Identification of Hammerstein Systems with Piecewise-Affine Nonlinearities

In this paper, we propose an identification method of Hammerstein systems with piecewise-affine (PWA) nonlinearities. This model is useful because it has characteristics of both Hammerstein systems and hybrid systems. We employ identification method using pseudo-random binary sequences (PRBS) inputs for decoupling the identification of nonlinear static block with that of PWA dynamic block, and we also employ statistical clustering technique for clustering the measured data into each sub-models. The validity of the method is demonstrated through numerical simulations.