雙反應曲面法於產品製程改善之應用

Application Dual Response Surface Method to Improve Product Process

黃語潔(Yu-Jie Huang)

指導教授 ： 李孟樺

國立虎尾科技大學/管理學院/工業管理系工業工程與管理碩士班/碩士(2017年)

摘要

本研究目的主要藉由分析光纖產品之實際製程資料，利用雙反應曲面法找出光纖產品製程最佳參數，以期降低光纖產品之生產成本。研究中利用雙反應曲面法找出曲率、軸偏、凹凸量的反應曲面，之後於多品質目標考量下找出之最佳化參數數值與最佳化參數條件，以助於光纖產品在目標值限制條件之製程參數調整。
本研究主要貢獻在於結合Box-Behnken與雙反應曲面法找出較佳因子，研究的目的能改善原有的製程能力及找出影響的關鍵因子，當品質特性稍有變化時，也可利用反應曲面來預估製程可能的反應，以適度調整其因子、水準，而達到滿足品貭特性的要求，執行驗証實驗以確認最佳參數水準組合之再現性。

關鍵字

光纖跳線 ； 製程改善 ； 陶瓷插芯球面3D ； 雙反應曲面法 ； 最佳3D研磨品質參數

並列摘要

This study analyzes the actual process data of optical fiber products, and uses the Dual Response Surface Method to determine the optimum parameters of the optical fiber product process, which intends to reduce the production costs of optical fiber products. The Dual Response Surface Method is used to determine the response surface of curvature, apex offset, and roughness, and then, the optimization parameter values and optimization parameter conditions are found by considering multi-quality targets, in order to contribute to the process parameter adjustment of optical fiber products under target value constraints.
The main contribution of this study is to combine Box-Behnken with the Dual Response Surface Method to identify better factors. The purpose of the study is to improve the original process capability and determine the key influencing factors. When quality characteristics are slightly changed, the response surface can be used to estimate the possible responses of the process, in order to appropriately adjust the factors and levels to meet the requirements of the quality characteristics. The reproducibility of the optimum parameter level combinations is confirmed by validation experiments.

並列關鍵字

Fiber Jumper ； Process improvement ； ferrule ； 3D grinding quality parameters ； Dual Response Surface Method

參考文獻

1.樂為良譯，Peter S. Pande， Robert P. Neyman， Roland R. Cavanagh著，2002，六標準差（奇異、摩托羅拉等頂尖企業的高績效策略），台北：美商麥格羅•希爾國際股份有限公司台灣分公司。

4.Bothe, D.R.,(1997), “Measuring Process Capability,” McGraw Hill.

5.Baba, I., Midi, H., Rana, S., & Ibragimov, G. (2015). An alternative approach of dual response surface optimization based on penalty function method. Mathematical Problems in Engineering, 2015.

6.Castillo,E.D. and Montgomery,D.C.,1993, A nonlinear programming solution to the dual response problem, Journal of Quality Technology,25,199-204.

7.Coronado, R.B. and Antony, J., 2002, “Critical success factors for the successful implementation of six sigma projects in organizations,” The TQM Magazine, vol.14, no.2, pp.92-99.