依據製程能力指標 Cpmk 應用複式抽樣方法於供應商選擇

Abstract

製程能力指標是藉由一個指標值來衡量製程的能力與產品的品質，過去學者對於以製程能力指標來衡量兩家供應商製程的問題已經提出了一些方法。然而，依據製程能力指標 Cpmk 於供應商選取的問題目前尚未被研究。這個指標的建構結合了 Cpk 與 Cpm 兩個指標的優點，同時考量到製程良率以及製程損失的特性。本篇論文的研究目的就是在兩家相互競爭的供應商之間選出一家具有較好製程能力的供應商，並建立了一個依據 Cpmk 指標的決策程序供使用者於決策時使用。本研究是應用複式抽樣的方法針對兩供應商之製程間的檢定統計量來估計信賴下界，藉由比較四種複式抽樣信賴區間的錯誤機率和篩選檢定力後，結果發現以偏誤校正的比例複式抽樣法 (BCPB) 在相同的樣本數下有較穩定的錯誤機率以及比較顯著的篩選檢定力。所以在這四種複式抽樣方法中，BCPB之複式抽樣法為表現比較好的方法。 最後，為了實務應用上的便利，我們提供一個供應商選取程序作為選取決策之參考。

Process capability indices (PCIs) intended to provide single-number assessments of ability to meet specification limits on quality characteristics. Many individuals have indicated various approaches for supplier selection or process comparison problem based on PCIs. However, the method of supplier selection based on process capability index Cpmk is not yet investigated. The index is constructed by combining the yield-based index Cpk and the loss-based index Cpm, taking into account the process yield as well as the process loss. The principal purpose of this thesis is to determine the more capable process between two competing suppliers and provide the supplier selection procedure based on Cpmk index for practical applications. In this study, we apply the bootstrap method, a data-based simulation technique, to construct lower confidence bound for the statistics between two suppliers. A comparison among four bootstrap methods is also analyzed by evaluating the error probability and the selection power. The result indicates that the BCPB method is the better approach among four bootstrap methods for process comparison due to its stable error probability and larger selection power with a fixed sample size. Finally, for convenience of applications, a practical step-by-step testing procedure for engineers is implemented to refer to supplier selection decisions.