Neural Network Dynamic Surface Backstepping Control for the Speed and Tension System of Reversible Cold Strip Rolling Mill

Abstract

AbstractTo weaken the influences of uncertainties and system coupling items on the coordinated tracking control performance of the speed and tension system of a reversible cold strip rolling mill, a control strategy is proposed based on nonlinear disturbance observers (NDOs), dynamic surface backstepping control, and neural network adaptive approximation. First, the transformation form of the system model is given, and then NDOs are developed to counteract the unmatched uncertainties. Next, controllers for the speed and tension system are presented by combining backstepping with dynamic surface control. Again, the neural network adaptive method is used to approximate the matched uncertainties of the system, and the approximation values are introduced into the designed controllers for compensation. Finally, simulation research is carried out on the speed and tension system of a 1422 mm reversible cold strip rolling mill by using the actual data, and the results show the validity of the proposed control strategy in comparison with the decentralized overlapping control strategy.