基于自归一化神经网络的电弧故障检测方法

电弧故障是电气火灾的重要原因.低压线路发生串联电弧故障时,回路电流波形的时域特征与正常工作状态类似,采用传统的特征提取方法无法完整表达时域信号的全部数据特征,限制了电弧故障的特征表达能力,导致检测结果的误报率和漏报率较高.针对此问题,提出基于自归一化卷积神经网络的电弧故障检测方法.该方法将采集到的不同种类负载的电流时间...

An arc fault detection method based on the self-normalizedconvolutional neural network

The electric arc fault is an important cause of electrical fire. When the series arc fault occurs in the low-voltage circuit, thetraditional feature extraction method cannot fully express all the data features of the time domain signal. The feature expression ability ofarc fault is limited, which may bring high false alarm rate and miss alarm rate of detection results. To solve this problem, an arc faultdetection method based on the self-normalized convolutional neural network is proposed. This method intercepts the current time series ofdifferent kinds of loads according to half period. Then, they are normalized. The two-dimensional images of arc faults and normaloperation are generated by the grayscale data transformation. The gray transformation features of arc faults are extracted by using theconvolutional neural network. The arc fault convolution features are identified by multi-layer full connection layer fitting calculation of thefollowing sampling information. The evaluation shows that the accuracy of the proposed method is 99. 67% , which is better than thetraditional convolutional neural network and has good generalization performance.