GeneralGageR RStudy TheAverageandRangeMethod TheANOVAMethod ThecommonstepforconductingGageR Rstudy 1 Verifycalibrationofmeasurementequipmenttobestudied 2 Obtainasampleofpartsthatrepresenttheactualorexpectedrangeofprocessvariation 3 Addaconcealedmarktoeachidentifyingtheunitsasnumbers1through10 Itiscriticalthatyoucanidentifywhichunitiswhich Atthesametimeitisdetrimentaliftheparticipantsinthestudycantelloneunitfromtheother maybiastheirmeasurementshouldtheyrecallhowitmeasuredpreviously 4 Request3appraisers RefertotheseappraisersasaA B andCappraisers Ifthemeasurementwillbedonerepetitivelysuchasinaproductionenvironment itispreferabletousetheactualappraiserthatwillbeperformingthemeasurement Forextremecases aminimumoftwoappraiserscanbeused butthisisstronglydiscouragedasalessaccurateestimateofmeasurementvariationwillresult 5 LetappraiserAmeasure10partsinarandomorderwhileyourecordthedatanotingtheconcealedmarking LetappraisersBandCmeasurethesame10partsNote Donotallowtheappraiserstowitnesseachotherperformingthemeasurement Thereasonisthesameaswhytheunitmarkingsareconcealed TOPREVENTBIAS 6 Repeatthemeasurementsforallthreeappraisers butthistimepresentthesamplestoeachinarandomorderdifferentfromtheoriginalmeasurements Thisistoagainhelpreducebiasinthemeasurements AnalysisTechniques VariableGageAnalysis 10Parts 3Appraisers 3Trials TheAverageandRangeMethod Arangecontrolchartiscreatedtodetermineifthemeasurementprocessisstableandconsistent Foreachappraisercalculatetherangeoftherepeatedmeasurementsforthesamepart AnalysisTechniques VariableGageAnalysis AnalysisTechniques VariableGageAnalysis Theaveragerangeforeachoperatoristhencomputed Theaverageofthemeasurementstakenbyanoperatoriscalculated Acontrolchartofrangesiscreated Thecenterlinerepresentstheaveragerangeforalloperatorsinthestudy whiletheupperandlowercontrollimitconstantsarebasedonthenumberoftimeseachoperatormeasuredeachpart trials AnalysisTechniques VariableGageAnalysis Thecenterlineandcontrollimitsaregraphedontoacontrolchartandthecalculatedrangesarethenplottedonthecontrolchart Therangecontrolchartisexaminedtodeterminemeasurementprocessstability Ifanyoftheplottedrangesfalloutsidethecontrollimitsthemeasurementprocessisnotstable andfurtheranalysisshouldnottakeplace However itiscommontohavetheparticularoperatorre measuretheparticularprocessoutputagainandusethatdataifitisin control AnalysisTechniques VariableGageAnalysis Repeatability EquipmentVariation E V Theconstantd2 isbasedonthenumberofmeasurementsusedtocomputetheindividualranges n ortrials thenumberofpartsinthestudy andthenumberofdifferentconditionsunderstudy TheconstantK1isbasedonthenumberoftimesapartwasrepeatedlymeasured trials Theequipmentvariationisoftencomparedtotheprocessoutputtoleranceorprocessoutputvariationtodetermineapercentequipmentvariation EV AnalysisTechniques VariableGageAnalysis Reproducibility AppraiserVariation A V Xdiffisthedifferencebetweenthelargestaveragereadingbyanoperatorandthesmallestaveragereadingbyanoperator TheconstantK2isbasedonthenumberofdifferentconditionsanalyzed Theappraiservariationisoftencomparedtotheprocessoutputtoleranceorprocessoutputvariationtodetermineapercentappraiservariation AV AnalysisTechniques VariableGageAnalysis RepeatabilityandReproducibility GageR R Thegageerror R R iscomparedtotheprocessoutputtolerancetoestimatetheprecisiontotoleranceratio P Tratio