Online Support Vector Regression Predictive Control Algorithm Based on Particle Swarm Optimization

For the problems of model mismatch and difficulty in solving objective function in the predictive control of the nonlinear system model, an online support vector regression predictive control algorithm based on particle swarm optimization (PSO) is proposed. An nonlinear predictive model for the object is built based on the online support vector regression, and the object is identified and the identified model also can be self-adjusted through online learning. Meanwhile, the objective function is solved by PSO, the rolling optimization is realized. The nonlinear system simulation results show the effectiveness and adaptability of the presented algorithm.