Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD

LI Mengjie; DONG Yuchen; ZHANG Bide

doi:10.13296/j.1001-1609.hva.2025.12.011

您当前的位置：

首页 >

文章列表页 >

Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD

Research & Analysis | 更新时间：2025-12-09

- Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD
- High Voltage Apparatus Vol. 61, Issue 12, Pages: 81-89(2025)
- 作者机构：
  
  国网四川省电力公司天府新区供电公司，成都 610095
  西华大学电气与电子信息学院，成都 610039
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2025.12.011
  CLC：
- Received：06 April 2025，
  
  Revised：2025-06-12，
  
  Published：16 December 2025
- 稿件说明：
移动端阅览
LI Mengjie, DONG Yuchen, ZHANG Bide. Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD[J]. High Voltage Apparatus, 2025, 61(12): 81-89.
DOI：

LI Mengjie, DONG Yuchen, ZHANG Bide. Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD[J]. High Voltage Apparatus, 2025, 61(12): 81-89. DOI： 10.13296/j.1001-1609.hva.2025.12.011.

摘要

电力变压器正常运行对保障电网安全稳定运行具有重要意义。为提高电力变压器故障检测性能与故障诊断性能，提出基于核边界流形嵌入（kernel marginal manifold embedding，KMME）的电力变压器故障检测与诊断方法。首先，提出一种新的图嵌入算法——KMME算法，旨在提取具有鉴别意义的低维特征；其次，在低维特征的条件下基于支持向量数据描述（support vector data description，SVDD）方法，根据不同的故障状态建立相应的检测子模型；最后，将待检测数据样本输入各检测子模型，并组合各子模型检测结果实现故障诊断。在电力变压器DGA数据集上的实验结果表明：采用KMME算法提取的低维特征在提升类内聚集性与类间区分度方面效果显著，且结合SVDD建立的故障检测模型，与常用故障检测方法进行对比，所提方法具有更强的故障检测能力，且具有良好的故障诊断性能。

Abstract

The normal operation of power transformer is crucial for ensuring safe and stable operation of power grid. For improving the fault detection and diagnosis performance of power transformer

a fault detection and diagnosis method for power transformer based on Kernel Marginal Manifold Embedding (KMME) is proposed. First

a novel graph embedding dimensionality reduction algorithm named KMME is proposed to extract low-dimensional features with discriminant significance. Then

under the condition of low-dimensional feature

the corresponding detection submodels are set up based on the support vector data descriptiion (SVDD) method and also in accordance with different fault states.Finally

data samples to be deteced are input into each detection submodel andeach submodel’s detection result is combined to achieve fault diagnosis. The experiment result on DGA data set of power transformer illustrates that the low-dimensional feature extracted by KMME has a remarkable effect in enhancing intra-class aggregation and inter-class discrimination. In addition

the fault detection model set upby combining SVDD is compared with traditional methods

proving that the proposed method has significantly improved performance in fault detection and diagnosis.

关键词

Keywords

references

郑业爽 , 李世春 , 鲁玲 . 基于多策略ISOA优化SVM的变压器故障诊断研究 [J ] . 智慧电力 , 2023 , 51 ( 2 ): 38 - 44 .

ZHENG Yeshuang , LI Shichun , LU Ling . Transformer fault diagnosis based on multi-strategy ISOA optimized SVM [J ] . Smart Power , 2023 , 51 ( 2 ): 38 - 44 .

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 .

李元 , 李星辉 , 孙渭薇 , 等 . 基于多模型级联的油浸式电力变压器故障诊断方法 [J ] . 智慧电力 , 2023 , 51 ( 6 ): 86 - 92 .

LI Yuan , LI Xinghui , SUN Weiwei , et al . Fault diagnosis method of oil-immersed power transformer based on multi-model cascade fusion [J ] . Smart Power , 2023 , 51 ( 6 ): 86 - 92 .

