• 沒有找到結果。

Using Neural-Taguchi Method and Genetic Algorithm in Optimization of Multi-Response Process Control 洪松男、駱景堯

N/A
N/A
Protected

Academic year: 2022

Share "Using Neural-Taguchi Method and Genetic Algorithm in Optimization of Multi-Response Process Control 洪松男、駱景堯"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

Using Neural-Taguchi Method and Genetic Algorithm in Optimization of Multi-Response Process Control

洪松男、駱景堯

E-mail: [email protected]

ABSTRACT

In the recently years, Taguchi method has been widely applied in the practical applications for optimizing the process parameters in the manufacturing process. However, the method only takes a single quality attribute into account. 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.

Keywords : Neural Network ; Taguchi ; Multiple Quality Attributes ; Fuzzy Theory ; Genetic Algorithm Table of Contents

封面內頁 簽名頁 授權書... iii 中文摘要... iv 英文摘

要... v 誌謝... vi 目錄... vii 圖目

錄... ix 表目錄... x 第一章 緒論... 1 1.1研究背景與 動機... 1 1.2研究目的... 2 1.3研究範圍... 3 1.4研究流 程... 4 第二章 文獻探討... 6 2.1類神經網路法... 6 2.2改良式田 口法... 7 2.3相關統計方法... 9 2.4結論... 10 第三章 研究 架構與方法... 12 3.1前言... 12 3.2田口式實驗設計... 15 3.3直交 表設計... 16 3.4 S/N比... 17 3.5回應表與確認實驗... 19 3.6模 糊集合理論... 20 3.7TOPSIS法... 23 3.8倒傳遞類神經網路... 26 3.9基因演算法... 32 3.10確認實驗... 34 第四章 實例說明... 35 4.1製程介紹... 35 4.2工程中重要的品質特性... 37 4.3品質特性量測方

式... 38 4.4實驗規劃... 39 4.5實驗數據整理與初步計算... 41 4.6 TOPSIS法與模糊理論運用... 46 4.7應用倒傳遞類神經網路... 50 4.8基因演算法最佳化條件蒐 尋... 52 4.9確認實驗... 58 第五章 結論與建議... 59 參考文

獻... 60 附錄A... 63 附錄B... 65 附 錄C... 66

REFERENCES

指導教授(英文姓名): Low, Chinyao 學位類別: 碩士 校院名稱: 大葉大學  系所名稱: 工業工程學系碩士班 學號: E9002015 學年度: 92 語文 別: 中文 論文頁數: 68 關鍵詞: 類神經田口法 ; 多品質特性 ; 模糊理論 ; 參數設計 ; 基因演算法 ; TOPSIS法 英文關鍵詞: Neural Network ; Taguchi ; Multiple Quality Attributes ; Fuzzy Theory ; Genetic Algorithm 被引用次數: 1 [ 摘要 ] 近年來,田口方法在工業上廣泛的被應用來 達成製程最佳化參數設計。但是,田口方法大多僅針對單一品質特性探討,對於多品質特性最佳化問題,並沒有適當的解決方案。而且 參數設計僅針對某些實驗水準點上的最佳化,而不是全域的最佳化。若因子間存在著交互作用或是因子與品質特性間屬於非線性關係,

參數設計的預測能力就會變差,進而影響實驗結果。    有鑑於此,本研究使用一系統的方法,應用TOPSIS法與模糊理論整合多個 品質特性為單一指標,並利用類神經田口法建構其系統模型,最後使用基因演算法蒐尋出似全域最佳解,以達成最佳化參數設計。  

 本研究將此一系統方法套用於一實例的製程最佳化參數設計,以期望快速提昇製程能力,並驗証此一方法的有效性。

[ 英文摘要 ] In the recently years, Taguchi method has been widely applied in the practical applications for optimizing the process parameters in the manufacturing process. However, the method only takes a single quality attribute into account. 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

(2)

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.

[ 論文目次 ] 封面內頁 簽名頁 授權書... iii 中文摘要... iv 英文摘

要... v 誌謝... vi 目錄... vii 圖目錄...

ix 表目錄... x 第一章 緒論... 1 1.1研究背景與動機... 1 1.2研究目 的... 2 1.3研究範圍... 3 1.4研究流程... 4 第二章 文獻探 討... 6 2.1類神經網路法... 6 2.2改良式田口法... 7 2.3相關統計方 法... 9 2.4結論... 10 第三章 研究架構與方法... 12 3.1前 言... 12 3.2田口式實驗設計... 15 3.3直交表設計... 16 3.4 S/N 比... 17 3.5回應表與確認實驗... 19 3.6模糊集合理論... 20 3.7TOPSIS 法... 23 3.8倒傳遞類神經網路... 26 3.9基因演算法... 32 3.10確認實 驗... 34 第四章 實例說明... 35 4.1製程介紹... 35 4.2工程中重要的品質特 性... 37 4.3品質特性量測方式... 38 4.4實驗規劃... 39 4.5實驗數據整理與初步計 算... 41 4.6 TOPSIS法與模糊理論運用... 46 4.7應用倒傳遞類神經網路... 50 4.8基因演算法最 佳化條件蒐尋... 52 4.9確認實驗... 58 第五章 結論與建議... 59 參考文

