基于神经网络补偿的二自由度PID控制

Two-degree-of-freedom PID control based on neural network compensation

提出一种基于神经网络补偿的二自由度PID控制方法。该方法将BP网络应用到传统二自由度PID控制中,克服了参数固定不变时,系统跟随性能和抗扰性能变差的缺点,有效地减弱了参数摄动对系统造成的影响,改善了系统的动态品质。仿真结果表明该方法的有效性。

The parameters of the traditional regulator are fixed as it was designed, and couldn't vary with the control objects. In this paper, a BP network is introduced into the traditional two-degree-of-freedom PID control system. The new method reduces the effect of parameter variations and improves the dynamic characterisitcs greatly. Simulation results show the validity of the new method.