System identification using Hammerstein model optimized with differential evolution algorithm

This paper aims to improve Hammerstein model for system identification area. Hammerstein model block structure is formed by cascade of linear and nonlinear parts. In literature, memoryless polynomial nonlinear (MPN) model for nonlinear part and finite impulse response (FIR) model or infinite impulse response (IIR) model for linear part are mostly preferred for Hammerstein models. In this study, a Hammerstein model is presented which is obtained by cascade form of a nonlinear second order volterra (SOV) and a linear FIR model. In addition, proposed Hammerstein model is optimized with differential evolution algorithm (DEA). In simulations, different types of systems are identified by proposed Hammerstein model. Also, performance of the proposed model is compared with different model performances. In conclusion it can be said that the main benefit of this study is that simulation results reveal the effectiveness and robustness of the proposed model.