The digital hydraulic cylinder position control based on neural network sliding mode active disturbance rejection control

Abstract Due to the multiple nonlinear composite disturbance problems such as gap, friction, hydraulic spring force and external load disturbance force in the double closed-loop digital hydraulic cylinder position control system, traditional or single structure controllers have no obvious effect on improving the performance of this complex nonlinear system. In this paper, the high-order state equation is obtained for the existing mathematical model of the double closed-loop digital hydraulic cylinder. Then, using ADRC, the high-order double closed-loop digital hydraulic cylinder control system is equivalent to a second-order integral series control system. Applying sliding mode variable structure control to ADRC, in order to improve the control accuracy of the sliding mode controller and reduce the influence of chattering, utilizing the external disturbance in the ESO observation system in ADRC, a control term f ( x ) in the system, which is an uncertain nonlinear variable due to the time-varying and unknown internal parameters of the system. RBF neural network is used to approximate f ( x ). Based on this, the RBF neural network sliding mode active disturbance rejection control strategy (RBFSMADRC) is proposed. The control law and adaptive law of the system are derived based on the Lyapunov method, and the stability of the whole closed -loop system is ensured by adjusting the size of the adaptive weight. Specifically, the effectiveness of the proposed control method is validated through simulation and experimentation.