《SPC英文版教材PPT课件》由会员分享，可在线阅读，更多相关《SPC英文版教材PPT课件（83页珍藏版）》请在金锄头文库上搜索。
1、.,Module 3: Statistical Process Control (SPC) Methodology,.,2,PCS Elements,Create Measurement Plan,Establish Monitor (SPC),Implement Response Flow Checklist (RFC),Element 1,Element 2,Element 3,.,3,Contents,Introduction 簡介 What is SPC 什麼是SPC? What is Stability 什麼是穩定性? What is a Control Chart 什麼是管制圖 H
2、ow to Set-up a Control Chart 如何建立管制圖 Type of Control Charts Available 管制圖的種類 How to Calculate the Control Limits 如何計算管制界限 SPC Trend Rules SPC法則 When to Revise Control Limits 何時重新計算管制界限 Process Capability Study 制程能力研討 Spec limits VS Control Limits 規格界限 vs. 管制界限 Stability VS Capability 穩定性 vs. 能力 Cont
3、rol Chart Reduction/Elimination 減少管制圖 SPC Expectations,.,4,What is SPC?,Statistical 統計 Anything that deals with the collection, analysis, interpretation some drift gradually, others may have occasional sudden changes in direction between periods of relative stability 傾向隨時間漂移,一般逐漸改變,有的會突然改變方向,Autocor
4、relation關連性,.,35,Caution When Using MR Method,If there is autocorrelation, MR(Summary Stat) will underestimate the true process variation & the control limits will be too narrow 如果數據有關連性,MR方法會低估制程變異,界限會太窄. If autocorrelation is evident, use Sigma (Std Dev) Method for control limits computation (Refe
5、r to Appendix B) 如果確定數據有關連性,使用sigma方法計算管制界限.,.,36,sigma方法計算管制界限, N = the number of lots, = the mean from the ith lot (i = 1,2,.,N), = the mean of the lot means, = the standard deviation of the lot means, where,Compute the control limits using:,.,37,Control Chart Trend Rules 趨勢規則,Purpose: Improve the
6、 responsiveness of the control chart 增進管制圖的反應 Detect more subtle shifts in the process more quickly 更快地察覺制程中細微的變化 Detect irregularities beyond normal 3 that indicate non-randomness in process 察覺在正常3 界限內的非隨機性變化,.,38,How to Interpret a Control Chart?,It is based on the Normal Distribution.,.,39,SPC Tr
7、end Rules,Rule# 1: A single point beyond either control limit 規則1: 單獨點超出管制界限 Uses: Detects very large/sudden shifts 用途: 察覺重大/突然的偏差 False alarm rate: 0.27% 機率: 0.27% Example:,.,40,SPC Trend Rules,Rule# 2: 9 consecutive points on the same side of the centerline 規則2: 連續9點在中心線同側 Uses: Detects small shif
8、ts or trends 用途: 察覺微小/趨勢性的偏差 False alarm rate: 0.39% 機率:0.39% Example:,.,41,SPC Trend Rules,Rule# 3: 6 consecutive points steadily increasing or Decreasing 規則3: 連續6點持續上升或下降 Uses: Detects strong trends 用途: 察覺強烈趨勢 Example:,.,42,SPC Trend Rules,Rule# 4: 14 (or more) consecutive points are alternating u
9、p and down. 規則4: 相鄰14點規則性上下變動 Uses: Detects systematic effects, such as alternating machines, operators, suppliers, etc. 用途: 察覺系統性的效性. 如交替機台,人員,供應商等. Example:,.,43,SPC Trend Rules,Rule# 5: 2 out of 3 consecutive points at least 2 std dev beyond the centerline, on the same side 規則5: 連續同側3點中,2點落在同側2標準
10、差之外 Uses: Detects large changes 用途: 察覺大改變 False alarm rate: 0.30% 機率: 0.30% Example:,.,44,SPC Trend Rules,Rule# 6: 4 out of 5 consecutive points on the chart are more than 1 std dev away from the CL 規則6: 連續同側5點中,4點超出1標準差 Uses: Detects moderate-sized changes 用途: 察覺中度改變 False alarm rate: 0.53% 機率: 0.5
11、3% Example:,.,45,SPC Trend Rules,Rule# 7: 15 (or more) consecutive points are within 1 std dev of the CL 規則7: 連續15點在1標準差內 Uses: Detects a decrease in process variation 用途: 察覺制程變異的降低 Example:,.,46,SPC Trend Rules,Rule# 8: 8 (or more) consecutive points are on both sides of the CL, but none are within
12、 1 std dev of it. 規則8: 連續不同側8點,沒有一點在1標準差內. Uses: Detects an increase in process variation 用途: 察覺制程變異的增加 Example:,.,47,Selection of Trend Rules,Using a large # of trend rules is unwise, since each trend rule has a false alarm rate & the cumulative false alarm rate can be very large 使用大量的判斷規則是不智的,因為每一
13、條都有誤判的機率,累積起來將可能很大 False alarm rate is the frequency of control chart signals when nothing at all is actually wrong with the process 誤判機率指的是制程一點問題都沒有,但規則確告訴我們有問題. False alarms are undesirable: 誤判警告並不是我們想要的 They reduce productivity & increase costs from unnecessarily shutting down the process 不必要的中斷生
14、產造成產能降低&增加成本 They erode confidence in control charts as useful tools. Eventually all out-of-control signals are ignored. As a result, quality, productivity, & cost will suffer. 侵蝕對管制圖的信心. 最後, 忽視所有失控的信號, 導致品質,產量&成品損失.,.,48,Trend Rule Recommendations 建議,All control charts should at least use the 1st r
15、ule: Point UCL or Point LCL 至少須使用第 1 條 For an automated SPC system with automated application of SPC trend rules, its highly recommended to add 5th rule to detect large shifts in mean, (i.e. 2 out of 3 rule) 若spc系統是自動的,非常建議增加第 5 條 Add other rules depending upon process knowledge ability to respond c
16、riticality of the monitor sensitivity requirements for the monitor Intel does recommend as a goal to use rules 1, 2, 5, & 6 when appropriate Intel建議使用1, 2, 5, & 6 條,.,49,Trend Rule Recommendations,Only use the trend rules that signal process instabilities for which you are capable of responding 在你有能力反應處理的不穩定制程,才使用趨勢規則 Justification needed for not using other SPC trend rules Std dev & range charts may choose not to react to Point LCL, however a LCL on these charts can be valu
