Model predictive engine control using support vector machine

This paper proposes a model predictive control strategy for the engine control. A data-driven modelling approach called support vector machine is used for modelling engine dynamics. More precisely, the engine model is developed by mapping the rotation speed as a function of fuel flow rate. Based on the SVM model, a model predictive controller is designed using Model Predictive Control Toolbox. The SVM model and the model predictive controller are implemented in the MATLAB/SIMULINK environment. Simulation results demonstrate the effectiveness of the model and the controller. The rotation speed is able to be maintained during abrupt changes in the load.