An Optimal Regions-based Identification Approach for Piecewise Affine Model of Nonlinear Systems

This paper proposes a new identification technique for the discrete-time MISO nonlinear systems, which formulated by the piecewise affine (PWA) form. Because of the correlation between the identification of submodels and the estimation of corresponding active regions, the proposed identification approach aims to find the optimal parameters of submodels and corresponding active regions simultaneously that minimize the suitably defined distance between local models and submodels in the same active region. The particle swarm optimization (PSO) is used in order to find the global optimal solution of the optimization problem. In this method, these local data sets that collect data generated by different submodels are abandoned, which highlights our method. At last, the proposed approach is implemented and tested on a continuous stirred-tank reactor (CSTR) system. The obtained results turn out to be satisfactory and show a good precision.