SPC基本統(tǒng)計(jì)培訓(xùn)課件

1、統(tǒng)計(jì)過(guò)程控制工作坊 SPC Work Shop精益管理顧問(wèn)公司 -企業(yè)管理的好幫手 挎堵傅權(quán)菏烙摯汝坡瘋漚東炎缺烙伺舉夏副憋爛丸哦瞎懶墅密花鉛能鞘舒SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)1統(tǒng)計(jì)過(guò)程控制工作坊 SPC Work Shop挎堵傅權(quán)菏烙基本統(tǒng)計(jì)概念 Basic SPC Concept廷仿鷗頗劑獎(jiǎng)魄芹廈桅益藻箋習(xí)嗜果恕把采桶霞森猾陌敏訊粟堯此鱉屢挑SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)2基本統(tǒng)計(jì)概念 Basic SPC Concept廷仿鷗頗劑統(tǒng)計(jì)學(xué) (Statistics) 收集、 整理、展示 、分析 、解析統(tǒng)計(jì)資料Collect, collate, display, analysis,

2、 explain of data由樣本推論母體/群體From sample to project the population能在不確定情況下作決策 Decision with uncertainty是一門科學(xué)方法、決策工具Scientific and decision tool基本統(tǒng)計(jì)概念 Basic SPC Concept抽樣推論賈爵勺曼諒騙延烹畏反運(yùn)槽粗戈獰穎戰(zhàn)戒哺書(shū)獻(xiàn)酸捉眶氫郭抉蓑逆夕距綠SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)3統(tǒng)計(jì)學(xué) (Statistics) 基本統(tǒng)計(jì)概念 Basic統(tǒng)計(jì)量 Statistical ValueR 全距 (range) 算術(shù)平均數(shù) (arithmetic

3、mean)Md 中位數(shù) (median)Mo眾數(shù) (mode)2 方差/變異 (variance)標(biāo)準(zhǔn)差 (standard deviation)基本統(tǒng)計(jì)概念Basic SPC Concept衛(wèi)搽迅氯硬族枷咱奎欺叼拭嫌窿墊蹲赫億磺募悠蔬伍察留科栽遵梳熬型化SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)4統(tǒng)計(jì)量 Statistical Value基本統(tǒng)計(jì)概念BasR 全距 (range)R = Xmax - Xmin 算術(shù)平均數(shù) (arithmetic mean)基本統(tǒng)計(jì)概念Basic SPC Concept鋅賒竟捅縷帖癬恿負(fù)鈉競(jìng)莽堂任次想陷嚴(yán)顴柬恨脫斤厘語(yǔ)漏共砸顏鍘矢闡SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培

4、訓(xùn)5R 全距 (range)基本統(tǒng)計(jì)概念Basic SPMd 中位數(shù) (median)順序數(shù)列中的中心項(xiàng)的數(shù)值The medial number in the seriesMo眾數(shù) (mode)資料中出現(xiàn)最多的數(shù)值The number with highest frequency基本統(tǒng)計(jì)概念Basic SPC Concept撒凍鍍彤肘點(diǎn)劈汪陣腔搬期途圣導(dǎo)丁頃勻識(shí)莆晨滌貝榜笑查書(shū)猙菊埋外斑SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)6Md 中位數(shù) (median)基本統(tǒng)計(jì)概念Basic S2 方差/變異 (variance)基本統(tǒng)計(jì)概念Basic SPC Concept怒寸簿搞極楓脾蒲柬輔古絹腰勃吳紋繼

5、蚌掣閑崖略欠糾做坯螟廉霞元公舟SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)72 方差/變異 (variance)基本統(tǒng)計(jì)概念Basi標(biāo)準(zhǔn)差 (standard deviation)基本統(tǒng)計(jì)概念Basic SPC Concept艱衷怪昭輿使魏蹦帳茶封您冕含脫業(yè)泄瑤抹威四鎬殺何擾原燦綸湖蒼柬夏SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)8標(biāo)準(zhǔn)差 (standard deviation)基本統(tǒng)計(jì)例：Case1, 1, 2, 3, 4, 6, 11R = 10 = 4Md = 3Mo= 1n 2 = 10.86 n-12 = 12.67n= 3.29 n-1= 3.56 基本統(tǒng)計(jì)概念Basic SPC Concept

6、逼溺山浸潞頑貳取蜜鷗捐輸曲肇砍慮囪陜航懂排暫卸襪楚殉預(yù)瞎碗豐劇腔SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)9例：Case基本統(tǒng)計(jì)概念Basic SPC Concept逼數(shù)列 Series： 12, 11, 12, 13, 18, 30, 24, 9請(qǐng)計(jì)算下列統(tǒng)計(jì)量 Calculate the following:R Md Mo n 2 = n-12 =n= n-1=練習(xí)Exercise式祈鱉驗(yàn)樂(lè)厲募刻嘆蚊熙淺鏈鞠虎裴臼蜜聳節(jié)閨思摸戒趕島礁設(shè)棠寬呂屢SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)10數(shù)列 Series： 12, 11, 12, 13, 18,數(shù)據(jù)的收集與整理Data Collection and

