2025年4月8日 周二
首页 > 过刊浏览>2023年第38卷第4期 >104-112. DOI:10.19781/j.issn.1673-9140.2023.04.011
PDF HTML阅读 XML下载 导出引用 引用提醒
基于多尺度卷积神经网络的变压器故障诊断方法
CSTR:
[cstr]
作者:
作者单位:

(1.国网浙江省电力有限公司杭州市余杭区供电公司，浙江 杭州 311100;2.杭州电力设备制造有限公司余杭群力成套电气制造分公司，浙江 杭州 311100;3.东北电力大学机械工程学院，吉林 吉林 132011)

通讯作者:

王辉东（1974—），男，硕士，高级工程师，主要从事电力设备状态评价与检测方面的研究；E?mail:18244891@qq.com

中图分类号:

TM411

基金项目:

吉林省科技发展计划(2021050959RQ)


A transformer fault diagnosis method based on multiscale 1DCNN
Author:
Affiliation:

(1. Yuhang District Power Supply Company, State Grid Zhejiang Electric Power Co., Ltd., Hangzhou 311100, China;2. Yuhang Qunli Complete Electric Manufacturing Branch, Hangzhou Electric Power Equipment Manufacturing Co., Ltd.,Hangzhou 311100, China;3.School of Mechanical Engineering，Northest Electric Power University, Jilin 132011, China)

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [24]
    • | | | |
  • 文章评论
    摘要:

    为了提高变压器故障识别的诊断精度，提出一种基于多尺度卷积神经网络模型的变压器故障诊断方法。首先，在1DCNN结构基础上设计2个多尺度卷积模块，构造变压器故障识别模型的总体结构。其次，针对样本特征较少问题，采用基于比值法的特征扩充方法，将样本特征由5维增强至25维；针对故障样本量少以及故障间样本数分布不平衡问题，采用基于对抗生成网络的样本数增强方法，生成大量模拟样本。最后，利用改造后的数据集对所设计的模型进行训练与测试。结果表明，模型平均准确率为93.24%，与相关主流方法在不同数据集下实验对比，本模型表现效果良好。

    Abstract:

    In order to improve the diagnostic accuracy of transformer fault, a transformer fault diagnosis method based on the multi?scale convolutional neural network model is proposed. Firstly, two multi?scale convolutional modules are designed on the basis of the 1DCNN structure, and the overall structure of the transformer fault identification model is constructed. Secondly, to handle the problem of less sample features, the feature expansion method based on the ratio method is adopted to enhance the sample features from 5 dimensions to 25 dimensions. To solve the small sample size of faults and uneven distribution of sample numbers between faults, a sample number enhancement method based on adversarial generation network is adopted, and a large number of simulated samples are generated. Finally, the modified dataset was used to train and test the designed model. The results show that the average accuracy of the model is 93.24%, and the model performs well compared with the relevant mainstream methods under different datasets.