韩金华 , 郭晓锋 , 靳鹏超 . 一起发电厂高压厂用分裂变压器故障分析 [J ] . 变压器 , 2024 , 61 ( 10 ): 59 - 64 .

HAN Jinhua , GUO Xiaofeng , JIN Pengchao . Fault analysis of duallow-voltage transformer used in high voltage plant of power plant [J ] . Transformer , 2024 , 61 ( 10 ): 59 - 64 .

侯玉鹏 , 李峰 , 艾福强 , 等 . 变压器绕组典型故障的特征参量及其变化规律研究 [J ] . 变压器 , 2023 , 60 ( 11 ): 17 - 28 .

HOU Yupeng , LI Feng , AI Fuqiang , et al . Research on characteristic parameters and their variation patterns of typical faults in transformer windings [J ] . Transformer , 2024 , 61 ( 11 ): 17 - 28 .

吴奇松 , 夏君宇 , 赵国庆 , 等 . CVT电容分压器末端放电故障分析 [J ] . 变压器 , 2024 , 61 ( 1 ): 62 - 65 .

WU Qisong , XIA Junyu , ZHAO Guoqing , et al . Analysis of discharge fault at end screen of CVT capacitor voltage divider [J ] . Transformer , 2024 , 61 ( 1 ): 62 - 65 .

梁栋 , 朱建华 , 张翠 , 等 . 变压器状态评估及故障诊断研究综述 [J ] . 变压器 , 2024 , 61 ( 2 ): 35 - 43 .

LIANG Dong , ZHU Jianhua , ZHANG Cui , et al . Review of transformer condition assessment and fault diagnosis [J ] . Transformer , 2024 , 61 ( 2 ): 35 - 43 .

甘强 , 房欣欣 , 张鹏飞 , 等 . 500 kV变压器绕组股间短路特征分析 [J ] . 变压器 , 2024 , 61 ( 2 ): 63 - 68 .

GAN Qiang , FANG Xinxin , ZHANG Pengfei , et al . Analysis of strand-to-strand short-circuit fault in 500 kV transformer [J ] . Transformer , 2024 , 61 ( 2 ): 63 - 68 .

李永康 , 张丙旭 , 杜振斌 , 等 . 一起低端换流变压器油中缓慢产生乙炔故障分析 [J ] . 变压器 , 2024 , 61 ( 2 ): 74 - 76 .

LI Yongkang , ZHANG Bingxu , DU Zhenbin , et al . Analysis of acetylene fault in oil of a low - end converter transformer [J ] . Transformer , 2024 , 61 ( 2 ): 74 - 76 .

徐耀松 , 李佳旺 , 段彦强 . 基于相似度机制AdaBoost-DBN的变压器故障层级诊断 [J ] . 高压电器 , 2023 , 59 ( 6 ): 154 - 164 .

XU Yaosong , LI Jiawang , DUAN Yanqiang . Fault hierarchical diagnosis of transformer based on AdaBoost - DBN similarity mechanism [J ] . High Voltage Apparatus , 2023 , 59 ( 6 ): 154 - 164 .

安国庆 , 史哲文 , 马世峰 , 等 . 基于RF特征优选的WOA-SVM变压器故障诊断 [J ] . 高压电器 , 2022 , 58 ( 2 ): 171 - 178 .

AN Guoqing , SHI Zhewen , MA Shifeng , et al . Fault diagnosis of WOA-SVM transformer based on RF feature optimization [J ] . High Voltage Apparatus , 2022 , 58 ( 2 ): 171 - 178 .

周家玉 , 侯慧娟 , 盛戈皞 , 等 . 状态参量关联规则挖掘及深度学习融合的变压器故障诊断算法 [J ] . 高压电器 , 2023 , 59 ( 3 ): 108 - 115 .

ZHOU Jiayu , HOU Huijuan , SHENG Gehao , et al . Transformer fault diagnosis algorithm based on association rules mining of state parameters and deep learning [J ] . High Voltage Apparatus , 2023 , 59 ( 3 ): 108 - 115 .

