基于GRNN神经网络的变压器励磁涌流识别方法

A method to identify excitation inrush current of transformer based on GRNN neural network

为了提高变压器差动保护识别励磁涌流与内部故障电流的能力,提出一种基于广义回归神经网络(GRNN)的变压器励磁涌流识别方法。首先通过全波傅里叶算法求得差动电流的特征量作为训练样本,然后利用交叉验证法寻找出GRNN神经网络的扩展常数spread的最优值,同时也计算出训练样本的最佳输入、输出值。由这些参数构建出识别励磁涌流的神经网络,仿真结果表明:GRNN神经网络收敛性好,运算速度快,并且预测输出精度非常高,能准确、有效、快速的识别出励磁涌流与内部故障电流。

In order to improve the ability of transformer differential protection to identify excitation inrush current and internal fault current,a new method to identify excitation inrush current of transformer based on generalized regression neural network（ GRNN） is proposed. Firstly,the full wave Fourier algorithm is used to calculate differential current characteristics as training samples,then,the cross validation method is used to find out optimal value of spread parameter of the GRNN neural network,meanwhile,the best input and output value of the training sample are calculated. A neural network for identifying excitation inrush current is constructed by these parameters,the simulation results show that the GRNN neural network has a good convergence,fast calculation and the prediction output precision is very high,which can accurately,effectively and rapidly identify the excitation inrush current and internal fault current.