    参考文献
    [1] 党东升,张树永,葛鹏江,等.基于改进量子粒子群优化支持向量机的变压器故障诊断方法[J].电力科学与技术学报,2019,34(3):108?113. DANG Dongsheng,ZHANG Shuyong,GE Pengjiang,et al.Transformer fault diagnosis method based on support vector machine optimized by improved quantum?behaved particle swarm optimization[J].Journal of Electric Power Science and Technology,2019,34(3):108?113.
    [2] 马鑫,尚毅梓,胡昊,等.基于数据特征增强和残差收缩网络的变压器故障识别方法[J].电力系统自动化,2022,46(3):175?183. MA Xin,SHANG Yizi,HU Hao,et al. Identification method of transformer fault based on data feature enhancement and residual shrinkage network[J].Automation of Electric Power Systems,2022,46(3):175?183.
    [3] 何宁辉,朱洪波,李秀广,等.基于贝叶斯网络和假设检验的变压器故障诊断[J].电力科学与技术学报,2021,36(6):20?27. HE Ninghui,ZHU Hongbo,LI Xiuguang,et al.Transformer fault diagnosis based on Bayesian network and hypothesis testing[J].Journal of Electric Power Science and Technology,2021,36(6):20?27.
    [4] 程宏波,刘嘉,康嘉斌,等.一种变压器健康状态的改进免疫识别方法[J].电力科学与技术学报,2018,33(2):141?147. CHENG Hongbo,LIU Jia,KANG Jiabin,et al.An improved immune recognition method for Transformer health status[J].Journal of Electric Power Science and Technology,2018,33(2):141?147.
    [5] 谭俊明,张诗建.变压器故障诊断研究综述[J].机电工程技术,2021,50(10):12?14. TAN Junming,ZHANG Shijian.Review of transformer fault diagnosis method[J].Mechanical & Electrical Engineering Technology,2021,50(10):12?14.
    [6] 谢乐,衡熙丹,刘洋,等.基于线性判别分析和分步机器学习的变压器故障诊断[J].浙江大学学报(工学版),2020,54(11):2262?2272. XIE Le,HENG Xidan,LIU Yang,et al.Transformer fault diagnosis based on linear discriminant analysisand step?by?step machine learning[J].Journal of Zhejiang University (Engineering Science),2020,54(11):2262?2272.
    [7] 李恩文,王力农,宋斌,等.基于改进模糊聚类算法的变压器油色谱分析[J].电工技术学报,2018,33(19):4594?4602. LI Enwen,WANG Linong,SONG Bin,et al.Analysis of transformer oil chromatography based on improved fuzzy clustering algorithm[J].Transactions of China Electrotechnical Society,2018,33(19):4594?4602.
    [8] 朱保军,咸日常,范慧芳,等.WRSR与改进朴素贝叶斯融合的变压器故障诊断技术研究[J].电力系统保护与控制,2021,49(20):120?128. ZHU Baojun,XIAN Richang,FAN Huifang,et al.Transformer fault diagnosis technology based on the fusion of WRSR and improved naive Bayes[J].Power System Protection and Control,2021,49(20):120?128.
    [9] 谢国民,蔺晓雨.基于改进SSA优化MDS?SVM的变压器故障诊断方法[J].控制与决策,2023,38(2):459?467. XIE Guomin,LIN Xiaoyu.Transformer fault diagnosis method based on improved SSA optimized MDS?SVM[J].Control and Decision,2023,38(2):459?467.
    [10] 刘云鹏,许自强,付浩川,等.采用最优云熵改进可拓云理论的变压器本体绝缘状态评估方法[J].高电压技术,2020,46(2):397?405. LIU Yunpeng,XU Ziqiang,FU Haochuan,et al.Insulation condition assessment method of power transformer based on improved extension cloud theory with optimal cloud entropy[J].High Voltage Technology,2020,46(2):397?405.
    [11] 李典阳,张育杰,冯健,等.变压器故障样本多维诊断及结果可信度分析[J].电工技术学报,2022,37(3):667?675. LI Dianyang,ZHANG Yujie,FENG Jian,et al. Multi?dimensional diagnosis of transformer fault sample and credibility analysis[J].Transactions of China Electrotechnical Society,2022,37(3):667?675.
    [12] 林凡勤,李明明,郭红.变压器故障诊断技术综述[J].计算机与现代化,2022(3):116?126. LIN Fanqin,LI Mingming,GUO Hong.Review on fault diagnosis technology of transform[J].Computer and Modernization,2022(3):116?126.
    [13] ZHOU D X.Universality of deep convolutional neural networks[J].Applied and Computational Harmonic Analysis,2020,48(2):787?794.
    [14] 杨德昌,廖文龙,任翔,等.基于胶囊网络的电力变压器故障诊断[J].高电压技术,2021,47(2):415?425. YANG Dechang,LIAO Wenlong,REN Xiang,et al.Fault diagnosis of transformer based on capsule network[J].High Voltage Technology,2021,47(2):415?425.
