Fault arc recognition method based on extraction current features

Abstract

The invention relates to a fault arc recognition method based on extraction current features. The fault arc recognition method based on extraction current features includes the steps: training a BP neural network by using the wavelet energy corresponding to the loop current in the normal state and the fault arc state to obtain a BP classification network based on current features, and performing fault arc recognition by using the BP classification network. The fault arc recognition method based on extraction current features effectively integrates the wavelet decomposition technology with theBP neural network intelligent algorithm, fully utilizes the advantages of wavelet decomposition to reflect the time-frequency domain change of the signal, and combines with the intelligent and accurate classification effect of the BP neural network to realize fast and accurate arc detection and improve the current fault arc detection level, so as to preferably guarantee the safe and reliable operation of power equipment, bring better benefits to the development of the power industry, and has very important practical significance for the safe, reliable and stable operation of the power grid.

Description

technical field [0001] The invention relates to the field of electrotechnical technology, in particular to a method for identifying an electric circuit fault arc. Background technique [0002] In the power grid, arcs will occur due to aging and damaged equipment insulation, damaged circuit components, accidental circuit breaks, etc. If not found in time and effective measures are taken, it will cause fires and other accidents, causing huge damage to personnel and equipment. When an arc fault occurs, the fault current will usually be distorted. At the same time, the arc fault distortion will be reflected differently under different loads, and there is a large randomness and uncertainty. The existing relays and circuit breakers cannot effectively detect the fault arc. Identification, can not play the role of protecting lines and electrical appliances. Therefore, the rapid and effective identification of fault arc is of great significance to realize the comprehensive protectio...

AI Technical Summary

Problems solved by technology

However, these three types of methods also have their own defects, which are as follows: (1) The parameters of the arc model cannot be obtained accurately, resulting in the inability to establish an accurate mathematical model; (2) To detect the physical phenomenon when the arc occurs, it is necessary to install the monitoring equipment To the vicinity of the fault point, it is impossible to monitor some independent small equipment; (3) detect the arc according to the current and voltage changes when the fault arc occurs. Many existing method models are mostly only for a single load. an accurate diagnosis cannot be made

Images