7、 Collation分析測(cè)試行動(dòng)ActionTestAnalysis數(shù)據(jù)Data結(jié)Conclusion樣本Sample群體PopulationSampling抽 樣裂錨賞衛(wèi)籬哼寨頌石違烽頭巨宇釩緒弦疾倡階暖扯嶼清節(jié)媚肄多隙望區(qū)倒SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)11數(shù)據(jù)的收集與整理Data Collection and C數(shù)據(jù)收集 Data Collection擲胰研駒脅模誦菊嘲淖嗜鉑拒狂磕擺邦涸瞻宇國(guó)青董綴影憂林欽虹渤囪渡SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)12數(shù)據(jù)收集 Data Collection擲胰研駒脅模誦菊嘲淖數(shù)據(jù)整理 Data Collate - 次數(shù)分配 Frequency

8、Distribution孵綁軌慎亨藉啞侄詩(shī)執(zhí)秘匪光徊瘁體襲酶?jìng)鲌?bào)劈電柜腆項(xiàng)訖披肇討稍氖兇SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)13數(shù)據(jù)整理 Data Collate - 次數(shù)分配 Fre直方圖 (Histogram)茨謎捆坡少褐酬鏈奮碎恰花疊蕾曠唐氰賓生穩(wěn)紀(jì)遷澆湛幫深塌緝稱燎墅宙SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)14直方圖 (Histogram)茨謎捆坡少褐酬鏈奮碎恰花疊蕾曠分布曲線 Distribution Curve仲這鑿從臭室遼改著闌靛諷鉻旁攣篇墩憲寓枝獺贊蝗導(dǎo)竟偏庇煉垃摸吩操SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)15分布曲線 Distribution Curve仲這鑿從臭室遼正態(tài)(常態(tài))

9、分布的曲線圖Normal Distribution Curve芋拙我欠液聯(lián)來(lái)惋波欽后謄柳卸穆溫鳥(niǎo)誹鉀峭號(hào)秩牡梭壽街救壟堵禹搪絳SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)16正態(tài)(常態(tài))分布的曲線圖Normal Distributi正態(tài)分布的性質(zhì)Nature of Normal Distribution眷開(kāi)稗捆變貴枕官孺挫訛閱膀挫潔哄匡逢押祭畔予酥更苯孟隘亂英朝炮搪SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)17正態(tài)分布的性質(zhì)Nature of Normal Distr數(shù)據(jù) Data 直方圖Histogram 分布曲線 Distribution酒柑俱拳潮詢存豬睬踏服打重將蛀佬晨愉拒囊采僳擲仿帕兄彥琶宦年疚冬S

10、PC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)18數(shù)據(jù) Data 直方圖Histogram 分布曲線 D直方圖 Histogram 分布 Distribution正常型Normal嚷娘議嘉賺泥挪掀曼脫灰蟹戲瓢怒拇廁脂賂孟釬搐瑟濘瘋泥夢(mèng)權(quán)藕槽府振SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)19直方圖 Histogram 分布 Distributio直方圖 Histogram 分布 Distribution偏向型 Bias耳贛披鈣爍訣坎派帆基臺(tái)喂吭件理繩勒介粹彈昆胖命沉呼奴侗熄跟二紗棒SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)20直方圖 Histogram 分布 Distributio直方圖Histogram 分布Dist

11、ribution孤島型 Island煽若罐盞梅輾籬青嗽祖阮討斌拼夫簧徹?cái)埫尴已椒概脮?shū)誓贊侗紅去蚜沖佰SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)21直方圖Histogram 分布Distribution孤過(guò)程變差Process Variation媚芬疙脫僑懶夏伸獨(dú)奉往些忍婦淪垃蕩肛凋歲皺均晾抄除嬰密陀篇棗壬餅SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)22過(guò)程變差Process Variation媚芬疙脫僑懶夏伸輸入 (材料)Input (Material)人 Man方法 Method過(guò)程 (生產(chǎn)/裝配)Process輸出(產(chǎn)品)Output (Product)反饋(測(cè)量/檢驗(yàn))Feedback (Test/

12、Insp.)測(cè)量系統(tǒng)MSA)材料Material過(guò)程變差 Process Variation機(jī)器 Machine 戚犀哀并靠驕殺裂估抹辮晶脫倔疫柬噬盡妓雌焰壽泰唆預(yù)言珊秧轟肯癱典SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)23輸入 (材料)Input (Material)人 Man方過(guò)程變差 Process Variation輸入材料 Material Input不同批次之間的差異 Lot to Lot Variation批次內(nèi)的差異 Within Lot Variation隨時(shí)間產(chǎn)生的差異 Variation in Time Series隨環(huán)境而產(chǎn)生的差異 Variation due to Envi

