Nonlinear model predictive control of MIMO system with Least squares support vector machines and Particle swarm optimization

Abstract

This paper demonstrates control accuracy and computational efficiency of nonlinear model predictive control (NMPC) strategy which utilizes a deterministic sparse kernel learning technique called Support vector regression (SVR) and particle swarm optimization wuth controllable random exploration velocity (PSO-CREV). An accurate reliable nonlinear model is first identified by SVR witha radial basis function (RBF) kernel and then the optimization of control sequence is speeded up by PSO-CREV. An improved system performance is quaranteed by an accurate sparse predictive model and an efficient and fast optimization algorithm. To compare the performance, model predictive control (MPC) using neural network (NN) model is done on a highly nonlinear distillation column with severe interacting process cariables. SVR based MPC shows improved tracking performance with very less computational effort which is much essential for real time control.