Nonlinear model predictive control based on support vector machine and genetic algorithm

This paper presents a nonlinear model predictive control (NMPC) approach based on support vector machine (SVM) and genetic algorithm (GA) for multiple-input multiple-output (MIMO) nonlinear systems. Individual SVM is used to approximate each output of the controlled plant. Then the model is used in MPC control scheme to predict the outputs of the controlled plant. The optimal control sequence is calculated using GA with elite preserve strategy. Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.

Model Predictive Control (MPC) has attracted more and more attention from academia and industry. However, the linear models widely used in MPC are usually not competent for industrial processes with high nonlinearity or large operating range. In this paper, Support Vector Machine (SVM) is adopted to model the nonlinear system, which brings a better modeling performance than neural network. Genetic Algorithm (GA) with elite preserve strategy, which does not need model linearization or objective functions derivative, is used to calculate the optimal control sequence. The two algorithms are integrated into the new nonlinear MPC control scheme for MIMO nonlinear system. Simulation results of a typical MIMO nonlinear system show that this new control scheme has a good ability of set points tracking and disturbance rejection.Figure optionsDownload as PowerPoint slide