臺灣博碩士論文加值系統

本論文旨在使用線性矩陣不等式與混合田口基因演算法(hybrid Taguchi-genetic algorithm, HTGA)來探討時延Takagi-Sugeno(T-S)模糊遞迴類神經網路系統之控制。研究主題包括一系列不確定性時延T-S模糊遞迴類神經網路之穩定化控制器設計、耗散性及狀態估測器設計，其中假設參數的不確定性為有界且時延為時變區間延遲。在穩定化分析方面，藉由Lyapunov-Krasovskii泛函及結合線性矩陣不等式法，可求得時延相關的充分條件，以保證閉迴路時延模糊遞迴類神經網路之整體指數強健穩定度。耗散性分析為針對時延模糊遞迴類神經網路系統，經由Lyapunov-Krasovskii泛函與結合線性矩陣不等式法，求得時延相關充分條件，以保證強健耗散性之穩定性。至於，狀態估測器設計，則提出一種創新整合技巧以改善推導過程的複雜性，利用Lyapunov-Krasovskii泛函與線性矩陣不等式法求得充分條件，並且使用混合田口基因演算法，以獲得狀態估測增益值，並滿足Lyapunov-Krasovskii泛函之穩定性不等式，以保證充分條件之穩定。最後，在本論文中，將以多個例題來說明所提方法之有效性與可應用性。

A complete study of the control of time-delay Takagi-Sugeno fuzzy recurrent neural networks via the linear matrix inequality (LMI) approach and hybrid Taguchi-genetic algorithm (HTGA) is proposed in this dissertation. This includes the developments of the stabilization control design/passivity analysis/state estimator design for a class of time-delay Takagi-Sugeno (T-S) fuzzy uncertain recurrent neural networks, where the parameters uncertainties are assumed to be norm-bounded and time delays are interval time-varying delays. For the stabilization analysis, based on Lyapunov-Krasovskii functional approach and linear matrix inequality (LMI) technique, delay-dependent sufficient conditions are derived to guarantee the globally robustly exponential stability for the closed-loop time-delay T-S fuzzy recurrent neural networks. For the passivity analysis, the delay-dependent sufficient conditions are obtained by using Lyapunov-Krasovskii functional approach and linear matrix inequality (LMI) technique guarantees this stability of robust passivity for time-delay T-S fuzzy recurrent neural networks. Also, for state estimator design, we develop a new integrative technique to reduced remarkably and facilitate the design task of the estimator for computational complexity, a new hybrid Taguchi-genetic algorithm (HTGA) method is integrated with a linear matrix inequality (LMI) method to seek the estimator gains that satisfy the Lyapunov-Krasovskii functional stability inequalities. Finally, some illustrative examples are presented to demonstrate the effectiveness and applicability of our methodologies.

中文摘要 i
Abstract ii
Acknowledgement iii
Contents iv
List of Tables vi
List of Figures vii
Chapter 1 Introduction 1
1.1 Time-Delay Systems 1
1.2 Delay-Independent/Delay-Dependent Conditions 4
1.3 Takagi-Sugeno (T-S) Fuzzy Model 5
1.4 Linear Matrix Inequality (LMI) 8
1.5 Recurrent Neural Networks 14
1.6 Hybrid Taguchi-Genetic Algorithm (HTGA) 16
1.7 Contributions of the Dissertation 20
1.8 Brief Sketch of the Contents 21
Chapter 2 Robust Stabilization for T-S Fuzzy Neural Network with Time Delays 22
2.1 Introduction 23
2.2 Model Description and Preliminaries 26
2.3 Main Results 31
2.4 Illustrative Examples 41
2.5 Summary 47
Chapter 3 Passivity Analysis for T-S Fuzzy Neural Network with Time Delays 48
3.1 Introduction 49
3.2 Model Description and Preliminaries 52
3.3 Main Results 56
3.4 Illustrative Examples 66
3.5 Summary 73
Chapter 4 State Estimator for T-S Fuzzy Neural Network with Time Delays 74
4.1 Introduction 75
4.2 Model Description and Preliminaries 78
4.3 Main Results 82
4.4 Illustrative Examples 93
4.5 Summary 104
Chapter 5 Conclusions and Future Research 105
5.1 Conclusions 105
5.2 Future Research Directions 107
References 108
Biography 119
Publication List 120

[1]Ahn, C. K., “Delay-dependent state estimation for T-S fuzzy delayed Hopfield neural networks, Nonlinear Dynam, vol. 61, pp. 483-489, 2010.