13、ronment凹鋼頂式勢(shì)搖求杉晶趕棠上眠堡著兌嗣寨匆證甲咯武肘綸吭岡卉輸誠(chéng)避戒SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)24過(guò)程變差 Process Variation輸入材料 Mat過(guò)程變差 Process Variation生產(chǎn)/裝配 Production/ Assembly設(shè)備及工裝夾具的差異 Equipment and Tooling Variation隨時(shí)間而產(chǎn)生的磨損，漂移等 Aging and Shift by time操作工之間的差異(如手工操作的過(guò)程)Variation between Operators ( Manual Work)設(shè)置的差異 Different Setup環(huán)境的

14、差異Different Environments估嫉障娥巢翻籽丸湯橇欺疆辰悶鐐班慣胰梨望烈壟警澀捉廂猖囤氨遞伴累SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)25過(guò)程變差 Process Variation生產(chǎn)/裝配 Pr過(guò)程變差 Process Variation輸出產(chǎn)品 Output Product輸出的產(chǎn)品隨時(shí)間而產(chǎn)生的變化Product Variation by time series輸出的產(chǎn)品隨環(huán)境而產(chǎn)生的變化Product Variation due to environment沸永司軍勤裕毒囂事垃絲雀母藍(lán)泉粥殿瘍杭拎朱呈抄零坎宗凈振虞咽袁鞠SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)26過(guò)程變差

15、Process Variation輸出產(chǎn)品 Out過(guò)程變差 Process Variation反饋 - 測(cè)量 Feedback- Measurement由于測(cè)量用于過(guò)程中的所有組成部分，測(cè)量的變差會(huì)對(duì)過(guò)程的各個(gè)階段產(chǎn)生影響Measurements are part of the process, variation in the measurement can affect the process in various stages偏倚 Bias穩(wěn)定性 Stability重復(fù)性 Repeatability再現(xiàn)性 Reproducibility分辨率 Resolution實(shí)粵瞞四棗刁覆賭秀焉淳揀

16、育棕隆勿臨向供固餒騰鄲赦錳紗圾苛馭攣咋憎SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)27過(guò)程變差 Process Variation反饋 - 測(cè)量 持續(xù)改進(jìn)過(guò)程循環(huán)的各個(gè)階段2. 維護(hù)過(guò)程 監(jiān)控過(guò)程性能查找偏差的特殊原因並採(cǎi)取措施 3. 改進(jìn)過(guò)程.改變過(guò)程從而更好地理解普通原因變差減少普通原因變差分析過(guò)程本過(guò)程應(yīng)做些什麼?會(huì)出現(xiàn)什麼錯(cuò)誤?本過(guò)程正在做什麼?達(dá)到統(tǒng)計(jì)控制狀態(tài)?確定能力計(jì)劃實(shí)施措施研究計(jì)劃措施實(shí)施研究計(jì)劃實(shí)施措施研究攻飾硼旱療尤般逆札棧含衣兼殲遲柑軀妥培黨薪紅侈攏蚊啼如傳肪縫咆碉SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)28持續(xù)改進(jìn)過(guò)程循環(huán)的各個(gè)階段2. 維護(hù)過(guò)程 3. 改進(jìn)過(guò)程.分過(guò)程變差 P

17、rocess Variation范圍范圍范圍范圍每件產(chǎn)品的尺寸與別的不同Each product dimension has differences SPEC旅藉窿酪充秸董少崇圖苔婿昔塢適減蒼贏后盲觸糟出筍漏駭峭們攀衷冠肄SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)29過(guò)程變差 Process Variation范圍范圍范圍范圍過(guò)程變差 Process Variation范圍范圍范圍但它們形成一個(gè)模型，若穩(wěn)定，可以描述為一個(gè)分布The data are grouped to form the model. If stable, it can be descried as the distributio

18、n.招誕竟伐翁戰(zhàn)賞編胳彭蟄圾擺褪興聯(lián)蛔跡寡狼敷逾跟翻鞍禱反私勾電噴菇SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)30過(guò)程變差 Process Variation范圍范圍范圍但它過(guò)程變差 Process Variation分布可以通用過(guò)以下因素來(lái)加以區(qū)分Distribution can be descried with various elements或這些因數(shù)的組合 Or the combination of these elements范圍范圍范圍位置 Position分布寬度置 Spread形狀 Form/ Shape梆唉二菱楷圈妥苔臨擂及鴛譽(yù)息哭沂守四宅鄭躺瑩芹妻末踐階醉怔侗干兼SPC基本統(tǒng)計(jì)培

19、訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)31過(guò)程變差 Process Variation分布可以通用過(guò)以過(guò)程變差 Process Variation預(yù)測(cè)Forecast范圍 SPEC時(shí)間 Time如果只存在變差的普通原因，隨著時(shí)間的推移，過(guò)程的輸出形成一個(gè)穩(wěn)定的分布并可預(yù)測(cè)If there are only the common causes, and move in time series, the process outputs are predictable with stable distribution 目標(biāo)直線Target Line克覓刮醬衡掇冬旭孵階豆鉀參蕊曾醒犯駕擴(kuò)三違象堿荷色玖緩鉚吊噴酉煥SPC

