(3.234.221.67) 您好!臺灣時間:2021/04/11 16:26
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:陳麒元
研究生(外文):Chen ,Chi-Yuan
論文名稱:應用拓樸理論與基因演算法於電動代步車結構最佳化設計之研究
論文名稱(外文):A Study on the Application of Topological Theory and Genetic Algorithm to the Optimum Structure Design of a Electric Scooter
指導教授:許進忠許進忠引用關係
指導教授(外文):Sheu, Jinn-Jong
學位類別:碩士
校院名稱:國立高雄應用科技大學
系所名稱:模具工程系碩士班
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:2004
畢業學年度:92
語文別:中文
論文頁數:187
中文關鍵詞:電動代步車拓樸最佳化類神經網路基因演算法田口實驗計畫法結構最佳化
外文關鍵詞:electric scooterneural networkgenetic algorithmtaguchi methodtopological optimizationstructure optimization
相關次數:
  • 被引用被引用:13
  • 點閱點閱:875
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:147
  • 收藏至我的研究室書目清單書目收藏:2
人口老化日趨嚴重,醫療輔助用品相關產品也相繼被推出,電動代步車就是其中的一項。由於銀髮族的使用率較高,因此安全性就顯得非常重要了。安全性的關鍵在車架結構,結構強度及變形的參數很多,工程師不易掌握。傳統的機械設計方式以試誤法為主,因而耗費大量的成本及時間。基於安全性及成本上的考量,本文提出一個「系統化設計方法」,輔助工程師做電動代步車結構最佳化設計。
本研究應用拓樸最佳化方法,找出代步車結構的雛型,以電腦輔助分析結合實驗計畫方法,考慮不同的受力方式、不同的結構件斷面形狀、材質以及車體拓樸造形等因素,以找出最佳的設計參數。將實驗產生的離散資料,利用類神經網路的倒傳遞法則,產生代步車結構變形的預測模型,再由基因演算法對預測模型找出最接近全域的最佳化設計參數,並將實驗設計法與基因演算法所產生之最佳的設計參數與以比較之。
類神經網路預測之變形與電腦分析結果吻合,最佳化參數也能與田口預測條件一致。為驗證理論分析結果,本研究組裝完成一台車架進行實驗,由理論位移與實驗結果的比較發現大小及趨勢都吻合,經由應變規量測之應變結果與理論比較也都吻合,驗證本研究所提出之設計方法可行。
The number of aged persons increased dramatically and the need of medical assistant equipments were promoted too. The electric scooter is one of the most popular devices. The structure of the scooter is the key point of the safety consideration for the aged users. The structure strength and the deformation of a scooter include a lot of parameters. In this research, a systematical design method was proposed to aid the structure optimization design of a scooter.
In this research, the prototypes of the scooter structure were obtained by using the topological optimization procedure. The computer aided engineering and the design of experiment technique were combined to find a feasible optimum design. The applied forces, the cross-section of the structure members, the type of material and the topological shape of the scooter were taken into consideration in this optimization research. The discrete experimental data were adopted in the artificial neural network (ANN) system with the back-propagation learning scheme. The ANN prediction model of the structure deformation of a scooter was established. An optimization design system using the genetic algorithm was established. The developed ANN system was integrated into the genetic optimization system to evaluate the evolution results. The optimized results of the DOE and the genetic system were compared.
The predicted deformation of the ANN system was in good agreement with the CAE. The optimization result was matched with the DOE result. A scooter structure was built and tested to verify the proposed system. The predicted displacement and the strain were in good agreement with the observation of the experiment results. It demonstrated the proposed method was applicable.
