臺灣博碩士論文加值系統

本論文提出小腦模型與回歸型小腦模型控制器於失效診斷調節控制，並分別用在蓄水池系統及引擎系統。本文利用小腦模型網路當成即時近似器以偵測系統失效。首先本文提出一種具有穩定特性及良好的失效調節系統設計，用於兩個不同的引擎系統及一個蓄水池系統，模擬結果顯示本系統可以達成良好的失效調節回復能力。然後再利用回歸型的小腦模型控制器，用於同樣之引擎系統，從模擬結果顯示失效系統的回復性能可以進一步改善。

This thesis presents the fault accommodation using Cerebellar-Model Articulation Controller and recurrent Cerebellar-Model Articulation Controller. These controllers are applied to a three-tank system and two engine systems to illustrate their effectiveness. First, a learning architecture, with CMAC network as on-line approximator of the off-nominal system behavior, is used for the accommodation control of two engine systems and a three-tank system. Simulation results show that this method can effectively achieve the fault accommodation. Furthermore, a robust fault accommodation scheme used recurrent Cerebellar-Model Articulation Controller approach, is used for two engine system faults. Simulation results show that the fault accommodation performance can be further improved.

摘要 i
Abstract ii
誌謝 iii
Contents iv
List of Tables and Figures vi
Chapter1 Introduction
1.1 General Remark and Overview of Previous Work 1
1.2 Organization of This Thesis 2
Chapter2 Cerebellar Model Articulation Controller (CMAC)
2.1 Overview 4
2.2 The Cerebellar Cortex
2.3 Original Cerebellar Model Articulation Controller 6
2.4 General Cerebellar Model Articulation Controller 9
Chapter3 Fault Accommodation for Nonlinear Systems Using Cerebellar-Model Articulation Controller
3.1 Overview 18
3.2 Problem Formulation 19
3.3 Fault Accommodation Using CMAC Network Approach 20
3.3.1 CMAC Network 21
3.3.2 Fault Accommodation Analysis 23
3.4 Simulation Results 26
3.4.1 A Jet Engine Compression System 27
3.4.2 A Four Cylinder Spark Ignition Engine System 28
3.4.3 A Three Tank System 30
3.5 Summary 32
Chapter4 Fault Accommodation for Nonlinear Systems Using Recurrent Cerebellar-Model Articulation Controller
4.1 Overview 43
4.2 Fault Accommodation Using Recurrent CMAC Approach 45
4.2.1 Implementation of Recurrent CMAC
4.2.2 Fault Accommodation Analysis 48
4.3 Simulation Results 50
4.3.1 A Jet Engine Compression System
4.3.2 A Four Cylinder Spark Ignition Engine System 51
4.4 Summary
Chapter5 Conclusions and Suggestions for Future Reasearch
5.1 Conclutions 55
5.2 Suggestions for Future Research
Reference 57
Autobiography 63

[1] K. S. Narendra and K. Parthasarathy, “Identification and control of dynamical systems using neural networks,” IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 4-27, 1990.
[2] R. M. Sanner and J. J. E. Slotine, “Gaussian networks for direct adaptive control,” IEEE Trans. Neural Networks, vol. 3, no. 6, pp. 837-863, 1992.
[3] A. Agarwal, “A systematic classification of neural-network-based control,” IEEE Control Systems Magazine, vol. 17, pp. 75-93, 1997.
[4] K. J. Hunt, D. Sbarbaro, R. Zbikowski, and P. J. Gawthrop, “Neural networks for control systems-A survey,” Automatic, vol. 28, pp. 1083-1112, 1992.
[5] F. L. Lewis, A. Yesildirek, and K. Liu, “Multilayer neural-net robot controller with guaranteed tracking performance,” IEEE Trans. Neural Networks, vol. 7, no. 2, pp. 388-399, 1996.
[6] K. Nam, “Stabilization of feedback linearizable systems using radial basis function network,” IEEE Trans. Automatic Control, vol. 44, no. 5, pp. 1026-1031, 1999.
[7] S. S. Ge, C. C. Hang, and T. Zhang, “Adaptive neural network control of nonlinear systems by state and output feedback,” IEEE Trans. Systems, Man, and Cybernetics- Part B: Cybernetics, vol. 29, no. 6, pp. 818-828, 1999.
[8] J. R. Noriega and H. Wang, “A direct adaptive neural-network control for unknown nonlinear systems and its application,” IEEE Trans. Neural Networks, vol. 9, no. 1, pp. 27-34, 1998.
[9] M. Zhihong, H. R. Wu, and M. Palaniswami, “An adaptive tracking controller using neural networks for a class of nonlinear systems,” IEEE Trans. Neural Networks, vol. 9, no. 5, pp. 947-1031, 1998.
[10] B. M. McFarland and A. J. Calise, “Neural networks and adaptive nonlinear
control of agile antiair missiles,” J. Guidance, Control, Dynamics, vol. 23, no. 3, pp. 547-553, 2000.
