Series arc fault online detection method and device

Abstract

The invention discloses a series arc fault on-line detection method and device, and the method employs loop current and power voltage signals of a three-phase motor, carries out the grouping of collected signals to determine the number of phases where an arc fault happens, and facilitates the quick troubleshooting of the arc fault. Then power supply harmonic waves and load noise in the current andvoltage signals can be separated by using a kernel principal component analysis method, a fifth principal component and a sixth principal component with obvious fault characteristics are selected tocarry out characteristic analysis, and the kurtosis and skewness of the fifth principal component and the kurtosis and skewness of the sixth principal component are taken as four-dimensional fault characteristic vectors; a firefly algorithm is adopted to optimize penalty coefficients and kernel function parameters of a support vector machine, a feature vector set is used for training the optimizedsupport vector machine to obtain a series fault recognition model, loop current and power supply voltage signals are collected in real time and input into the series fault recognition model to achieve real-time detection of series faults. The method has a fault positioning function and is high in fault identification accuracy.

Description

technical field [0001] The invention relates to the technical field of on-line detection of series arc faults, in particular to a method and device for on-line detection of series arc faults. Background technique [0002] In the coal mine underground power supply system, due to the humidity of the environment, mechanical vibration, electric repulsion, and the pulling of cables when moving electrical equipment, electrical connectors will be corroded, loose and other faults. In severe cases, arc discharge will occur, and even fire accidents. According to incomplete statistics, more than 70% of mine cable fire accidents are caused by local overheating of cables caused by series arc faults. [0003] At present, there are two main types of series arc fault detection methods: one is to detect series arc faults through physical effects such as arc sound, arc light, electromagnetic radiation, etc. when series arc faults occur. This method is only suitable for online detection of spe...

AI Technical Summary

Problems solved by technology

[0004] Underground coal mines, motors and frequency converters are widely used as load equipment. It also contains rich harmonic components, coupled with the serious electromagnetic noise interference generated by other equipment, resulting in a low accuracy rate of online detection of series arc faults in the load circuit of motors in underground mines, and there are cases of false fault

Images