類神經網路自組織滑動模糊控制器在雙軸電液伺服系統之應用

簡易檢索 / 詳目顯示

回結果列表

研究生：	李宗倫 Zong-lun Li
論文名稱：	類神經網路自組織滑動模糊控制器在雙軸電液伺服系統之應用 Neural Network Self-Organizing Sliding Mode Fuzzy Controller Applied in Double-Axial Electro-Hydraulic Servo System
指導教授：	莊福盛 Fu-Sheng Chuang
口試委員:	蔡明俊 none 林鴻裕 none 王英才 Ying-Tsai Wang
學位類別：	碩士 Master
系所名稱：	工程學院 - 機械工程系 Department of Mechanical Engineering
論文出版年：	2013
畢業學年度：	101
語文別：	中文
論文頁數：	93
中文關鍵詞：	滑動模糊控制器、自組織滑動模糊控制器、類神經網路自組織滑動模糊控制器、雙軸電液控制系統
外文關鍵詞：	sliding mode fuzzy control, self-organizing sliding mode fuzzy control, neural network self-organizing sliding mode fuzz, double-axial electro-hydraulic control system
相關次數：	點閱：338 下載：4
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

以滑動模糊控制器作為基礎，設計具有自我學習機制之自組織滑動模糊控制器及具有即時修正輸出增益之類神經自組織滑動模糊控制器，進行不同頻率與輸入訊號之雙軸電液伺服控制實驗，並比較三種控制器之控制特性。結果顯示，步階實驗中類神經自組織滑動模糊控制器有較短的暫態響應以及良好的精度。在低頻疲勞實驗時，三種控制器間性能差異不明顯，但在高頻疲勞實驗時，類神經自組織滑動模糊控制器明顯比滑動模糊及自組織滑動模糊控制器有較高之控制強健性與控制精度。

Based on sliding mode fuzzy control theorem, this thesis designs sliding mode fuzzy controller, self-organizing sliding mode fuzzy controller and neural network self-organizing sliding mode fuzzy controller for applications of double-axial electro-hydraulic control system. The self-organizing sliding mode fuzzy controller provides a learning mechanism to modify the fuzzy rule table online. The neural network self-organizing sliding mode fuzzy controller adds a neural network to modify the defuzzification gain. Different experiments, including step and sinusoidal commands, are performed to compare their transient and steady state performances of the above three controllers. Experimental results reveal that the neural network self-organizing sliding mode fuzzy controller has fast transient response and excellent accuracy in step command experiment. In the low frequency fatigue experiment, experimental results indicate that these are no significant difference among these three controllers. However, in high-frequency fatigue experiments, the neural network self-organizing sliding mode fuzzy controller has more significant robustness and better accuracy than the sliding mode fuzzy controller and the self-organizing sliding mode fuzzy controller.

中文摘要..................................................I
Abstract................................................II
目錄.....................................................IV
圖片索引..................................................VII
表格索引..................................................X
符號索引..................................................XI
第一章緒  論............................................1
1.1研究動機與目的...........................................1
1.2 文獻回顧...............................................4
1.3 論文大綱...............................................7
第二章 系統架構.............................................9
2.1 系統架構...............................................9
2.2 液壓設備...............................................11
2.3 控制設備...............................................13
2.4 工作流程...............................................22
第三章 控制理論.............................................23
3.1滑動模糊控制器(SMFC).....................................24
3.1.1滑動模式控制(sliding mode control).....................26
3.1.2模糊化(fuzzification).................................28
3.1.4模糊推論(fuzzy inference).............................32
3.1.5解模糊化(defuzzification).............................33
3.2自組織滑動模糊控制器(SOSMFC)...............................34
3.3類神經網路自組織滑動模糊控制器(NSOSMFC)......................39
3.3.1類神經網路控制架構......................................40
3.3.2倒傳遞類神經網路(back-propagation neural network).......41
3.3.3類神經網路方程式推導.....................................43
第四章 實驗結果與分析.........................................45
4.1 實驗規劃................................................45
4.2 實驗參數設定.............................................47
4.3 步階實驗分析.............................................51
4.3.1步階實驗...............................................52
4.3.2步階實驗結論............................................55
4.4  疲勞實驗分析............................................57
4.4.1 0.1Hz~2.0Hz同向疲勞實驗................................57
4.4.2 0.1Hz~2.0Hz同向疲勞實驗結論.............................67
4.4.3 0.1Hz~2.0Hz反向疲勞實驗................................68
4.4.4 0.1Hz~2.0Hz反向疲勞實驗結論.............................74
第五章 結  論................................................75
參考文獻.....................................................77