罗超月岭 , 郑韵馨 , 徐帧雨 , 等 . 基于Borderline-SMOTE-IHT混合采样的改进GWO-SVM变压器故障诊断方法 [J ] . 智慧电力 , 2023 , 51 ( 7 ): 108 - 114 .

LUO Chaoyueling , ZHENG Yunxin , XU Zhenyu , et al . Improved GWO-SVM transformer fault diagnosis method based on BorderlineSMOTE-IHTmixed sampling [J ] . Smart Power , 2023 , 51 ( 7 ): 108 - 114 .

邢雅 , 侯峰 , 樊博 , 等 . 基于改进K-means聚类的变压器局部放电定位诊断方法 [J ] . 智慧电力 , 2023 , 51 ( 3 ): 53 - 58 .

XING Ya , HOU Feng , FAN Bo , et al . Transformer partial discharge fault location and diagnosis based on improved K-means clustering algorithm [J ] . Smart Power , 2023 , 51 ( 3 ): 53 - 58 .

马宏忠 , 李楠 , 杨启帆 , 等 . 基于多特征声纹图谱的变压器绕组松动在线故障诊断方法 [J ] . 电机与控制学报 , 2023 , 27 ( 5 ): 76 - 87 .

MA Hongzhong , LI Nan , YANG Qifan , et al . On-line fault diagnosis method of transformer winding looseness based on multi-characteristic voiceprint maps [J ] . Electric Machines and Control , 2023 , 27 ( 5 ): 76 - 87 .

李继攀 , 刘宏领 , 郭奇军 , 等 . 基于功率因数角的接地变压器匝间短路故障辨识 [J ] . 供用电 , 2023 , 40 ( 9 ): 50 - 57 .

LI Jipan , LIU Hongling , GUO Qijun , et al . Identification of inter turn short circuit fault of grounding transformer based on power factor angle [J ] . Distribution & Utilization , 2023 , 40 ( 9 ): 50 - 57 .

周晨辉 , 金玉琪 , 穆海宝 , 等 . 基于宽频等值电路的变压器局部放电电气定位研究 [J ] . 浙江电力 , 2023 , 42 ( 12 ): 3 - 11 .

ZHOU Chenhui , JIN Yuqi , MU Haibao , et al . Research on localization of partial discharges in transformers based on wideband equivalent circuit [J ] . Zhejiang Electric Power , 2023 , 42 ( 12 ): 3 - 11 .

张龙 , 武玉才 , 马明晗 . 开口变压器法检测汽轮发电机转子绕组故障的有效性验证 [J ] . 大电机技术 , 2023 ( 6 ): 29 - 34 .

ZHANG Long , WU Yucai , MA Minghan . Validation of opening transformer method for detecting rotor winding faultof turbogenerator [J ] . Large Electric Machine and Hydraulic Turbine , 2023 ( 6 ): 29 - 34 .

王玉楹 , 张亚杰 , 陈波 , 等 . 箔式绕组双分裂变压器损耗异常分析 [J ] . 变压器 , 2024 , 61 ( 10 ): 65 - 69 .

WANG Yuying , ZHANG Yajie , CHEN Bo , et al . Analysis of loss anomalies in foil - winding double - split transformers [J ] . Transformer , 2024 , 61 ( 10 ): 65 - 69 .

马向南 , 杨涛 , 王云龙 , 等 . 基于轻量化神经网络及模型压缩的变压器油色谱故障诊断方法 [J ] . 供用电 , 2023 , 40 ( 5 ): 84 - 91 .

MA Xiangnan , YANG Tao , WANG Yunlong , et al . Transformer dissolved gas fault diagnosis method based on lightweight neural network and model quantization [J ] . Distribution & Utilization , 2023 , 40 ( 5 ): 84 - 91 .

