跳到主要內容

臺灣博碩士論文加值系統

(23.20.20.52) 您好!臺灣時間:2022/01/24 18:22
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:竇振誠
研究生(外文):Chen-Cheng Tou
論文名稱:CMAC類神經網路控制系統及CMAC晶片實現
論文名稱(外文):On the Design of the CMAC Neural Network Control System, and the Implementation of CMAC chip
指導教授:陳福川陳福川引用關係
指導教授(外文):Fu-Chuang Chen
學位類別:碩士
校院名稱:國立交通大學
系所名稱:電機與控制工程系
學門:工程學門
學類:電資工程學類
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:106
中文關鍵詞:CMAC類神經網路CMAC晶片
外文關鍵詞:CMAC neural networkCMAC chip
相關次數:
  • 被引用被引用:1
  • 點閱點閱:359
  • 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
本論文的目的主要可以分為系統分析以及硬體設計兩方面。在系統分析方面,本論文研究CMAC類神經網路控制系統的控制行為並分析系統的特性。這裡使用Runge-Kutta法來模擬受控系統的輸出/輸入特性。CMAC控制系統不需要關於機械臂的任何資訊,而且可以應付很大的負載變化。當輸入向量緩慢的移動的時候,CMAC控制器會產生龐大的積分動作。但是當輸入向量快速變化的時候,CMAC控制器也能有效的產生“遺忘”效應。論文中也證明CMAC控制系統能夠在目標位置收斂。在硬體設計方面,本論文規劃了CMAC類神經網路控制晶片的架構以及用硬體描述語言VHDL做更進一步的實現。在架構設計上,包括引用權重直接定址方式以心縮式陣列(Systolic Array)的結構來實現CMAC類神經網路中的映射關係,以及使用線性回饋暫存器(Linear Feedback Shift Register)所具備產生偽亂數的功能來簡化並完成雜湊編碼所能達到的目標等。最後,本論文提供此CMAC類神經網路控制晶片平行處理的解決方案,藉以增加晶片內部單元平行處理的套數並做適當的排程來大幅提升不同應用所可能需求的更高處理速度。
There are two main objective of this paper, system analysis and hardware design. In the aspect of system analysis, the behavior of the CMAC control system has been studied and stability of the system has been analyzed in this thesis. The Runge-Kutta method is adapted to find out the characteristic between output and input of plant. However, the CMAC requires no information about the robot, and can deal with large variations in load. The CMAC produces enormous integration action when the input vector moves slowly in the space, but it can also forget efficiently when the input vector moves fast in the space. It is shown that the CMAC control system can converge into the target position. In the aspect of hardware design, on the architecture design and further implementation in Hardware Description Language VHDL have been focused in this thesis. On architecture design, the systolic array structure in the proposed Direct Weight Address Mapping method is adapted to implement the mapping relationship in the CMAC neural network. And the hash coding function is simplified and achieved by generating pseudo-random function in the Linear Feedback Shift Register. At last but not least, the solution of parallel processing in the CMAC neural network chip is provided, for higher processing speed in accordance to different application.
目錄
中文摘要 ………………………………………………………………………… i
英文摘要 ………………………………………………………………………… ii
誌謝 …………………………………………………………… iii
目錄 ………………………………………………………………………… iv
表目錄 …………………………………………………………………… vi
圖目錄 ……………………………………………………………………… vii
第一章 緒論…………………………………………………………………… 1
1.1 研究動機、背景與目的…………………………………………… 1
1.2 論文內容介紹…………………………………………………… 4
第二章 控制對象及PD控制結果…………………………………………… 7
2.1 四階Runge-Kutta法求解常微分方程式………………………… 7
2.2 單軸機械臂……………………………………………………… 9
2.2.1 PID控制結果…………………………………………… 11
第三章 CMAC控制器及其控制模擬結果……………………………… 15
3.1 CMAC控制系統………………………………………………… 15
3.2 CMAC之計算架構……………………………………………… 16
3.3 CMAC工作原理………………………………………………… 21
3.4 記憶體配置及存取……………………………………………… 23
3.5 CMAC控制系統的特點……………………………………… 25
3.6 CMAC控制系統模擬結果…………………………………… 26
3.7 CMAC控制系統模擬結果分析……………………………… 27
3.8 CMAC控制系統Tracking控制結果.……………………… 39
第四章 CMAC控制晶片的理論規劃與架構設計…………………………… 43
4.1 CMAC類神經網路控制晶片的設計考量……………… 43
4.2 權重位址映射單元的位址映射架構……………………… 46
4.3 雜湊編碼處理單元的偽亂數產生機制…………………… 56
4.4 權重擷取單元的常數乘法結構……………………… 61
第五章 CMAC類神經網路控制晶片的實現………………………… 64
5.1 CMAC控制系統硬體架構……………………………………… 64
5.1.1 CMAC類神經網路控制晶片參數選取………………… 64
5.1.2 CMAC控制系統電路板之設計………………………… 65
5.2 CMAC 類神經網路控制晶片內部元件設計…………………… 71
5.2.1 前置處理單元 (Pre-processing block)……………… 71
5.2.2 量化執行單元 (Quantization block)…………………… 77
5.2.3 權重位置映射單元 (Weight address mapping block)…… 79
5.2.4雜湊編碼處理單元 (Hash coding processing block)…… 84
5.2.5 權重擷取單元 (Weight retrieving block)………………… 86
5.2.6嵌入式記憶體 (Embedded Memory)………………… 90
5.3 CMAC類神經網路晶片平行度的設計考量………………… 94
5.4 CMAC類神經網路晶片的實作結果…………………………… 98
第六章 結論與未來展望………………………………………………… 101
參考文獻……………………………………………………………………… 102
[1] J. S. Albus, “A New Approach in the Cerebellar Model Articulation Controller (CMAC),” Journal of Dynamic Systems, Measurement and Control, pp. 220-227, Sep. 1975 .
