An Improved Differential Evolution Trained Neural Network Scheme for Nonlinear System Identification

Abstract

This paper presents an improved nonlinear system identi¯cation scheme using di®erential evolution (DE), neural network (NN) and Levenberg Marquardt algorithm (LM). With a view to achieve better convergence of NN weights optimization during the training, the DE and LM are used in a combined framework to train the NN. We present the convergence analysis of the DE and demonstrate the e±cacy of the proposed improved system identi¯cation algorithm by exploiting the combined DE and LM training of the NN and suitably implementing it together with other system identi¯cation methods, namely NN and DE+NN on a number of examples including a practical case study. The identi¯cation results obtained through a series of simulation studies of these methods on di®erent nonlinear systems demonstrate that the proposed DE and LM trained NN approach to nonlinear system identi¯cation can yield better identi¯cation results in terms of time of convergence and less identi¯cation error.