石姜 , 孙月磊 , 冷玉祥 , 等 . 电力变压器铝箔绕组的研究与仿真分析 [J ] . 变压器 2024 , 61 ( 12 ): 41 - 46 .

SHI Jiang , SUN Yuelei , LENG Yuxiang , et al . Research and simulation analysis of aluminum foil winding of power transformer [J ] . Transformer , 2024 , 61 ( 12 ): 41 - 46 .

盖曜麟 , 葛丽娟 , 郭懿中 , 等 . 基于改进SVM算法的高压断路器故障诊断 [J ] . 高压电器 , 2022 , 58 ( 12 ): 14 - 20 .

GE Yaolin , GE Lijuan , GUO Yizhong , et al . Fault diagnosis of high voltage circuit breaker based on improved SVM algorithm [J ] . High Voltage Apparatus , 2022 , 58 ( 12 ): 14 - 20 .

苏磊 , 陈璐 , 徐鹏 , 等 . 基于GRNN和KPCA组合模型的变压器油中气体体积分数短期预测 [J ] . 高压电器 , 2021 , 57 ( 1 ): 82 - 88 .

SU Lei , CHEN Lu , XU Peng , et al . Short-term prediction of gases dissolved in transformer oil based on GRNN and KPCA model [J ] . High Voltage Apparatus , 2021 , 57 ( 1 ): 82 - 88 .

陈铁 , 吕长钦 , 张欣 , 等 . 基于KPCA-WPA-SVM的变压器故障诊断模型 [J ] . 电测与仪表 , 2021 , 58 ( 4 ): 158 - 164 .

CHEN Tie , LYU Changqin , ZHANG Xin , et al . Transformer fault diagnosis model based onKPCA - WPA - SVM [J ] . Electrical Measurement & Instrumentation , 2021 , 58 ( 4 ): 158 - 164 .

武文栋 , 施保华 , 郑传良 , 等 . 基于KPCA-ISSA-KELM的光伏阵列故障诊断方法 [J ] . 智慧电力 , 2022 , 50 ( 11 ): 69 - 76 .

WU Wendong , SHI Baohua , ZHENG Chuanliang , et al . Fault diagnosis method of PV array based on KPCA-ISSA-KELM [J ] . Smart Power , 2022 , 50 ( 11 ): 69 - 76 .

崔佳嘉 , 马宏忠 . 基于改进MFCC和3D-CNN的变压器铁心松动故障声纹识别模型 [J ] . 电机与控制学报 , 2022 , 26 ( 12 ): 150 - 160 .

CUI Jiajia , MA Hongzhong . Voiceprint recognition model of transformer core looseness fault based on improved MFCC and 3D-CNN [J ] . Electric Machines and Control , 2022 , 26 ( 12 ): 150 - 160 .

孙长海 , 苏晓敏 , 李天伦 , 等 . 基于概率神经网络的油纸绝缘局部放电发展阶段识别 [J ] . 高压电器 , 2022 , 58 ( 1 ): 138 - 147 .

SUN Changhai , SU Xiaomin , LI Tianlun , et al . Development stage recognition of partial discharge in oil-paper insulation based on probabilistic neural network [J ] . High Voltage Apparatus , 2022 , 58 ( 1 ): 138 - 147 .

龚思聪 , 徐洁 , 万鸣华 . 边界流形嵌入在特征提取中的应用 [J ] . 计算机工程与应用 , 2022 , 58 ( 23 ): 245 - 253 .

GONG Sicong , XU Jie , WAN Minghua . Marginal manifold embedding for feature extraction [J ] . Computer Engineering and Applications , 2022 , 58 ( 23 ): 245 - 253 .

张丞鸣 , 谢菊芳 , 胡东 , 等 . 基于QPSO-SVM与DGA五边形解释工具的变压器故障诊断方法 [J ] . 高压电器 , 2021 , 57 ( 12 ): 117 - 124 .