獻... 60 附錄A... 63 附錄B... 65 附

錄C... 66 [ 參考文獻] 1.王宗富(2001),” 多重品質特性製程參數最佳化研究-以高分子有機電激發光顯示器為例

”,國立台灣科技大學工業管理系碩士論文。 2.余淑惠(1993),”以兩階段熱處理程序進行玻璃纖維織物退漿之研究”,萬能學報,

卷15,頁23-44。 3.吳榮晏(2000),”低介電酚醛環氧樹脂製備及其積層電路板特性研究”,長庚大學化學工程學系碩士論文。 4.葉怡 成(1998),”類神經網路模式應用與實作”,儒林圖書有限公司。 5.葉馨雅(1997),”動態系統多重品質特性最佳化之研究”,國立交通 大學工業工程研究所碩士論文。 6.戴金琪(2003),”以反應曲面方法改善銅導線晶圓封裝之銲線製程問題”, 元智大學工業工程與管理研 究所碩士論文。 7.蘇朝墩(2002),”品質工程”,中華民國品質工程學會發行。 8.Goldberg,David E.(1989) , ”Genetic Algorithms In Search Optimization Machine Learning” , Addison Wesley publishing Co. 9.Holland,J.(1975) , ” Adaptation in natural and artificial systems” , University of Michigan Press , Ann Arbor. 10.Hwang,C. L. and Yoon,K.(1981) , ” Multiple Attribute Decision Making-Method and Applications

” , A State-of-the-Art Survey , Springer-Verlag , New York. 11.Li,Y. , Mahajan,R. L. and Tong,J.(1993) , ”Design Factors and Their Effect on PCB Assembly Yield-Statistical and Neural Network Predictive Models” , IEEE/CHMT International Electronics Manufacturing Technology Symposium , pp.353-361. 12. Lin,J. L. , Wang,K. S. , Yan,B. H. , Tarng,Y. S.2000) , ” Optimization of the electrical discharge machining process based on the Taguchi method with fuzzy logics” , Journal of Materials Processing Technology , Vol.102 , pp.48-55 13. Montgomery,Douglas C.(1997) , ”Design and Analysis of Experiments” , 5th Edition,John Wiley & Sons Inc. 14. Ross,Phillip J.(1996) , ”Taguchi Techniques for Quality Engineering ” , 2th Edition , McGraw-Hill Inc. 15.Stefan,Sette , Luc,Boullart , Lieva,Van Langenhove(1996) , ” Optimising a

Production Process by a Neural Network/Genetic Algorithm Approach” , Engineering Applications of Artificial Intelligence , Vol. 9 , pp.681-689 16.Su,Chao-Ton and Chiang,Tai-Lin(2002) , ”Optimal Design for a Ball Grid Array Wire Bonding Process Using a Neural-Genetic Approach” , IEEE Transactions On Electronics Packaging Manufacturing , Vol.25 , No.1 , pp. 13-18. 17.Su,Chao-Ton and Tong,Lee-Ing(1997) , ”

Multi-response robust fdesign by principal analysis” , Total Quality Management , Vol.8 , pp. 409-416 18.Tarng,Y. S. , Juang,S. C. , Chang,C.

H.(2002) , ” The use of grey-based Taguchi methods to determine submerged arc welding process parameters in hardfacing” , Journal of Materials Processing Technology , vol.128 , pp.1-6 19.Tong,L. I. and Su,C. T.(1997) , “Optimizing Multi-response Problems in the Taguchi Method by Fuzzy Multiple Attribute Decision Making” , Quality and Reliability Engineering International , Vol.13 , pp.25-34. 20.Wang,G. J. , Tsai,J. C. , Tseng,P. C. and Chen,T.C. (1998) , ”Neural-Taguchi Method for Robust Design Analysis” , Journal of the Chinese Society of Mechanical Engineers , Vol.19 , No.2 , pp. 223 -230. 21.Yager,R. R.(1981) , ” on a general class of fuzzy connectives” , fuzzy sets and systems , vol. 4 22.Zadeh,L. A.(1965) , ”Fuzzy Sets” , Information and Control , Vol. 8 , pp.338-353.

參考文獻

相關文件

• MIPS consolidates multiple, quality programs into a single program to improve quality care.. https://www.healthit.gov/topic/meaningful-use-and-macra/meaningful-use

Moreover, this chapter also presents the basic of the Taguchi method, artificial neural network, genetic algorithm, particle swarm optimization, soft computing and

“A Comprehensive Model for Assessing the Quality and Productivity of the Information System Function Toward a Theory for Information System Assessment.”,

To solve this problem, this study proposed a novel neural network model, Ecological Succession Neural Network (ESNN), which is inspired by the concept of ecological succession

Secondly then propose a Fuzzy ISM method to taking account the Fuzzy linguistic consideration to fit in with real complicated situation, and then compare difference of the order of

Thus, the proposed approach is a feasible and effective method for process parameter optimization in MIMO plastic injection molding and can result in significant quality and

In the second phase, quality characteristics optimization- to meet the target under the adjustment of control factors’ levels via ANOVA analysis, and using the quality characteristic

Kuo, R.J., Chen, C.H., Hwang, Y.C., 2001, “An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and