[2]Ali, M. S. and Balasubramaniam, P., “Global exponential stability of uncertain fuzzy BAM neural networks with time-varying delays, Chaos, Solitons and Fractals, vol. 42, pp. 2191-2199, 2009.
[3]Anderson, B. D. O. and Vongpanitlerd, S., Network Analysis Synthesis-A Modern Systems Theorem Approach, Englewood Cliffs, NJ: Prentice Hall, 1973.
[4]Balasubramaniam, P. and Ali, M. S., “Robust exponential stability of uncertain fuzzy Cohen-Grossberg neural networks with time-varying delays, Fuzzy Sets and Systems, vol. 161, pp. 608-618, 2010.
[5]Balasubramaniam, P., Vembarasan, V., and Rakkiyappan, R., “Delay-dependent robust asymptotic state estimation of Takagi–Sugeno fuzzy Hopfield neural networks with mixed interval time-varying delays, Expert Systems with Applications, vol. 39(1), pp. 472-481, 2011.
[6]Baldi, P. and Atiya, A. F., “How delays affect neural dynamics and learning, IEEE Trans. Neural Networks, vol. 5(4), pp. 612-621, 1994.
[7]Boukas, E. K. and Liu, Z. K., Deterministic and Stochastic Time Delay System, Birkhauser, Boston, 2002.
[8]Boyd, S., Ghaoui, L. E., Feron, E., and Balakrishnan, V., Linear Matrix Inequalities in System and Control Theory, Philadelphia, PA: SIAM, 1994.
[9]Calcev, G., Gorez, R., and Neyer, M. De., “Passivity approach to fuzzy control systems, Automatica, vol. 34, pp. 339-344, 1998.
[10]Cao, J. and Wang, J., “Global asymptotic stability of a general class of recurrent neural networks with time-varying delays, IEEE Transactions on Circuits and Systems I, vol. 50(1), pp. 34-44, 2003.
[11]Cao, J., Yuan, K., and Li, H. X., “Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays, IEEE Transactions on Neural Networks, vol. 17, pp. 1646-1651, 2006.
[12]Cao, Y. Y. and Frank, P. M., “Analysis and synthesis of nonlinear time-delay systems via fuzzy control approach, IEEE Transactions on Fuzzy Systems, vol. 8, pp. 200-211, 2000.
[13]Cao, Y. Y. and Frank, P. M., “Stability analysis and synthesis of nonlinear time-delay systems via linear Takagi-Sugeno fuzzy models, IEEE Transactions on Fuzzy Systems, vol. 124, pp. 213-229, 2001.
[14]Chen, B., Li, H., Lin, C., and Zhou, Q., “Passivity analysis for uncertain neural networks with discrete and distributed time-varying delays, Physics Letters A, vol. 373, pp. 1242-1248, 2009.
[15]Chen, D. and Zhamg, R., “Passivity analysis for fuzzy stochastic neural works with uncertainty and time varying delays, 2008 2nd International Symposium on Intelligent Information Technology Application, vol. 2, pp. 669-672, 2008.
[16]Chen, J. and Chaudhari, N. S., “Segmented-memory recurrent neural networks, IEEE Transactions on Neural Networks, vol. 20(8), pp. 1267-1280, 2009.
[17]Chen, S., Zhang, Q., and Wang, C., “Existence and stability of equilibria of the continuous-time Hopfield neural network, Journal of Computational and Applied Mathematics, vol. 169, pp. 117-125, 2004.
