基于小波包变换的模糊神经网络小电流接地系统故障选线

根据小波包变换和模糊神经网络的特点，提出了基于小波包变换模糊神经网络的一种小电流接地系统单相接地故障选线方法，即利用经过接地后零序电流训练的小波模糊神经网络来判别接地线路。该方法适用于任何小电流接地系统，并且不受负荷谐波、暂态过程、故障点过渡电阻等因素的影响，从理论上解决了传统方法选线准确率低的问题。EMTP仿真计算结果表明，该方法是准确和可靠的，具有实用潜力。

Discrimination of Fault Line Based on Wavelet Packet and Fuzzy Neural Networks in Distribution Systems

According to the characteristic of wavelet packet transformation and fuzzy neural network, this paper proposed a new method of discriminating fault line for single-phase ground in distribution system based on the wavelet packet transformation and fuzzy neural network. The wavelet packet fuzzy neural network trained by the post fault zero sequence current is used to discriminate the fault line. This method is suitable for any distribution system, not influenced by load harmonic, transient process and transient resistance of the fault point. This mothod in theory solves the problem of the traditional methods that select fault line incorrectly. The EMTP simulation shows that the proposed method is accurate and reliable, and has great application potential.