Training elman neural network for dynamic system identification using an adaptive local search algorithm

Recurrent neural networks, especially for Elman Neural Network, have attracted the attention of researchers in the fields of Dynamic System Identification (DSI) since they took the m,em,ory unit through the context delay. In this paper, we propose an Adaptive Local Search (ALS) algorithm, to train Elman Neural Network (ENN) for Dynamic Systems Identification (DSI) from a new angle instead of traditional Back Propagation (BP) based, gradient descent technique. Experimental results show that the proposed algorithm has greatly effective performances in the identification of linear and nonlinear dynamic systems in comparison with BP based, algorithms. The results also demonstrate that the proposed, algorithm, is an alternative means of training ENN when the gradient-based methods fail to find an acceptable solution. So the proposed algorithm can be regarded as a new tool or identification approach to identify dynamical systems for the auto-control systems.