由於類神經網路 (Artificial neural networks) 系統本身即具有學習的能力，因此透過離線訓練的方式 (Off-line training) 或是線上的適應性調整 (On-line adaptive)，能利用此一由模仿人類神經系統靈感出發的類神經網路系統，來逼近或重現任何所須之輸入輸出的對應關係 (Mapping)。正因為這樣的優異特性，類神經經網路已被廣泛的使用於許多不同的領域，在學術的發展及工程應用上，更是方興未艾。本論文針對類神經網路於非線性的控制應用，除了探討其相關的理論研究與發展，並應用於實際非線性系統的控制器實現。
首先，由於傳統之以輻射函數為基底的類神經網路架構 (Radial-basis-function，RBF)，為了簡化控制器的架構，只調變網路輸出權重的部分，一方面因而減弱了該類神經網路系統的函數逼近能力，另一方面也使得設計的過程中必須先離線選取適當的隱藏層 (Hidden layer) 中高斯函數 (Gaussian functions) 的變異量參數 (Variance parameters)，使得控制器設計的過程變得較不系統化 (Systematic)。反觀，多層式的類神經網路架構 (Multi-layer perceptron，MLP)，雖然擁有較佳的函數逼近能力，但是由於加入數目繁多之輸入-隱藏層 (Input-to-hidden layer) 的可調參數，使得整個控制器架構的複雜性相對地提高了許多。因此，本論文針對此一課題，結合了 MLP 網路的參數調整，提出了一改良型之以輻射函數為基底的類神經網路架構。不但能提升傳統以輻射函數為基底的類神經網路架構之函數逼近能力，更由於能線上自動調整，而不須離線選取所需的變異量參數，也使得控制器的設計過程更為系統化。

其次，由於多數之類神經網路於非線性的控制應用，均只限制在最小相系統 (Minimum phase system)。因此本論文提出藉由設計一穩定複合系統 (stable compound system) 的觀念來達成對於非最小相系統 (Non-minimum phase system) 的輸出穩定控制 (Output regulation) 與輸出追蹤控制 (Output tracking)，並將類神經網路系統於非線性之非最小相系統的控制應用做了完整的探討與控制器設計。

再者，穩定性 (Stability) 的保證更是此類神經經網路系統於線上適應性控制器應用的一大課題。所以在本論文中，直接型 (Direct-type) 之適應性架構結合滑動模式控制 (Sliding-mode control) 的技巧被用於控制器的設計，使得所提出之類神經網路控制器，不但能線上重建 (Re-construct) 所需的控制量，更能確保整個系統的穩定性。

最後，除了藉由理論的推導，模擬的驗證，更進一步予以硬體實現，實際應用於一倒單擺 (Inverted pendulum system) 的輸出追蹤控制。除了能將滑車上之倒單擺平衡於上方的不穩定平衡點 (Stabilize unstable zero-dynamics)，同時也能進行滑車位置之追蹤控制 (Output tracking)。以便對所提出之以類神經網路為基礎的非線性控制應用有更為完整的體驗。

Artificial neural networks (ANNs) have been successfully applied in various areas ranging from signal processing to automatic control. This success is mostly due to the fact that neural networks are equipped with a remarkable learning capability such that a desired input-output mapping can be discovered through training by examples or by on-line adaptation with stable adaptive laws. Although many types of neural networks have been studied and reported, there are still many valuable topics needed to be further investigated.
The conventional radial-basis-function (RBF) neural networks adjust only output weights in order to simplify the controller structure. However, this simplification will decrease the approximation ability of NN system. For the multi-layer perceptron neural network, it adapts both of the weights of input-to-hidden layer and hidden-to-output layer, and the approximation ability is highly increased in this MLP-based NN. However, those added adaptation laws for tuning the weights of input-to-hidden layer markedly increase the complexity of the whole adaptive NN system. The aim of this dissertation is to construct an advanced adaptation scheme for upgrading the approximation accuracy of RBF-based neural network. Therefore, we propose an enhanced adaptive RBFN control methodology, in which the stable adaptations of variance parameters is involved to enhance the controller performance and simultaneously the complexity of the controller for the whole system isn’t increased too much.

