【正文】 Measurement Systems Analysis (MSA) Attribute特性數(shù)據(jù) MSA The Breakthrough Strategy174。 And Measurement System Evaluation ? Measurement Systems Analysis will help us decide if we can adequately measure our output characteristic測量系統(tǒng)分析有助于確認是否能夠勝任測量輸出特性的要求 ? Then after we’ve improved the process, we will need to assess it again and potentially need to improve it/在改善過程以后，我們需要再次評價測量系統(tǒng)，以及潛在的測量系統(tǒng)的改進 1. Select Output Characteristic 2. Define Performance Standards 3. Validate Measurement System確認測量系統(tǒng) 4. Establish Baseline Process Capability 5. Define Performance Objectives 6. Identify Variation Sources 7. Screen Potential Causes 8. Discover Variable Relationships 9. Establish Operating Tolerances – Implement Improvements 10. Validate Measurement System確認測量系統(tǒng) 11. Determine Final Process Capability 12. Implement Process Controls 1 Measurement Systems Analysis (MSA) Variables Module Objectives By the end of this module, the participant should be able to: ? Discuss the need for an Attribute Measurement System Analysis探討屬性數(shù)據(jù)測量系統(tǒng)分析所需條件 ? Describe the types of Attribute Measurement System Analyses and when to use them 敘述屬性數(shù)據(jù)測量系統(tǒng)分析以及何時使用 ? Perform an Attribute Measurement System Analysis 實施屬性數(shù)據(jù)測量系統(tǒng)分析 2 Measurement Systems Analysis (MSA) Attribute Typical Measurement Systems Attribute MSA ? Examples Data collection form Survey Customer satisfaction Academic grades Plug gages (go/nogo) Thread gages (go/nogo) Visual defect check Note that often Attribute Measurement Systems involve human judgment – Is it reliable for use in decision making?/注意屬性數(shù)據(jù) MSA經(jīng)常包含人員的判定 –判定可靠嗎？ 3 Measurement Systems Analysis (MSA) Attribute Purpose Of Attribute MSA ? Accuracy checks 準確性檢查 Assess standards against customers’ requirements 評價標準和顧客要求對比 Identify how well Measurement System conforms to a “known master” /識別測量系統(tǒng)符合 ”已知標準 ”的程度 ? Precision checks 精密性檢查 To determine if inspectors (Appraisers) across all shifts, machines, lines, etc… use the same criteria to evaluate items – Reproducibility / 確認檢查員 (評價者 )所有班次、設(shè)備、生產(chǎn)線是否使用相同標準評價 – 再現(xiàn)性 To quantify the ability of inspectors (Appraisers) or gages to accurately repeat their inspection decisions – Repeatability / 量化檢查員 (評價者 )或儀器準確重復檢查結(jié)果的能力 –重復性 ? To identify how well inspectors/gages measure a known master (possibly defined by the customer) to ensure no misclassification occurs /識別檢查員 /儀器測量 ”已知標準 ”(可能是顧客定義 )確保沒有錯誤分類的能力 How often operators decide to ship truly defective product 多久操作員會將不良品判為合格品？ How often operators do not ship truly acceptable product 多久操作員會將合格品判為不良品？ ? To determine areas where 確定以下范圍 Training is needed 是否需要培訓 Procedures or Control Plans are lacking 是否缺乏程序或控制計劃 Standards are not clearly defined 標準是否未定義 Gage adjustment or correlation is necessary 儀器調(diào)整或相互性是必須的 4 Measurement Systems Analysis (MSA) Attribute Attribute Data With Unordered Categories非順序型的屬性數(shù)據(jù) – Kappa ? Suppose that invoice quality is a key to the process Throughput. In other words, if an invoice is inplete, the rework required impacts the quantity that can be processed in a day. Two Appraisers are asked to independently evaluate ten invoices randomly selected from different days. The results of the study are shown below:/假定發(fā)票質(zhì)量是過程輸出的關(guān)鍵，換句話說，如果一張發(fā)票不完整，再作業(yè)就會影響當天的產(chǎn)量。 2個評價者獨立評價隨機在不同日期抽取的 10張發(fā)票。結(jié)果如下所示： Invoice Appraiser 1 Appraiser 2 Agreement? 1 Bad Bad Y 2 Good Bad N 3 Good Good Y 4 Bad Bad Y 5 Good Good Y 6 Good Good Y 7 Good Bad N 8 Good Bad N 9 Good Good Y 10 Good Good Y ? We could simply look at the percent of the time they agree as metric for between Appraiser agreement: 我們可以只考慮評價者判定一致的百分率作為衡量指標 ? But what would that not take into account? 但是還有什么沒有考慮？ _____ % agree _____ % disagree 5 Measurement Systems Analysis (MSA) Attribute Kappa pares the proportion of agreement between Appraisers after removing agreement by chance / Kappa 比較了評價者之間去除了的偶然性的一致性比率 The proportion that the judges are in agreement is Pobserved /判斷一致的比率是 Pobserved The proportion expected to occur by chance is: 由于偶然性一致的比率 Pchance = (P Insp1 Good) (P Insp2 Good) + (P Insp1 Bad)(PInsp2 Bad) 1. What would the Kappa be if the judges agreed on every part?/如果每個 零件的判定都一致， Kappa是多少？ 2. How would you interpret a Kappa of zero?怎么解釋 Kappa為 0？ 3. What would be the Kappa if the judges never agreed? 如果判定都不一 致 Kappa又是多少？ Definition Of Kappa cha ncecha nceobs erv e dP1 PPKap pa ? ??Let’s walk through the calculation by hand. 6 Measurement Systems Analysis (MSA) Attribute How To Calculate Kappa – By Hand Build contingency table Sum columns and rows Calculate Pobs by adding diagonal Calculate Pchance Calculate Kappa Pchance = (PR1bad)(PR2bad)+(PR1good)(PR2good)