Location method of single-phase ground fault section in 10kv distribution network

Abstract

A method for locating single-phase grounding faults in a 10kV distribution network, obtains the inherent characteristics of the distribution network and the fault location condition characteristics and result characteristics in the historical fault records from the power distribution and consumption information data source of the power grid; The inherent characteristics of the power grid are used as the input of the self-organizing mapping neural network SOM for clustering, and the distribution networks with similar characteristics are clustered into one class; the fault location condition features and result features of each type of distribution network are used as the generalized regression neural network. The input of GRNN is trained to obtain the fault location model of each type of distribution network; when a single-phase ground fault occurs in the distribution network during operation, according to the cluster category to which the faulted distribution network belongs, the distribution network The fault location condition characteristics of each power supply section of the network are input into the distribution network fault location model corresponding to this category, and the fault location result is obtained. The invention has wide data sources, high fault tolerance, and can quickly and accurately locate the faulty section.

Description

technical field [0001] The invention relates to the field of power grid operation management, in particular to a method for locating a single-phase ground fault section of a 10kV distribution network. Background technique [0002] The most prone fault in distribution network is single-phase-to-ground short-circuit fault (hereinafter referred to as single-phase-to-ground fault). Most of the 10kV distribution network in my country adopts the low-current grounding method. After a single-phase ground fault occurs, the line voltage is still symmetrical and the fault current is small. Although it does not affect the continuous power supply to the load temporarily, long-term operation may cause the fault to expand or damage electrical equipment. , so finding the fault location quickly and accurately is of great significance to the safe and stable operation of the distribution network. However, due to the large number of branch lines of the 10kV distribution network, it is difficult...

AI Technical Summary

Problems solved by technology

Most of the matrix algorithms are based on the monitoring devices installed in the distribution network, and need to use the signals monitored by fault indicators and feeder terminal units (FTU) for positioning, which largely depends on the distribution network FTU configuration, and due to The outdoor environment is harsh and misreporting is prone to occur. In addition, because only a single indicator is used and the fault tolerance is not high, positioning errors often occur

There are many branch lines in the 10kV distribution network, and the traveling wave method is easily affected by the transition resistance and the operation mode of the power grid, and because the wave velocity of the traveling wave in the hybrid line of the cable and the overhead line is inconsistent, and the traveling wave will frequently reflect at many line branch points , these will have a great impact on the accuracy of fault location

Images