[18]Chou, J. H., Liao, W. H., and Li, J. J., “Application of Taguchi-genetic method to design optimal grey-fuzzy controller of a constant turing force systems, in Proc. 15th CSME Annu. Conf., Tainan, Taiwan, R.O.C., pp. 31-38, 1998.
[19]Cohen, M. and Grossberg, S., “Absolute stability of global pattern formation and parallel memory storage by competitive neural networks, IEEE Transactions on Systems, Man and Cybernetics, vol. 13(5), pp. 815-826, 1983.
[20]Draye, J. P., Pavisic, D., Cheron, G., and Libert, G., “Dynamic recurrent neural networks: a dynamical analysis, IEEE Transactions on Systems Man, and Cybernetics, vol. 26(5), pp. 692-706, 1996.
[21]Forti, M. and Tesi, A., “New conditions for global stability neural networks with application to linear and quadratic programming problems, IEEE Transactions on Circuits and Systems I, vol. 42, pp. 354-365, 1995.
[22]Fridman, E. and Shaked, U., “On delay-dependent passivity, IEEE Transaction on Automatic Control, vol. 47, pp. 664-669, 2002.
[23]Fu, J., Zhang, H., Ma, T., and Zhang, Q., “On passivity analysis for stochastic neural networks with interval time-varying delay, Neurocomputing, vol. 73, pp. 795-801, 2010.
[24]Gahinet, P., Nemirovski, A., Laub, A. J., and Chilai, M., LMI Control Toolbox, The Math Works, Inc., Boston, 1995.
[25]Gen, M. and Cheng, R., Genetic Algorithms and Engineering Design, New York: Wiley, 1997
[26]Gorecki, H., Fuksa, S., Grabowski, P., and Korytowski, A., Analysis and Synthesis of Time Delay System, John Wiley and Sons, Warszawa, 1989.
[27]Hahnloser, R. L. T., “On the piecewise analysis of linear threshold neural networks, Neural Networks, vol. 11(4), pp. 691-697, 1998.
[28]Haykin, S., Neural Networks: A Comprehensive Foundation, Englewood Cliffs, NJ: Prentice-Hall, Bergen, 1999.
[29]He, Y., Wang, Q. G., Wu, M., and Lin, C., “Delay-dependent state estimation for delayed neural networks, IEEE Transactions on Neural Networks, vol. 17, pp. 1077-1081, 2006.
[30]Ho, W. H., Chen, S. H., Liu, T. K., and Chou, J. H., “Design of robust-optimal output feedback controllers for linear uncertain systems using LMI-based approach and genetic algorithm, Information Sciences, vol. 180(23), pp. 4529-4542, 2010.
[31]Ho, W. H., Chou, J. H., and Guo, C. Y., “Parameter identification of chaotic systems using improved differential evolution algorithm, Nonlinear Dynamics, vol. 61, pp. 29-41, 2010.
[32]Hochreiter, S., “The vanishing gradient problem during learning recurrent neural nets and problem solutions, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 6(2), pp. 107-116, 1988.
[33]Hopfield, J., “Neural networks and physical systems with emergent collective computational abilities, Proceedings of the National Academy of Sciences of the United States of America, vol. 79, pp. 2554-2558, 1982.
[34]Hopfield, J., “Neurons with graded response have collective computational properties like those of two-state neurons, Proceedings of the National Academy of Sciences of the United States of America, vol. 81, pp. 3088-3092, 1984.
[35]Hou, Y. Y., Liao, T. L., and Yan, J. J., “Stability analysis of Takagi-Sugeno fuzzy cellular neural networks with time-varying delays, IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, vol. 37(3), pp. 720-726, 2007.
[36]Hu, S., Liao, X., and Mao, X., “Stochastic Hopfield neural network, Joural of Physics A: Mathematical and General, vol. 9, pp. 47-53, 2004.
[37]Huang, H., Feng, G., and Cao, J., “Robust state estimation for uncertain neural networks with time-varying delay, IEEE Transactions on Neural Networks, vol. 19(8), pp. 1329-1339, 2008.
