为实现对电液伺服系统非线性、不确定性和未建模动态等因素的有效补偿,将系统转换成具有自适应动态递归模糊神经网络(ADRFNN)辨识误差,即二次不确定性的等效线性数学模型,利用增益自适应滑模变结构控制(GASMC)方法对系统进行综合设计.实验结果表明:ADRFNN的高精度在线辨识和GASMC校正项的增益自适应功能使系统具有较强鲁棒性和更高的稳态精度,同时使系统控制量的颤振现象得到有效抑制. In order to realize the effective compensation of electro-hydraulic servo system such as nonlinearity, uncertainty and unmodeled dynamic, the system is transformed into an adaptive dynamic recursive fuzzy neural network (ADRFNN) identification error, that is, second-order uncertainty Efficiency linear mathematic model and the GASMC method is used to design the system.The experimental results show that the high-precision on-line identification of ADRFNN and the gain adaptive function of GASMC correction make the system robust Sexual and higher steady-state accuracy, while the amount of system flutter control effectively suppressed.