KNN-based distribution network ground fault identification method

Abstract

The invention provides a KNN-based distribution network ground fault identification method comprising steps of obtaining the zero-sequence current waveform data of different fault causes through an artificial grounding test or field actual fault recording, extracting five feature parameters representing the different fault causes and including the self-recovery, the transition time, the zero-current time, the distortion degree and the random degree to form a feature sample database; and when a fault occurs, calculating the above features of an input waveform and searching for a cause categoryof the fault by an KNN algorithm. The method, on the one hand, can focus on the fault cause before fault inspection so as to formulate a targeted inspection scheme, greatly improve fault finding efficiency and reduce power outage loss; on the other hand, can accurately obtain the distribution law of the distribution network fault causes of a certain supply area, creates hidden danger treatment andfault prevention measures, promotes the improvement in the level of distribution network operation and maintenance management, and improves the feature sample database with an increase in the numberof fault samples and features so as to achieve a high recognition success rate.

Description

technical field [0001] The invention relates to the field of diagnosis of grounding faults of distribution networks, in particular to a KNN-based identification method for grounding faults of distribution networks. Background technique [0002] The fault recording data obtained by the transient wave recording type power distribution terminal and the grounding line selection device record the transient and steady-state electrical quantity change information on the line before and after the fault occurs, conduct in-depth analysis on it, and dig out the characteristics that characterize the cause of the fault It is the key to realize the identification of the cause of the fault. Its significance lies in: on the one hand, by focusing on the cause of the fault before the fault inspection, a targeted inspection plan can be formulated, which can greatly improve the efficiency of fault finding and reduce power outage losses; on the other hand, it can accurately grasp the cause of th...

AI Technical Summary

Problems solved by technology

Previous studies mainly focused on the non-electrical characteristics of faults, such as analyzing the historical occurrence time, geographical location, weather conditions and other temporal and spatial characteristics of lightning strikes, tree barriers and other fault causes, and looking for the relationship between fault characteristics and causes to evaluate The occurrence probability of faults and corresponding preventive measures have been proposed, but the correlation between fault electrical characteristics and causes has not been focused on, and it is difficult to trace the source, which is significantly affected by factors such as geography and meteorological environment in different regions

In recent years, with the large-scale construction and application of distribution network automation systems, the means of obtaining fault information have become increasingly abundant. Based on characteristic information such as fault arc voltage amplitude, current attenuation coefficient, and phase plane clustering, the fault electrical and There has been some progress in the research of fault cause identification based on quantitative features, but the number of features used in the identification process is limited, which limits the accuracy of identification to a certain extent.

Images