[38]Huang, H., Ho, D., and Lam, J., “Stochastic stability analysis of fuzzy Hopfield neural networks with Time-Varying Delays, IEEE Transactions on Circuits and Systems II, Express Briefs, vol. 52, pp. 251-255, 2005.
[39]Huang, T., “Exponential stability of fuzzy cellular neural networks with distributed delay, Physics Letters A, vol. 351, pp. 48-52, 2006.
[40]Huang, Z. and Xia, Y., “Global exponential stability of BAM neural networks with transmission delays and nonlinear impulses, Chaos, Solitons Fractals, vol. 38, pp. 489-498, 2008.
[41]Kickert, W. J. and Mamdani, E. H., “Analysis of a fuzzy logic controller, Fuzzy Sets and Systems, vol. 1, pp. 29-44, 1978.
[42]Kuang, Y., Smith, H. L., and Martin, R. H., “Global stability for infinite-delay, dispersive Lotka-Volterra systems: Weakly interacting populations in nearly identical patches, Journal of Dynamics and Differential Equations, vol. 3, pp. 339-360, 1991.
[43]Kolmanovskii, V. B. and Myshkis, A., Introduction to the Theory and Applications of Functional Differential Equations, Dordrecht, Kluwer Academic Publishers, 1999.
[44]Li, C. and Liao, X., “Passivity analysis of neural networks with time delay, IEEE Transactions on Circuits and Systems II, Express Briefs, vol. 52, pp. 471-475, 2005.
[45]Li, C., Zhang, H., and Liao, X., “Passivity and passification of fuzzy systems with time delays, Computer ＆ Mathematics with Applications, vol. 52, pp. 1067-1078, 2006.
[46]Li, H., Chen, B., Zhou, Q., and Qian, W., “Robust stability for uncertain delayed fuzzy Hopfield neural networks with Markovian jump parameters, IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, vol. 39, pp. 94-102, 2009.
[47]Li, T., Fei, S. M., and Zhu, Q., “Design of exponential state estimator for neural networks with distributed delays, Nonlinear Analysis: Real World Applications, vol. 10, pp. 1229-1242, 2009.
[48]Li, W. and Lee, T., “Hopfield neural networks for affine invariant matching, IEEE Transactions on Neural Networks, vol. 12, pp. 1400-1410, 2001.
[49]Liang, J., Wang, Z., and Liu, X., “Robust passivity and passification of stochastic fuzzy time-delay systems, Information Sciences, vol. 180, pp. 1725-1737, 2010.
[50]Liao, X. F., Wang, K. W., and Li, C. G., “Global exponential stability for a class of generalized neural networks with distributed delays, Nonlinear Analysis.: Real World Applications., vol. 5, pp. 527-547, 2004.
[51]Lien, C. H. and Chung, L. Y., “Global asymptotic stability for cellular neural networks with discrete and distributed time varying delays, Chaos, Solitons, Fractals, vol. 34, pp. 1213-1219, 2007.
[52]Liu, Y. R., Wang, Z. D., and Liu, X., “Global exponential stability of generalized recurrent neural networks with discrete and distributed delays, Neural Networks, vol. 19, pp. 667-675, 2006.
[53]Liu, Y., Wang, Z., and Liu, X., “Design of exponential state estimators for neural networks with mixed time delays, Physics Letters A, vol. 364(5), pp. 401-412, 2007.
[54]Lou, X. Y. and Cui, B. T., “Robust asymptotic stability problem of fuzzy BAM neural networks with time-varying delays, Fuzzy Sets and Systems, vol. 158, pp. 2746-2756, 2007.
[55]Lozano, R., Brogliato, B., Egeland, O., and Maschke, B., “Dissipative systems analysis and control theory and applications, Measurement Science and Technology, vol. 12, 2001.
[56]Lu, C. Y., Tsai, H. H., Su, T. J., Tsai, J. S. H., and Liao, C. W., “A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying delay, Neural Processing Letters, vol. 51, pp. 237-246, 2008.
