跳到主要內容

臺灣博碩士論文加值系統

(3.238.225.8) 您好!臺灣時間:2022/08/09 00:41
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:鄭价廷
研究生(外文):Jie-Ting Zheng
論文名稱:應用基因遺傳演算法於零工式工場生產排程
論文名稱(外文):Applications of Genetic Algorithm to Job-Shop Scheduling
指導教授:劉東官劉東官引用關係
指導教授(外文):Tung-Kuan Liu
學位類別:碩士
校院名稱:國立高雄第一科技大學
系所名稱:機械與自動化工程所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:68
中文關鍵詞:模具業遺傳演算法生產排程田口法
外文關鍵詞:die industrygenetic algorithmproduction sche
相關次數:
  • 被引用被引用:8
  • 點閱點閱:511
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在本文裡,我們探討應用遺傳演算法 (Genetic Algorithm,GA) [1] [8] [15] 改善生產程序的排程規劃的問題中的零工式工廠生產排程問題 (Job-Shop Scheduling Problem) [4] [5] [6] [11] 。如何縮短生產排程的最長完工時間 (makespan) ,是本篇論文的研究目標之一。本篇論文的研究分為兩個方向:
(1)本研究針對 GA 的運算子 (GA operator) 差異所構成的不同演算方式之結果作探討,並觀察不同運算子的影響,藉以求得更趨近最佳值的較好的運算模式。對於遺傳演算法的參數選擇,我們運用田口實驗方法從中找出最佳之參數組合,再將排程結果作比較,證實我們提出的方法,可確實將生產排程的總工作時間作大幅度縮短,成功的將遺傳演算法應用於零工式工廠的生產流程規劃上。
(2)於實際應用上,目前大部分企業都是以人工的方式或是建置模擬專家經驗系統方式進行排程。這些方式對於現今企業均極欲提高競爭力的現況來說,效率低、浪費時間及人力或是無法達到預期效果。為了解決上述問題,於實際應用方面,本研究與國內知名的研究中心-財團法人金屬工業研究發展中心(Metal Industries Research & Development Center) 合作,結合該中心現有之模具廠資訊管理系統 (以下簡稱 E-Pass) 及遺傳演算法之理論,並考量時間及人力的效益,針對模具工業的生產排程進行研究,發展出一套解決模具業生產排程的有效解法,達到理論與實際應用結合的目標。
In this thesis, we confer using Genetic Algorithm to improve the scheduling of production plan about a job-shop scheduling problem. How to shorten total working time of production scheduling is a goal of research in the thesis. In the thesis, we research in two directions:
(1) We discuss the result with using differential GA operators, and observe the influence of differential operators for the purpose of getting the best operation mold, which tends to optimal solution more. For selecting the parameter of genetic algorithm, we use Taguchi method to find the optimal parameter combination, and compare each scheduling result to prove that our way can slash total working time of production scheduling exactly. Consequentially, we successfully apply genetic algorithm to the production flow chart in the Job Shop Scheduling.
(2) Now most scheduling of die industry are used by the artificial way or built by professional experience in the actual application. These ways are inefficient, waste time and manpower or can’t reach desirable result for the condition that businesses want to raise competitiveness nowadays. To solving this problem, we cooperate with the famous national research center, Metal Industries Research & Development Center, in the actual application of the thesis. We combine the MIS system of factory from Metal Industries Research & Development Center (for short: E-Pass) with the program based on the genetic algorithm theory, and think about the efficiency of time and manpower. To production scheduling in the die industry, we have developed an effective method, which reach the goal that genetic algorithm can combine with the actual application.
摘要i
ABSTRACTii
誌謝iv
目錄索引v
圖片目錄ix
表目錄xi
符號說明xii
一、緒論1
1.1研究動機1
1.2研究目標2
1.3研究範圍3
1.4研究方法與內容3
1.5研究流程架構5
二、文獻探討6
2.1遺傳演算法簡介6
2.2 Job Shop Scheduling Problem 基本定義6
2.3遺傳演算法與 Job Shop Scheduling 名詞的對照6
2.4遺傳演算法法則7
2.5 Job Shop Scheduling 相關文獻10
2.6遺傳演算法於 Job Shop Scheduling 相關文獻11
三、遺傳演算法於 JSP 問題研究及分析13
3.1 JSP 問題基本假設13
3.2研究方法13
3.3研究項目17
3.3.1研究項目類別17
3.3.2 多目標評比:20
3.3.3研究例子23
3.4研究結果24
3.4.1 GA 與兩種類神經網路24
3.4.2 GA 的不同運算方式配合25
3.5結果分析與討論29
3.5.1 GA與兩種類神經網路29
3.4.2 GA 的不同運算方式配合29
四、使用田口方法設計遺傳演算法參數31
4.1田口法簡介31
4.1.1田口法的實驗步驟:31
4.1.2實驗計劃用語:31
4.2實驗結果32
4.2.1直交表選擇32
4.2.2 GA 參數設計33
4.2.3實驗結果與分析33
五、 GA 排程與 E-Pass 之資料整合41
5.1模具業生產限制條件與注意事項41
5-2輸入資料模式說明43
5.3輸出資料模式說明45
六、遺傳演算法程式於實際排程處理47
6.1後續製程47
6.2多工令單48
6.2.1工令單的絕對優先次序49
6.2.2工令單的可插入點49
6.3排程基準點50
七、結果與討論53
7.1 E-Pass 排程甘特圖53
7.2 E-Pass 與 GA 排程結果比較54
八、結論與未來展望56
參考文獻57
附錄一程式流程圖61
附錄二系統實驗資料64
