Fast approximate identification of non linear systems

Abstract

A method is presented to extend the classical linear system identification methods towards nonlinear modelling. A well chosen nonlinear model structure is proposed that is identified in a 2-step procedure. First, a best linear approximation is identified using the classical linear identification methods. Next, the nonlinear extensions are identified with a linear least squares method. The proposed model not only includes Wiener and Hammerstein systems, it is also suitable to model nonlinear feedback systems. The method is illustrated on experimental data.