研究生: |
洪春金 Chung-Kam Horng |
---|---|
論文名稱: |
可微小腦模型連結控制器在系統識別及控制之研究 The Study of System Identification and Control Using Differentiable CMAC |
指導教授: |
洪欽銘
Hong, Chin-Ming |
學位類別: |
碩士 Master |
系所名稱: |
工業教育學系 Department of Industrial Education |
論文出版年: | 1999 |
畢業學年度: | 87 |
語文別: | 中文 |
論文頁數: | 73 |
中文關鍵詞: | 高斯函數、系統識別、小腦模型連結控制器 |
英文關鍵詞: | Gaussian Function, System Identification, |
論文種類: | 學術論文 |
相關次數: | 點閱:171 下載:0 |
分享至: |
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 |
近年來小腦模型連結控制器已常被用在自我學習的控制運用上,其可視為一種基本函數類神經網路(Basis Function Neural Network),而傳統小腦模型連結控制器(Cerebellar Model Articulation Controller,CMAC)的輸出為一常數,與輸入之變數無直接關聯,因此無法獲得所對應於每一輸入量化狀態之輸出衍生訊息,本研究主要針對此缺點,輸出以高斯可微函數取代之,提出一個新的「可微小腦模型連結控制器」(Differential Cerebellar Model Articulation Controller,DCMAC)架構。本架構先以一個DCMAC正向系統識別受控體,藉以產生受控本體模擬器,然後結合另一個DCMAC作為系統的主控制器,當輸出有誤差發生時,模擬器會以倒傳遞的學習法則去修改主控制器之參數,直到達到最佳控制為止。本DCMAC控制架構於MATLAB軟體模擬後,確能以DCMAC倒傳遞學習法則達到系統識別目的,且能改善控制之性能。
The Cerebellar Model Articulation Controller(CMAC) is a neural network model, which is viewed as a Basis Function Network(BFN). The conventional CMAC uses constant basis function is replaced by Gaussian Basis Function(a differentiable function) for retrieving the derivative information and to improve the generalization ability of CMAC. Not only the weights but also the means and variances are adjusted during the learning process.
The new diferentiable CMAC network control system is established. The mathematical foundation for the new scheme is derived and the learning algorithm for control system is provided. After applying the new technique in some plant models, system identification and control performed to demonstrate the improvement of accuracy and the capability in providing derivative information.
英文部分
1. Albus, J. S., "A New Approach to Manipulator Control : The Cerebellar Model Articulation Controller(CMAC)," Journal of Dynamic System, and Control, Transaction of ASME , pp. 220-227,1975.
2. Albus, J. S., "Data Storage in the Cerebellar Model Articulation Controller (CMAC),"Journal of Dynamic Systems, Measurement, and Control, Transactions of ASME, pp.228-233, 1975.
3. Chun-Shin Lin; Ching-Tsan Chiang, "Learning convergence of CMAC technique," Neural Networks, IEEE Transactions on Volumn:86, Page(s): 1281-1292. Nov., 1997.
4. Commuri, S.; Lewis, F.L.; Jagannathan, S. "Discrete-time CMAC neural networks for control applications," Decision and Control, 1995, Proceeding of the 34th IEEE Conference on Volumn: 3,Page(s): 2420-2426 vol3., 1995.
5. Commuri, S.; Lewis, F.L.; "Control of unknow nonlinear dyynamical systems using CMAC neural networks: structure, stability, and passivity," Intelligent Control, 1995., Proceedings of the 1995 IEEE International Symposium on, , Page(s): 123-129.,1995.
6. Kraft, L.G.;Campagna, D.P. "Comparison of convergence properties of CMAC neural networks and traditional adaptive controllers, " Decision and Control, 1989., Proceedings oh the 28th IEEE Conference on Page(s): 1744-1745 vol.2,1989.
7. Mo-Yuen Chow; Menozzi, A. "A self-organized CMAC controller" Industrial Technology, 1994., Proceeding of the IEEE International Conference on, Page(s): 68-72.,1994.
8. Rummelhart, D. E.; Hinton, G. E.; Williams, R. j., "Learning Representations by Back-Propagation Errors," Nature 323, pp.533-536, 1986.
9. Seyedrasoul Saneifard and Howard A., "Fuzzy-Logic-Based SpeedControl of a Shunt DC Motor, "IEEE Transactions on Education, Vol. 41, no.2 pp.159-170, 1998.
10. Shu Yao and Bo Zhang, "The Learning Convergence of CMAC in Cyclic Learning," Proceedings of 1993 International Joint Conferenceon Neural Networks, pp.2582-2586,1993.
11. W. Thomas Miller , Filson H. Glanz and L. Gordon Kraft , "CMAC: An Associative Neural Network Alternative to Backpropagation ," Proceeding of the IEEE, Vol. 78, No.10, pp.1561-1567,1990.
12. Wong, Y. and Sideris, A., "Learning Convergence in the Cerebellar Model Articulation Controller, "IEEE Transactions on Neural Networks, Vol. 3, no.1, pp.115-121, 1992.
13. Zhou Fuzhang; Shi Weixiang, "CMAC neural network fuzzy control," Robot and Human Communication, 1997. RO-MAN'97. Proceeding., 6th IEEE International Workshop on, Page(s): 236-241, 1997.
中文部分
14. 王藏億,〞高性能直流馬達類神經控制器〞,國立中山大學機械工程研究所碩士論文,1995。
15. 李宜達,〞控制系統設計與模擬〞,全華科技圖書股份有限公司,1997。
16. 林宏欣,〞植基於遺傳演算法之模糊灰色預測控制器設計及應用",國立台灣師範大學工業教育研究所碩士論文,1997。
17. 秉昱科技編譯,〞模糊邏輯與類神經模糊〞,儒林圖書有限公司,pp.4-2~4-8,1996。
18. 柯玄能,〞小腦模式即時控制器於直流馬達之應用〞,國立中山大學機械工程研究所碩士論文,1995。
19. 陳文城,"植基於模糊推論之小腦模型控制器之研究",國立台灣師範大學工業教育研究所碩士論文,pp.8-19,1998。
20. 陳昱仁,〞機器人視覺追蹤之研究〞,國立中正大學電機工程研究所碩士論文,1996。
21. 黃泰林、何志宏,〞適應性號誌中類神經網路轉向比推估模式之建立〞,中華民國運輸學會第九屆學術論文研討會論文集,pp.411-418,1994。