某新型电液伺服系统神经网络自抗扰控制

Neural Network Based Active Disturbance Rejection Control of Novel Electro-hydraulic Servo System

针对某新型同源平衡及定位电液伺服系统,设计了一种基于RBF神经网络在线整定ESO参数的神经网络自抗扰控制器(NNADRC)。利用RBF神经网络在线整定可调误差校正增益,实现非线性特性的实时、精确估计和补偿。数值仿真结果表明,NNADRC控制的稳态精度明显高于ADRC控制,且对外部负载扰动和内部参数摄动具有良好的鲁棒性,可以实现电液伺服系统的快速、平稳、高精度、无超调稳定控制。

Aiming at simultaneous balancing and positioning of the electro-hydraulic servo (EHS) system,a novel neural network based active disturbance rejection control (NNADRC) strategy is developed.In the NNADRC,the radial basis function (RBF) neural network is employed in on-line updating parameters of the extended state observer (ESO).By on-line updating the estimator gains of the ESO,the real time and accurate estimation and compensation can be made for the nonlinear behavior and external disturbance of the system.The effectiveness and efficiency of the system are critically investigated by numerical simulations.The results show that compared with the conventional ADRC strategy,its stability and robustness are better and its accuracy is higher. It is of fast,stable,smooth and accurate control function.