l連接控制圖方法與流程改進(jìn)方法 Link Control Chart methods to the Process Improvement Methodology TM l討論不同類型的變差 Discuss different types of variation l介紹各種類型的控制圖 Introduce various types of Control Chartsl討論如何解釋控制圖 Discuss the interpretation of Control Charts目的Objectives.2023/8/151.2023/8/152我們是否應(yīng)該采取行動(dòng)？Should we take action?每天我們都被數(shù)據(jù)淹沒,而且不得不作出決定Every day we are flooded by data and we are forced to make decisions工廠產(chǎn)量下降Plants Output Decreases By 4%美國(guó)貿(mào)易赤字增加億 US Trade Deficit Rises By$40Billion 某公司獲利比上季度降低億Company Xs Earnings Are Off$240Million From Previous Quarter 我們需要解釋數(shù)據(jù)的方法 We Need Ways to Interpret Data.2023/8/153今天采集什么樣的數(shù)據(jù)？What Type Of Data Is Collected Today?制造業(yè) Manufacturing:_非制造業(yè) Non-Manufacturing _如何分析數(shù)據(jù)？How Is It Analyzed?制造業(yè) Manufacturing :_非制造業(yè) Non-Manufacturing _得知數(shù)據(jù)好壞后該當(dāng)如何？What Happens If It Is Bad/Good?制造業(yè) Manufacturing :_非制造業(yè) Non-Manufacturing _ _.2023/8/154客戶需求下限Lower“Customer”Requirement這一方法THIS METHOD告訴你關(guān)于客戶的需求Tells you where you are in regards to customers needs不告訴你怎么滿足用戶需求及下一步怎么辦 It will NOT tell you how you got there or what to do next客戶需求上限Upper“Customer”Requirement 我們管理數(shù)據(jù)的方式過去(歷史來講)的方式 The Way We Manage Data Historically不用管它,不會(huì)壞的Leave It Alone.It Aint Broke痛苦,受累Pain&Suffering痛苦,受累Pain&Suffering.2023/8/155這一方法導(dǎo)致何種管理行為？This method causes what type of management behavior?客戶需求下限Lower“Customer”Requirement客戶需求上限Upper“Customer”Requirement 我們管理數(shù)據(jù)的方式歷史來講的方式 The Way We Manage Data Historically不用管它,不會(huì)壞的Leave It Alone.It Aint Broke痛苦,受累Pain&Suffering痛苦,受累Pain&Suffering.2023/8/15623Scrap Level(%)廢品率11996Celebration Time工廠廢品率為年度最低的The factory scrap level is at a year low of 2%經(jīng)理給工廠頒獎(jiǎng)Manager presents an award to the plant 在餐廳進(jìn)行慶祝：每人都可分享免費(fèi)皮薩餅和飲料 Ceremony in the cafeteria:pizza and refreshments for all!“每人都應(yīng)為他們的成就驕傲每人都應(yīng)為他們的成就驕傲”“Everyone should be proud of what theyve accomplished”.Everyone should be proud of what theyve accomplished”.Derived from Understanding Variation:The Key To Managing Chaos,Donald J.Wheeler,SPC Press.1993.年月 APRIL 1996J F M A .2023/8/1572311996經(jīng)理希望能將發(fā)出去的獎(jiǎng)收回來Manager wants to take back award廢品率連續(xù)三個(gè)月持續(xù)增長(zhǎng)Three consecutive months of scrap increases.經(jīng)理希望能將發(fā)出去的獎(jiǎng)收回來Manager wishes he could take back the award經(jīng)理考慮要采取行動(dòng)了 Manager is thinking about taking actionScrap Level(%)廢品率年月 JUNE 1996Derived from Understanding Variation:The Key To Managing Chaos,Donald J.Wheeler,SPC Press.1993.J F M A M J.2023/8/1582311996No more“Nice Guy”不再充好人了廢品率上升到 Scrap rises to a value of 2.6%經(jīng)理決定采取行動(dòng) Manager decides to take action召開一個(gè)“特別會(huì)議”來尋求一個(gè)永久性的解決方案A“special meeting”is called to solve this problem once and for all.