Hybrid Neural Network Controller Using Adaptation Algorithm
Neural network controller using adaptation algorithm is a new and simple controller, in which a feedback network propagating the error is not required. So it can be applied to hardware easily. Nevertheless, our simulations show that while the order of controlled plant is high, some unstable phenomenon appear and we also find that sometimes the error is far from being satisfactory, although when the order of controlled plant is low. Moreover, the present adaptation algorithm can not solve this problem. In this paper we will give our derivation of adaptation algorithm used in the neural network controller and configuration of an adaptive neural network controller. Then give some simulation figures to illustrate defect for the new controller. Finally we will develop a hybrid neural network to solve the problem and improve the accuracy as well as reduce the cost to the least in the practical application.
KeywordsNeural Network Learning Rate Output Error Adaptation Algorithm Neural Network Controller
Unable to display preview. Download preview PDF.
- 1.Brandt, R.D., Lin, F.: Supervised Learning in Neural Network Without Explicit Error Back-propagation. In: Proceeding of the 32nd Annual Allenton Conference on Communication, Control and Computing, pp. 294–303 (1994)Google Scholar
- 2.Brandt, R.D., Lin, F.: Can Supervised Learning be Achieved without Explicit Error Back-propagation. In: Proceeding of International conference on Neural Networks, pp. 300–305 (1996)Google Scholar
- 3.Sakelaris, G., Lin, F.: A neural Network Controller by Adaptive Interaction. In: Proceedings of the American Control Conference, Arrington, VA, June 25–27 (2001)Google Scholar
- 6.Brandt, R.D., Lin, F.: Optimal Layering of Neurons. In: IEEE International Symposium on Intelligent Control, pp. 497–501 (1996)Google Scholar
- 10.Chen, F.C., Khalil, H.K.: Adaptive Control of Nonlinear Systems Using Neural Networks. In: IEEE Proceedings on the 29th Conference on Decision and Control, vol. 3, pp. 1707–1712 (1990)Google Scholar
- 17.Sakelaris, G., Lin, F.: A neural Network Controller by Adaptive Interaction. In: Proceedings of the American Control Conference, Arrington VA, June 2001, pp. 25–27 (2001)Google Scholar
- 18.Brandt, R.D., Lin, F.: Supervised Learning in Neural Networks Without Feedback Network. In: IEEE International Symposium on Intelligent Control, pp. 86–90 (1996)Google Scholar