Supervisory predictive control based on least square support vector machine and improved particle swarm optimization

Abstract

Least square support vector machine is a kind of thought to solve structural risk minimization method, which is used for system identification, nonlinear control, and fault diagnosis, and has important research value. Based on the identification function of least square support vector machine, according to the identified parameters, which are used in supervisory predictive control algorithm, and for function optimization problems, particle swarm optimization algorithm is used to solve the dynamic setpoint optimization problems. Simulation results show that least square support vector machine algorithm learns fast, has good nonlinear modeling and generalization ability, and the supervisory predictive control algorithm based on least square support vector machine and the particle swarm optimization has better control performance.