為了解決傳統類神經網路在輸入變數增加時會產生大量的權重參數以致於耗費大量運算時間甚至造成電腦無法運算的問題，我們使用了數個模糊類神經網路來達成階層式的學習架構，並將其稱之為「合併式模糊類神經網路」。在此論文中，我們證明此合併式模糊類神經網路近似器具有一般性。此合併式模糊類神經網路分別被應用到系統鑑別及控制器設計的問題。在系統鑑別的應用中，合併式模糊類神經網路的學習機制是藉由B-spline函數做為可區域調整之歸屬函數，並結合循序搜尋的簡化型基因演算法來調整網路的權重值以及BMF的控制點，來達成我們所近似的目標。在實際應用中，一2階層12輸入單輸出的合併式模糊類神經網路被使用來近似一個由四個鋰電池串聯的充放電機置。此機置包括了12個輸入4個輸出。在模擬的結果中，我們證實了合併式模糊類神經網路在簡化型基因演算法的學習下可得到比倒傳式類神經網路較好的效果。另一方面，在針對一般性非線性系統的控制器設計方面，合併式模糊類神經網路可大幅降低直接適應性模糊類神經控制器中的被調整的參數，因此可解決因為需要大量運算而造成的控制器延遲問題。在論文中，我們證明了合併式模糊類神經網路在直接適應性控制器設計中可以取代傳統的模糊類神經網路，並同時可減少運算時間及維持與傳統設計中的控制性能。

To solve learning problems with vast numbers of inputs, this dissertation proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this dissertation, the merged-FNN is proved to be a universal approximator. Two different applications demonstrate that the merged-FNN has greater potential than the neural network and traditional FNN in real systems. One is the system identification and the other is the controller design for nonaffine nonlinear systems. In the system identification, the computing approach uses the merged-FNN using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). The reduced-form genetic algorithm is employed to tune all free parameters of the merged-FNN, including both control points of the B-spline membership functions and weights of the small fuzzy neural networks. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of traditional neural networks with back-propagation learning. In the aspect of the controller design, we propose an observer-based adaptive fuzzy-neural controller for nonaffine nonlinear systems, structured by the merged-FNN to substantially reduce the number of adjustable parameters and the computation time of the controller. The traditional direct adaptive fuzzy-neural control scheme for nonaffine nonlinear systems has a vast number of free parameters if many inputs (linguistic terms) and membership functions of the fuzzy-neural network (FNN) are required. This leads to the problem of a huge computation time. Spending so much computation time adjusting these parameters results in a serious controller time-delay problem. To solve this problem, the traditional FNN is replaced by the merged-FNN to form an observer-based adaptive controller. We prove that the merged-FNN can take the place of the traditional fuzzy-neural networks under some assumptions while maintaining the property of stability. Moreover, the adaptive scheme using the proposed merged-FNN guarantees that all signals involved are bounded and the output of the closed-loop system asymptotically tracks the desired output trajectory. From experimental examples, the proposed merged-FNN has far fewer parameters than the traditional FNN, and the computation time is significantly reduced.

[1] G.K. Heitman, “Complexity of identification of input-output systems,” Journal of Mathematical Analysis and Applications, vol. 192, pp. 1007-1033, 1995.
[2] V. Duong and A.R. Stubberud, “System identification by genetic algorithm,” IEEE Aerospace Conference Proceedings, vol. 5, pp. 2331-2337, 2002.
[3] M.P. Schoen, “Input design for on-line system identification of a human respiratory system,” Proceedings of the American Control Conference, vol. 5, pp. 3361-3365, 2002.
[4] N. Xie and H. Leung, “A novel GA multiple model prediction approach with application to system identification driven by chaotic signals,” IEEE International Symposium on Intelligent Control, pp. 502-507, 2002.
[5] S. Mori, K. Hirasawa, and J. Hu, “A stock price prediction model by using genetic network programming,” SICE Conference, vol. 2, pp. 1186-1191, 2004.
[6] H.M. Kim and B. Kosko, “Fuzzy prediction and filtering in impulsive noise,” Fuzzy Sets and Systems, vol. 77, pp. 15-33, 1996.
[7] L.X. Wang and J.M. Mendel, "Fuzzy basis functions, universal approximation, and orthogonal least squares learning," IEEE Transactions on Neural Networks, vol. 3, no. 5, pp. 807-814, 1992.
[8] L.X. Wang, Adaptive fuzzy systems and control: design and stability analysis, Prentice Hall International, 1994.