Thisisimportanttodetermineifthemeasurementsystemcandiscriminatebetweengoodandbadoutput Thebasicinterestofstudyingthemeasurementprocessistodetermineifthemeasurementsystemiscapableofmeasuringaprocessoutputcharacteristicwithitsownuniquevariability ThisisknowasthePercentR R P Pratio R R andcalculatedasfollows AnalysisTechniques VariableGageAnalysis ProcessorTotalVariation Iftheprocessoutputvariation m isnotknown thetotalvariationcanbeestimatedusingthedatainthestudy Firstthepartvariationisdetermined Rpistherangeofthepartaverages whileK3isaconstantbasedonthenumberofpartsinthestudy Thetotalvariation TV isjustthesquarerootofthesumofthesquaresofR Randthepartvariation AnalysisTechniques VariableGageAnalysis TheANOVAMethod AweaknesswiththeAverage RangemethodofusingtherangetodeterminegageRwhilerepeatabilityisestimatedby r2 AnalysisTechniques VariableGageAnalysis Part Operator Interaction Repeatability AnalysisTechniques VariableGageAnalysis Total ThegageR Rstatisticsarethencalculatedasfollows MeasurementError Part Operator Interaction Reproducibility Repeatability MeasurementError Total AnalysisTechniques VariableGageAnalysis AcceptabilityCriteria Thegagerepeatabilityandreproducibility RP Tration totaloftolerance Lessthan10 Outstanding10 to20 Capable20 to30 MarginallyCapableGreaterthan30 NOTCAPABLEFortheP PratioandtheP Tratio eitherorbothapproachescanbetakendependingontheintendeduseofthemeasurementsystemandthedesiresofthecustomer Generally Ifthemeasurementsystemisonlygoingtobeusetoinspectiftheproductmeetsthespecs thenweshouldusethe R Rbaseonthetolerance P Tratio Ifthemeasurementsystemisgoingtobeuseforprocessoptimization characterizationanalysis thenweshouldusethe R Rbaseontotalvariation P Pratio AnalysisTechniques VariableGageAnalysis AcceptabilityCriteria ForaGagedeemedtobeINCAPABLEforit sapplication Theteammustreviewthedesignofthegagetoimproveit sintendedapplicationandit sabilitytomeasurecriticalmeasurementscorrectly Also ifare calibrationisrequired pleasefollowcaliberationsteps Ifrepeatabilityislargecomparedtoreproducibility thereasonsmightbe 1 theinstrumentneedsmaintenance thegageshouldberedesigned2 thelocationforgagingneedstobeimproved3 thereisexcessivewithin partvariation Ifreproducibilityislargecomparedtorepeatability thenthepossiblecausescouldbe 1 inadequatetrainingonthegage 2 calibrationsarenoteffective 3 afixturemaybeneededtohelpusethegagemoreconsistently AnalysisTechniques VariableGageAnalysis TheMeasurementBias Usingacertifiedsample andacontrolchartofrepeatedmeasurements thebiasofameasurementprocesscanbedetermined Biasisthedifferencebetweentheknownvalueandtheaverageofrepeatedmeasurementoftheknownsample Biasissometimescalledaccuracy ProcessVariation 6SigmaRange AnalysisTechniques VariableGageAnalysis Linearity Linearityofameasurementprocessisthedifferenceinthebiasorprecisionvaluesthroughtheexpectedoperatingrangeofthegauge Toevaluatelinearity agraphcomparingthebiasorprecisiontotheexpectedoperatingrangeiscreated Aproblemwithlinearityexistsifthegraphexhibitsdifferentbiasorprecisionfordifferentexpectedoperatingranges Byusingthefollowingprocedure linearitycanbedetermined 1 Selectfivepartswhosemeasurementscovertheoperatingrangeofthegage 2 Verifythetruemeasurementsofeachpart 3 Haveeachpartberandomlymeasured12timesonthegagebyoneoperator 4 Calculatethepartaverageandthebiasforeachpart 5 