Small current grounding system multicriteria fault line selection method based on radial basis function network

The invention discloses a small current grounding system multicriteria fault line section method based on a radial basis function (RBF) network. For small current grounding system fault line section,zero sequence current signals under different fault conditions are adopted, a fundamental wave characteristic component, a fifth harmonic characteristic component, an active component and a transientstate component are extracted, the components are input into an RBF neural network, and structure parameters of the RBF network are trained by utilizing a differential evolution (DE) algorithm, thus optimal parameters of the RBF neural network are obtained. Test results show that the RBF network trained by virtue of the DE algorithm is high in convergence rate and small in output error, and a built line selection model has high accuracy and is not influenced by various fault conditions. 本发明公开了一种基于径向基(RBF)网络的小电流接地系统多判据故障选线方法。针对小电流接地系统故障选线，采样不同故障条件下的零序电流信号，提取基波特征分量、5次谐波特征分量、有功分量及暂态分量，输入RBF神经网络，并利用差分进化算法(DE)对RBF网络结构参数进行训练