[2] J. S. Albus, “Data Storage in The Cerebellar Model Articulation Controller”, Journal of Dynamic Systems, Measurement and Control, pp. 228-233, Sept. 1975
[3] Martin.C., “ http://ai.iit.nrc.ca\~martin\talks\bio_learning_control\, “, 1998
[4] 歐陽楷, 陳卉, 周萍, 周琛, “神經計算中座標變換的網路模型(CMAC)的泛化特性”, 自動化學報, ACTA AUTOMATICA SINICA ,1997年 第23卷 第4期 Vol.23 No.4 1997
[5] W. T. Miller, “A nonlinear learning controller for robotic manipulators,” in Proc. SPIE, Intell. Robots and Computer Vision, vol. 726, pp. 416—423, Oct. 1986.
[6] W.T. Miller, F.H. Glanz and L.G. Kraft, “Application of a General Learning Algorithm to the Control of Robotic Manipulators,” International Journal of Robotic Research, Vol. 6, No. 2, pp. 84-98, 1987
[7] W.T. Miller, R.H. Hewes, F.H. Glanz and L.G. Kraft, “Real-Time Dynamic Control of an Industrial Manipulator using Neural-Network-Based Learning Controllers,” IEEE Transactions on Robotics and Automation, pp. 1-9, Feb. 1990
[8] 段培永, 邵惠鶴, “CMAC(小腦模型)神經計算與神經控制”,資訊與控制, INFORMATION AND CONTROL, 1999年 第28卷 第3期 Vol.28 No.3 1999
[9] F.-C. Chen and C.-C. Liu, “Adaptive Control of Nonlinear Continuous-Time Systems using Neural Networks,” IEEE Transactions on Automatic Control, pp. 1306-1310, June 1994.
[10] F.-C. Chen and H.K. Khalil, “Adaptive Control of a Class of Nonlinear Discrete-Time Systems using Neural Network,” IEEE Transactions on Automatic Control, pp. 791-801, May 1995.
[11] F.L. Lewis, A. Yesildirek, and K. Liu, “Multilayer Neural-Net Robot Controller with Guaranteed Tracking Performance,” IEEE Transactions on Neural Networks, pp. 1-11, Mar. 1996.
[12] G.A. Larsen, S. Cetinkunt and A. Donmez, “CMAC Neural Network Control for High Precision Motion Control in the Presence of Large Friction,” ASME Journal of Dynamics Systems, Measurement and Control, pp. 415-420, Sep. 1995.
[13] H. Shiraishi, S.L. Ipri and D. Cho, “CMAC Neural-Network Controller for Fuel-Injection Systems,” IEEE Transaction on Control Systems Technology, Vol. 3, pp. 32 — 38, 1995
[14] F.-C. Chen and C.-H. Chang, “Practical Stability Issues in CMAC Neural Network Control Systems,” IEEE Transactions on Control Systems Technology, pp. 86-91, January 1996.
[15] C.-C. Lin and F.-C. Chen, “An Improved CMAC Neural Network Control Scheme,” IEE Electronics Letters, Vol. 35, No. 2, pp. 157-158, Jan. 1999.
[16] S. Nakamura, “Applied Numerical Methods with Software,” Prentice-Hall international editions, pp. 299-308, 1991.
[17] L.G. Kraft and D.P. Campagna, “A Comparison Between CMAC Neural Network Control and Two Traditional Adaptive Control Systems,” American Control Conference, Pittsburgh, Pennsylvania, June 21-23, 1989.
[18] B.C. Kuo, “Automatic Control System,” Prentice-Hall, Sixth Edition, pp.400-401, 1991.
