失效模式與效應分析係種預防性可靠度工程技術,以其提高產品之可靠度、降低失敗成本。電子業的失效模式與效應分析製作通常是由各個相關部門人員一起協商,在製作上得花費大批的人力和金錢,本研究以電子連接器公司為研究對象,導入結合案例式推導與集群分析法之預測模型,導入案例式推理目的在模仿人類的經驗法則,利用案例的特徵值搜尋最相似案例作為新案例的預測值,以解決複雜且非結構的問題,並加入集群分析法,進行雙重搜尋最相似案例。 一般傳統衡量失效模式與效應分析之輕重是以風險優先數的大小為指標,風險優先數之因子等級並無法突顯等級間真正的差異性,而且過去傳統案例式推理在歐幾里德公式假設權重是一樣,也就是每個變數影響性相同,此與現實情況不同,因此藉由等級加入權重和以屬性與風險優先數相關性之正規化,以期能提高預測能力。經實例驗證得知透過案例式推理結合集群分析法並且加入權重後MAPE值可降低至3.64%。
In this paper, a technique for prioritizing corrective actions in failure mode and effects analysis (FMEA) is proposed. This technique extends the risk prioritization beyond the conventional risk priority number (RPN) method. The ranks 1 through 1000 are used to represent the increasing risk of the 1000 .A higher rank of failure is, a higher priority is. Traditionally, FMEA identifies the risk associated with a product failure through assignment of a standard RPN.A fundamental problem with FMEA is that it attempts to quantify risk without adequately quantifying the factors that contribute to risk, so the rank accedes to the weight in the study. In the problem-solving process, human experts often recall similar cases to help identifying the mechanism involved. This has motivated the use of case-based reasoning to develop a system for failure mechanism in this study. To determine its accuracy, the system is evaluated using historical data. It is thus concluded that case-based reasoning is a viable approach for the identification of failure mechanisms. The numerical results show that the Mean Absolute Percentage Error(MAPE)is 3.64% . We can conclude that case-based reasoning is a viable approach for the mechanisms.