Since almost all of the reported NN-based controller design are only applicable on the minimum phase cases, in order to cope with the non-minimum phase cases, we introduced a generalized controller structure based on the notion of synthesizing a stable compound system. Based on this generalization, we can extend the proposed enhanced RBFN system to deal with the output tracking control for a class of nonlinear systems with non-minimum phase.

In addition, the stability assurance is highly important in these on-line control applications. Therefore, in this dissertation, the direct-type adaptive-control architecture is employed, in which the proposed enhanced adaptive RBFN system combined with sliding mode control is used to on-line re-construct the desired control law so that the problem of controller singularity can be avoided. Not only stability of the whole adaptive neural-network-based system is guaranteed but also the influence of the re-construction error and external disturbance can be well compensated.

Furthermore, the practical realization is also an important issue on the application of the neural-network-based controllers. Not only through computer simulations, we also realize the hardware implementation on a practical experimental pole-cart system to verify the effectiveness of the proposed schemes.

[1] J. M. Zurada, Introduction to Artificial Neural Networks, St. Paul: West Publishing Company, 1992.
[2] M. T. Hagan, H. B. Demuth and M. Beale, Neural Network Design, Boston: PWS Publishing Company, 1996.
[3] J.-S. R. Jang, C. T. Sun and E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Upper Saddle River, NJ, U. S. A.: Prentice Hall, 1997.
[4] K. J. Hunt, D. Sbarbaro, R. Zbikowski and P. J. Gowthrop, "Neural networks for control systems – a survey", Automatica, vol. 28, no. 6, pp. 1083-1112, 1992.
[5] C. T. Lin and C.-S. G. Lee, Neural fuzzy systems: a neuro-fuzzy synergism to intelligent systems, Upper Saddle River, NJ, U. S. A.: Prentice Hall, 1999.
[6] K. S. Narendra and K. Parthasarathy, "Identification and control of dynamic systems using neural networks", IEEE Transactions on Neural Networks, vol. 1, no. 1, pp. 4-27, 1990.
[7] K. S. Narendra and K. Parthasarathy, "Gradient methods for the optimization of dynamical systems containing neural networks", IEEE Transactions on Neural Networks, vol. 2, no. 2, pp. 252-262, 1991.
[8] M. M. Gupta, D. H. Rao and H. C. Wood, "Learning and adaptive neural controller", Proceedings of the IEEE International Joint Conference on Neural Networks, Singapore, pp. 2380-2384, November, 1991.
[9] K. J. Hunt and D. Sbarbaro, "Neural networks for nonlinear internal model control", IEE Proceedings, Part D: Control Theory and Applications, vol. 138, no. 5, pp. 431-438, 1991.
[10] M. Sarens and A. Soquet, "Neural controller based on back-propagation algorithm", IEE Proceedings, Part F: Radar and Signal Processing, vol. 138, no. 1, pp. 55-62, 1991.
[11] K. S. Narendra, "Adaptive control of dynamical systems using neural networks", Handbook of Intelligent Control, Neural, Fuzzy, and Adaptive Approaches, edited by D. A. White and D. A. Sofge, New Yourk: Multiscience, pp. 141-184, 1992.
[12] R. M. Sanner and J.-J. E. Slotine, "Gaussian networks for direct adaptive control", Proceedings of the 1991 American Control Conference, Sofge, Green Valley, AZ, U.S.A., pp. 2153-2159, June, 1991.
[13] R. M. Sanner and J.-J. E. Slotine, "Stable adaptive control and recursive identification using radial Gaussian networks", Proceedings of the 30th IEEE Conference on Decision and Control, Brighton, England, pp. 11-13, December, 1991.
