基于混合采样和支持向量机的变压器故障诊断

doi:10.11930/j.issn.1004-9649.202109153

中国电力 ›› 2021, Vol. 54 ›› Issue (12): 150-155.DOI: 10.11930/j.issn.1004-9649.202109153

基于混合采样和支持向量机的变压器故障诊断

李亮¹, 范瑾², 闫林², 张宓¹, 王鹏飞³, 赵小军⁴, 肖海滨⁵

1. 生态环境部核与辐射安全中心, 北京 102400;
2. 中国核电工程有限公司, 北京 100840;
3. 西安交通大学核科学与技术学院, 陕西西安 710049;
4. 华北电力大学电力工程系, 河北保定 071003;
5. 保定天威保变电气股份有限公司, 河北保定 071000

收稿日期:2021-10-08 修回日期:2021-11-10 出版日期:2021-12-05 发布日期:2021-12-16
作者简介:李亮(1981-),男,硕士,高级工程师,从事电气仪控设备设计制造研究,E-mail:liliangfj@126.com;张宓(1971-),男,通信作者,硕士,高级工程师,从事电气仪控设备设计制造研究,E-mail:zhangmi@chinansc.cn
基金资助:
河北省自然科学基金资助项目（特高压并联电抗器的电磁-力-振动耦合机理与本体降噪关键技术研究，E2017502061）

Transformer Fault Diagnosis Based on Hybrid Sampling and Support Vector Machines

LI Liang¹, FAN Jin², YAN Lin², ZHANG Mi¹, WANG Pengfei³, ZHAO Xiaojun⁴, XIAO Haibin⁵

1. Nuclear and Radiation Safety Center MEE, Beijing 102400, China;
2. China Nuclear Power Engineering Co., Ltd., Beijing 100840, China;
3. College of Nuclear Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China;
4. Department of Electrical Engineering, North China Electric Power University, Baoding 071003, China;
5. Baoding Tianwei Baobian Electric Co., Ltd., Baoding 071000, China

Received:2021-10-08 Revised:2021-11-10 Online:2021-12-05 Published:2021-12-16
Supported by:
This work is supported by Natural Science Foundation of Hebei Province (Study on Electromagnetic-Force-Vibration Coupling Mechanism of UHV Shunt Reactor and the Key Technology of Noumenon Noise Reduction, No.E2017502061).

摘要/Abstract

摘要： 针对变压器不平衡数据集对变压器故障诊断模型产生的影响，提出了基于混合采样和支持向量机（support vector machines, SVM）的变压器故障诊断方法，利用合成少数类过采样技术（synthetic minority oversampling technique, SMOTE）和基于最近邻规则的欠采样方法，分别对变压器故障数据和正常数据进行采样，再利用混合采样得到的平衡数据训练基于支持向量机变压器故障诊断模型。通过测试集对比不平衡数据和平衡数据下基于SVM的变压器故障诊断模型的性能。最后分析了采样率对于变压器故障诊断模型诊断准确率的影响。实验结果表明，该方法可以有效降低不平衡数据对诊断模型的影响，提高变压器故障诊断模型的准确率。

关键词: 变压器, 不平衡数据, 混合采样, 支持向量机

Abstract: Aiming at the impact of transformer imbalanced data set on transformer fault diagnosis model. A transformer fault diagnosis method based on hybrid sampling and support vector machines (SVM) is proposed. It uses synthetic minority oversampling technique (SMOTE) and under sampling method based on nearest neighbor rules to underestimate transformer fault data and normal data, respectively. Sampling and oversampling, and then using the balanced data obtained by hybrid sampling training based on support vector machines transformer fault diagnosis model. The performance of the SVM-based transformer fault diagnosis model is compared through the test set under imbalanced data and balanced data. Finally, the influence of sampling rate on the diagnostic accuracy of transformer fault diagnosis model is analyzed. Experimental results show that this method can effectively reduce the impact of imbalanced data on the diagnostic model and improve the diagnostic accuracy of the transformer fault diagnostic model.

Key words: transformer, imbalanced data, hybrid sampling, support vector machines

李亮, 范瑾, 闫林, 张宓, 王鹏飞, 赵小军, 肖海滨. 基于混合采样和支持向量机的变压器故障诊断[J]. 中国电力, 2021, 54(12): 150-155.