ZHANG Chengming , XIE Jufang , HU Dong , et al . Fault diagnosis method of transformer based onQPSO-SVMand DGA pentagonal interpretation tool [J ] . High Voltage Apparatus , 2021 , 57 ( 12 ): 117 - 124 .

许海林 , 林春耀 , 罗颖婷 , 等 . 基于Shapelet识别的变压器在线DGA异常检测 [J ] . 高压电器 , 2021 , 57 ( 7 ): 175 - 181 .

XU Hailin , LIN Chunyao , LUO Yingting , et al . On-line DGA abnormal detection on power transformer based on Shapelet identification [J ] . High Voltage Apparatus , 2021 , 57 ( 7 ): 175 - 181 .

王文森 , 杨晓西 , 刘阳 , 等 . 基于层次聚类分析的变压器油中溶解气体在线监测数据异常检测 [J ] . 高压电器 , 2023 , 59 ( 1 ): 142 - 147 .

WANG Wensen , YANG Xiaoxi , LIU Yang , et al . Anomaly detection of online monitoring data of dissolved gases in transformer oil based on hierarchical cluster analysis [J ] . High Voltage Apparatus , 2023 , 59 ( 1 ): 142 - 147 .

杨次 , 沈洪 , 柯康观 , 等 . 一起110 kV变压器内部总烃超标缺陷分析及处理 [J ] . 变压器 , 2024 , 61 ( 9 ): 65 - 68 .

YANG Ci , SHEN Hong , KE Kangguan , et al . Analysis and treatment of defect of total hydrocarbon exceeding standard inside 110 kV transformer [J ] . Transformer , 2024 , 61 ( 9 ): 65 - 68 .

曲文韬 , 赵航 . 巴基斯坦拉合尔换流站换流变压器绝缘油中乙炔产生原因分析及应对措施 [J ] . 变压器 , 2024 , 61 ( 9 ): 69 - 75 .

QU Wentao , ZHAO Hang . Acetylene production in insulating oil of converter transformer analysis and countermeasures of lahore converter station inPAKISTAN [J ] . Transformer , 2024 , 61 ( 9 ): 69 - 75 .

徐铭璐 , 马超 , 曹立锟 . 基于径向基神经网络的变压器电气设备热缺陷诊断方法 [J ] . 变压器 , 2024 , 61 ( 4 ): 34 - 38 .

XU Minglu , MA Chao , CAO Likun . Intelligent diagnosis method for thermal defects of current heating transformer based on RBFNN [J ] . Transformer , 2024 , 61 ( 4 ): 34 - 38 .

赵睿 , 景瑞斌 , 赵龙 , 等 . 绝缘介质理化特性辅助油浸式电抗器故障定位及诊断 [J ] . 变压器 , 2024 , 61 ( 4 ): 62 - 66 .

ZHAO Rui , JING Ruibin , ZHAO Long , et al . Physical and chemical characteristics of insulating medium assist fault location and diagnosis of oil-immersed reactor [J ] . Transformer , 2024 , 61 ( 4 ): 62 - 66 .

胡进 , 宋玉锋 , 余霖 , 等 . 变压器铁心多点接地导致高温过热故障分析 [J ] . 变压器 , 2023 , 60 ( 4 ): 67 - 70 .

HU Jin , SONG Yufeng , YU Lin , et al . Research on high temperature overheat fault caused by multi-point grounding of transformer core [J ] . Transformer , 2023 , 60 ( 4 ): 67 - 70 .

刘建永 , 刘霖 , 王欣 , 等 . 一起220 kV主变引线折弯过大造成的跳闸故障 [J ] . 变压器 , 2023 , 60 ( 4 ): 71 - 74 .

LIU Jianyong , LIU Lin , WANG Xin , et al . Fault caused by excessive lead bending of 220 kV main transformer [J ] . Transformer , 2023 , 60 ( 4 ): 71 - 74 .

