當管制圖中出現非隨機性模型時,表示製程可能正處於管制外。不同的非隨機性模型大都是由特定之可歸屬原因所造成,因此只要能偵測出非隨機性模型的種類,便可大量節省在尋找可歸屬原因時所花費之時間。過去有許多學者致力於管制圖非隨機性模型辨認之研究,但大多數的研究都只針對單一模型或是多模型單獨出現之情形。 本研究之目的是以類神經網路來發展一個偵測管制圖非隨機性模型之管制程序。我們所考慮的非隨機性模型包含趨勢模型、週期性模型、平均值跳動模型及此三種模式混合出現之情況。類神經網路之輸入包含製程之原始資料及由製程數據中所擷取出之一些重要特徵指標。 本研究以正確辨認率與偵測到目標模型的平均連串長度作為系統的評估指標。模擬分析之結果顯示,本研究所提出的方法能有效且迅速的偵測出管制圖之非隨機性混合模型,正確辨認率可達92%。另外,分析之結果也顯示,本研究所發展之特徵指標可有效地提升正確辨認率。
A control chart may indicate an out-of-control condition when some nonrandom patterns occur. Different nonrandom patterns can be associated with a specific set of assignable causes. Hence, identification of nonrandom patterns can greatly narrow the set of possible causes that must be investigated, and thus the diagnostic search could be reduced in length. In the past, studies on control chart patterns recognition have focused on the recognition of single patterns, little has been done on situations where multiple patterns exist. In this research, we develop a neural network-based pattern recognizer for the analysis of control chart patterns. This patterns recognizer looks for the following nonrandom patterns: trend, cycle, shift and the multiple combinations of these patterns. In addition to the raw data, some important features extracted from process data were used as the inputs of neural network. The pattern recognizer has been evaluated by estimating the average run length and the rate of correct classification. The simulation results show that the pattern recognizer can recognize the control chart patterns with correct classification rate of 92%. The results also show that the features developed in this research can significantly improve the performance of neural network.
為了持續優化網站功能與使用者體驗,本網站將Cookies分析技術用於網站營運、分析和個人化服務之目的。
若您繼續瀏覽本網站,即表示您同意本網站使用Cookies。