Plotthebiasandthereferencevalues 6 Calculatethelinearregressionlinethatbestfitsthesepoints AnalysisTechniques VariableGageAnalysis 7 Calculatethegoodnessoffitstatistic AnalysisTechniques VariableGageAnalysis 8 Determinelinearityandpercentlinearity Linearity SlopexProcessvariation m Linearity 100 linearity ProcessVariation TheacceptabilitycriteriaofBias LinearitydependonQualityControlPlan characteristicbeingmeasuredandgagespeciality suggestedcriteriaofESGisasfollowing Under5 acceptable5 to15 maybeacceptablebaseduponimportanceofapplication costofmeasurementdevice costofrepairs etc Over15 Considerednotacceptable everyeffortshouldbemadetoimprovethesystemThestabilityisdeterminedthroughtheuseofacontrolchart Itisimportanttonotethat whenusingcontrolcharts onemustnotonlywatchforpointsthatfalloutsideofthecontrollimits butalsocareotherspecialcausesignalssuchastrendsandcenterlinehugging GuidelineforthedetectionofsuchsignalscanbefoundinmanypublicationsonSPC AnalysisTechniques AttributeGageStudy ShortMethod AShortMethodexampleforbatterylengthgo no gogagestudy TheShortmethodneedtobeconductbyselecting20partswhichhavebeenmeasuredbyavariablegageinadvance someofthepartsareslightlybelowandabovebothspecificationlimits Twoappraisersthenmeasureallpartstwicerandomly MeasurementResulttable1 AnalysisTechniques AttributeGageStudy Acceptabilitycriteria Ifallmeasurementresults fourperpart agree thegageisacceptable Ifthemeasurementresultsdonotagree thegagecannotbeaccepted itmustbeimprovedandre evaluated Conclusion Becausetable1listedmeasurementresultsarenotwholeagreement atpart15 and17 appraiser sdecisionsarenotagree sothebatterylengthgagecannotbeusedandmustbeimprovedandre evaluated AnalysisTechniques AttributeGageStudy HypothesisTestAnalysis Shortmethodshouldknowthevariablereferencevalueofsamplesinadvance However insomesituationsitishardtorealizetogetallsamplesvariablereferencevalue Sointhiscase Hypothesistestanalysisshallbeappliedforgagestudy AnalysisTechniques AttributeGageStudy Hypothesistestanalysisdependsoncrosstabulationmethodwhichneedstotakearandomsampleof50partsfromthepresentprocessanduse3appraiserswhomake3measurementsoneachpartanddecideifthepartisacceptableornot Appraisersmeasurethepartsandifthepartiswithinlimitstheygive 1 andifnottheygive 0 andwritethoseresultsinatable Inordertoeliminateanybiasproduced thelabeledsamplesaremixedbeforegivingtoappraisersforidentificationineachtrails Followingtable2listedfillergagemeasuringresultsforthebattery weldinggap 50Samples 3Appraisers 3Trials Table2Fillergagemeasuringresult Table2Fillergagemeasuringresult Table2Fillergagemeasuringresult AnalysisTechniques AttributeGageStudy Inordertodeterminethelevelofagreementamongtheappraisers weappliedCohen sKappawhichisusedtoassessinter raterreliabilitywhenobservingorotherwisecodingqualitative categoricalvariables Itcanmeasuretheagreementbetweentheevaluationsoftworaterswhenbothareratingthesameobject Step1 Organizethescoreintoacontingencytable Sincethevariablebeingratedhastwocategories thecontingencytablewillbea2 2table Table3 AnalysisTechniques AttributeGageStudy A BCross TabulationTable3 AnalysisTechniques AttributeGageStudy Step2 Computetherowtotals sumacrossthevaluesonthesamerow andcolumntotalsoftheobservedfrequencies Step3Computetheoveralltotal showinthetable3 Asacomputationalcheck besurethattherowtotalsandthecolumntotalssumtothesamevaluefortheoveralltotal