基于深度学习的杆塔接地网断点诊断方法研究

在使用电磁感应方法诊断杆塔接地网断点的过程中,针对人工诊断引起的误差问题,提出了一种基于一维卷积神经网络(one dimensional-eonvolutional neural network,1D-CNN)的诊断模型,诊断模型以接地网正上方的一维磁场数据为输入,通过深度神经网络输出断点故障的数量和位置.首先通过实验...

Research on diagnosis method of tower grounding gridbreakpoints based on deep learning

In the process of using electromagnetic induction method to diagnose the breakpoint of the grounding grid of the tower, aimingat the error caused by manual diagnosis, this paper proposes a diagnosis model based on one dimensional-convolutional neural network(1D-CNN), the diagnosis model takes the one-dimensional magnetic field data directly above the grounding grid as input, and outputsthe number and location of breakpoint faults through a deep neural network. This paper firstly verified the effectiveness of electromagneticinduction method in the diagnosis of tower grounding grid breakpoints through experiment, then a magnetic field breakpoint fault datasetwas established and a 1D-CNN diagnosis model was trained. In the diagnostic accuracy verification experiment, the diagnostic modelreached 97. 50% diagnostic accuracy on 40 faulty magnetic field samples, showing good generalization. The comparison experiment of thediagnosis effect shows that the AUC value of the 1D-CNN diagnosis model reaches 0. 951, the average recognition rate of various faults inthree random trainings reaches 92. 08%, and the average test set accuracy in 15 trainings reaches 94. 30%. and the average training timeper generation is 0. 875 0 s, which has obvious advantages over DNN and RNN in various indicators.