臺灣博碩士論文加值系統

本論文目的在於利用類神經網路學習一階動態系統，用以控制一迴授系統。為了學習一階動態系統，提出兩種簡單的類神經網路架構，一種是一般的類神經網路，另一種加入了參數影響，而此參數是根據一階差分方程而來的。另外，本論文不用常見的倒傳遞學習法則，而用一演化策略，因為倒傳遞學習法則必須知道反向動態系統，但反向動態系統並不容易得到，而該演化策略並無此缺點。雖然使用該演化策略的學習時間較長，但類神經網路經過演化策略的學習後，能表現的跟目標系統極度相似，即使將此類神經網路放入一有外來雜訊的迴授系統當控制器時，亦能控制系統穩定不受雜訊影響。

Chinese Abstract i
English Abstract ii
Acknowledgement iii
Contents iv
List of Figures vi
List of Tables viii
Notation ix

Chapter 1 Introduction 1
Chapter 2 Intelligent Control 3
2.1 Introduction to Neural Network 3
2.2 Neural Network for Control 8
Chapter 3 Evolution Strategies 15
3.1 Modeling of First Order LTI System 15
3.2 Neural Network Structure 18
3.2.1 Structure for The First Order Difference Equation 18
3.2.2 General Structure 19
3.2.3 Structure with Sampling Time 21
3.3 Evolution Strategies 22
3.3.1 Initial Individuals Creation 24
3.3.2 Reproduction Process 25
3.3.3 Learning Process 28
3.3.4 Elite Process 30
3.3.5 Flow Chart 33
Chapter 4 Simulation Results 34
4.1 Influence of The Sampling Time 35
4.2 Influence of The Initial Weights Setting 49
4.3 Implement as a Controller 55
4.3.1 System with First Order LTI Plant 56
4.3.2 System with Second Order LTI Plant 58
Chapter 5 Conclusion 62
References 64

[1] L. A. Zadeh, "Knowledge representation in fuzzy logic," IEEE Transaction on Knowledge Data Engineering, vol. 1, pp. 89-100, 1989.
[2] D. E. Goldberg, Genetic Algorithms in Search Optimization and Machine Learning, Addison-Wesley, 1989.
[3] K. F. Man, K. S. Tang and S. Kwong, "Genetic algorithms: concepts and applications [in engineering design]," IEEE Transactions on Industrial Electronics, vol. 43, pp. 519-534, 1996.
[4] M. Mitchell, An Introduction to Genetic Algorithms, Cambridge, MA, USA: MIT Press, 1996.
[5] S. Haykin, Neural Networks. A Comprehensive Foundation, New York: Macmillan College Publishing, 1994.
[6] C. G. Looney, Pattern Recognition using Neural Networks: Theory and Algorithms for Engineers and Scientists, New York, NY, USA: Oxford University Press, Inc, 1997.
[7] A. Hiramatsu, "ATM communications network control by neural networks," IEEE Transactions on Neural Networks, vol. 1, pp. 122-130, 1990.
[8] W. T. Miller III, R. S. Sutton and P. J. Werbos, Neural Networks for Control, Cambridge, MA, USA: MIT Press, 1990.
[9] C. Breazeal, Sociable machines: Expressive social exchange between humans and robots, Ph.D. dissertation, Department Electrical Engineering and Computer Science Massachusetts Institute Technology, Cambridge, 2000.
[10] H. Mobahi, Building an Interactive Robot Face from Scratch, project report, Azad University, South of Tehran campus Tehran, Iran, May 2003
[11] T. Lee, Structure Level Adaptation for Artificial Neural Networks, Norwell, MA, USA: Kluwer Academic Publishers, 1991.

[12] P. A. Mastorocostas and J. B. Theocharis, "A stable learning algorithm for block-diagonal recurrent neural networks: application to the analysis of lung sounds," IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 36, pp. 242-254, 2006.
[13] S. J. Han and S. B. Cho, "Evolutionary neural networks for anomaly detection based on the behavior of a program," IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 36, pp. 559-570, 2006.
[14] C. Lin and C. S. G. Lee, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, Upper Saddle River, NJ, USA: Prentice-Hall, Inc, 1996.
[15] M. Gori and A. Tesi, "On the problem of local minima in backpropagation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, pp. 76-86, 1992.
[16] 林俊良，智慧型控制分析與設計，全華科技圖書股份有限公司，2005。
[17] G. Lightbody and G. W. Irwin, "Direct neural model reference adaptive control," IEE Proceedings of Control Theory and Applications, vol. 142, pp. 31-43, 1995.
[18] D. Nguyen and B. Widrow, "The truck backer-upper: an example of self-learning in neural networks," In Proceedings of the International Joint Conference on Neural Networks, Vol. 2, pp. 357-363, 1989.
[19] J. Zhang, S. S. Ge and T. H. Lee, "Output feedback control of a class of discrete MIMO nonlinear systems with triangular form inputs," IEEE Transactions on Neural Networks, vol. 16, pp. 1491-1503, 2005.
[20] R. J. Williams and D. Zipser, "A learning algorithm for continually running fully recurrent neural networks," Neural Computation, vol. 1, pp. 270-280, 1989.
[21] C. Chen, System and Signal Analysis, 2nd ed. Orlando, Florida, USA: Saunders College Publishing, 1994.
[22] C. Darwin, On the Origin of Species by Means of Natural Selection, London: John Murray, 1859.
[23] A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing (Natural Computing Series), Springer, 2003.