A novel nonlinear model parameters identification algorithm

Abstract

It is difficult for least square method (LS) to deal with the ill-conditioned matrix of nonlinear polynomial model. In the case of the higher order of system, the matrix inversion is very complicated. A new approach based on LS is present which is combined with mirror-injection algorithm in order to obtain polynomial parameters identification of nonlinear system model. The columns of coefficient matrix of the inconsistent equations of nonlinear polynomial model are orthogonalized. The novel method avoids the high-order matrix inversion and ill-conditioned matrix problem. The precision and velocity of identification are improved, while the computation load is low simultaneously. Performance analysis is carried out using MATLAB simulation. The results prove the effectiveness of the proposed approach.