標題: 以資料聚集分佈估測法為基礎的模糊建模演算法
Fuzzy Logic Modeling Algorithm Based on Cluster Estimation Method
作者: 楊俊勇
Jiunn-Yeong Yang
邱俊誠
Jin-Chern Chiou
電控工程研究所
關鍵字: 模糊邏輯建模演算法;資料聚集估測法;逆迴遞學習法;類神經網路;化學氣相沈積;Fuzzy logic modeling algorithm;cluster estimation method;backpropagation learning method;aritificial neural network;Chemical vapor deposition
公開日期: 1998
摘要: 在此論文中,我們提出一種以資料聚集估測法為基礎的模糊模式建模法則。這種建模方式主要以資料聚集估測法與逆迴遞學習演算法為基礎,藉由訓練用資料(training data)建立模糊模式。當資料聚集估測法所劃分資料區的結果不同時,所得的模糊模式亦不相同,因此一個最佳結構模糊模式的搜尋演算法在此論文中提出,此演算法用互相關係數(multiple correlation coefficient)為模糊模式的精準度標準,並用測試用資料(testing data)來測試精準度以找出最佳結構的模糊模式。當最佳結構模糊模式找到後,我們用全部資料作為逆迴遞學習演算法的學習樣本(pattern)來微調模糊模式的參數。 為了要測試我們提出的模糊模式建模演算法之經確性,我們以幾組不同的非線性函數及一個化學氣相沈積製程的數值模擬做為例子。我們將結果與其他現有的模糊模式及神經網路模式做比較,顯示出我們所提的法則能有效率建立準確的模糊模式。
A fuzzy logic modeling algorithm have been proposed for semiconductor fabrication processes. The fuzzy logic modeling algorithm consists of a cluster estimation method and backpropagation learning method to construct a number of modeling structures from the training data. A decision rule based on the multiple correlation coefficient is used to obtain the optimum structure of fuzzy modeling from using the testing data. Upon the optimum structure has been reached, the gradient-descent method is used to refer the parameters of the final fuzzy model using both training and testing data. The algorithm has been applied to various nonlinear functions and a chemical vapor deposition process. The results demonstrate the efficiency and effectiveness of the proposed fuzzy logic model in comparison with existing fuzzy logic models and artificial neural network models.
URI: http://140.113.39.130/cdrfb3/record/nctu/#NT870591023
http://hdl.handle.net/11536/64951
顯示於類別:畢業論文