【正文】 What Is An MSA? Scientific and objective method of analyzing the validity of a measurement system 一種科學(xué)客觀的方法，用于有效的分析測(cè)量系統(tǒng) –A “tool” which quantifies: 一種工具，它量化： 1. Equipment Variation 設(shè)備波動(dòng) 2. Appraiser (Operator) Variation 評(píng)估者波動(dòng) 3. The Total Variation of a Measurement System 測(cè)量系統(tǒng)總的波動(dòng) –MSA is NOT just Calibration 測(cè)量系統(tǒng)分析不僅僅是校準(zhǔn) Measurement System Analysis is often a “project within a project” 測(cè)量系統(tǒng)分析經(jīng)常是 ”項(xiàng)目中的項(xiàng)目 ” Main Sources Of Variation ?Materials 材料 ?Methods 方法 ?Machines 機(jī)器 ?People 人員 ?Environment 環(huán)境 ?Measures 測(cè)量 Measurement systems are the most neglected 測(cè)量系統(tǒng)經(jīng)常被忽視 測(cè)量系統(tǒng)：是用來(lái)對(duì)被測(cè)特性定量測(cè)量或定性評(píng)價(jià)的儀器或量具、標(biāo)準(zhǔn)、操作、方法、夾具、軟件、人員、環(huán)境和假設(shè)的集合；用來(lái)獲得測(cè)量結(jié)果的整個(gè)過(guò)程。 1) average of repeated measurements from more accurate measuring equipment用更準(zhǔn)確的測(cè)量設(shè)備測(cè)量多次取平均值 2) values endorsed by a professional group專(zhuān)業(yè)機(jī)構(gòu)認(rèn)可的值 3) values agreed upon by the affected parties客戶(hù)認(rèn)可的值 4) values defined by law法律規(guī)定的值 ? To measure the master sample 25 times in same condition at least, record the measurements. 在相同條件下重復(fù)測(cè)量標(biāo)準(zhǔn)樣品至少 25次，記錄每次測(cè)量數(shù)據(jù) Study Method 在此處輸入測(cè)量數(shù)據(jù) 在此處輸入標(biāo)準(zhǔn)值 在此處輸入測(cè)量值 的公差規(guī)格 Example of Type 1 Gage Study 1 Open the worksheet . 2 Choose Stat Quality Tools Gage Study Type 1 Gage Study. 3 In Measurement data, enter Diameter. 4 In Reference, type . 5 Under Tolerance, choose Upper spec lower spec and type . Click OK. Example of Type 1 Gage Study 4 64 13 63 12 62 11 61 1611 2 . 3 1 01 2 . 3 0 51 2 . 3 0 01 2 . 2 9 5O b s e r v a t i o nDiameter R e f R e f + 0 . 1 0 * T o lR e f 0 . 1 0 * T o lR e f e r e n c e 1 2 . 3 0 5M e a n 1 2 . 3 0 2 6 9S t D e v 0 . 0 0 3 6 3 16 * S t D e v ( S V ) 0 . 0 2 1 7 8 3T o l e r a n c e ( T o l ) 0 . 0 5B a s i c S t a t i s t i c sB i a s 0 . 0 0 2 3 1T 4 . 5 0 6 8 9 2P V a l u e 0 . 0 0 0( T e s t B i a s = 0 )B i a sC g 0 . 4 6C g k 0 . 2 5C a p a b i l i t y% V a r ( R e p e a t a b i l i t y ) 4 3 . 5 7 %% V a r ( R e p e a t a b i l i t y a n d B i a s ) 8 1 . 1 0 %G a g e n a m e : D a t e o f s t u d y : R e p o r t e d b y : T o l e r a n c e : 0 . 0 5M i s c : R u n C h a r t o f D i a m e t e rT y p e 1 G a g e S t u d y f o r D i a m e t e r1）分析結(jié)果顯示偏倚量是 ， P值等于 0說(shuō)明測(cè)量系統(tǒng)的偏倚是統(tǒng)計(jì)顯著的 同樣從圖上可以看出大部分的測(cè)量數(shù)據(jù)都低于標(biāo)準(zhǔn)值。 assessments agree with each other. All Appraisers vs. Standard Assessment Agreement Inspected Matched Percent (%) % CI 30 23 ( , ) Matched: All appraisers39。 ? 讓 3個(gè)檢查員獨(dú)立地評(píng)估手中的第一份樣本并判斷每一個(gè)方盒是否有缺陷 ? 每個(gè)方盒只給 5秒的時(shí)間做判斷。 Presentation 56 Variables Measurement System Studies 連續(xù)型數(shù)據(jù) 測(cè)量系統(tǒng)研究 Step Variables MSA ? Step 1: Randomly select 10 samples. In addition, identify the operators who use this instrument daily. ? 第一步 : 隨機(jī)選取 10個(gè)能夠代表過(guò)程變異的樣品 ,指定常用該檢驗(yàn)裝置的操作員來(lái)做檢查人員 ? Step 2: Calibrate the gage or verify the last calibration date is valid. ? 第二步 : 檢驗(yàn)儀器 ,確認(rèn)儀器在校準(zhǔn)合格期以?xún)?nèi) ? Step 3: Set up the Minitab data collection sheet for the RR study. ? 第三步 : 用 Minitab設(shè)定做 GRR分析的數(shù)據(jù)收集表格 ? Step 4: Ask the first operator to measure all the samples once in random order. Blind sampling, in which the operator does not know the identity of each part should be used to reduce human bias. ? 第四步 : 要求第一個(gè)操作員隨機(jī)測(cè)量所有樣品一次 ,注意不能讓操作員知道樣品的編號(hào) ,以減少人為偏差 . ? Step 5: Have the second operator measure all the samples once in random order and continue until all operators have measured the samples once (this is trial 1) ? 第五步 : 讓第二個(gè)操作員隨機(jī)測(cè)量所有樣品一次 ,繼續(xù)直到所有操作員都測(cè)量樣品一次 .這算完成第一輪測(cè)量 . Step Variables MSA ? Step 6: Repeat steps 4 5 for the required number of trials. It is best if these measurements can be done over several days. ? 第六步 : 重復(fù)第 4和第 5步直到完成需要的輪次 .如果可能 ,測(cè)量最好是在跨時(shí)間段完成 . ? Step 7: Enter the data and tolerance information into Minitab ? 第七步 : 把數(shù)據(jù)和公差信息輸入到 Minitab中 ? Step 8: Analyze the results by assessing the quality of the measurement system based on the guidelines on the following page. Determine followup actions. ? 第八步 : 根據(jù)后續(xù)的測(cè)量系統(tǒng)評(píng)估指標(biāo)的指導(dǎo)原則來(lái)分析測(cè)量系統(tǒng)是否可以接受 ,決定采取必要的行動(dòng) . SAMPLE SELECTION – Option 1: if process variability is known, the samples selected should be representative of the normal process/product variation – Option 2: if process variability is unknown, the samples selected should uniformly span beyond the width of the specs ? 樣品選擇的原則 : 1) 如果過(guò)程變異已知 ,那么樣品要盡量展現(xiàn)正常過(guò)程 /產(chǎn)品的變異范圍 2) 如果過(guò)程變異未知 ,那么樣品要盡量在規(guī)格范圍內(nèi)均勻取樣 . Trials And Data Collection ? Generally two to three operators 一般選取 2到 3個(gè)操作者 ? Generally 510 process outputs to m