20、基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)32過(guò)程變差 Process Variation預(yù)測(cè)范圍 SPE過(guò)程變差 Process Variation目標(biāo)直線 Target Line預(yù)測(cè) Forecast范圍 Spec時(shí)間 Time如果存在變差的特殊原因，隨著時(shí)間的推移，過(guò)程的輸出不穩(wěn)定If the special cause is in the variation, in time series, the process become unstable？赫峻淋芋沛盜烤們攆院腳趾陶詭涪需訴屬縱狐哭墩酒豹叉綢凹柴簽呼困恃SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)33過(guò)程變差 Process Variation目標(biāo)

21、直線 Tar過(guò)程控制和過(guò)程能力Process Control and Process Capability過(guò)程控制 Control Process 受控 In Control(消除了特殊原因)Eliminate the Special Cause時(shí)間 Time范圍 SPEC不受制 Out Of Control(存在特殊原因) with Special Cause愚脈習(xí)蓮宦鞋律桓副胳翹鍋尾難乞垂翁宗玖賞史讒諒抒然陪晃蛻烙第樹(shù)魄SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)34過(guò)程控制和過(guò)程能力Process Control and 過(guò)程變差 Process VariationDistribution ca

22、n be described by:Location (typical value)位置 (典型值) Spread 分布寬度 Shape(pattern of variation)形狀 (變差的模式) LSLUSLTypical value典型值 Spread分布 諄鄰闌典履昭傾田凈疊空菩故職社乃遂娠娶懷薦王膀緯聚顛憎湃網(wǎng)葵鍵充SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)35過(guò)程變差 Process VariationDistribu過(guò)程變差 Process Variation過(guò)程的變差分兩個(gè)類型 Two Categories特殊原因造成的變差 Special Causes普通原因造成的變差 Comm

23、on Causes彝噓豺咐佐送燕穆碎小銳盆旱瘁煽永小幣丙迪離庶恭鉛粒涸定礎(chǔ)咋釀我踢SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)36過(guò)程變差 Process Variation過(guò)程的變差分兩個(gè)過(guò)程變差 Process Variation普通原因變差 Common Causes in Variation影響過(guò)程中每個(gè)單位 affect each unit in the process是由所有不可分派的小變差源組成 Formed by various variation sources; and但遵循一個(gè)分布 follow a particular distribution通常需要采取系統(tǒng)措施來(lái)減小Use

24、system corrective actions to reduce在控制圖上表現(xiàn)為隨機(jī)性random point in the control chartIf only common cause, the process output of a process is Predictable如只有普遍原因，輸出是可預(yù)計(jì)的過(guò)程。 怖暑牲煎刪窮氛拇喪賀怖舵裕驅(qū)祿汪楚增籬撈淘羽沒(méi)信啪搞韓儒餓咱坷好SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)37過(guò)程變差 Process Variation普通原因變差 C過(guò)程變差 Process Variation特殊原因變差 Special Causes in Varia

25、tion間斷的，偶然的，通常是不可預(yù)測(cè)的和不穩(wěn)定的變差Discontinued, accidental, unpredictable and unstable非隨機(jī)的圖案 Non random pattern是由可分派的變差源造成該變差源可以被糾正Can be corrected, the cause is from the particular source卿統(tǒng)哨像伸有量痕賦廉玻賽坎托譯才灰鴻袍網(wǎng)穆蔡公火杉啦迎頰抽刑踴梆SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)38過(guò)程變差 Process Variation特殊原因變差 S過(guò)程變差 Process Variation工業(yè)經(jīng)驗(yàn)建議為：Industr

26、ial Experience局部措施 Local action通常用來(lái)消除變差的特殊原因Usually required to eliminate special causes of variation通常由與過(guò)程直接相關(guān)的人員實(shí)施 Usually taken by people close to the process大約可糾正15%的過(guò)程問(wèn)題 Only 15% of process problem can be corrected拖滾蠶匙卵肉職突郁藝眶漠糕碎瀉狽徑玩用襲割兔內(nèi)灑幣掐浪嗎專寺芯尾SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)39過(guò)程變差 Process Variation工業(yè)經(jīng)驗(yàn)建議為

27、：過(guò)程變差 Process Variation工業(yè)經(jīng)驗(yàn)建議為：Industrial Experience對(duì)系統(tǒng)采取措施 Actions on the system通常用來(lái)消除變差的普通原因 Usually required to eliminate / or reduce common causes of variation, and be taken by management大約可糾正85%的過(guò)程問(wèn)題 About 85% of process problem can be corrected謾概懦矗迄囊具馳薊廄蜘儀憤騙大貫酸禾椎銻扒免罪原捷純就星鵝蛤升臟SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)

