论文部分内容阅读
基于有功功率反馈参与控制的水轮机调节系统，以几个典型工况下的最优ＰＩＤ系数作为训练样本，训练了一个三层ＢＰ神经网络，设计了一个用ＢＰ神经网络实现变参数的ＰＩＤ控制器；并构造了一个目标函数，设计了一个自适应神经元，利用神经元的自学习功能，在线优化控制器的输出，以期达到最优控制的目的。对简单电力系统的仿真结果表明，这种控制器可以达到较常规的变参数ＰＩＤ较好的控制效果，是实现水轮机调节系统自适应控制的一种可行的方法。
Based on the PID control system with active power feedback control, a three-layer BP neural network is trained with the optimal PID coefficients of several typical operating conditions. A PID controller with variable parameters is designed by BP neural network An objective function is designed and an adaptive neuron is designed. The neuron self-learning function is used to optimize the output of the controller online in order to achieve the optimal control. The simulation results of simple power system show that this kind of controller can achieve better control effect than the conventional variable parameter PID and is a feasible method to realize the adaptive control of turbine governing system.