李辉 , 杨杰 , 王耀强 , 等 . 66 kV干式变压器雷电冲击试验故障分析 [J ] . 变压器 , 2024 , 61 ( 5 ): 65 - 70 .

LI Hui , YANG Jie , WANG Yaoqiang , et al . Analysis of lighting impulse test failure of 66 kV dry-type transformer [J ] . Transformer , 2024 , 61 ( 5 ): 65 - 70 .

尹琦琳 , 宋媛 , 王帅 , 等 . 基于绝缘油色谱试验的110 kV变压器异常状态分析 [J ] . 变压器 , 2024 , 61 ( 5 ): 71 - 74 .

YIN Qilin , SONG Yuan , WANG Shuai , et al . Analysis of abnormal state of 110 kV transformer based on insulation oil chromatographytes [J ] . Transformer , 2024 , 61 ( 5 ): 71 - 74 .

段成 , 李丰 , 杨嘉炜 , 等 . 一起110 kV变压器高压套管故障原因分析 [J ] . 变压器 , 2024 , 61 ( 8 ): 58 - 61 .

DUAN Cheng , LI Feng , YANG Jiawei , et al . Cause analysis of failure of high - voltage bushing of 110 kV transformer [J ] . Transformer , 2024 , 61 ( 8 ): 58 - 61 .

朱擘 , 王聪 , 胡利成 , 等 . 一起500 kV变压器压钉松动放电产气故障分析 [J ] . 变压器 , 2024 , 61 ( 9 ): 55 - 59 .

ZHU Bo , WANG Cong , HU Licheng , et al . Analysis of gas generation fault caused by loose discharge of pressure nails in 500 kV transformer [J ] . Transformer , 2024 , 61 ( 9 ): 55 - 59 .

XU Erbao , LI Yan , PENG Lining , et al . An unknown fault identification method based onPSO-SVDDin the IoT environment [J ] . Alexandria Engineering Journal , 2021 , 60 ( 4 ): 4047 - 4056 .

马良玉 , 程善珍 . 基于支持向量数据描述和XGBoost的风电机组异常工况预警研究 [J ] . 电工技术学报 , 2022 , 37 ( 13 ): 3241 - 3249 .

MA Liangyu , CHENG Shanzhen . Abnormal state early warning of wind turbine generator based on support vector data description and XGBoost [J ] . Transactions of China Electrotechnical Society , 2022 , 37 ( 13 ): 3241 - 3249 .

王荣昊 , 李喆 , 孙正 , 等 . 基于FISVDD与GRU的变压器声纹识别技术 [J ] . 高电压技术 , 2022 , 48 ( 11 ): 4546 - 4556 .

WANG Ronghao , LI Zhe , SUN Zheng , et al . Transformer voiceprint recognition technology based on FISVDD and GRU [J ] . High Voltage Engineering , 2022 , 48 ( 11 ): 4546 - 4556 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on GIS Integrated Monitoring and Status Assessment Technology Based on Digital Twin

Series Arc Fault Detection Method for Photovoltaic Systems Based on Spectral Cosine Distance

Research on Influence of Crack Depth and Position on Vibration Detection of 220 kV Porcelain Post Insulators

Real-time Monitoring System for Generator Stator and Rotor Faults Based on Edge Intelligence

Multi-signal Joint Identification and Intelligent Diagnosis of High Voltage Circuit Breaker Faults Based on VMD-BiLSTM

Related Author

QIN Yousu

XU Hui

WU Yanmeng

LEI Zhanfei

YANG Qun

ZHANG Yiming

GUO Jiahao

XIAO Xiaolong

Related Institution

State Grid Ningxia Electric Power Co., Ltd. EHV Company

Henan Pinggao Electric Co., Ltd.

Pinggao Group Co., Ltd

国网江苏省电力有限公司电力科学研究院，南京 211103Electric Power Research Institute, State Grid Jiangsu Electric Power Co., Ltd., Nanjing 211103, China

国网江苏省电力有限公司，南京 210000State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210000, China

⁰