Model reference adaptive control of electro-hydraulic servo system based on RBF neural network and nonlinear disturbance observer

For the electro-hydraulic servo systems (EHSS) subjected to parameter uncertainties and unknown load disturbances, a model reference adaptive controller (MRAC) is proposed in this paper. Based on radial basis function neural networks (RBF NN) and nonlinear disturbance observer (NDO), it ensures a high performance in tracking output to the reference model. Firstly, a nominal MRAC is developed using Liapunov theory. In addition, a RBF NN is constructed to approximate parameter uncertainty and other nonlinear functions online. Then, the NDO is devised to estimate the nonlinear terms containing unknown load disturbances and compensate for disturbance. Besides, the stability of the closed-loop system is analyzed. Finally, the proposed controller is simulated and experimentally verified. According to the simulation results, the control method proposed in this paper is advantageous over other controllers in improving the accuracy of position tracking and enhancing the robustness of the system. Moreover, the superiority of this control method is demonstrated by the experimental results.