提出一种基于滑模的神经元网络自适应控制方法,并把它应用于液压伺服系统的位置控制.基于滑模学习策略,根据从一优化了的滑模控制所得到的系统输入/输出信号,设计一神经元网络,离线训练该神经元网络的权值,然后综合一简单的自适应环节,得到完整的基于滑模的神经元网络自适应控制.仿真实验结果表明,相对于纯优化的滑模控制而言,所提出的控制方法能使系统具有响应速度快,控制精度高的特点,综合控制效果明显. A sliding mode based neural network adaptive control method is proposed and applied to the position control of hydraulic servo system.Based on the sliding mode learning strategy and according to the system input / output signal obtained from an optimized sliding mode control , A neural network is designed, the weights of the neural network are trained offline, and then a complete adaptive control based on the sliding mode neural network is obtained by integrating a simple adaptive algorithm.The simulation results show that, compared with the purely optimized For sliding mode control, the proposed control method can make the system have the characteristics of fast response and high control precision, and the comprehensive control effect is obvious.