摘 要 i
ABSTRACT ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 x
符號說明 xiii
一、 緒論 1
1.1前言 1
1.2文獻回顧 2
1.3研究動機及目的 9
二、研究理論探討 10
2.1電動代步車介紹 10
2.2拓樸最佳化 11
2.3 有限元素法 13
2.4 田口實驗計畫法 19
2.5類神經網路 27
2.6基因演算法 33
三、研究方法及步驟 47
3.1分析方法驗證 49
3.1.1拓樸最佳化驗證 49
3.1.2車架有限元素分析 52
3.1.3類神經網路驗證方式 60
3.1.4基因演算法驗證方式 64
3.1.5 車架實驗之應變規驗證 66
3.2拓樸最佳化與車架初始設計 69
3.3田口實驗法評估設計因子及最佳化條件方式 74
3.4類神經網路建立代步車預測模型方式 84
3.5基因演算法最佳化代步車設計因子方式 87
3-6車架位移及應變實驗 88
四、結果與討論 100
4.1田口實驗法之最佳參數條件 100
4.1.1田口實驗法靜態設計分析重要因子結果 100
4.1.2參數設計分析最佳組合條件結果 110
4.1.3最大位移,應力及應變量發生位置及特性比較 123
4.2類神經網路之預測模型建立 128
4.3基因演算法之最佳化參數 133
4.4車架位移及應變實驗結果 135
4.4.1 應變值結果比較 135
4.4.2 位移量結果比較 141
五、結論與建議 143
5.1拓樸最佳化與田口實驗法分析部分 143
5.2類神經網路預測及基因演算法最佳化部分 144
5.3車架實驗部份 144
六、未來展望 145
七、參考文獻 146
附錄一 150
A.1 MSD含有平均數( )及變異數(σ)的統計評量指標之公式證明。 150
A.2 輸入層與隱藏層之倒傳遞運算公式證明 151
A.3蝴蝶花分類問題 154
A.4代步車結構之類神經網路權值及閥值數據表 157
A.5類神經網路程式流程圖 161
A.6基因演算法程式流程圖 165
八、簡歷 167
1.梁智傑,2000,從老人生活型態探討電動代步車設計,大葉大學,碩士論文。
2.王子彰,2000,混合動力型代步車輛之系統規劃與控制系統開發製作,元智大學,碩士論文。
3.陳志達,2000,電動助行車與無人自行車之控制系統研製,國立中興大學,碩士論文。
4.游許銓,2001,電動輪椅動力驅動之解析模型,國立成功大學,碩士論文。
5.梁望遵,1983,電動車路況模擬系統之研製,國立清華大學,碩士論文。
6.李陳國,2000,臺灣電動機車產業發展與競爭策略之研究,中華大學,碩士論文。
7.張時中,2001,電動機車之建模分析與再生煞車控制,國立交通大學,碩士論文。
8.郭春寶,1994,電動車之理論與實驗分析,國立中正大學,碩士論文。
9.林昆民,2000,電動車整體性能之電腦輔助設計分析,國立清華大學,碩士論文。
10.鍾添東,1985,最佳化理論在機械結構設計上之應用,國立台灣大學,博士論文。
11.劉英偉,1991,結構輕量化最佳設計之分析方法,國立中興大學,博士論文。
12.葉俊銘,1991,傳統迭代法與似牛頓法於靜力再分析之比較,逢甲大學,碩士論文。
13.蔡銘山,2000,鋼構架結構之最佳化設計,屏東科技大學,碩士論文。
14.黃瑞宏,2000,登山自行車後懸吊機構系統之設計,國立中山大學,碩士論文。
15.姜冠貞,2000,拓樸最佳化設計系統整合之研究,國立中正大學,碩士論文。
16.趙立祥,1998,整合拓樸與形狀最佳化之自動化技術,國立台灣科技大學,碩士論文。
17.林彥志,2000,類神經網路於結構最佳化的應用,國立成功大學,碩士論文。
18.林志豐,2000,機械結構之有限元素法拓樸最佳化設計與分析,淡江大學,碩士論文。
19.X. Guo, G.D. Cheng,2000,” An extrapolation approach for the solution of singular optima”, Structural and Multidisciplinary Optimization, Volume 19 Issue 4, pp 255-262.
20.Y.S. Shin , R.V. Grandhi,2001,” A global structural optimization technique using an interval method”, Structural and Multidisciplinary Optimization, Vol. 22 Issue 5, pp 351-363.
21.X. Guo, G. Cheng, K. Yamazaki , 2001,” A new approach for the solution of singular optima in truss topology optimization with stress and local buckling constraints”, Structural and Multidisciplinary Optimization ,Vol. 22 Issue 5 , pp 364-373.
22.H. Harasaki, J.S. Arora, 2001,” A new class of evolutionary methods based on the concept of transferred force for structural design”, Structural and Multidisciplinary Optimization, Vol.22, Issue 1, pp 35-56.
23.Schmit.L.A. ,1960,”Structural Design by Systematic Synthesis”,Proceedings of the 2nd Conference on Eletronic Computation, ASCE, NewYork, pp. 105-122 (American Society of Civil Engineers, ASCE)
24.Dorn,W.S., Gomory,R.E., and H.J. Greenberg. ,March 1964,”Autimatic Design of Optimal Structures”, Journal of Mechanique, Vol.3, No.1, pp.25-52.
