具有遗传算法优化BP神经网络调节的HVDC PID控制器设计

高压直流输电(HVDC)定电流控制是直流输电系统的控制方式之一,为了使HVDC PID控制器具有较好的自适应性,实现控制器参数自动调整,提出一种具有遗传算法优化BP神经网络调节的HVDC PID控制器。该控制器首先利用遗传算法对BP神经网络的初始权值进行优化,再利用BP神经网络对PID三个参数进行在线调整。仿真研究表明:具有遗传算法优化BP神经网络调节的PID控制器可以保证系统动态响应具有较好的快速性和对系统扰动的自适应性,是可行的。

Design of HVDC PID Controller with BP Neural Network Optimized by Genetic Algorithm

In order to make HVDC PID controller have a good adaptivity and automatically adjust the controller parameters,a kind of HVDC PID controller with BP neural network optimized by genetic algorithm was proposed.The controller first employed the genetic algorithm to optimize BP neural network＇s initial weights,then to adjust three PID parameters on-line.The simulation results demonstrate that HVDC PID controller can ensure the closed-loop system＇s better dynamic response and the adaptation to the disturbance.