Neural network–based adaptive sliding mode control of three-dimensional double-pendulum overhead cranes with prescribed performance

Abstract

In order to tackle the uncertainties encountered in the operation of three-dimensional (3D) overhead crane systems and enhance the overall robustness of the control system, an adaptive sliding mode control (SMC) method based on prescribed performance is proposed in this work. Specifically, an integral sliding mode controller (ISMC) based on prescribed performance is designed for the 3D overhead crane dynamics model with double-pendulum effect, which is used to constrict system error. By considering the case of model uncertainty, time-varying parameters, track friction, and so on, the neural network (NN) is employed to estimate unknown terms in the controller design, and the Lyapunov function is applied to analyze the stability of the close-loop system. The results demonstrated that the proposed method can effectively improve the positioning accuracy and payload swing suppression performance of the overhead crane system, and also improve the robustness of the control system to deal with uncertainties.