Open AccessLeast squares support vector machine method for load identification of nonlinear system
Author(s) -
Pan Zhou,
Jianghui Xin,
Weiyan Shang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1798/1/012036
Subject(s) - nonlinear system , least squares support vector machine , inverse , support vector machine , least squares function approximation , computer science , system identification , identification (biology) , inverse problem , control theory (sociology) , mechanical system , algorithm , non linear least squares , mathematics , artificial intelligence , estimation theory , data modeling , mathematical analysis , physics , statistics , geometry , botany , control (management) , quantum mechanics , database , estimator , biology
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.