Dynamic neural network based nonlinear adaptive control for a distillation column

In this paper, a dynamic neural network is used to learn the input-output behaviors of a binary distillation column by combining the mechanistic property. The model can be online identified. The weight-training algorithm is proposed. The convergence of the algorithm is discussed by using the Lyapunov method. Based on the identified model, a nonlinear adaptive controller is designed, which can preserve the stability and robustness of the closed loop system. Some simulation results are illustrated to show the effectiveness of the controller.