Electricity theft detection method based on multi-domain feature fusion

IF 1.4 4区 工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Hong-shan Zhao, Cheng-yan Sun, Li-bo Ma, Yang Xue, Xiao-mei Guo, Jie-ying Chang
{"title":"Electricity theft detection method based on multi-domain feature fusion","authors":"Hong-shan Zhao,&nbsp;Cheng-yan Sun,&nbsp;Li-bo Ma,&nbsp;Yang Xue,&nbsp;Xiao-mei Guo,&nbsp;Jie-ying Chang","doi":"10.1049/smt2.12133","DOIUrl":null,"url":null,"abstract":"<p>To solve the problem of low accuracy of the previous electricity theft detection methods, the authors propose a multi-domain feature (MDF) fusion electricity theft detection method based on improved tensor fusion (ITF). Firstly, the original electricity consumption series is transformed by gram angle field (GAF) to obtain the time-domain matrix. The original electricity consumption series is converted into frequency-domain by Maximal Overlap Discrete Wavelet Transform (MODWT) to obtain the frequency-domain matrix. Then, the convolutional neural networks (CNN) are used to extract features of the time-domain matrix and frequency-domain matrix, respectively. Next, in order to fuse single-domain feature information and MDF interaction information while reducing redundant information, the authors propose an ITF method to obtain a multi-domain fusion tensor. Finally, the multi-domain fusion tensor is input into the electricity theft inference module to judge whether the user implements electricity theft behaviour. The authors simulate six electricity theft types and evaluate the method's performance separately for each electricity theft type. The results show that the proposed method outperforms other methods.</p>","PeriodicalId":54999,"journal":{"name":"Iet Science Measurement & Technology","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/smt2.12133","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Science Measurement & Technology","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/smt2.12133","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

To solve the problem of low accuracy of the previous electricity theft detection methods, the authors propose a multi-domain feature (MDF) fusion electricity theft detection method based on improved tensor fusion (ITF). Firstly, the original electricity consumption series is transformed by gram angle field (GAF) to obtain the time-domain matrix. The original electricity consumption series is converted into frequency-domain by Maximal Overlap Discrete Wavelet Transform (MODWT) to obtain the frequency-domain matrix. Then, the convolutional neural networks (CNN) are used to extract features of the time-domain matrix and frequency-domain matrix, respectively. Next, in order to fuse single-domain feature information and MDF interaction information while reducing redundant information, the authors propose an ITF method to obtain a multi-domain fusion tensor. Finally, the multi-domain fusion tensor is input into the electricity theft inference module to judge whether the user implements electricity theft behaviour. The authors simulate six electricity theft types and evaluate the method's performance separately for each electricity theft type. The results show that the proposed method outperforms other methods.

Abstract Image

基于多域特征融合的窃电检测方法
针对以往窃电检测方法精度低的问题,提出了一种基于改进张量融合的多域特征融合窃电检测算法。首先,对原始耗电量序列进行g角场变换,得到时域矩阵。通过最大重叠离散小波变换(MODWT)将原始用电量序列转换为频域,得到频域矩阵。然后,使用卷积神经网络(CNN)分别提取时域矩阵和频域矩阵的特征。接下来,为了融合单域特征信息和MDF交互信息,同时减少冗余信息,作者提出了一种ITF方法来获得多域融合张量。最后,将多域融合张量输入窃电推理模块,判断用户是否实施窃电行为。作者模拟了六种窃电类型,并分别评估了每种窃电方式的方法性能。结果表明,该方法优于其他方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Iet Science Measurement & Technology
Iet Science Measurement & Technology 工程技术-工程:电子与电气
CiteScore
4.30
自引率
7.10%
发文量
41
审稿时长
7.5 months
期刊介绍: IET Science, Measurement & Technology publishes papers in science, engineering and technology underpinning electronic and electrical engineering, nanotechnology and medical instrumentation.The emphasis of the journal is on theory, simulation methodologies and measurement techniques. The major themes of the journal are: - electromagnetism including electromagnetic theory, computational electromagnetics and EMC - properties and applications of dielectric, magnetic, magneto-optic, piezoelectric materials down to the nanometre scale - measurement and instrumentation including sensors, actuators, medical instrumentation, fundamentals of measurement including measurement standards, uncertainty, dissemination and calibration Applications are welcome for illustrative purposes but the novelty and originality should focus on the proposed new methods.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信