    [15] 李辉,张志攀,张中卫.基于卷积神经网络的变压器故障诊断[J].河南理工大学学报(自然科学版),2018,37(6):118?123. LI Hui,ZHANG Zhipan,ZHANG Zhongwei.Fault diagnosis of transformer based on convolutional neural network[J].Journal of Henan Polytechnic University (Natural Science Edition),2018,37(6):118?123.
    [16] 王伟,李开成,许立武,等.基于一维卷积神经网络多任务学习的电能质量扰动识别方法[J].电测与仪表,2022,59(3):18?25. WANG Wei,LI Kaicheng,XU Liwu,et al.Power quality disturbance recognition method based on multi?task learning and one?dimensional convolutional neural network[J].Electrical Measurement & Instrumentation,2022,59(3):18?25.
    [17] 卞景艺,刘秀丽,徐小力,等.基于多尺度深度卷积神经网络的故障诊断方法[J].振动与冲击,2021,40(18):204?211. BIAN Jingyi,LIU Xiuli,XU Xiaoli,et al.Fault diagnosis method based on a multi?scale deep convolutional neural network[J].Journal of Vibration and Shock,2021,40(18):204?211.
    [18] 林晓静,刘文,甘超飞,等.基于卷积神经网络与多维度电力大数据的信用评估系统[J].电测与仪表,2021,58(11):101?106. LIN Xiaojing,LIU Wen,GAN Chaofei,et al.Corporate credit assessment system based on convolutional neural network and multi?dimensional power big data[J].Electrical Measurement & Instrumentation,2021,58(11):101?106.
    [19] 李军,李明.改进多尺度卷积神经网络的人脸表情识别研究[J].重庆邮电大学学报(自然科学版),2022,34(2):201?207. LI Jun,LI Ming.Research on facial expression recognition based on improved multi?scale convolutional neural networks[J].Journal of Chongqing University of Posts and Telecommunications (Natural Science),2022,34(2):201?207.
    [20] KHARGHANIAN R,PEIRAVI A,MORADI F,et al.Pain detection using batch normalized discriminant restricted Boltzmann machine layers[J].Journal of Visual Communication and Image Representation,2021,76:103062
    [21] 王健一,李金忠,凌愍,等.新版电力行业标准《变压器油中溶解气体分析判断导则》解读[J].变压器,2014,51(12):49?53. WANG Jianyi,LI Jinzhong,LING Min,et al.Interpretation of the new electricity industry standard guide to the analysis and the diagnosis of gases dissolved in transformer oil[J].Transformer,2014,51(12):49?53.
    [22] 李平,胡根铭.基于改进神经网络与比值法融合的变压器故障诊断方法[J/OL].高电压技术:1?9[2022?08?05].https://kns.cnki.net/kcms/detail/42.1239.TM.20220804. 1702.035.html. LI Ping,HU Genming.Transformer fault diagnosis method based on the fusion of improved neural network and ratio method[J/OL].High Voltage Technology,1?9[2022?08?05].https://kns.cnki.net/kcms/detail/42.1239.TM.20220804. 1702.035.html.
    [23] 李雅欣,侯慧娟,胥明凯,等.基于策略梯度和生成式对抗网络的变压器油色谱案例扩充方法[J].电力自动化设备,2020,40(12):211?218. LI Yaxin,HOU Huijuan,XU Mingkai,et al.Oil chromatogram case generation method of transformer based onpolicy gradient and generative adversarial networks[J].Electric Power Automation Equipment,2020,40(12):211?218.
    [24] 苏小盟.基于神经网络和注意力机制的变压器状态预测和故障诊断研究[D].济南：山东大学,2021. SU Xiaomeng.Research on transformer state prediction and fault diagnosis based on neural network and attention mechanism[D].Jinan：Shandong University,2021.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王辉东,姚海燕,郭 强,等.基于多尺度卷积神经网络的变压器故障诊断方法[J].电力科学与技术学报,2023,38(4):104-112.
WANG Huidong, YAO Haiyan, GUO Qiang, et al. A transformer fault diagnosis method based on multiscale 1DCNN[J]. Journal of Electric Power Science and Technology,2023,38(4):104-112.

复制
分享
文章指标
  • 点击次数:223
  • 下载次数: 943
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2023-11-06
文章二维码

微信公众号二维码

您是本站第 86000 访问者

通信地址：长沙市（天心区）万家丽南路960号长沙理工大学

电话/传真：0731-85258195 E-mail：dlxb04@163.com

版权所有：电力科学与技术学报 ® 2025 版权所有

京公网安备 11010802026262号