[9] C. T. Lin, C.S. George Lee, Neural Fuzzy Systems – A Neuro-Fuzzy Synergism to Intelligent Systems, Prentice Hall International, Inc. 1999.
[10] O. Huwendiek, and W. Brockmann, “Function approximation with decomposed fuzzy systems,” Fuzzy sets and systems, vol. 101, pp. 273-283, 1999.
[11] W. Y. Wang, T. T. Lee, C. L. Liu, and C. H. Wang, “Function approximation using fuzzy neural networks with robust learning algorithm,“ IEEE Transactions on Systems, Man, And Cybernetics-Part B, vol. 27, no. 6, pp. 740-747, Dec. 1997.
[12] J.J. Buckley, “Sugeno type controllers are universal controller,” Fuzzy sets and systems, vol. 53, pp. 299-303, 1993.
[13] L.X. Wang and J.M. Mendel, "Fuzzy basis functions, universal approximation, and orthogonal least squares learning," IEEE Transactions on Neural Networks, vol. 3, no. 5, pp. 807-814, 1992.
[14] H. Qiao, J. Peng, and Z.B. Xu, and B. Zhang, “A reference model approach to stability analysis of neural networks,” IEEE Transactions on Systems, Man, And Cybernetics-Part B, vol. 3, no. 6, pp. 925-936, Dec. 2003.
[15] Z.G. Hou, M.M. Gupta, P.N. Nikiforuk, and M. Tan, and L. Cheng, “A recurrent neural network for hierarchical control of interconnected dynamic systems,” IEEE Transactions on Neural Networks, vol. 18, no. 2, pp.466-481, 2007.
[16] S.H. Huang and H.C. Zhang, “Artificial neural networks in manufacturing: concepts, applications, and perspectives,” IEEE Transactions on Components, Packaging, and Manufacturing Technology Part-A, vol. 17, no. 2, pp. 212-228, 1994.
[17] K. Hornick, M. Stinchcombe, H. White, “ Mutlilayer feed-forward networks are universal approximators,” Neural Networks, vol. 2, pp. 359-366, 1989.
[18] H. Nomura, I. Hayashi and N. Wakami, “A self-tuning method of fuzzy control by descend method,” Proceedings of 4th IFSA Congress, Engineering, pp. 155-158, 1991.
[19] Y. Ito, “Representation of functions by superpositions of a step of sigmoid function and their applications to neural networks theory,” Neural Networks, vol. 4, pp. 385-384, 1991.
[20] M. Karam, M.S. Fadali, and K. White, “A Fourier/Hopfield neural network for identification of nonlinear periodic systems,” IEEE Transactions on System Theory, pp. 53 -57, 2003.
[21] Q.Z. Chang, and M. Sami Fadali, “Nonlinear system identification using a Gabor/Hopfield network,” IEEE Transactions. on Systems, Man, and Cybernetics, vol. 26, no. 1, pp. 124-134, February 1996.
[22] S.K. Park, “Bearing estimation using Hopfield neural network,” IEEE Conference on System Theory, pp. 440-443, March 1990.
[23] N. Kamiura, T. Isokawa, N. Matsui, “Learning based on fault injection and weight restriction for fault-tolerant Hopfield neural networks,” IEEE Intl. Symposium on Defect and Fault Tolerance in VLSI Systems, pp.339-346, Oct. 2004.
[24] C.H. Wang, W.Y. Wang, T.T. Lee, and P.S. Tseng, “Fuzzy B-spline membership function (BMF) and its applications in fuzzy-neural control,” IEEE Transactions on Systems Man and Cybernetics, Vol. 25, No. 5, pp. 841-851, May 1995.
[25] H. Nomura, I. Hayashi and N. Wakami, “A self-tuning method of fuzzy control by descend method,” Proceedings of 4th IFSA Congress, Engineering, pp. 155-158, 1991.
[26] W. Y. Wang, C. C. Hsu, C. W. Tao, and Y. H. Li, “Fuzzy-neural function approximation using a vector evaluation genetic algorithm,” ICONS, 2003.
[27] W. Y. Wang and Y. H. Li, “Evolutionary learning of BMF fuzzy-neural networks using a reduced-form genetic algorithm,” IEEE Transactions on Systems, Man, And Cybernetics-Part B, vol. 33, no. 6, pp. 966-976, Dec. 2003.
[28] Y. S. Lee, C. H. Kao, and W. Y. Wang, “BMF fuzzy neural network with genetic algorithm for forecasting electric load,” IEEE PEDS, pp. 1662-1667, 2005.