[11] M. A. Mayosky and G. I. E. Cancelo, “Direct adaptive control of wind energy conversion system using Gaussian network,” IEEE Trans. Neural Networks, vol. 10, no. 4, pp. 898-906, 1999.
[12] C. M. Lin and C. F. Hsu, “Neural-network-based adaptive control for induction servomotor drive system,” IEEE Trans. Industrial Electronics, vol. 49, no. 1, pp. 115-123, 2002.
[13] C. C. Ku and K. Y. Lee, “Diagonal recurrent neural networks for dynamic systems control,” IEEE Trans. Neural Networks, vol. 6, no. 1, pp. 144-156, 1995.
[14] F. J. Lin, R. J. Wai, and C. M. Hong, “Recurrent neural network control for LCC-resonant ultrasonic motor drive,” IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control, vol. 47, no. 3, pp. 737-749, 2000.
[15] T. W. S. Chow and Y. Fang, “A recurrent neural-network-based real-time learning control strategy applying to nonlinear systems with unknown dynamics,” IEEE Trans. Industrial Electronics, vol. 45, no. 1, pp. 151-161, 1998.
[16] C. Gan and K. Danai, “Model-based recurrent neural network for modeling nonlinear dynamic systems,” IEEE Trans. Systems, Man, and Cybernetics- Part B: Cybernetics, vol. 30, no. 2, pp. 344-351, 2000.
[17] Y. Fang, T. W. S. Chow, and X. D. Li, “Use of a recurrent neural network in discrete sliding-mode control,” IEE Proc., Control Theory & Applications, vol. 146, no. 1, pp. 84-90, 1999.
[18] F. J. Lin and R. J. Wai, “Hybrid control using recurrent fuzzy neural network for linear induction motor servo drive,” IEEE Trans. Fuzzy Systems, vol. 9, no. 1, pp. 102-115, 2001.
[19].M. M. Polycarpou and A. J. Helmicki, “Automated fault detection and accommodation : a learning systems approach,” IEEE Trans. Systems, Man and Cybernetics, vol. 25, no. 11, pp. 1447-1458, 1995.
[20] A. T. Vemuri and M. M. Polycarpou, “On-line approximation-based method for
robust fault detection,” The 13th IFAC World Congress, pp. 319-324, 1996.
[21] A. Vemuri and M. Polycarpou, “Robust nonlinear fault diagnosis in input-output
systems,” The American Control Conference, pp. 927-931, June 1997.
[22].M. M. Polycarpou and P. A. Ioannou, “On the existence and uniqueness of solutions in adaptive control systems,” IEEE Trans. on Automatic Control, vol. 38, no. 3, pp. 474-479, 1993.
[23].R. J. Patton, P. M. Frank, and R. N. Clark, Eds., Fault Diagnosis in Dynamic Systems, Englewood Cliffs, NJ: Prentice-Hall, 1989.
[24].M. M. Polycarpou and A. B. Trunov, “Learning approach to nonlinear fault diagnosis: detectability analysis,” IEEE Trans. on Automatic Control, vol. 45, no. 4, pp. 806-812, 2000.
[25].J. Farrell, T. Berger and B. D. Appleby, “Using learning techniques to accommodate unanticipated faults,” IEEE Control Systems Magazine, vol. 13, no. 3, pp. 40-49, 1993.
[26].H. Wang, Z. J. Huang, and S. Daley, “On the use of adaptive updating rules for actuator and sensor fault diagnosis,” Automatic, vol. 33, pp. 217-225, 1997
[27].J. S. Albus, “A new approach to manipulator control: The cerebellar model articulation controller (CMAC),” J. Dynamic system, Measurement, control, vol. 97, pp. 220-227, 1975.
[28].S. H. Lane, D. A. Handelman, and J. J. Gelfand, “Theory and development of higher-order CMAC neural networks,” IEEE Control Systems Magazine, vol. 28, no. 2, pp. 680-692, 1998.
[29] K. S. Hwang and C. S. Lin, “Smooth trajectory tracking of three-link robot: a self-organizing CMAC approach,” IEEE Trans. Systems, Man and Cybernetics, Part B, vol. 28, no. 5, pp. 680-692, 1998.
[30] A. L. Kun, and W. T. Miller, “Control of variable speed gaits for a biped robot,” IEEE Robotics & Automation Magazine, vol. 6, no. 3, pp. 19-29, 1999.
[31].H. Shiraishi, S.L. Ipri, and D. D. Cho, “CMAC neural network controller for fule-injection systems,” IEEE Trans. Control System Technology, vol. 3, no. 1, pp. 32-38, 1995.
[32] F. J. Gonzalez-Serrano, A. R. Figueiras-Vidal, and A. Artes-Rodriguez, “Generalizing CMAC architecture and training,” IEEE Trans. Neural Networks, vol. 9, no. 6, pp. 1509-1514, 1998.