25.Bendsoe, M.P. and N. Kikucki, 1988, "Generating Optimal Topologies in Structural Design Using a Homogenization Method ", Computer Methods in Applied Mechanics and Engineering, Vol. 71, pp. 197-224 .
26.Robert L.Harvey, 1994, Neural Network Principles, Prentice Hall, Englewood Cliffs, New Jersey.
27.McCulloch, W.S., and W.H. Pitts ,1943,”A Logical Caculus of the Ideas Imminent in Nervous Activity”, Bulletin of Mathematical Biophysics,Vol.5,pp115-133.
28.Hebb, D.O.,1949, The Organization of Behavior , A Neuropsychological Theory,John Wiley, New York
29.Rosenblatt, F.,1958,”The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain”,Psych.Rev.,65,pp.386-408
30.Minsky, M., and S.Papert,1969, Perceptrons ,An Introduction to Computational Geometry, MIT Press, Cambridge,MA
31.Rumelhart, D.E., Hinton, G.E. and R.J.Williams,1986,” Learning Internal Representations by Error Propagation”, in D.E. Rumelhart and J.L.McClelland, eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pp.318-362, MIT Press,Camdridge,MA
32.Werbos, P.,1974,”Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences” ,Ph.D., Thesis, Harvard Unversity.
33.Parker, D.B., October 1982,”Learning Logic”, Invention Report S81-64, File 1, Office of Technology Licensing, Standford University.
34.Stephen I. Gallant , 1993, Neural Network Learning and Expert Systems , MIT Press Cambridge, MA.
35.Holland, J.H., 1975“Adaptation in Natural and Artificial System,” University of Michigan Press,Ann Arbor,MI
36.Morikawa, K., Furuhashi, T., Uchikawa, Y., Jun 1994,” Evolution of CIM System with Genetic Algorithm”, Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on , 27-29 Page(s): 746 -749 vol.2
37.H. Harasaki , J.S. Arora , 2001,”A new class of evolutionary methods based on the concept of transferred force for structural design”, Structural and Multidisciplinary Optimization Vol. 22, Issue 1, pp 35-56
38.Hao, Zhou, Kefa, Cen, Jianbo, Mao , December, 2001” Combining Neural Network and Genetic Algorithms to Optimize Low NOx Pulverized Coal Combustion ”, Fuel Vol. 80, Issue: 15, pp. 2163-2169
39.Simo, J.C. and Vu-Quoc, L.,1986, ”A Three Dimensional Finite Strain Rod Model. Part II: Computational Aspects”, Computer Methods in Applied Mechanics and Engineering, Vol. 58, pp. 79-116 .
40.Ibrahimbegovic, Adnan,1995,”On Finite Element Implementation of Geometrically Nonlinear Reissner''s Beam Theory: Three-dimensional Curved Beam Elements”, Computer Methods in Applied Mechanics and Engineering, Vol. 122, pp. 11-26 .
41.Ashok D. Belegundu, Tirupathi R. Chandrupatla,1999, Optimization concepts and applications in engineering , Prentice Hall, Upper Saddle River, New Jersey.
42.David E. Goldberg, 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison Wesley, New York.
43.Yang, R.J. and C.H.Chuang,1994,”Optimal topology design using linear programming”, Computer and Structure ,Vol.52, No.2, pp 265-275.
44.H. Harasaki , J.S. Arora ,“A new class of evolutionary methods based on the concept of transferred force for structural design”, Structural and Multidisciplinary Optimization,Vol. 22, Issue 1, pp 35-56.
45.Saeed Moavent, 1999, Finite Element Analysis Theory and Application with ANSYS , Prentice Hall.
46.PHILLIP J.ROSS, 1996, Taguchi Techniques For Quality Engineering, McGraw-Hall.
47.鍾清章校訂,1989,田口式品質工程導論,中華民國品質管制協會。
48.吳玉印,1987,新版實驗計劃法,中興管理顧問公司。
49.陳順宇 鄭碧娥,1996,統計學,華泰書局。
50.吳宗益,2002,應用基因演算法及田口實驗法於模具生產排程系統之研究,國立高雄第一科技大學,碩士論文。
51.黃國源,2003,類神經網路與圖形辨識,維科圖書有限公司。
52.葉怡成,1993,類神經網路模式應用與實作,儒林圖書有限公司。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