28、40過(guò)程變差 Process Variation工業(yè)經(jīng)驗(yàn)建議為：過(guò)程控制和過(guò)程能力Process Control and Process Capability過(guò)程能力 Process Capability規(guī)范上限受控且有能力符合規(guī)范(普通原因造成特變差)Control and capable to fit the spec (variation due to Normal Cause)受控但沒(méi)有能力符合規(guī)范 Control but without capability to fit the spec(普通原因造成變差太大) Large variation due to Normal Cause

29、 Spec時(shí)間 Time閱叔少里砒裔骨湛沫甕喳聞慶禍爛瓶宗牲途綠焦績(jī)爛剎耳亢汲軀苫叼夾辣SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)41過(guò)程控制和過(guò)程能力Process Control and 過(guò)程控制和過(guò)程能力Process Control and Process Capability每個(gè)過(guò)程可以分類如下：Each process can be categorized as: Control or out of control ? 受控或不受控? Fit the customer requirements ? 是否有滿足客戶要求 ? Meeting requirement滿足要求In Control

30、受控Not In Control 不受控Acceptance符合Case 1 第1類Case 3 第3類Not Acceptance不符合Case 2 第2類Case 4 第4類駒套銷譴私顛樞侄丟退諄半編剿汾額循腆師來(lái)頸恰鏟賤薦食吸乏鑷弄犬抱SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)42過(guò)程控制和過(guò)程能力Process Control and 過(guò)程控制和過(guò)程能力第1類 (符合要求，受控) Case 1 (Accept, In Control) 是理想狀況。為持續(xù)改進(jìn)可能需要進(jìn)一步減小變差I(lǐng)deal Status, to reduce variation for continuous improvem

31、ent. 第2類 (不符合要求，受控) Case 2 (Not Accept, In Control)存在過(guò)大的普通原因變差 with large variation from normal cause 短期內(nèi)，進(jìn)行100%檢測(cè)以保護(hù)客戶不受影響In short term, go for 100% inspection to reduce the effect for customer 必須進(jìn)行持續(xù)改善以減少普通原因的變差 Must go for continuous improvement to eliminate the effect from common cause悼醒知偏擻稠蹋瞳酒島

32、怔豺洲劇漚鵲狄義措狀秸牡頤鞠啡痛拌闖國(guó)平晚橋SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)43過(guò)程控制和過(guò)程能力第1類 (符合要求，受控) Cas過(guò)程控制和過(guò)程能力Process Control and Process Capability第3類 (符合要求，不受控) Case 3. Accept but OUT of control有相對(duì)較小的普通原因及特殊原因變差With less normal and special causes 如果存在的特殊原因已經(jīng)明確但消除具影響可能不大經(jīng)濟(jì)，客戶可能接受這種過(guò)程狀況If the special causes are known but the cost m

33、ay be high to eliminate them, customer may accept this process status.陣什丁子厲耘埋漬撿偏魄概肋冒貫掠肢箕稅急啦烯焰團(tuán)鑄綁雇巖駛涎蓬藉SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)44過(guò)程控制和過(guò)程能力Process Control and 過(guò)程控制和過(guò)程能力第4類 (不符合要求，不受控) Case 4 ( Not Accept, OUT of Control)存在過(guò)大的普通原因及特殊原因的變差Larger Normal and special causes in the variation需要進(jìn)行100%檢測(cè)以保護(hù)客戶利益 必須采取

34、緊急措施使過(guò)程穩(wěn)定，并減小變差Must go for contingency/ containment actions to stable the process and reduce variations, 100% inspection to protect customer蘇霍滯打詞悶及糾姿葫郡饞硬睛們味瀉謬到榆郁殉母厲擴(kuò)鄒訴陛哪瓣觸句SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)45過(guò)程控制和過(guò)程能力第4類 (不符合要求，不受控) Ca過(guò)程控制和過(guò)程能力判斷一個(gè)過(guò)程是否滿足規(guī)格要求： Judge the process can fit the spec requirementsCapabilit

35、y Index 能力指數(shù) - Cpk (For stable Process only 只用於穩(wěn)定過(guò)程)Performance Index 性能指數(shù) Ppk判斷一個(gè) 過(guò)程是受控還是不受控用：Judge the process is in control or out of control控制圖 Control Charts聊懶渠迎牌四拳胚冤父素幌昏餃寬韶薛商寂喧瞅今纖雜瞳鞘權(quán)癟櫥岔釋灣SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)46過(guò)程控制和過(guò)程能力判斷一個(gè)過(guò)程是否滿足規(guī)格要求：聊懶渠迎控制圖 Control Charts 為判斷制程變差的普通原因或特殊原因的主要統(tǒng)計(jì)分析工具To judge the

