Series fault arc detection device and method based on convolutional neural network

Abstract

The invention provides a series fault arc detection device based on a convolutional neural network. The series fault arc detection device comprises a line current signal acquisition unit, a data processing unit, a fault arc model construction unit and a result output unit. The line current signal acquisition unit acquires and converts arc current data; the data processing unit arranges the arc current data into a current sample data set; and after an arc current database is established, a sample training set and a sample test set are formed. The fault arc detection model construction unit carries out normalization processing on the samples and constructs a series fault arc detection model based on a convolutional neural network for training and testing to obtain a trained series fault arcdetection model. The result output unit acquires arc current data to be detected and imports the arc current data to be detected into the trained series fault arc detection model to determine whetherthe arc current data to be detected are series fault arcs. The series fault arc detection device and method have the characteristics of strong generalization ability, high detection accuracy, low misjudgment rate and the like.

Description

technical field [0001] The invention relates to the technical field of arc detection, in particular to a device and method for detecting series fault arcs based on a convolutional neural network. Background technique [0002] Arc, commonly known as "electric spark", has the characteristics of high temperature, small current, and short duration. It is a gas free discharge phenomenon caused by electric breakdown of gas due to excessive electric field strength. will appear frequently. Because the arc discharge will generate a lot of heat, which can ignite the surrounding flammable and explosive products, causing fire or even explosion, so the fault arc is identified as an important cause of electrical fires, and it is necessary to conduct in-depth research on fault arc detection. [0003] Arc faults are mainly divided into three types, including series fault arcs, parallel fault arcs and ground fault arcs. Among them, the series fault arc is more difficult to detect and relat...

AI Technical Summary

Problems solved by technology

[0005] Although the above research on arc faults can detect arc faults to a certain extent, when the power environment changes and the threshold value changes, it is easy to cause misjudgment.

Images