locally recurrent neural networks (lRNNS) controller for dynamical system

Abstract

The ability of Artificial Neural Network (ANN) for controlling of dynamical system is presented. The structure of neural controller based on model reference adaptive control (MRAC) is available. The Levenberg-Marquardt back propagation (LMBP) is used in the learning of Locally Recurrent Neural Networks (LRNNs) which used for identify the plant and it used as neural controller. This method has ability to capture the nonlinearly and overcome the problems of dynamic system. The parameters of neural controller are adjusted with time by using the error signal between output of model reference and output of system through the adjusting mechanism based on LMBP algorithm. A simple airplane channel at certain freezing point is used as an example in this paper, satisfactory results are obtained, which explain the ability of locally recurrent neural network (LRNN) controller, when comparison the results with classical controller for dynamical system.