臺灣博碩士論文加值系統

台灣傳統製造業對於生產製程中所產生的不良率採取的方式主要為尋求廠商協助、或者是逐一因子以試誤的方式取得提升良率之製程參數範圍。其缺點是一旦所面對的工件是較特殊的加工製程就無法提供有效的方法。若以試誤的方式一旦有錯誤也不易發現而必須重新再來一次，當因子越來越多時就無法負荷，往往在花費極大之人力與物力後仍無法有效改善製程之穩定度。電動工具起子頭於走心式自動車床製程即是此類較特殊的加工製程，且其所要求的品質特性不只一個，而品質特性間又多具有相關聯性，如何以最少的實驗成本與最短的實驗時間得到最佳的製程參數組合，是製程研發人員所必須重視的。
本研究首先運用品管七大手法之柏拉圖法分析各不良原因之比例，接著運用特性要因圖進行腦力激盪，將所有可能影響品質之因素透過討論與腦力激盪的方式一一列舉，第二階段則就影響產品品質特性之關鍵因子，以反應曲面法之中央合成設計求解出最佳解組合。接著，我們以求解出之最佳化參數值進行模式驗證，且確認達到此次實驗的最終目的，尋求製程穩定的效果，至此，則我們可以直接投入量產。

In traditional manufacturing industry, there are mainly two solutions for seeking assistance when defect rate is too high. One is getting help from contractors while the second is testing piece by piece in order to cutting down the defect rate. The disadvantages of the solutions are the solutions are not very efficient when facing special processes. Furthermore, it is not easy to find out errors and the whole testing needs to be re-done again. If there are too many errors, the stability of the process still cannot be improved even spending a lot of manpower and resources. The CNC lathe is one of the special processes that the number of quality characteristics is more than one which are tightly related with each other. R&D people should emphasize on how to get the best result by using the least experimental cost and consuming the shortest time.
This research adopted the Pareto Diagram of quality improvement methods to analyze the defect rate and then followed up a brain storming to generate cause and effect diagram which listed all possible factors that affected quality of products. The second step was to search for the key factors affecting the product quality and optimized the factor parameters by central composite design of response surface method. Also we confirmed the optimal parameters through field testing to ensure the purpose of the experiment has been achieved. The testing result showed the process became stable and then we are able forward to make mass production thereafter.

摘要………………………………………………………………………………………i
英文摘要……………………………………………… ………………………………ii
目次……………………………………………………………………………………iii
表目錄……………………………………………………………………………………v
圖目錄……………………………………………………………………………………vi
第一章 緒論 ………………………………………………………………………………1
1.1 研究動機………………………………………………………………………………1
1.2 研究目的與範圍………………………………………………………………………2
1.3 研究限制………………………………………………………………………………4
1.4 研究流程與內容………………………………………………………………………4
第二章 文獻探討……………………………………………………………………………7
2.1 品質工程………………………………………………………………………………7
2.2 品質管理………………………………………………………………………………9
2.2.1 柏拉圖………………………………………………………………………………9
2.2.2 特性要因圖……………………………………………………………11
2.3 實驗設計法…..………………………………………………………………………15
2.4 部分因子實驗設計法…………………………………………………………………17
2.5 反應曲面法簡介………………………………………………………………20
第三章 研究方法……………………………………………………………………………23
3.1 走心式車床簡介………………………………………………………………………23
3.2 品質不良原因分析……………………………………………………………………25
3.3 關鍵因子分析…………………………………………………………………………26
3.4 反應曲面法……………………………………………………………………………28
3.5最佳值決定………………………………………………………………………………31
第四章 實驗結果討論………………………………………………………………………33
4.1 製程實驗結果……………………………………………………………………33
4.2 反應曲面最佳解…………………………………………………………………37
4.3 確認實驗…………………………………………………………………………38
第五章 結論與未來研究建議………………………………………………………………41
5.1 結論………………………………………………………………………………41
5.2 未來研究建議……………………………………………………………………42
參考文獻………………...…………………………………………………………………43

1. 方俊雄，反應曲面在公差分配的應用分析，逢甲大學碩士論文，台中，1998。
2. 白賜清，品質管制之相關與迴歸分析，中華民國品質學會，2003。
3. 陳台昆，在熱效應之影響下，以統計方法作參數與公差設計，逢甲大學工業工程研究所碩士論文，台中，2001。
4.陳永生， QC 七大手法--最簡明的使用方法，品質管制月刊，第三十卷第二十期，96-107頁。
5. 陳順宇，實驗設計，華泰書局，2002。
6. 鄭清和，品管七大手法，復文書局， 2002。
7. 黎正中、陳源樹編譯，實驗設計與分析，高立圖書，2006。
8. 黎正中譯，穩健設計之品質工程，台北圖書有限公司，1993。
9. 鍾清章，田口式品質工程導論，中華民國品質學會2003。
10. Biles, W. E. and Swain, J. J. (2000), “Response Surface Method for Experiential Optimization of Multi-Responses Process”, Industrial and Engineering Chemistry, Vol. 13, pp. 134-155.
11. Box, G. E., and Draper, N. R. (1997), Empirical Model Building and Response Surface, John Wiley and Sons, New York.
12. Box, G.E.P. and J.S. Hunter (1957) “Multifactor Experimental Designs for Exploring Response Surface”, Annals of Mathematical statistics, Vol. 38, pp. 195-242.
13. Derringer, G. and Suich, R. (1980). “Simultaneous Optimization of Several Response Variables”, Journal of Quality Technology Vol.12, pp. 214-219.
14. Giovanni, M. (1983). “Response Surface Methodology and Product Optimization”, Food Technology, Vol. 37, No. 11, pp. 41-45.
15. Harrington, E. C., Jr. (1965), “The Desirability Function”, Industrial Quality Control, Vol. 21, No. 10, pp. 494-498.

16. Jang, A.(1999), “Robust Tolerance Design by Response Surface Methodology,” International Journal of Advanced Manufacturing Technology, Vol. 15, No. 6,
pp. 399-403.
17. John A.Cornell“How to Apply Response Surface Methodology”, American
Society for Quality Control, Volume 8 pp.21-29.
18. Khuri, A. J., and Cornell, J. A. (1996), Response Surface: Design and Analysis, Marcel Dekker, New York.
19. Montgomery, D.C. (2001).Design and Analysis of Experiment, 5th ed., New York, John Wiley and Sons, Inc.
20. Myers, R. H., and Montgomery, D. C. (1995). Response Surface Methodology :
Process and Product Optimization Using Designed Experiments. John Wiley,
New York.