[57]Mahmoud, M. S. and Ismail, A., “Passivity and passification of time-delay systems, Journal of Mathematical Analysis and Applications, vol. 292, pp. 247-258, 2004.
[58]Mahmoud, M. S., Robust Control and Filtering for Time-Delay Systems, New York: Marcel Dekker, 2000.
[59]Malek-Zavarei, M. and Jamshidi, M., Time-Delay System, Analysis, Optimization and Application, North-Holl and System and Control Series, 1987.
[60]Meyer-Bäse, A., Roberts, R., and Yu, H. G., “Robust stability analysis of competitive neural networks with different time-scales under perturbations, Neurocomputing, vol. 71, pp. 417-420, 2007.
[61]Mohamad, S., Gopalsamy, K., and Akqa, H., “Exponential stability of artificial neural networks with distributed delays and large impulses, Nonlinear Analysis.: Real World Applications., vol. 9, pp. 872-888, 2008.
[62]Niculescu, S. I. and Lozano, R., “On the passivity of linear delay systems, IEEE Transaction on Automatic Control, vol. 46, pp. 460-464, 2001.
[63]Niculescu, S. I., Delay Effects on Stability, Springer-Verlag, London, 1991.
[64]Niculescu, S. I., Verriest, E. I., Dugard, L., and Dugard, J. M., “Stability of linear systems with delayed state, a guide tour in Stability and Control of Time-Delay Systems, Dugard L. and Verriest E. I., Eds, Lecture Notes in Control and Information Sciences, vol. 228, pp. 1-71, Springer-Verlag, London, 1997.
[65]Park, J. H. and Cho, H. J., “A delay-dependent asymptotic stability criterion of cellular neural networks with discrete and distributed time varying delays, Chaos, Solitons ＆ Fractals, vol. 33, pp. 436-442, 2007.
[66]Park, J. H., “Further results on passivity analysis of delayed cellular neural networks, Chaos, Solitons and Fractals, vol. 34, pp. 1546-1551, 2007.
[67]Principle, J. C., Kuo, J. M., and Celebi, S., “An analysis of the gamma memory in dynamic neural networks, IEEE Transaction on Neural Networks, vol. 5, pp. 337-361, 1994.
[68]Rakkiyappan, R. and Balasubramaniam, P., “LMI conditions for global asymptotic stability results for neutral-type neural networks with distributed time delays, Applied Mathematics and Computation, vol. 204, pp. 317-324, 2008.
[69]Ruan, S. and Filfil, R. S., “Dynamics of two-neuron system with discrete and distributed delays, Physica D: Nonlinear Phenomena, vol. 191, pp. 323-342, 2004.
[70]Rutkowski, L., “Adaptive probabilistic neural networks for pattern classification in time-varying environment, IEEE Transaction on Neural Networks, vol. 15, pp. 811-827, 2004.
[71]Sheng, L. and Yang, H., “Delay-dependent exponential stability analysis of fuzzy delayed Hopfield neural networks: a fuzzy Lyapunov-Krasovskii functional approach, 2009 American Control Conference, USA, June, 10-12, pp. 4296-4301, 2009.
[72]Sheng, L., Gao, M., and Yang, H., “Delay-dependent robust stability for uncertain stochastic fuzzy Hopfield neural networks with time-varying delays, Fuzzy Sets and Systems, vol. 160, pp. 3503-3517, 2009.
[73]Song, Q., Liang, J., and Wang, Z., “Passivity analysis of discrete-time stochastic neural networks with time-varying, Neurocomputing, vol. 72, pp. 1782-1788, 2009.
[74]Squartini, S., Hussain, A., and Piazza, F., “Attempting to reduce the vanishing gradient effect through a novel recurrent multiscale architecture, International Joint Conference on Neural Networks, vol. 4, pp. 2819-2824, 2003.
[75]Sugeno, M., Industrial Applications of Fuzzy Control, New York: Elsevier, 1985.