                                

【1】Zhang Z.W. and Song J.C., “Study on motorcycle fatigue test with electro hydraulic servo system,” ICIEA 2009. 4th IEEE Conference on Digital Object Identifier, pp.1686-1689, 2009
【2】方昭欽,“液壓主動式控制車輛懸吊系統之研究,”國立成功大學機械工程學系碩士論文, 2002
【3】Li D. and Salcudean S.E., “Modeling simulation and control of a hydraulic stewart platform,” IEEE International Conference on Robotics and Automation, Vol.4,pp.3360-3366,1997
【4】Wang C.L., Ding F., Cui J. and Li Q.P., “Dynamic characteristics of nozzle flapper servo valve based on GMA,” Chinese Journal of Mechanical Engineering, Vol.42, pp.23-26, 2006
【5】Almansa A. and De La Sen M., “Advanced control techniques based in artificial intelligence for robotics manipulators.” IEEE International Conference on Emerging Technologies and Factory Automation, Vol.1, pp.605-614, 1999
【6】Zhang H., Ukrainetz P.R. ,Burton R.T. and Nikiforuk P.N., “Implementation of neural network approach in MIMO electrohydraulic servosystem control,” IEEE International Conference on Control, Vol.2, pp.1468-1473, 1996
【7】Mamdani E.H., “Application of fuzzy algorithms for control of simple dynamic plant,” Proceedings of the Institution of Electrical Engineers, Vol.121, No.12, pp.1585-1588, 1974
【8】Wang C.L., Ding F., Cui J. and Li Q.P3, “Dynamic characteristics of nozzle flapper servo valve based on GMA,” Chinese Journal of Mechanical Engineering, Vol.42, pp.23-26, 2006
【9】Zadeh L.A., “Electrical engineering at the crossroads,” IEEE Transactions on Education,Vol.8,pp.30-33, 1965
【10】Mo J.H. and Wang H., “Modeling and fuzzy PID control of the VVVF based pressure control system of man-made diamond hydraulic force machine,” International Conference on Mechatronics and Automation, pp.3610-3615, 2007
【11】Huang C.Y., Chena T.C. and Huang C.L., “Robust control of induction motor with a neural-network load torque estimator and a neural-network identification,” IEEE Transactions on Education, Vol.46, pp.990-998, 1999
【12】Ku C.C. and Lee K.Y., “Diagonal recurrent neural networks for dynamic systems control,” IEEE Transactions on Neural Networks, Vol.6, pp.114-156, 1995
【13】Lin C.T. and Lee C.S.G., “Neural-network-based fuzzy logic control and decision system,” IEEE Transactions on Computers, Vol.40, pp.1320-1336, 1991
【14】Lin C.T. and Lee C.S.G., “Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systemsm,” IEEE Transactions on Fuzzy systems, Vol.2, pp.46-63, 1994
【15】Werbos P., “Beyond regression :new tools for prediction and analysis in the behavioral sciences,” PhD thesis, Harvard, Cambridge, 1974
【16】Parker D. B., “Learning logic,” Technical Report TR-47, Center for Computational Research in Economics and Management Science, MIT, Cambridge, 1985
【17】Rumelhart D.E. and McClelland J.L., “Parallel distributed processing,” MIT Press, Vol.1, 1989
【18】陳映辰, “以影像為基礎之電液伺服疲勞試驗機,” 國立台灣科技大學碩士學位論文, 2010
【19】左維雄, “DSP雙軸電液疲勞試驗機之應用與比較,” 國立台灣科技大學碩士學位論文, 2008

簡易檢索 / 詳目顯示

相關論文