[33] J. C. Jan and S. L. Hung, “High-order MS_CMAC neural network,” IEEE Trans. Neural Networks, vol. 12, no. 3, pp. 598-603, 2001.
[34] C. T. Chiang and C. S. Lin, “CMAC with general basis functions,” Neural Networks, vol. 9, no. 1, pp. 1199-1211, 1996.
[35] D. Marr, “A theory of cerebellar cortex,” J. Physiological, vol. 202, pp. 437-470, 1969.
[36] J. S. Albus, “A theory of cerebellar function,” Mathematical Biosciences, vol. 10, pp. 25-61, 1971.
[37] D. J. Linden, “Cerebellar long-term depression as investigated in a cell culture preparation,” Behavioral and Brain Sciences, vol. 19, pp. 339-346, 1996.
[38] P. Chauvet and G. A. Chauvet, “Mathematical conditions for adaptive control in Marr’s model of the sensorimotor system,” Neural Networks, vol. 8, pp. 693-706, 1995.
[39] M. Ito, The Cerebellum and Neural Control. Raven Press, New York, 1984.
[40] D. O. Hebb, The Organization of Behavior: A Neuropsychological Theory. New York: Wiley, 1949.
[41] M. Ito, “Mechanisms of motor learning in the cerebellum,” Brain Research Interactive, vol. 886, pp. 237-245, 2000.
[42] Y. H. Kim and F. L. Lewis, “Optimal design of CMAC neural-network controller for robot manipulators,” IEEE Trans. Systems, Man and Cybernetics, Part C, vol. 30, no. 1, pp. 22-31, 2000.
[43] S. Jagannathan, “Discrete-time CMAC NN control of feedback linearizable nonlinear systems under a persistence of excitation,” IEEE Trans. Neural Networks, vol. 10, no. 1, pp. 128-137, 1999.
[44].J. J. Gertler, “Survey of model-based failure detection and isolation in complex
plants,” IEEE Control Systems Magazine, vol. 8, no. 455, pp. 3-11, 1988.
[45] M. M. Polycarpou, “Fault accommodation of a class of multivariable nonlinear dynamical systems using a learning approach,” IEEE Trans. Automatic Control, vol. 46, no. 5, pp. 736-742, 2001.
[46] G. G. Yen and L. Ho, “Reconfigurable control system design for fault diagnosis and accommodation,” International Journal of Neural Systems, vol. 12, no. 6, pp. 497-520, 2002.
[47] G. G. Yen and L. Ho, “On-line multiple-model based fault diagnosis and accommodation,” IEEE Trans. Industrial Electronics, vol. 50, no. 2, pp. 296-312, 2003.
[48].H. K. Khalil, Nonlinear Systems, Englewood Cliffs, NJ: Prentice Hall, vol. 2, 1996.
[49] G. G. Yen and L. Ho, “Fault tolerant control: An intelligent sliding mode control strategy,” The American Control Conference, pp. 4204-4208, 2000.
[50].X. Zhang, M. M. Polycarpou, and T. Parisini,” Abrupt and incipient fault isolation of nonlinear uncertainty systems,” The American Control Conference, pp. 3713-3717, 2000.
[51].L. X. Wang, Adaptive Fuzzy Systems and Control: Design and Stability Analysis.
Englewood Cliffs, NJ: Prentice-Hall, 1994.
[52].C. F. Chang, N. P. Fekete, A. Amstutz, amd J. D. Powell, “Air-fuel control in
spark-ignition engines using estimation theory,” IEEE Trans. Control Systems
Technology, vol. 3, no. 1, pp. 22-31, 1995.
[53] A. T. Vemuri, “Sensor bias fault diagnosis in a class of nonlinear system,” IEEE
Trans. Automatic Control, vol. 46, no. 6, pp. 949-954, 2001.
[54] Y. Li, N. Sundararajan, and P. Saratchandram, “Stable neuro-flight-controller
using fully tuned radial basis function neural networks,” J. Guidance, Control,
Dynamics, vol. 24, no. 4, pp. 665-674, 2001.
[55] C. H. Lin, W. D. Chou, and F. J. Lin, “Adaptive hybrid control using recurrent-neural-network for linear synchronous motor servo drives,” IEE Proc., Control Theory & Applications, vol. 148, no. 2, pp. 156-168, 2001.
[56] H. Tolle and E. Ersu, Neurocontrol-learning control systems inspired by neural
architectures and human problem solving strategies, Berlin, Germany: Springer-
Verlag, 1992.
[57] M. Brown, C. J. Harris, and P. C. Parks, “The interpolation capabilities of the binary CMAC,” Neural Networks, vol. 6, pp. 429-440, 1993.
[58] R. J. Wai, C. M. Lin, and Y. F. Peng, “Robust CMAC neural network control for LLCC-resonant driving linear piezoelectric ceramic motor,” IEE Proc., Control Theory & Applications, vol. 150, no. 3, pp. 221-232, 2003.