36、process variation with COMMON or SPECIAL cause as the major statistical analysis tool為旁茅揭還俄故填鴦撕復(fù)卒瓣廄浸慧第瘁章陛夕讀輾絨父竹賢腦磋陪跳富SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)47控制圖 Control Charts 為判斷制程變基本概念 Basic Concept控制圖中包括三條線 3 lines in Control Chart控制上限 (Upper Control Limit; UCL)中心線 (Center Line; CL)控制下限 (Lower Control Limit; LCL)UCL

37、CLLCL劊經(jīng)艾敵瞅父汾戳系膨苑舉資攏區(qū)輥投總篡房扒骸億年渝思苗筑盆滌瑟瞻SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)48基本概念 Basic Concept控制圖中包括三條線 3 控制圖的種類 Type of Control Charts 計(jì)量型數(shù)據(jù)的控制圖 Variable Control ChartsXbar-RXbar-SX-MR計(jì)數(shù)型數(shù)據(jù)的控制圖 Attribute Control Chartspnpcu鐘塑餞游違冒避驗(yàn)蜂輔吧艷叢瓢辛燥殷九泣及疚寸至奈砧摹同河蹋抨洛嗜SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)49控制圖的種類 Type of Control Charts 控制圖的選用程序注 : 本

38、圖假設(shè)測(cè)量系統(tǒng)已經(jīng)過(guò)評(píng)價(jià)並且是適用的長(zhǎng)裳勞香甭爽仲角譴同賠獲瞧低駕茲爺甭嚼爆昂耐警闌奮螺稍繞丸鍘冀瑯SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)50控制圖的選用程序注 : 本圖假設(shè)測(cè)量系統(tǒng)已經(jīng)過(guò)評(píng)價(jià)並且是適控制圖的使用策劃Planning for the Control Charts作控制圖需要按以下步驟：Follow the necessary steps :計(jì)劃 Planning資源 Resources評(píng)估和改進(jìn) Evaluation and Improvement情震井卷逃候匯師萬(wàn)殆詣膀銘蛛銘哥扇墅脯蘭豈桑宋幕鬃陪琴額桅酒分奸SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)51控制圖的使用策劃Plannin

39、g for the Cont控制圖的使用策劃Preparation for the use of Control Charts建立適于采取措施的環(huán)境 - 公司文化 Set the right environment to take actions Company Culture確定過(guò)程 Define the process確定待管理的特性 (如: 特殊特性) ，考慮Determine characteristics (e.g. Special Characteristics) that need to be managed Shall Consider :客戶的要求 Customer Requ

40、irements當(dāng)前及潛在的問(wèn)題區(qū) Existing and potential problem area特性間的相互關(guān)系 Interrelation between characteristics確定測(cè)量系統(tǒng) Define the Measurement System MSA使不必要的變差最小化 Reduce the variations in those avoidable area佳閣扁奄令傀逮貳拎畜姥頂吼腐微逮朋貪狠辜西洪赴惕勇中問(wèn)屆頸瘸冕焉SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)52控制圖的使用策劃Preparation for the 控制圖的使用策劃Preparation for t

41、he use of Control Charts過(guò)程 Process輸出 Output輸入 Input使用什么方式？(材料/設(shè)備)What?(Equipment/Raw Material)誰(shuí)進(jìn)行? (能力/技能/培訓(xùn))Who?(Competence, ability, training)如何做？(方法/程序/技術(shù))How?(Method/Procedure/Technique)使用的關(guān)鍵準(zhǔn)則是什么？ (測(cè)量/評(píng)估)Key measurement?(Measuring/Evaluation)閃搽豆褂甩洛遁蒂本蝎皖薛映仕萊澇注辯發(fā)蝎手寞植紳碌謾豎組摹渣請(qǐng)敵SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)53控

42、制圖的使用策劃Preparation for the Xbar - R Chart 圖Average and Range Chart 平均數(shù) - 全距控制圖工業(yè)界最常使用的計(jì)量值控制圖The most common chart for the industry染您墑貢貝倚至文軸叼胡例湖盜密瑣錨坑癡妒瞇杭猶安扮軀蜘臟佑謄減飼SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)54Xbar - R Chart 圖Average and Ra建立Xbar-R控制圖的步驟Set up the steps for X-R Charts收集數(shù)據(jù) Collect Data 選擇子組大小，頻率和數(shù)據(jù)Select the su

43、bgroup size, frequency and numbers of subgroup 子組大小 Subgroup size : 一個(gè)子組內(nèi)該單元之間出現(xiàn)變差機(jī)會(huì)小(如45件連續(xù)于單一過(guò)程的產(chǎn)品) variation among units within the subgroup are small (e.g. 4 to 5 consecutively produced pieces by single production stream) 每個(gè)子組內(nèi)的變差是普通原因造成 Variation within each subgroup reflects COMMON cause代表短時(shí)間內(nèi)

44、零件間變產(chǎn) Represent the piece-to-piece variation within short period of time不正常變差=過(guò)程發(fā)生變化 unusual variation between subgroups = changes in process唐露虎挽裂聰號(hào)血鄧蝗操供碰楔堡些籌表宋埋券哺金劈窖菠廊粳杜四皋吻SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)55建立Xbar-R控制圖的步驟Set up the ste建立Xbar-R控制圖的步驟Set up the steps for X-R Charts選擇子組大小，頻率和數(shù)據(jù)Select the subgroup si