[76]Taguchi, G., Chowdhury, S., and Taguchi, S., Robust Engineering, New York: McGraw-Hill, 2000.
[77]Takagi, T. and Sugeno, M., “Fuzzy identification of systems and its application to modeling and control, IEEE Transactions on Systems, Man, and Cybernetics, vol. 15, pp. 116-132, 1985.
[78]Takagi, T. and Sugeno, M., “Stability analysis and design of fuzzy control systems, Fuzzy Sets and Systems, vol. 45, pp. 135-156, 1992.
[79]Tank, D. W. and Hopfield, J. J., “Neural computation by concentrating information in time, Proceedings of the National Academy of Sciences of the United States of America, vol. 84, pp. 1896-1991, 1987.
[80]Tong, R. M., “A control engineering review of fuzzy systems, Automatica, vol. 13, pp. 559-568, 1977.
[81]Tsai, J. T., Chou, J. H., and Liu, T. K., “Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm, IEEE Transactions on Neural Networks, vol. 17(1), pp. 69-80, 2006.
[82]Tsai, J. T., Liu, T. K., and Chou, J. H., “Hybrid Taguchi-genetic algorithm for global numerical optimization, IEEE Transactions on Evolutionary Computation, vol. 8(4), 2004.
[83]Tseng, K. H., Tsai, J. S. H., and Lu, C. Y., “ A delay-dependent approach to robust control of Takagi-Sugeno fuzzy uncertain recurrent neural networks with discrete and distributed interval time-varying delays, Journal of Circuits, Systems, and Computers, vol. 20(8), pp. 1571-1589, 2011.
[84]Tseng, K. H., Tsai, J. S. H., and Lu, C. Y., “ A delay-dependent approach to robust passivity analysis for Takagi-Sugeno fuzzy uncertain recurrent neural networks with mixed interval time-varying delays, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2012 (Accepted for publication).
[85]Tseng, K. H., Tsai, J. S. H., and Lu, C. Y., “ Design of delay-dependent exponential estimator for T-S fuzzy neural networks with mixed time-varying interval delays using hybrid Taguchi-genetic algorithm, Neural Processing Letters, vol. 36, no. 1, pp. 49-67, 2012.
[86]Wang, H. O., Tanaka, K., and Griffin, M. F., “An approach to fuzzy control of nonlinear systems: stability and design issues, IEEE Transactions on Fuzzy Systems, vol. 4, pp. 14-23, 1996.
[87]Wang, Z. D., Ho, D. W. C., and Liu, X. H., “State estimation for delayed neural networks, IEEE Transactions on Neural Netw, vol. 16(1), pp. 279-284, 2005.
[88]Wang, Z., Liu, Y., and Liu, X., “On global asymptotic stability of neural networks with discrete and distributed delays, Physics Letters, vol. 345, pp. 299-305, 2005.
[89]Wu, Y., Taguchi Methods for Robust Design, New York: Amer. Soc. Mech. Eng., 2000.
[90]Yang, H. and Sheng, L., “Robust stability of uncertain stochastic fuzzy cellular neural networks, Neurocomputing, vol. 73, pp. 133-138, 2009.
[91]Yang, R., Gao, H., Lam, J., and Shi, P., “New stability criteria for neural networks with distributed and probabilistic delays, Circuits Systems Singal Process, vol. 28, pp. 505-522, 2009.
[92]Yao, X., Wu, L., Wang, W. X., and Wang, C., “Passivity analysis and passification of Markovian jump systems, Circuits Systems Singal Process, vol. 29, pp. 709-725, 2010.
[93]Yu, G. J., Lu, C. Y., Tsai, J. S. H., Su, T. J., and Liu, B. D., “Stability of Cellular Neural Networks with Time-varying Delay, IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, vol. 50(5), pp. 677-679, 2003.
[94]Zadeh, L. A., “Outline of a new approach to analysis of complex systems and decision processes, IEEE Transactions on Systems, Man, and Cybernetics, vol. 3, pp. 28-44, 1973.