Dynamic prediction and control of heat exchangers using artificial neural networks

We extend the artificial neural network (ANN) technique to the simulation o f the time-dependent behavior of a heat exchanger (HX) and use it to contro l the temperature of air passing over it. The experiments are carried out i n a open loop test facility. First a methodology is proposed for the traini ng and prediction of the dynamic behavior of thermal systems with heat exch angers. Then an internal model scheme is developed for the control of the o ver-tube air temperature with two artificial neural networks, one to simula te the heat exchanger and another as controller. An integral control is imp lemented in parallel with the filter of the neural network controller to el iminate a steady-state offset. The results are compared with those of stand ard PI and PID controller. There is less oscillatory behavior with the neur al network controller, which allows the system to reach steady-state operat ing conditions in regions where the PI and PID controllers are not able to perform as well. (C) 2001 Elsevier Science Ltd. All rights reserved.