[1] T.K.Liu, “Application of Multi-objective Genetic Algorithms to Control System Design ”, Doctorial Thesis in Tohoku University.[2] Kyung-Mi Lee and Takeshi Yamakawa, 1998, ”A Genetic Algorithm for General Machine Scheduling Problems”, School of Computer Science and System Engineering, Kyushu Institute of Technology , IEEE.[3] Tsujimura, Y.; Mafune, Y.; Gen, M., 2001, “Effects of symbiotic evolution in genetic algorithms for job-shop scheduling ” , System Sciences , Proceedings of the 34th Annual Hawaii International Conference on.[4] Guoyong Shi, 1997, “A Genetic Algorithm Applied to a Classic Job-shop Scheduling Problem “, International Journal of Systems Science, Vol.28, No.1, pp25-32.[5] Lee, C.Y. , Piramuthu,S. and Tsai,Y.K., 1997, “Job shop Scheduling with a genetic algorithm and machine learning“, International Journal of Production Research, 35 (4), pp.1171-1191.[6] D.R.Sule, 1996, Industrial Scheduling, PWS Publishing Company, pp149~185.[7] Lawton ,G., 1992, ”Genetic Algorithm for Schedule Optimization”, AI Expert, Vol.17, No.5, pp23-27.[8] Srinivas, M. and L.M. Patnaik, 1994, Genetic Algorithm: A Survey , IEEE Computer, June, pp.17-26.[9] Carlos M.Fonseca and Peter J.Fleming , “Genetic Algorithms for Multiobjective Optimization:Formulation,Discussion and Generalization” , Automatic Control and Systems Eng., pp.416-423.[10] Conway , R.W.,W.L.,and L.Miller, 1967, Theory of Scheduling, Addison-Wesley, Reading, MA.[11] Muth, J.F., and G.L. Thompson, 1963, Industrial Scheduling, Prentice Hall, Englewood Cliffs, NJ.[12] GouYong Shi, 1997, “A genetic algorithm applied to classic job-shop scheduling problem”, International Journal of System Science.[13] Mitsuo Gen, Runwei Cheng, 1997, Genetic algorithms and engineering design, Wiley, New York.[14] 林我聰,83年,現場排程專家系統,台北:資訊與電腦叢書。[15] 周明、孫樹棟,遺傳算法原理及應用,北京:國防工業出版社。[16] 周至宏,品質工程,國立高雄第一科技大學機械與自動化系。[17] 劉庭瑋、何信瑩,2002,”使用智慧型基因演算法設計太空大型結構控制器”,中華民國自動控制研討會,國立成功大學,p1461~p1466。[18] 劉修任、楊憲東,2000,“結合基因演算法與田口實驗法於飛行控制設計”,中國航空太空學會學刊,32卷,3期,頁223~236。[19] 張孝德、蘇木春,86年12月,機器學習類神經網路、模糊系統及基因演算法則,9-1,90年7月,全華科技圖書股份有限公司。[20] 專案管理99風雲榜,http://project.engineer.com.tw/[21] 洪茂森,2002,應用類神經網路於零工式生產排程之研究,國立高雄第一科技大學,碩士論文。[22] K. R. Baker, 1984, “Sequencind Rules and Due-Date Assignments in a Job Shop”, Management Sciences 30, 9, pp. 1093-1104.[23] J. H. Blackstone, Jr., D. T. Phillips, G. L. Hogg, 1982, “A State-of-the-Art Survey of Dispatching Rules for Manufacturing Job Shop Operations”, International Journal of Production Research 20, 1, pp.27-45.[24] A. S. Kiran, M. L. Smith, 1984, “Simulation Studies in Job Shop Scheduling - A Survey”, Computers and Industrial Engineering 8, 2, pp.87-93.[25] A. S. Kiran, M. L. Smith, 1984, “Simulation Studies in Job Shop Scheduling - Performance of Priority Rules”, Computers and Industrial Engineering 8, 2, pp.95-105.[26] S. S. Panwalkar, W. Iskander, 1977, “A Survey of Scheduling Rules”, Operations Research 25, 1, pp.45-61.[27] Yang, S.; Dingwei Wang, March 2000, “Constraint satisfaction adaptive neural network and heuristics combined approaches for generalized job-shop scheduling”, Neural Networks, IEEE Transactions on , Vol.11, Issue: 2, pp.474 -486.[28] Chuan Yu Chang; Mu Der Jeng, 1995, “A neural network model for the job-shop scheduling problem with the consideration of lot sizes”, Robotics and Automation. Proceedings., IEEE International Conference on , Vol.1 , pp.202 -207.[29] Guohua Wan; Yen, P.-C. , 1999, “A fuzzy logic system for dynamic job shop scheduling” ,Systems, Man, and Cybernetics, IEEE SMC ''99 Conference Proceedings. IEEE International Conference on , Vol. 4, pp.546 —551.[30] H. Fisher and G. Thompson, 1963, Industrial Scheduling, J. Muth and G. Thompson eds., Prentice-Hall, pp.1225-1251.[31] Chou J. H., Liao, W. H., and Li, J. J., 1998, “Application of Taguchi-Genetic Method to Design Optimal Gray-Fuzzy Controller of a Constant Turing Force System”, 第十五屆機械工程研討會控制與自動化組論文集, pp.31-38.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