Adaptive neural network model based nonlinear predictive control of a fluid catalytic cracking unit

Neural Networks are used for a wide variety of chemical applications because of their ability to learn system features. This paper presents the use of artificial neural networks (ANN) for dynamic modeling and nonlinear model predictive control of a fluid catalytic unit (FCCU). An off-line trained ANN model based predictive control structure (NNMPC) and on adaptive neural network model based predictive control (ANNMPC) scheme were tested. Both control structures give a superior control performance compared to the classical proportional-integral (PI) controllers. To improve the convergence of the optimization process in both the off-line or on-line training of the ANN model and in the on-line control problem the use of genetic algorithm (GA) in combination with the classical optimization algorithms was proposed.