[29] Y. S. Lee, T. Y. Kuo, and W. Y. Wang, “Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter,” IEEE Conference on Power Electronics Specialists Conference, pp. 2759-2765, 2004.
[30] I-Hsum Li, Wei-Yen Wang, Shun-Feng Su, and Yuang-Shung Lee, “A Novel Learning Structure of Fuzzy Neural Networks Using Reduced-Form Genetic Algorithms,” 12th International Conference on Neural Information Processing, pp. 219-223, Oct., 2005.
[31] Z. Michalewicz, Genetic Algorithms + Data Structure = Evolution Program. New York: Springer-Verlag, 1996.
[32] D. Lawrence, Handbook of Genetic Algorithms. New York: Van Nos-trand, 1991.
[33] D. Goldberg, Genetic Algorithms in Search, Optimisation, and Machine Learning, Addison-Wesley, 1989.
[34] K. Kristinsson and G. Dumont, “System identification and control using genetic algorithms,” IEEE Transactions on Systems, Man and Cybernetics, vol. 22, pp. 1033–1046, 1992.
[35] C.T. Lin and C.P. Jou, “GA-based fuzzy reinforcement learning for control of a magnetic bearing system,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 30, No. 2, PP. 276 –289, April 2000.
[36] Wael A. Farag, Victor H. Quintana, and Germano Lambert-Torres, “A Genetic-Based Neuro-Fuzzy approach for modeling and control of dynamical systems,” IEEE Transactions on neural networks, Vol. 9, No. 5, Sept. 1998.
[37] B. Porter and A. Jones, “Genetic tuning of digital PID controllers,” Electronic Letters, Vol. 28, pp. 843-844, 1992.
[38] C. Hsu, K. Tse and C. Wang, “Digital Redesign of Continuous Systems with Improved Suitability Using Genetic Algorithms,” Electronics Letters, Vol. 33, no. 15, pp. 1345-1347, 1997.
[39] R. Caponetto, L. Fortuna, S. Graziani, and M. Xibilia, “Genetic algorithms and applications in system engineering: a survey,” Trans. Inst. Meas. Control, Vol. 15, pp. 143-156, 1993.
[40] G W Game, and C D James, “The Application of Genetic Algorithms to the Optimal Selection of Parameter Values in Neural networks for Attitude Control System,” IEEE Colloquium on High Accuracy Platform Control in Space, pp. 3/1-3/3, 1993.
[41] G. W. Game, C. D. James, “The Application of Genetic Algorithms to the Optimal Selection of Parameter Values in Neural networks for Attitude Control System,“ IEEE Colloquium on High Accuracy Platform Control in Space, pp. 3/1-3/3, 1993.
[42] Yu Nong, Li Yushu and Xu Qifu, “Genetic Training Algorithm of Morphological Filters,” WCCC-ICSP 2000. 5th International Conference on Signal Processing Proceeding, Vol. 1, pp. 476-479, 2000.
[43] Goldberg D. E., Genetic Algorithm in search, Optimization and Machine Learning, Reading, MA:Addision-Weskey, 1989.
[44] Haupt R. L., and Haupt S. E., Practical Genetic Algorithms, Wiley Interscience, 1998.
[45] Man, Tang and Kwong, Genetic Algorithms Springer, 1999.
[46] Mitchell, M., An Introduction to Genetic Algorithms, Cambridge, MA: The
[47] C. Hsu, K. Tse and C. Wang, “Digital Redesign of Continuous Systems with Improved Suitability Using Genetic Algorithms,” Electronics Letters, Vol. 33, no. 15, pp. 1345-1347, 1997.
[48] R. Caponetto, L. Fortuna, S. Graziani, and M. Xibilia, “Genetic algorithms and applications in system engineering: a survey,” Trans. Inst. Meas. Control, Vol. 15, pp. 143-156, 1993.
[49] G W Game, and C D James, “The Application of Genetic Algorithms to the Optimal Selection of Parameter Values in Neural networks for Attitude Control System,” IEEE Colloquium on High Accuracy Platform Control in Space, pp. 3/1-3/3, 1993.
[50] C.H. Wang, H.L. Liu and C.T. Lin, “Dynamic optimal learning rates of a certain class of fuzzy neural networks and its applications with genetic algorithm,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 31, No. 3 , pp.467 –475, June 2001.
[51] C.T. Lin and C.P. Jou, “GA-based fuzzy reinforcement learning for control of a magnetic bearing system,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 30, No. 2, PP. 276 –289, April 2000.