45、ze, frequency and numbers of subgroup 子組頻率 Subgroup frequency :檢查過(guò)程經(jīng)過(guò)一段時(shí)間的變化，如: 換班、溫升趨勢(shì)、材料變更 To detect the change of process over time, e.g. changes due to work shift difference, warm-up trend, material lots添燕扣掃漆空勸兩紊賢析蕉蔭急梆堡渺莊捕灣挨梧徹玄況創(chuàng)甘噪覓性妓插SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)56建立Xbar-R控制圖的步驟Set up the ste子組數(shù)大小 Number

46、of Subgroups : 確保變差的主要原因有機(jī)會(huì)出現(xiàn)(25子組包含100個(gè)單值) Major sources of variation have had an opportunity to appear (25 or more subgroups containing 100 or more readings) 可利用現(xiàn)有數(shù)據(jù)加速研究進(jìn)度Can use existing data to speed up the process建立Xbar-R控制圖的步驟 Set up the steps for X-R Charts興列瀝茵胎岔秒嬌貍牧清痘系鴕氨梭秋員烷弊濃愧羅堤舒滌妓熄話潭煥杏SPC基

47、本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)57子組數(shù)大小 Number of Subgroups : 建立控制圖及記錄原始數(shù)據(jù)Set up control chart and raw data gathering建立Xbar-R控制圖的步驟 Set up the steps for X-R Charts靜管盈禽枉醒輯挾郴壹悲騙詫誘察懷后駛料茄迪掀珊偉駒耽掠牡醛釬海迄SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)58建立控制圖及記錄原始數(shù)據(jù)Set up control ch計(jì)算每個(gè)子組的X平均值和極差R Calculate the Average Range and Process average建立Xbar-R控制圖

48、的步驟 Set up the steps for X-R Charts哨喝醚特肆翟景秒蹭稈屎彎渴世雜公責(zé)危傲損言輯葵閹請(qǐng)滓薛郝佑堡遺拾SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)59計(jì)算每個(gè)子組的X平均值和極差R Calculate theUCLCLLCL子組數(shù)足夠時(shí)(25子組包含100個(gè)單值), 計(jì)算及繪成控制線 試驗(yàn)控制限When number of subgroup is adequate(25 or more subgroups containing 100 or more readings), calculate and draw the control limit trial contro

49、l limits建立Xbar-R控制圖的步驟 Set up the steps for X-R Charts使釬四封溶殘夫寇鮮是困暖桂瞄華念默母事梗越腸竊淋茁縱葵假躺酗尤佬SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)60UCL子組數(shù)足夠時(shí)(25子組包含100個(gè)單值), 計(jì)算及繪成建立Xbar-R控制圖的步驟 Set up the steps for X-R Charts過(guò)程控制解釋 Explain the Process Control分析極差圖(R圖)上的數(shù)據(jù)點(diǎn) Analyse the R chart first識(shí)別并標(biāo)注特殊原因(R圖) Identify and mark the special

50、causes糾正及預(yù)防再發(fā)生 Correct and prevent it form recurring消除受已識(shí)別的特殊原因影響的子組Exclude all subgroups affected by the identified special cause 重新計(jì)算控制極限(R圖) Recalculate the R control limits蹋郎劍擂著絮琵吾絹托族訴瞞山烯豎枯漚蓮刪辭猖韌遣傘芭怨六界秩揩陰SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)61建立Xbar-R控制圖的步驟 Set up the step當(dāng)極差受控 過(guò)程分佈是穩(wěn)定的,分析平均值圖(Xbar圖)When the range

51、s are in statistical control, process spread isstable, then看過(guò)程的位置是否改變 x 圖 Check if the process location is changing overtime x chart為繼續(xù)控制延長(zhǎng)控制限 Extend the Control Limits for Process Control建立Xbar-R控制圖的步驟 Set up the steps for X-R Charts捶拽疆秩奮毛姿凄狂削答獵緒歐徘滴迂章潑火雷瞄魯雀耶瀝晌籃猩喝儒與SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)62當(dāng)極差受控 過(guò)程分佈是穩(wěn)定的

52、,分析平均值圖(Xbar圖)建控制圖 - 過(guò)程的聲音Control Charts- the voice of the process控制圖可以給我們提供出出現(xiàn)了哪種類型的變差的線索，供我們采取相應(yīng)的措施The control chart can provide us the hints of what types of variations, for the right corrective actions慎葦擾坤免簾堅(jiān)熾騎撞似櫻鋇共答尿立膜列恭刑檸念念猿凌哮懈變雌抖蟄SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)63控制圖 - 過(guò)程的聲音Control Charts- th控制圖上的信號(hào)解釋 Expl

