发电机进相能力的RBF神经网络模型

发电机进相运行是调节电网电压、改善电能质量的一种经济性、技术性皆优的先进手段。由于发电机是一个多变量、强耦合的非线性系统,基于传统分析方法难以精确建立其进相能力分析模型,本文提出基于径向基函数(RBF)神经网络的发电机进相能力模型,以发电机有功功率和无功功率为输入,以发电机功角、电网电压为输出,采用江苏电网某600MW发电机进相试验数据训练和测试RBF网络,并探讨了基宽、神经元数的选择对RBF网络收敛精度的影响。研究表明本文所建立的发电机进相RBF模型具有速度快、精度高的优点,具有良好的泛化能力,其性能优于BP神经网络模型。本文提出的方法能有效克服传统进相分析方法的局限性,适用于发电机进相运行实时控制,有推广应用价值。

Generator Leading Phase Ability Model Based on RBF Neural Network

Generator leading phase operation is a kind of economic and effective measures of voltage regulation and power quality improvement.Due to the synchronous generator is a multivariable and strong coupling nonlinear system,it is difficult to obtain satisfactory results by traditional analysis method.This paper proposes a new method of modeling generator leading phase ability based on radial basis function(RBF) neural network.The model with active power and reactive power of generator for input,with generator voltage and power-angle for output,using a 600 MW generator leading phase test data training RBF neural network and testing network generalization ability,the choice of the base wide,the number of neurons in hidden layer in RBF network convergence precision influence are discussed.Research shows that this generator leading phase RBF model set up in the paper has the advantages of high speed and precision,and its performance is superior to the BP neural network model.