andtheoveralltotalmatchesthenumberofcasesintheoriginaldataset Step4Computethetotalnumberofagreementsbysummingthevaluesinthediagonalcellsofthetable a 53 89 142Step5Computetheexpectedfrequencyforthenumberofagreementsthatwouldhavebeenexpectedbychanceforeachcodingcategory ef 21 6Repeattheformulaforothercell wegototherexpectedcount showinthetable3 rowtotal coltotal overalltotal 59 55 150 Step6Computethesumoftheexpectedfrequenciesofagreementbychance ef 21 6 57 6 79 2Step7ComputeKappaK 0 89Step8EvaluateKappa Ageneralruleofthumbisthatvaluesofkappagreaterthan0 75indicategoodtoexcellentagreement valueslessthan0 4indicatepooragreement Repeatabovestep wecangotfollowingkappameasuresfortheappraisers Table4 AnalysisTechniques AttributeGageStudy a ef N ef 142 79 2 150 79 2 Table4 Usingthesamestepstocalculatedthekappameasuretodeterminetheagreementofeachappraisertothereferencedecision Table5TotalsummaryonTable6 AnalysisTechniques AttributeGageStudy Table5 AnalysisTechniques AttributeGageStudy AnalysisTechniques AttributeGageStudy TheAIAGMSAreferencemanualedition3providesacceptabilitycriteriaforeachappraisersresults Definition FalseAlarm Thenumberoftimesofwhichtheoperator s identifyagoodsampleasabadone Miss Thenumberoftimesofwhichtheoperatorsidentifyabadsampleasagoodone AnalysisTechniques AttributeGageStudy Sosummarizingalltheinformationoftheexamplewiththistable Table7 AnalysisTechniques AttributeGageStudy Conclusion ThemeasurementsystemwasacceptablewithappraiserB marginalwithappraiserA andunacceptableforC SoweshalldetermineifthereisamisunderstandingwithappraiserCthatrequiresfurthertrainingandthenneedtore doMSA Thefinaldecisioncriteriashouldbebasedontheimpacttotheremainingprocessandfinalcustomer Generally themeasurementsystemisacceptableifall3factorsareacceptableormarginal Minitabalsocanperformattributegageanalysis butitdidn tdeclaretheacceptabilitycriteria soitisnotrecognizedbyQS9000standard AnalysisTechniques AttributeGageStudy SignalDetectionTheoryistodetermineanapproximationofthewidthoftheregionIIareasoastocalculatethemeasurementsystemGR R AlsousedfillergageasexampletoperformSignalDetectionapproach Thetoleranceis0 45 0 55mm Theprocessneedstotakearandomsampleof50partsfromthepracticalprocessanduse3appraiserswhomake3measurementsoneachpart andthengotfollowingtable Table8 Table8SignalDetectionTableforFillerGage Table8SignalDetectionTableforFillerGage AnalysisTechniques AttributeGageStudy Abovetable8showsthe50partsmeasurementresult 0 standardrejected 1 standardacceptable code standardregionI code x standardregionII code standardregionIII AndthenbaseonthepartreferencevaluetoarrangeinorderfromMax toMin meanwhiletoshowthecode Table9 RegionIII RegionI RegionI RegionII RegionII AnalysisTechniques AttributeGageStudy NextstepweshouldfindXavaluewhichlocatedregionI butisthenearesttoregionII XbvaluewhichlocatedregionIII butisthenearesttoregionII AndthencalculatethedistanceofregionII dLSL Xa LSL Xb LSL 0 446697 0 470832 0 024135dUSL Xa USL Xb USL 0 566152 0 542704 0 023448 0 023791 0 55 0 45 GR R 0 277 27 7 GR R USL LSL Conclusion The GR Rislargerthan10 butlessthan30 itmaybeacceptablebaseduponimportanceofapplication costofmeasurementdevice costofrepairs etc AnalysisTechniques AttributeGageStudy LongMethodisusedtheconceptoftheGagePerformanceCurve GPC todevelopameasurementsystemstudy Itfocus