1统计过程控制工作坊SPCWorkShop精益管理顾问公司---企业管理的好帮手2基本统计概念BasicSPCConcept3统计学(Statistics)收集、整理、展示、分析、解析统计资料Collect,collate,display,analysis,explainofdata由样本推论母体/群体Fromsampletoprojectthepopulation能在不确定情况下作决策Decisionwithuncertainty是一门科学方法、决策工具Scientificanddecisiontool基本统计概念BasicSPCConcept抽样推论x4统计量StatisticalValueR全距(range)算术平均数(arithmeticmean)Md中位数(median)Mo众数(mode)2方差/变异(variance)标准差(standarddeviation)基本统计概念BasicSPCConcept)(x5R全距(range)R=Xmax-Xmin算术平均数(arithmeticmean)基本统计概念BasicSPCConceptnxfxniii1)(x6Md中位数(median)顺序数列中的中心项的数值ThemedialnumberintheseriesMo众数(mode)资料中出现最多的数值Thenumberwithhighestfrequency基本统计概念BasicSPCConcept72方差/变异(variance)基本统计概念BasicSPCConcept])xx(....)xx()xx[(1n11n)xx(f2n2221n1i2ii21n])xx(....)xx()xx[(n1n)xx(f2n2221n1i2ii2n8标准差(standarddeviation)基本统计概念BasicSPCConcept2n2221n1i2iin)xx(...)xx()xx[(n1n)xx(f2n2221n1i2ii1n)xx(...)xx()xx[(1n11n)xx(f9例:Case1,1,2,3,4,6,11R=10=4Md=3Mo=1n2=10.86n-12=12.67n=3.29n-1=3.56基本统计概念BasicSPCConceptx10数据的收集与整理DataCollectionandCollation分析测试行动ActionTestAnalysis数据Data结Conclusion样本Sample群体PopulationSampling抽样11数据收集DataCollection33333031313128292934273327302933312827343326323532263228342828293028293432303128302732293026302831303132292527293027303329292926313212数据整理DataCollate-次数分配FrequencyDistribution数值Value次数划记FreqMarks次数Freq25X126XX427XXXXXX628XXXXXXXX829XXXXXXXXXX1030XXXXXXXXXX1031XXXXXXXX832XXXXXX633XXXXXX634XXXX435X113直方图(Histogram)14分布曲线DistributionCurve15正态(常态)分布的曲线图NormalDistributionCurve0.4)(zf0.30.20.1-2.5-2.0-1.5-1.0-0.500.51.01.52.02.522121)(zezf1116正态分布的性质NatureofNormalDistribution-3-2-1123机会率Probaility0.6750.00%168.26%1.9695.00%295.45%2.5899.00%399.73%17数据Data直方图Histogram分布曲线Distributionxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx33333031313128292934273327302933312827343326323532263228342828293028293432303128302732293026302831303132292527293027303329292926313218直方图Histogram分布Distribution0102030405052553053554054555055556056557057558001020304050-0.75-0.7-0.65-0.6-0.55-0.5-0.45-0.4正常型Normal19直方图Histogram分布Distribution02468101211811912012112212312412512612712812901020304016171819202122232425偏向型Bias20直方图Histogram分布Distribution02468100.640.660.680.70.720.740.76051015200.530.550.570.590.610.630.650.670.690.710.730.750.770.790.810.83孤岛型Island21过程变差ProcessVariation22输入(材料)Input(Material)过程(生产/装配)Process输出(产品)Output(Product)反馈(测量/检验)Feedback(Test/Insp.)测量系统MSA)材料Material过程变差ProcessVariation23过程变差ProcessVariation输入材料MaterialInput不同批次之间的差异LottoLotVariation批次内的差异WithinLotVariation随时间产生的差异VariationinTimeSeries随环境而产生的差异VariationduetoEnvironment24过程变差ProcessVariation生产/装配Production/Assembly设备及工装夹具的差异EquipmentandToolingVariation随时间而产生的磨损,漂移等AgingandShiftbytime操作工之间的差异(如手工操作的过程)VariationbetweenOperators(ManualWork)设置的差异DifferentSetup环境的差异DifferentEnvironments25过程变差ProcessVariation输出产品OutputProduct输出的产品随时间而产生的变化ProductVariationbytimeseries输出的产品随环境而产生的变化ProductVariationduetoenvironment26过程变差ProcessVariation反馈-测量Feedback-Measurement由于测量用于过程中的所有组成部分,测量的变差会对过程的各个阶段产生影响Measurementsarepartoftheprocess,variationinthemeasurementcanaffecttheprocessinvariousstages偏倚Bias稳定性Stability重复性Repeatability再现性Reproducibility分辨率Resolution27持續改進過程循環的各個階段2.維護過程•監控過程性能•查找偏差的特殊原因並採取措施3.改進過程.•改變過程從而更好地理解普通原因變差•減少普通原因變差1.分析過程•本過程應做些什麼?•會出現什麼錯誤?•本過程正在做什麼?•達到統計控制狀態?•確定能力計劃實施措施研究計劃措施實施研究計劃實施措施研究28过程变差ProcessVariation范围范围范围范围每件产品的尺寸与别的不同EachproductdimensionhasdifferencesSPEC29过程变差ProcessVariation范围范围范围但它们形成一个模型,若稳定,可以描述为一个分布Thedataaregroupedtoformthemodel.Ifstable,itcanbedescriedasthedistribution.30过程变差ProcessVariation分布可以通用过以下因素来加以区分Distributioncanbedescriedwithvariouselements或这些因数的组合Orthecombinationoftheseelements范围范围范围位置Position分布宽度置Spread形状Form/Shape31过程变差ProcessVariation预测Forecast范围SPEC时间Time如果只存在变差的普通原因,随著时间的推移,过程的输出形成一个稳定的分布并可预测Ifthereareonlythecommoncauses,andmoveintimeseries,theprocessoutputsarepredictablewithstabledistribution目标直线TargetLine32过程变差ProcessVariation目标直线TargetLine预测Forecast范围Spec时间Time如果存在变差的特殊原因,随著时间的推移,过程的输出不稳定Ifthespecialcauseisinthevariation,intimeseries,theprocessbecomeunstable???????????????33过程控制和过程能力ProcessControlandProcessCapability过程控制ControlProcess受控InControl(消除了特殊原因)EliminatetheSpecialCause时间Time范围SPEC不受制OutOfControl(存在特殊原因)withSpecialCause34过程变差ProcessVariationDistributioncanbedescribedby:Location(typicalvalue)位置(典型值)Spread分布宽度Shape(patternofvariation)形状(变差的模式)LSLUSLTypicalvalue典型值Spread分布35过程变差ProcessVariation过程的变差分两个类型TwoCategories特殊原因造成的变差SpecialCauses普通原因造成的变差CommonCauses36过程变差ProcessVariation普通原因变差CommonCausesinVariation影响过程中每个单位affecteachunitintheprocess是由所有不可分派的小变差源组成Formedbyvariousvariationsources;and但遵循一个分布followaparticulardistribution通常需要采取系统措施来减小Usesystemcorrectiveactionstoreduce在控制图上表现为随机性randompointinthecontrolchartIfonlycommonc