负载模拟器的DRNN神经网络控制

DRNN NEURAL NETWORK CONTROL ON ELECTRO-HYDRAULIC LOAD SIMULATOR

为了增强负载模拟器的自适应能力以抵抗系统的非线性、时变参数及运动扰动的影响,特提出利用对角回归神经网络(DRNN)与PID的并联进行控制与调节的控制方法。PID保证了系统的初始稳定性,由于神经网络引入了速度信号作为参考输入,使系统具有了很好的自适应消扰能力,减小了多余力的影响。仿真和试验证明了该方法的可行性和有效性,收到了很好的控制效果。

A new control structure for load simulator to improve its performance is presented, in which the DRNN neural network is adopted to combine with PID controller. The DRNN is of ability to deal with dynamic problem, which is used to identify the broad sense inverse model. It includes system input, output and disturbance. The nonlinear problem will be solved properly. The neural network PID controller is designed by requirement for steady, which overcome the shortcoming of the only neural network controller. The speed is taken as reference input of the DRNN neural network, which improves the system's robustness to the influence of extraneous force. The simulation and experiment are carried out, which show a good result. This method is of validity and robustness.