[52] K. Kristinsson and G. Dumont, “System identification and control using genetic algorithms,” IEEE Trans. Syst., Man, Cybern., vol. 22, pp. 1033–1046, 1992.
[53] X.J. Zeng and J.A. Keane, “Approximation capabilities of hierarchical hybrid systems,” IEEE Transactions on Systems, Man and Cybernetics, Part A, vol. 36, no. 5, September, 2006.
[54] X.J. Zeng and J.A. Keane, “Approximation capabilities of hierarchical fuzzy systems,” IEEE Transactions on Fuzzy Systems, vol. 13, no. 5, October, 2005.
[55] C. Xu and K. Kijima, “Dominant incentive straegies for hierarchical systems with incomplete information structure,” IEEE Transactions on Systems, Man and Cybernetics, vol. 25, no. 1, January, 1995.
[56] R.J. Leduce, B.A. Brandin, M. Lawford, and W.M. Wonham, “Hierarchical interface-based supervisory control-part I: serial case,” IEEE Transactions on Automatic Control, vol. 50, no. 9, September 2005.
[57] Y.L. Hu, and W.G. Wee, “A hierarchical system for economic dispatch with environmental constraints,” IEEE Transactions on Power Systems, vol. 9, no. 2, May 1994.
[58] X.J. Zeng and J.A. Keane, “Separable approximation property of hierarchical fuzzy systems,” IEEE Conf. on Fuzzy System, pp. 951-956, May 2005.
[59] Caumont, P. Le Moigne, C. Rombaut, and X. Muneret, “Energy gauge for lead-acid batteries in electric vehicles,” IEEE Trans. on Energy Conversion, Vol. 15, No.3, pp.354-360, September 2000.
[60] J. Garche, and A. Jossen, “Battery management systems (BMS) for increasing battery life time,” Telecommunications Energy Special, 2000. TELESCON. The Third International Conference, pp.81-88, 2000.
[61] G. Nagasubramanian, and R.G.Jungst, “Energy and power characteristics of lithium-ion cells”, Journal of Power Sources 72, pp.189-193, 1998.
[62]W. X. Shen, C.C. Chan, E.W.C. Lo, and K.T. Chau, “Adaptive neuro-fuzzy modeling of battery residual for electric vehicles,” IEEE Transactions on Industrial Electronics, Vol.49, pp.677–684, Jun 2002.
[63] M. H. Yang, C. H. Hsieh, and B. M. Lin, “Development of Li-ion battery for electric bike application,” in Proceeding of The 18th International Battery, Hybrid and Fuel Cell Electric Vehicle Symposium & Exhibition, EVS18, Oct. 2001, 6D.
[64] Y. S. Lee, Wei-Yen Wang, T. Y Kou, “Soft Computing for Battery State-of-Charge (BSOC) Estimation in Battery String Systems,” accepted and to appear IEEE Trans. on Industrial Electronics, 2006.
[65] Y. G. Leu, T. T. Lee, and W. Y. Wang, “Observer-based adaptive fuzzy-neural control for unknown nonlinear dynamical systems,” IEEE Trans. Syst. Man, Cybern. B, Cybern., vol. 29, no. 5, pp. 583-591, Oct. 1999.
[66]W. Y. Wang, C. Y. Cheng, and Y. G. Leu, “An online GA-based output-feedback direct adaptive fuzzy-neural controller for uncertain nonlinear systems,” IEEE Transactions on Systems, Man, And Cybernetics-Part B, vol. 34, no. 1, pp. 334-345, Feb. 2004.
[67] Y. G. Leu, W. Y. Wang, T. T. Lee, “Observer-based direct adaptive fuzzy-neural control for nonaffine nonlinear systems,“ IEEE Transactions on Neural networks, vol. 16, no. 4, pp. 853-861, July 2005.
[68]Y. G. Leu, T. T. Lee, and W. Y. Wang, “On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems,” IEEE Transactions on Systems, Man, And Cybernetics-Part B, vol. 27, no. 6, pp. 1034-1043, Dec. 1997.
[69]Y. G. Leu, W. Y. Wang, and T. T. Lee, “Robust adaptive fuzzy-neural controllers for uncertain nonlinear systems,” IEEE Transactions on Robotics and Automation, vol. 15, no. 5, pp. 805-817, Oct. 1999.
[70] I. H. Li, W. Y. Wang, S. F. Su, M. C. Chen, “A merged-fuzzy-neural network and its application in fuzzy-neural control,“ IEEE International Conference on Systems, Man and Cybernetics, pp. 4529-4534, Oct. 2006.