經(jīng)理在長(zhǎng)篇大論次品率多么重要后離開了雇員們不知道該干什么另外，他們有其他更重要的評(píng)估標(biāo)準(zhǔn)于是，他們什么也沒做 After a sound lecture on the importance of scrap,the manager leaves.Employees arent sure what to do.Besides,they have other metrics which have more importance.So they do nothing.Scrap Level(%)廢品率年月NOVEMBER 1996Derived from Understanding Variation:The Key To Managing Chaos,Donald J.Wheeler,SPC Press.1993.J F M A M J J A S O N.2023/8/159經(jīng)理看到從去年開始廢品率持續(xù)下降 Manager has seen reduced scrap levels since the end of last year 教訓(xùn)教訓(xùn)：“嚴(yán)格的管理會(huì)出成效！嚴(yán)格的管理會(huì)出成效！”The Learning:“A tough management style gets results!”“A tough management style gets results!”Manager concludes:“Tough Love Makes Things Happen”23119961997Scrap Level(%)廢品率1997年6月 JUNE 1997Derived from Understanding Variation:The Key To Managing Chaos,Donald J.Wheeler,SPC Press.1993.J F M A M J J A S O N D J F M A M J.2023/8/1510Derived from Understanding Variation:The Key To Managing Chaos,Donald J.Wheeler,SPC Press.1993.將數(shù)據(jù)置于統(tǒng)計(jì)流程控制圖中Putting The Data In A SPC Chart23119961997Scrap Level(%)廢品率J F M A M J J A S O N D J F M A M JUCLLCL.2023/8/1511統(tǒng)計(jì)流程控制圖顯示不同的解釋,可為什么呢?SPC Tells A Different Story.But Why?23119961997Scrap Level(%)廢品率J F M A M J J A S O N D J F M A M JUCLLCL.2023/8/1512“人們已知的最佳方式之一是如不能使用控制圖分析數(shù)據(jù)會(huì)：增加成本,浪費(fèi)的努力和降低士氣;-Donald J.Wheeler 博士“Failure to use control charts to analyze data is one of the best ways known to mankind to:increase costs waste effort andlower morale.”-Dr.Donald J.Wheeler統(tǒng)計(jì)流程控制圖顯示不同的解釋,可為什么呢?SPC Tells A Different Story,But Why?.2023/8/1513S=統(tǒng)計(jì)技術(shù):檢查偏差 Statistical techniques used to examine process variationC=控制過程通過積極管理 Controlling the process through active managementP=過程,任何過程 Process,ANY Process現(xiàn)在我們管理數(shù)據(jù)的方法-SPCThe Way We Manage Data-Today SPC顯示過程偏差隨時(shí)間變化的圖形.2023/8/1514控制圖方法Control Charts Method它從哪里來的?Where Did It Come From?19世紀(jì)20 年代-西部電器 的 Walter Shewhart博士:1920s-Western Electric/Dr.Walter Shewhart慣于確認(rèn)受控的&未受控的偏差 Used to identify Controlled&Uncontrolled Variation 受控制的:普通原因或固有偏差Controlled:Common Cause or Inherent Variation未控制的:特殊起因或可指定的偏差Uncontrolled:Special Cause or Assignable Variation在背景噪聲中試圖發(fā)現(xiàn)由特殊原因造成的偏差Tries to find the special cause variation in all of the background noise使用控制圖作為主要工具Uses Control Charts as main tool.2023/8/1515Five Main Uses of Control Charts 控制圖的5個(gè)主要用途To reduce scrap and rework and for improving productivity.為了減少?gòu)U品和返工及提高生產(chǎn)力Defect prevention.In control means less chance of nonconforming units produced.預(yù)防缺陷Prevents unnecessary process adjustments by distinguishing between common cause variation and special or assignable cause variation.