Least squares support vector machine method for load identification of nonlinear system

Abstract

In order to eliminate the dependence of load identification problem on the prior knowledge of current mechanical system, least squares support vector machine was applied to identify the inverse model of nonlinear system, and then based on this inverse model operational responses were adopted to determine real time excitation force. A nonlinear system was applied to conduct the simulation and calculate the steady and unsteady input force in this paper to verify the validity of the proposed method. Simulation results reveal that least squares support vector machine is able to identify reliable inverse model of nonlinear system and then reconstruct accurate real time excitation force. According to the present approach, a small quantity of training samples is needed rather than complete knowledge of the mathematical model and parameters of nonlinear system, so this approach can be extended to engineering application.