论文部分内容阅读
设计了一个三层ＢＰ神经网络，对有功功率反馈参与控制的水轮机调节系统，以其典型工况下的最优ＰＩＤ系数作为训练样本，对所设计的ＢＰ神经网络进行离线训练，进而构成一个基于ＢＰ神经网络的变参数ＰＩＤ控制器；利用ＢＰ神经网络的函数逼近能力来实现ＰＩＤ控制器在线调整，以达到优化控制的目的。对简单电力系统的仿真结果表明，这种控制器与常规ＰＩＤ控制器相比可以取得较好的控制效果，是实现水轮机调节系统自适应控制的一种可行的方法。
A three-layer BP neural network is designed to control the hydraulic turbine governing system with active power feedback. With the best PID coefficients under typical conditions as the training samples, the designed BP neural network is trained offline, BP neural network variable parameter PID controller; the use of BP neural network function approximation ability to achieve online adjustment of PID controller in order to achieve the purpose of optimal control. The simulation results of the simple power system show that this kind of controller can get a better control effect than the conventional PID controller and is a feasible method to realize the adaptive control of the turbine governing system.