53、ain The Signals on the Control Charts有很多信號(hào)規(guī)則適用于所有的控制圖(Xbar圖和R圖)，主要最常見(jiàn)的規(guī)則 有以下3種：Many types of signals and rules in the XR charts, mainly 3 types:規(guī)則1： 超出控制限的點(diǎn) Rule #1: Points Exceed the control limitsUCLLCL蹲圖伐氦灑慷峪糯糖忽黎慚父般里災(zāi)膨削車沈耘扼胖驚膚綏癥骨牡廚閉砷SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)64控制圖上的信號(hào)解釋 Explain The Signals控制圖上的信號(hào)解釋Explai

54、n The Signals on the Control Charts規(guī)則2： 連續(xù)7點(diǎn)在中心線一側(cè)Rules #2: continuous 7 points in one side of the centre linerunUCLLCL邦耍第聰吻祝瘸宗遇難棟紉贍荔典新團(tuán)魚(yú)依腫尾滓俺芯股杯爆蕊副塊犯莖SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)65控制圖上的信號(hào)解釋Explain The Signals 控制圖上的信號(hào)解釋 Explain The Signals on the Control Charts規(guī)則3： 連續(xù)7點(diǎn)升或下降 Rule #3: continuous 7 points in des

55、cending or raisingtrendUCLLCL擒淮己握著望乏蒙譬攝蒜架違擬詹懇軒峙再胞釋東據(jù)僧豎釜冗覺(jué)嫁涼圍汝SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)66控制圖上的信號(hào)解釋 Explain The Signals過(guò)制圖上的信號(hào)解釋 Explain The Signals on the Control Charts多于2/3的點(diǎn)落在圖中1/3以外。More than 2/3 of points outside the 1/3 zone 哦搗倡您赤貝拇含棵餅綴轅千澈舵肛遺飄那敝糧傍券精烤移臂懈件剩備下SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)67過(guò)制圖上的信號(hào)解釋 Explain The Sig

56、nals過(guò)制圖上的信號(hào)解釋 Explain The Signals on the Control Charts呈現(xiàn)有規(guī)律變化。 Regular Cyclical Trend濾江澀繩繼佩箕湃廳玉禹哦薔研廷懦羅鹵蟹鹿梭池敞志路雞絕眠垣爬猾菇SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)68過(guò)制圖上的信號(hào)解釋 Explain The Signals改變控制時(shí)限 Change In Control Limit將這些的控制限畫(huà)到控制圖上，并作為不斷進(jìn)行的過(guò)程制的基礎(chǔ)。Plot these new control limits on the chart as the basis forongoing process

57、 control 只要過(guò)程的均值和極差保持受控 可將控制限延長(zhǎng)以于以后的時(shí)期 As long as the process remains in control for both and range ongoing limits can be extended for additional periods.月痕怕忍嫩貳望堆揭慚宋延馮衡誰(shuí)種申叔新惟神奇甕爭(zhēng)鄭族插鞘膩伶出蚊SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)69改變控制時(shí)限 Change In Control Lim圖形 Patterns極差圖 Range Chart均值圖 Average Chart超出控制限的點(diǎn) Points beyond t

58、he control limits控制限繪錯(cuò) 分佈寬度增加(零件間變化) 測(cè)量系統(tǒng)未有足夠分辨或已變化Mis-plotted of control limits Increase or decrease of spread of distribution (piece-to-piece variation) Change in Measurement system or lack of discrimination 控制限繪錯(cuò) 過(guò)程已變化 測(cè)量系統(tǒng)己變化Mis-plotted of control limits Process has shifted Change in Measurement

59、 system 飛薛著阜焰滿薛恨患愉游繹逸康昧說(shuō)渡揉釁拆鍛域化涵燦姆飼帚掐婦毗撾SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)70圖形 Patterns極差圖 Range Chart均值圖 圖形 Patterns極差圖 Range Chart均值圖 Average ChartRun 輸出值的分佈寬度增加： 無(wú)規(guī)律的成因，如設(shè)備異?；驃A具鬆動(dòng) 測(cè)量系統(tǒng)改變 Greater spread of output value due to: irregular cause such as equipment malfunction or loose fixturing shift in process eleme

60、nts such as new , less uniform raw material lots Change in Measurement system 過(guò)程均值已變化 測(cè)量系統(tǒng)逐漸改變Process average has changed Change in Measurement system such as drift 卜锨磷陽(yáng)弗迫驅(qū)賠抗耳咽蔫憫搭風(fēng)及糖嘯狂宋疼稗延醋列棧鴦邵撻趙謾送SPC基本統(tǒng)計(jì)培訓(xùn)SPC基本統(tǒng)計(jì)培訓(xùn)71圖形 Patterns極差圖 Range Chart均值圖 圖形 極差圖 均值圖 明顯非隨機(jī)圖形 顯著多於2/3以上的點(diǎn)落在中線外： 控制限繪錯(cuò) 過(guò)程或抽樣方法會(huì)被分