Keywords:

Abstract:

This paper presents a simulation of heat exchanger temperature controlling using adaptive neuro-fuzzy technique. Heat exchanger is a highly nonlinear process; therefore, a nonlinear prediction method can be a better match in a predictive control strategy. An adaptive neuro-fuzzy based predictive controller is designed to govern the dynamics of a heat exchanger pilot plant. Advantages of neural networks and fuzzy logics for the process modeling are studied and a neuro-fuzzy based predictor is designed, trained and tested as a part of the predictive controller. The dynamics of the plant is identified using a backpropagation neural network. The predictive control strategy based on the neuro-fuzzy model of the plant is applied then to achieve set point tracking of the output of the plant. Simulations have been carried out using the Matlab-Simulink software. Obtained results demonstrate the effectiveness and superiority of the proposed approach.