采用EMD谱带通滤波和近似熵识别的配电网单相接地故障区段定位新方法

A New Single-Phase Grounding Fault Location Approach in Distribution Network Based on EMD Spectrum Band-Pass Filter and Approximate Entropy

配电网单相接地故障定位技术,是提高配电网供电可靠性的关键。在研究接地故障暂态特征的基础上,结合经验模态分解(EMD)和近似熵方法,提出了一种基于暂态零模电流的定位新方法。该方法利用故障点上下游暂态电流差异大、故障点同侧暂态电流基本相同的特征,首先用EMD方法把电流信号分解为多个内在的频带分量,然后求取其近似熵值并利用K均值聚类综合判断故障区段。该方法通信传输量小,能够克服幅值小、噪声大等不利因素,很好地实现故障信号特征的定量提取,比传统近似熵算法的定位准确度更高。最后通过仿真和现场录波验证了该方法的有效性。

The location technology for single-phase grounding fault is a key work to improve power supply reliability.Combined with EMD and approximate entropy,this paper studies transient characteristics in grounding fault,proposing a new approach for transient zero-module current faulty section location.The proposed approach is on the basis of the fact that the transient currents of upstream and downstream of fault points are very different,and transient currents of the same side of fault points are basically the same.The current signal is decomposed into several intrinsic frequency components by EMD,then approximate entropy is calculated,and the fault location is detected by using the K-means clustering.This approach can well realize the quantitative extraction of power faulty signals under the condition of shore time-series,small magnitude and so on.Therefore,it has better accuracy than tradition approximate entropy in fault location.Finally,the effectiveness of this method is verified by simulation and field data.