Neuro predictive control of a heat exchanger: comparison with generalized predictive control

In this paper, a neural network-based predictive controller is designed to govern the dynamics of heat exchanger process. Heat exchanger is a highly nonlinear process; therefore, a nonlinear prediction method can be a better match in a predictive control strategy. Advantages of neural networks for the process modeling are studied and a neural network based predictor is designed, trained and tested as a part of the predictive controller. The neuro predictive controller is utilized in setpoint tracking of a heat exchanger plant. The performance of the proposed controller is compared with that of Generalized Predictive Control (GPC) through simulation studies. Obtained results demonstrate the effectiveness and superiority of the proposed approach.