基于多维度特征提取的电弧故障检测方法

针对当前含多种电气故障的复杂电路电弧故障识别率低、训练速度慢的问题,提出一种窗口划分结合小波分解与经验模态分解(empirical mode decomposition,EMD)分别从时域、频域及时间尺度等多个维度提取电流特征量,利用机器学习分类模型进行电弧故障识别的方法.首先,利用搭建的电气故障实验平台采集故障及正常...

Arc fault detection based on multi-dimension feature extraction

Aiming at the problem of low accuracy and slow training speed in complex circuits with multiple electrical faults, a method ofwindow division combined with wavelet decomposition and empirical mode decomposition ( EMD) is proposed to extract currentcharacteristic quantities respectively from multiple dimensions in time domain, frequency domain and time scale, identifying arc fault byusing machine learning classification models. Firstly, the fault and normal current data are collected by the electrical fault experimentalplatform, and the current data is segmented by window. Then, the wavelet transforming and EMD methods are used to decompose thecurrent signal and calculate the characteristic quantities in different dimensions. The characteristic information collected is used as theinput of the classification algorithm for arc fault diagnosis. The experimental results show that the arc fault detection accuracy of thefeature extraction method on the gradient boosting decision tree (GBDT) is as high as 98%, which is 1. 87% higher than that of thecurrent without segmentation. It can effectively obtain the arc fault characteristics and realize the detection of arc fault with highefficiency and high accuracy.