Novel MOA Fault Detection Technology Based on Small Sample Infrared Image

Kaiyun Wen,Fangming Deng,Yande Liu,Baoquan Wei,Wei Luo,Yong Zuo

doi:10.3390/electronics10151748

Kaiyun Wen, Fangming Deng + Show 4 more

Open Access

https://doi.org/10.3390/electronics10151748

Copy DOI

Journal: Electronics	Publication Date: Jul 21, 2021
Citations: 8	License type: CC BY 4.0

Affiliation: East China Jiaotong University

Abstract

This paper proposes a novel metal oxide arrester (MOA) fault detection technology based on a small sample infrared image. The research is carried out from the detection process and data enhancement. A lightweight MOA identification and location algorithm is designed at the edge, which can not only reduce the amount of data uploaded, but also reduce the search space of cloud algorithm. In order to improve the accuracy and generalization ability of the defect detection model under the condition of small samples, a multi-model fusion detection algorithm is proposed. Different features of the image are extracted by multiple convolutional neural networks, and then multiple classifiers are trained. Finally, the weighted voting strategy is used for fault diagnosis. In addition, the extended model of fault samples is constructed by transfer learning and deep convolutional generative adversarial networks (DCGAN) to solve the problem of unbalanced training data sets. The experimental results show that the proposed method can realize the accurate location of arrester under the condition of small samples, and after the data expansion, the recognition rate of arrester anomalies can be improved from 83% to 85%, showing high effectiveness and reliability.

Highlights

A metal oxide arrester (MOA) is widely used as an important protection equipment for safe operation of power transmission and the transformation system
In order to get more accurate judgment accuracy and improve the generalization ability of the defect recognition model, this paper proposes a multi-model combination strategy based on weighted voting rule and F1 score
To evaluate the performance of the proposed MOA defect detection system, we tested it on a MOA image data set of a substation in Jiangxi Province, China

Summary

Introduction

A metal oxide arrester (MOA) is widely used as an important protection equipment for safe operation of power transmission and the transformation system. All the above methods can realize the fault identification of an MOA, it cannot avoid the shortcomings of an artificial neural network, such as long training time and poor generalization ability, which has proven difficult to deal with the massive data of today’s power grid. In the actual power grid system, the number of some defect samples is scarce, In the case of small samples, there is not enough data for the deep learning algorithm to fully train, so the risk of overfitting is very easy to occur in the model training process, which makes it difficult to train a detection model with good performance [19]. An infrared thermal fault detection technology for the MOA is proposed, which is based on small sample infrared images.

System Overview

A Alarlgaregneunmubmebreorfof nonrmoramlaMl MOAOAimiamgaegses

Data Expansion Model Based on TL-DCGAN

IImmpprroovveedd Discriminator Structure

MOA Fault Detection Based on Integrated Learning

Experimental Results and Analysis

MOA Positioning Experiment