[19] D. Ellison, “On The Convergence of the Multidimensional Albus Perceptron,” The International Journal of Robotics Research, Vol. 10, No. 4, pp. 338-357, August 1991.
.
[20] Jar-Shone Ker; Yau-Hwang Kuo; Rong-Chang Wen; Bin-Da Liu, “Hardware implementation of CMAC neural network with reduced storage requirement”, IEEE Transactions on Neural Networks,, Volume: 8 Issue: 6 , Nov. 1997
Page(s): 1545 -1556.
[21] Ker, J.-S.; Kuo, Y.-H.; Liu, B.-D., “Systolic implementation of higher-order CMAC and its application in colour calibration”, Circuits, Devices and Systems, IEE Proceedings- , Volume: 144 Issue: 3 , June 1997 Page(s): 129 -137
[22] Jar-Shone Ker, “Hardware design of the CMAC-based neural network and its application on color reproduction systems”, PhD thesis, 1995.
[23] J.-S.Ker ,R.-C.Wen Y.-H.Kuo, B.-D.Liu, “Enhancement Of The Weight Cell Utilization For Cmac Neural Networks: Architecture Design And Hardware Implementation” Microelectronics for Neural Networks and Fuzzy Systems, Proceedings of the Fourth International Conference, 1994.
[24] Clark S. Lindsey, “Neural Networks in Hardware : Architectures, Products and Applications”, http://www.particle.kth.se/~lindsey
[25] W.S.Mischo ,”A CMAC-Type Neural Memory for Control Applications” -, Proceedings of Fifth International Conference on Microelectronics for Neural Networks, 1996.
[26] Rakesh J.Patel , Bhavesh N.Patel, Hemnag P.Trivedi “Parallel processing : an overview” IEEE Potentials,1990
[27] S.Y.Kung ,J.N.Hwang “Parallel architecture for artificial neural network” ., IEEE International Conference on neural network ,1988
[28] S.Y.Kung ,J.N.Hwang, ”Systolic architecture for artificial neural nets”. IEEE Journal of Robotics and Automation, special issue on Computational Algorithm and Architectures in Robotics and Automation, 1988.
[29] Sun-Yuan Kung, “On Supercomputing with Systolic/ Wavefront Array Processors,” Proceedings of the IEEE, July 1984.
[30] Chang, L.-W.; Lin, J.-H., A bit-level systolic array for median filter, Signal Processing, IEEE Transactions on , Volume: 40 Issue: 8 , Aug. 1992, Page(s): 2079 -2083
[31] S.Y.Kung , VLSI Array Processors, Pretence-Hall International, Inc 1988
[32] Keshab K. Parhi, VLSI Digital Signal Processing System — Design and Implementation, John Wiley & Sons, Inc. 1999
[33] Henry C. Jen, Zhuang Tian, Russell L. Smith, George G. Coghill , “Hardware Implementation of a CMAC Neural Network Using PLDs” , System Sciences,
[34] Zi-Qin Wang, J.L.Schiano, M.Ginsberg, “Hash-coding in CMAC neural networks”, IEEE International Conference on Neural Networks, 1996.
[35] Russell L. Smith, “Intelligent Motion Control with an Artificial Cerebellum”, Ph.D. thesis, the department of Electrical and Electronic Engineering at the University of Auckland, New Zealand.
[36] http://homepage.mac.com/afj/lfsr.html
[37] http://www.chipcenter.com/circuitcellar/august99/c89r4.htm
[38] Behrooz Parhami , “Computer arithmetic” Oxford University Press, 2000
[39] Douglas J Smith, “HDL Chip Design”, Doone Publication, 1996
[40] Texas Instruments, “TMS320C240 User’s Guide”, 1994
[41] Vijay K. Madisetti , “Digital Signal Processors: An Introduction to Rapid Prototyping and Design Synthesis” IEEE Press, 1995
[42] Angilent Corp., “HCTL-2016 datasheet”
[43] Analog Devices Inc. , “AD7541A datasheet”
[44] Chung-Yu Wu, “ Embedded memory “, Excepted from “The VLSI handbook”. CRC Press 2000
[45] K.C. Chang, “Digital systems design with VHDL and synthesis — an integrated approach” IEEE computer society 1999
[46] X.Benavent, J.Domingo, F.Vegara, J.Pelechano, “Two suggestions for efficient implementation of CMAC''S”, International Symposium on Intelligent Control, 2000. Proceedings of the 2000 IEEE
[47] 何智南, “以FPGA實現CMAC類神經網路控制器”, 國立交通大學控制工程研究所碩士論文, 1997
[48] 林桓宇, “以CMAC類神經網路控制器實現機器人控制“, 國立交通大學電機與控制工程研究所碩士論文, 2000
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top