[71] L. H. Chien, W. Y. Wang, I. H. Li, and S. F. Su, “T-S fuzzy control for uncertain nonlinear systems using adaptive fuzzy approach,“ IEEE International Conference on Fuzzy Systems, pp. 3697-3702, July 2006.
[72] R. V. Monopoli, “Model reference adaptive control with an augmented error signal,” IEEE Trans. Autom. Control, vol. AC-19, no. 5, pp. 474-484, Oct. 1974.
[73] K. S. Narendra and A. M. Annaswamy, Stable Adaptive Systems. Englewood Cliffs, NJ: Prentice-Hall, 1989.
[74] S. S. Sastry and M. Bodson, Adaptive Control: Stability, Convergence, and Robustness. Englewood Cliffs, NJ: Prentice-Hall, 1989.
[75] P. A. Ioannou and K. S. Taskalis, “A robust direct adaptive controller,” IEEE Trans. Autom. Control, vol. AC-31, no. 11, pp. 1033-1043, Nov. 1986.
[76] P. A. Ioannou and A. Datta, “Robust adaptive control: A unified approach,” Proc. IEEE, vol. 79, no. 12, pp. 1735-1768, Dec. 1991.
[77] P. A. Ioannou and J. Sun. Robust Adaptive Control. Englewood Cliffs, NJ: Prentice-Hall, 1996.
[78] A. Isidori, Nonlinear Control System. New York: Springer-Verlag, 1989.
[79] J. J. E. Slontine and W. Li, Applied Nonlinear Control. Englewood Cliffs, NJ: Prentice-Hall, 1991.
[80] S. S. Sastry and A. Isidori, “Adaptive control of linearizable systems,” IEEE Trans. Autom. Control, vol. 34, no. 11, pp. 1123-1131, Nov. 1989.
[81] S. Monaco and D. Normand-Cyrot, “Minimum-phase nonlinear discrete-time systems and feedback stabilization,” in Proc. IEEE Conference on Decision Control, Los Angeles, CA, 1987, pp. 979-986.
[82] B. Jakubezyk, “Feedback linearization of discrete time system,” Syste Control Lett., vol. 9, pp. 411-416, 1987.
[83] S. S G, C. C. Hang, and T. Zhang, “Adaptive neural network control of nonlinear systems by state and output feedback,” IEEE Transactions on Systems, Man, And Cybernetics, part-B, vol. 29, no. 6, pp. 818-828, Dec. 1999.
[84] H. K. Khalil, Nonlinear Systems. New York: Macmillan, 1992.
[85] J. D. Boskovic, L. Chen, and R. K. Mehra, “Adaptive Tracking Control of a Class of Non-Affine Plants Using Dynamic Feedback,” Proceedings of the American Control Conference, pp. 2450-2455, June 2001.
[86] S. N. Huang, K. K. Tan, and T. H. Lee, “Nonlinear adaptive control of interconnected systems using neural networks,” IEEE Transactions on Neural Networks, Vol. 17, No. 1, pp. 243 – 246, Jan. 2006.
[87] C. F. Hsu, C. M. Lin, and T. T. Lee, “Wavelet Adaptive Backstepping Control for a Class of Nonlinear Systems,” IEEE Transactions on Neural Networks, Vol. 17, No. 5, pp. 1175 – 1183, Sept. 2006.
[88] C.J. Lin and C.H. Chen, “A self-constructing compensatory neural fuzzy system and its applications,” Mathematical and Computer Modeling, vol. 42, pp. 339-351, 2005.
[89] A. Chatterjee, A. Rakshit, and P. Siarry, “Generalised influential rule search scheme for fuzzy function approximation,” Soft Computing, vol. 10, pp. 631-642, 2006.
[90] T. Feuring and J.J. Buckley, “Fuzzy neural nets can solve the overfitting problem,” IEEEE International Conference on Neural Network, vol. 6, pp.4192-4201, 1999.
[91] T. Feuring and J.J. Buckley, “Overfitting: a fuzzy neural net solution,” IEEE International Conference on Fuzzy Systems, vol. 1, pp. 61-65, 1999.
[92] Peter Merz and Bernd Freisleben, “Fitness Landscape Analysis and Memetic Algorithms for the Quadratic Assignment Problem,” IEEE Trans. On Evolutionary Computation, vol. 4, no. 4, pp. 337-352, 2000.
[93] J.C. Doyle, Essentials of robust control, Prentice Hall International, Inc. 1998.