Evolutionary computation approach to Wiener model identification

Abstract

A novel approach for nonlinear dynamic system identification is addressed for Wiener models, which are composed of a linear dynamic system part followed by a nonlinear static part. Assuming the nonlinear static part is invertible, we approximate the inverse function by a piecewise linear function, which is estimated by using the evolutionary computation approach such as genetic algorithm (GA) and evolution strategies (ES), while we estimate the linear dynamic system part by the least squares method.