近年來，田口方法在工業上被廣泛的應用來達成製程參數設計之最佳化。有鑑於此，本研究針對具多品質特性之製程參數最佳化問題建構一系統的方法，首先結合理想解順序偏好法與模糊理論將多個品質特性整合為單一指標，並利用類神經網路與田口法建構其系統模型，隨後以基因演算法搜尋產品最佳製程參數之設定。為驗証此一方法的適用性與有效性，本研究將此一系統套用於電子級玻纖布二次退漿製程最佳化參數設計，結果顯示本研究所建構之系統可以有效的搜尋較佳之製程參數來滿足產品對於多項品質特性之要求，藉以快速提昇製程能力。

In the recently years, Taguchi methods have been widely applied in the practical applications for optimizing the process parameters in the manufacturing process. In this research, a systematic method is proposed to optimizing the process parameters with multiple quality attributes encountered. The method begins on applying TOPSIS and fuzzy theory techniques to integrate the multiple quality attributes into a single quality index, then a neural network model is designed for establishing the output prediction function; finally, a genetic algorithm is employed to obtain a set of process parameter for satisfying the various quality requirements in the manufacturing process. A practical example is demonstrated to verify the adaptability of the proposed method. The results show that the proposed method performs well.