Training Elman neural network for dynamical system identification using stochastic dynamic batch local search algorithm

In thts paper, we propose a Stochastic Dynamic Batch Local Srarch (SDBLS) algorithm to train Elman Neural Network (ENN) for Dynamic Systems Identificahon (DSI). First, we propose a new Batch Local Search (BLS,) algorithm for ENN from a new angle instead of traditional Back Propagation (BP) based gradient descent technique, then add the stochastic dynamic signal into the network in order to avoid the possible local minima problem caused by the BLS method. Erperimental results show that the proposed algorithm has greatly effective performances in the identification of linear and nonlinear dynamic systems in comparison with other algorithms without calculating any derivations. The results conclude 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 identification approach to identify DSI for the auto-control systems.