A combined differential evolution and neural network approach to nonlinear system identification

This paper addresses the effectiveness of soft computing approaches such as Evolutionary Computation (EC) and Artificial Neural Network (ANN) to system identification of nonlinear systems. In this work, three approaches namely a neuro-fuzzy, differential evolution (DE) and a combined DE-ANN have been applied for nonlinear system identification problem. Results obtained envisage that the proposed combined differential evolution-ANN approach to identification of nonlinear system exhibits better model identification accuracy and less computation time compared to the existing neural network approach and neuro-fuzzy technique (NFT).