預(yù)防不必要的過程調(diào)整 Provides diagnostic information so that an experienced operator can determine the state of the process by looking at patterns within the data.The operator can then make the necessary changes to improve the process performance.提供過程診斷信息Provides information about important process parameters over time.提供過程重要參數(shù)隨時(shí)間推移的信息.2023/8/1516 差異類型-“普遍 VS 特別”Types of Variation“Common vs.Special”普遍原因 COMMON CAUSE呈現(xiàn)在每個(gè)過程中 Is present in every process 自然的 Natural 隨機(jī)的 Random可能被去除和或變小,但在過程上要求一個(gè)根本變化Can be removed and/or lessened but requires a fundamental change in the process穩(wěn)定的,可重復(fù)的過程偏差來源.存在于每一個(gè)操作/過程由過程本身造成的(由我們做事的方式?jīng)Q定的)一般來說,通過管理可以控制.2023/8/1517特殊原因 SPECIAL CAUSE不可預(yù)見的Unpredictable與普通偏差比較大 Typically large in comparison to Common Cause variation可以由基本的過程控制和監(jiān)視去除或變小 Can be removed/lessened by basic process control and monitoring 偏差類型“普遍 VS 特別 Types of Variation“Common vs.Special”時(shí)不時(shí)地存在于大多數(shù)操作/過程,并且持續(xù)地存在于某些過程.由一個(gè)或一系列的干擾造成的.一般來說,通過操作者可以控制(至少可以發(fā)覺).我們認(rèn)為如果過程中有我們認(rèn)為如果過程中有特別原因偏差特別原因偏差,它們就是它們就是失控和不穩(wěn)定的失控和不穩(wěn)定的.A process exhibiting Special Cause variation is said to be Out-of-Control and Unstable.2023/8/1518練習(xí)Exercise當(dāng)它與你的項(xiàng)目有關(guān)系時(shí),確認(rèn)某種“普通原因”和“特別原因”偏差可能的形式As it relates to your project,identify some possible forms of“common cause”and“special cause”variation普遍原因Common Cause特殊原因Special Cause.2023/8/1519Minitab 控制圖 Control Charts.2023/8/1520Minitab 控制圖練習(xí)Control Charts Exercise我們用一些隨機(jī)的數(shù)據(jù)Lets use some Random data從您的生意中，我們使用一些代表性的數(shù)值和正態(tài)偏差創(chuàng)造25 行任意正常數(shù)據(jù)，Create 25 rows of random normal data using some representative values for Mean and Std Dev from your business繪制單獨(dú)圖 Plot an Individuals chart注意監(jiān)視時(shí)間和價(jià)值被繪制在Y 軸 Note that monitoring over time and the value is plotted in the Y axis.2023/8/1521隨時(shí)間變化的數(shù)據(jù) DATA PLOTTED OVER TIMEMONITORED CHARACTERISTICUCLCenter LineLCLUCL=Upper Control Limit /LCL=Lower Control LimitPlotted Data主要部分-控制圖Key Component -Control Charts.2023/8/1522Definitions 定義In Control 受控No special cause variation present 在波動(dòng)中沒有特殊原因引入All variation is random所有的波動(dòng)都是隨機(jī)的Out of Control失控At least one special cause is present至少有一個(gè)特殊原因引入Some variation is non-random 一些波動(dòng)不是隨機(jī)的關(guān)于測(cè)試我們建議The tests we suggest:-MINITAB 測(cè)試Minitab tests:全部測(cè)試All Tests(測(cè)試1-8Test 01 through 08)-樣品規(guī)則Pattern rule:如果你看到一個(gè)樣品，過程已經(jīng)失控If you see a pattern,the process is out of control.2023/8/1523 1 Sigma2 Sigma3 Sigma1 Sigma2 Sigma3 Sigma60-75%90-98%99-99.9%of Data PointsUCLLCL時(shí)間時(shí)間 TIMETIME我們測(cè)量的項(xiàng)目 The Item We Are Measuring標(biāo)準(zhǔn)偏差的規(guī)則Rules of Standard Deviation數(shù)據(jù)應(yīng)該在哪?“Where should the data lie?”