[14] M. M. Polycarpou and P. A. Ioannou, "Neural networks as on-line approximators of nonlinear systems", Proceedings of the 31th IEEE Conference on Decision and Control, Tucson, Arizona, U.S.A., pp. 16-18, December, 1992.
[15] R. M. Sanner and J. E. Slotine, "Gaussian networks for direct adaptive control", IEEE Transactions on Neural Networks, vol. 3, no. 6, pp. 837-863, 1992.
[16] E. Tzirkel-Hancock and F. Fallside, "Stable control of nonlinear systems using neural networks", International Journal of Robust and Nonlinear Control, vol. 2, pp. 63-86, 1992.
[17] R. M. Sanner and J. E. Slotine, "Stable adaptive control of robot manipulators using neural networks", Neural Computation, vol. 7, pp. 753-790, 1995.
[18] M. M. Polycarpou, "Stable adaptive neural control scheme for nonlinear systems", IEEE Transactions on Automatic Control, vol. 41, no. 3, pp. 447-451, 1996.
[19] N. Sadegh, "A perceptron network for functional identification and control of nonlinear systems", IEEE Transactions on Neural Networks, vol. 4, no. 6, pp. 1045-9227, 1993.
[20] F. L. Lewis, K. Liu and A. Yesildirek, "Neural net robot controller with guaranteed tracking performance", IEEE Transactions on Neural Networks, vol. 6, no. 3, pp. 703-715, 1995.
[21] N. Sadegh, "A multilayer nodal link perceptron network with least squares training algorithm", Internal Journal of Control, vol. 70, no. 3, pp. 385-404, 1998.
[22] J. F. de , A. G. Cerezo and I. G. Moral, "Direct control with radial basis function networks: stability analysis and applications", Internal Journal of Control, vol. 70, no. 3, pp. 385-404, 1998.
[23] M. Zhihong, H. R. Wu and M. Palaniswami, "An adaptive tracking controller using neural networks for a class of nonlinear systems", IEEE Transactions on Neural Networks, vol. 9, no. 5, pp. 947-955, 1998.
[24] F. Sun, Z. Sun and P. Y. Woo, "Stable neural-network-based adaptive control for sampled-data nonlinear systems", IEEE Transactions on Neural Networks, vol. 9, no. 5, pp. 956-968, 1998.
[25] K. Nam, "Stabilization of feedback linezarizable systems using a radial basis function network", IEEE Transactions on Automatic Control, vol. 44, no. 5, pp. 1026-1031, 1999.
[26] S. S. Ge, 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, vol. 29, no. 6, pp. 818-828, 1999.
[27] S. S. Ge, C. C. Hang and T. Zhang, "A direct method for robust adaptive nonlinear control with guaranteed transient performance", Systems and Control Letters, vol. 37, pp. 275-284, 1999.
[28] F. C. Chen and C. C. Liu, "Adaptively controlling nonlinear continuous-time systems using multilayer neural networks", IEEE Transactions on Automatic Control, vol. 39, no. 6, pp. 1306-1310, 1994.
[29] F. C. Chen and C. C. Liu, "Adaptive control of a class of nonlinear discrete-time systems using neural networks", IEEE Transactions on Automatic Control, vol. 40, no. 5, pp. 791-801, 1995.
[30] A. Yesidirek and F. L. Lewis, "Feedback linearization using neural networks", Automatica, vol. 31, pp. 1659-1664, 1995.
[31] S. Jagannathan and F. L. Lewis, "Multilayer discrete-time neural-net controller with guarantted performance", IEEE Transactions on Neural Networks, vol. 7, no. 1, pp. 107-130, 1996.
[32] F. L. Lewis, A. Yesildirek and K. Liu, "Multilayer neural-net robot controller with guaranteed tracking performance", IEEE Transactions on Neural Networks, vol. 7, no. 2, pp. 388-399, 1996.
[33] T. Zhang, S. S. Ge and C. C. Hang, "Design and performance analysis of a direct adaptive controller for feedback linearizable systems", Proceedings of the 1998 American Control Conference, pp. 3746-3750, Philadelphia, Pennsylvania, U.S.A., June, 1998.