統計製程管制 (statistical process control) 是廣泛被工業界採用在製程監控的重要方法,其主要是監控製程是否存在可歸屬原因 (assignable causes) 所導致之變異,以提早採取製程改善之行動,避免增加產品額外的生產成本。而在統計製程管制方法中管制圖 (control chart) 是最常被應用之重要工具,用來決定系統狀態並偵測製程中可能隨時發生的異常情況,這是屬於一種分類問題;近年來支援向量機 (support vector machine) 被廣泛的應用在分類問題上,並有許多研究指出具有良好的效益,因此本研究擬應用支援向量機做為線上偵測製程之監控系統。在過去的製程辨識文獻大多應用原始資料數據做為訓練樣本,在本研究將結合製程統計特徵做為訓練樣本,且證實結合製程統計特徵能有效的提昇管制圖辨識之正確率。除此之外,本研究將和過去製程監控文獻中大多學者使用之類神經網路(artificial neural network) 做比較,並從實驗的結果中得知支援向量機具有較好的正確率。
Statistical process control is an important method for control process in industry. It can detect assignable cause during the process control which may occur and provide help to improve process and reduce unnecessary product cost. Hence, control chart is an important tool at statistical process control. Control charts can detect abnormal status during the process control which may occur at any time. Essentially, the judgement of the process states can be seen as a classification problem in artificial intelligence. Recently, support vector machine (SVM) is generally used in classification pattern, and a lot of researches point out that SVMs have excellent performances. In the past, many literatures concerned control chart pattern recognition (CCPR) used original data as the test samples. In this research, original data and statistical feather data are used to be the test samples. Using simulation, it is demonstrated that integrating statistical feather data in the test samples can improve recognition ability. Many researches in the literature have used neural network to recognize patterns. Hence in this research the performances of SVM on control chart pattern recognition will be compared with neural network, based on the result of the experiment, the performances of support vector machines are batter than neural network in on-line CCPR.
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。