Neural Network Based Adaptive Backstepping Control for Electro-Hydraulic Servo System Position Tracking

The modeling uncertainties and external disturbances of electro-hydraulic servo system (EHSS) deteriorate the system's trajectory tracking performance. To cope with this issue, an adaptive backstepping controller based on neural network (NN) is proposed in this paper. A radial-basis-function neural network (RBF NN) is constructed to approximate the lumped uncertainties caused by modeling uncertainties and external disturbances, where the adaptive law is adopted to adjust controller parameters online. The backstepping control is used to eliminate mismatched nonlinear terms and stabilize the system. The dynamic surface control (DSC) is adopted to handle the "explosion of complexity" problem of backstepping method and reduce the computational burden. Compared to the traditional backstepping control, the proposed control scheme improves the steady-state tracking precision and makes the control signal smaller. In addition, the stability analysis shows that the tracking error can asymptotically converge to zero in the face of time-varying unknown dynamics. Simulation and experiment results demonstrate the effectiveness of the controller in term of tracking accuracy and disturbance rejection in comparison with other controllers for the EHSS.