.2023/8/1524Minitab 測(cè)試TestsTest#1Test#2.2023/8/1525過程控制測(cè)試標(biāo)準(zhǔn)Process Control Tests我們建議使用。全部測(cè)試We suggest using.all tests.2023/8/1526在控制下還是失控？In Control or Out of Control?如果在控制以外,打破了什么規(guī)則或表現(xiàn)出什么條件?If out of Control,which rule(s)is broken or condition(s)is present?.2023/8/1527在控制下還是失控？In Control or Out of Control?如果在控制以外,打破了什么規(guī)則或表現(xiàn)出什么條件?If out of Control,which rule(s)is broken or condition(s)is present?.2023/8/1528在控制下還是失控？In Control or Out of Control?如果在控制以外,打破了什么規(guī)則或表現(xiàn)出什么條件?If out of Control,which rule(s)is broken or condition(s)is present?.2023/8/1529.2023/8/1530失控意味什么?What does Out-of-Control mean?查出控制的缺陷Detecting Lack of Control.2023/8/1531如果您確定您的過程是“失控”你應(yīng)該做什么？What should you do if you determine that your process is“Out of Control?”查出控制的缺陷 Detecting Lack of Control.2023/8/1532因此,根據(jù)現(xiàn)在你所知道的,如果你的過程在控制下，在控制上限和下限之間百分之多少數(shù)據(jù)點(diǎn)將會(huì)下降?Therefore,based on what you know so far,what percent of data points should fall between the upper control limit(UCL)and lower control limit(LCL)if your process is in-control?UCLLCLTIMETIME控制極限 VS 規(guī)格限制 Control Limits vs.Specification Limits.2023/8/1533如果點(diǎn)落在上限之外或控制下限之下，是否意味著我們?yōu)轭櫩妥隽艘粋€(gè)缺陷產(chǎn)品?If a point falls beyond the upper or lower controlcontrol limit does this mean we are making a defect for the customer?控制極限 VS 規(guī)格限制 Control Limits vs.Specification Limits UCLLCLTIMETIME.2023/8/1534控制極限對(duì)規(guī)格限制 Control Limits vs.Specification Limits過程控制極限是由過程能力決定的 Process Control Limits are calculated based on data from the process itself他們根據(jù)+/-3s(99.73%我們期望過程偏差落在這些極限之間)They are based on+/-3s (99.73%of the process variation is expected to fall between these limits)產(chǎn)品規(guī)格極限規(guī)范極限是由客戶的要求決定的,不是在控制圖上發(fā)現(xiàn)的Product Specification Limits ARE NOTARE NOT found on the control chart很重要一點(diǎn)是要了解程序控制與顧客要求如何吻合.Understanding how the process matches up against customer requirements IS IS important to know確定過程執(zhí)行如何滿足顧客期望,需要進(jìn)行過程能力研究。To determine how the process performs to Customer Expectations,a Process Capability StudyProcess Capability Study is required.2023/8/1535n把規(guī)格限制放在在控制圖上Putting specification limitsspecification limits on a Control Chartn 把控制上限和控制下限當(dāng)做規(guī)格限制 Treating UCL and as a specification limit2個(gè)控制圖的大錯(cuò)誤TWO BIG CONTROL CHART ERRORS控制極限對(duì)規(guī)格限制 Control Limits vs.Specification Limits當(dāng)你把任意上下限作為監(jiān)視工具時(shí)，他就不再是個(gè)控制圖.LCL When you do either of these the control chart becomes just an inspection tool-its no longer a control chart.控制上限和控制下限并不直接與客戶缺陷有聯(lián)系!UCL/LCL are not directly tied to customer defects!.2023/8/1536如何收集數(shù)據(jù)How to Collect Data合理分組 Rational subgroups n通過合理分組，使各組只包括普遍原因 collect data so that subg