LI Liang, FAN Jin, YAN Lin, ZHANG Mi, WANG Pengfei, ZHAO Xiaojun, XIAO Haibin. Transformer Fault Diagnosis Based on Hybrid Sampling and Support Vector Machines[J]. Electric Power, 2021, 54(12): 150-155.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202109153

https://www.electricpower.com.cn/CN/Y2021/V54/I12/150

参考文献

[1] 陈欢, 彭辉, 舒乃秋, 等. 基于蝙蝠算法优化最小二乘双支持向量机的变压器故障诊断[J]. 高电压技术, 2018, 44(11): 3664–3671
CHEN Huan, PENG Hui, SHU Naiqiu, et al. Fault diagnosis of transformer based on LS-TSVM optimized by bat algorithm[J]. High Voltage Engineering, 2018, 44(11): 3664–3671
[2] 黄新波, 李文君子, 宋桐, 等. 采用遗传算法优化装袋分类回归树组合算法的变压器故障诊断[J]. 高电压技术, 2016, 42(5): 1617–1623
HUANG Xinbo, LI Wenjunzi, SONG Tong, et al. Application of bagging-CART algorithm optimized by genetic algorithm in transformer fault diagnosis[J]. High Voltage Engineering, 2016, 42(5): 1617–1623
[3] 黄新波. 变电设备在线监测与故障诊断[M]. 2版. 北京: 中国电力出版社, 2013.
[4] 国家能源局. 变压器油中溶解气体分析和判断导则 DL/T 722—2014[S]. 北京: 中国电力出版社, 2015.
National Energy Bureau of the People's Republic of China. Guide to the analysis and the diagnosis of gases dissolved in transformer oil. DL/T 722—2014[S]. Beijing: China Electric Power Press, 2015.
[5] 吐松江·卡日, 高文胜, 张紫薇, 等. 基于支持向量机和遗传算法的变压器故障诊断[J]. 清华大学学报(自然科学版), 2018, 58(7): 623–629
KARI·Tusongjiang, GAO Wensheng, ZHANG Ziwei, et al. Power transformer fault diagnosis based on a support vector machine and a genetic algorithm[J]. Journal of Tsinghua University (Science and Technology), 2018, 58(7): 623–629
[6] 白翠粉, 高文胜, 金雷, 等. 基于3层贝叶斯网络的变压器综合故障诊断[J]. 高电压技术, 2013, 39(2): 330–335
BAI Cuifen, GAO Wensheng, JIN Lei, et al. Integrated diagnosis of transformer faults based on three-layer Bayesian network[J]. High Voltage Engineering, 2013, 39(2): 330–335
[7] 吕忠, 周强, 周琨, 等. 基于遗传算法改进极限学习机的变压器故障诊断[J]. 高压电器, 2015, 51(8): 49–53
LYU Zhong, ZHOU Qiang, ZHOU Kun, et al. Fault diagnosis of transformer based on extreme learning machine optimized by genetic algorithm[J]. High Voltage Apparatus, 2015, 51(8): 49–53
[8] 任静, 黄家栋. 基于免疫RBF神经网络的变压器故障诊断[J]. 电力系统保护与控制, 2010, 38(11): 6–9,14
REN Jing, HUANG Jiadong. Transformer fault diagnosis based on immune RBF neural network[J]. Power System Protection and Control, 2010, 38(11): 6–9,14
[9] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32–42
ZHANG Xuegong. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000, 26(1): 32–42
[10] 刘晨斐, 崔昊杨, 李鑫, 等. 不对称样本下基于支持向量机的变压器故障诊断[J]. 高压电器, 2019, 55(7): 216–220
LIU Chenfei, CUI Haoyang, LI Xin, et al. Transformers fault diagnosis based on SVM for unbalanced data[J]. High Voltage Apparatus, 2019, 55(7): 216–220
[11] 杨明, 尹军梅, 吉根林. 不平衡数据分类方法综述[J]. 南京师范大学学报(工程技术版), 2008, 8(4): 7–12
YANG Ming, YIN Junmei, JI Genlin. Classification methods on imbalanced data: a survey[J]. Journal of Nanjing Normal University (Engineering and Technology Edition), 2008, 8(4): 7–12
[12] 闫欣. 综合过采样和欠采样的不平衡数据集的学习研究[D]. 吉林: 东北电力大学, 2016.
YAN Xin. Comprehensive oversampling and undersampling study of imbalanced data sets[D]. Jilin: Northeast Electric Power University, 2016.
[13] 肖坚. 基于随机森林的不平衡数据分类方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2013.
XIAO Jian. Research on imbalanced data classification method based on random forest algorithm[D]. Harbin: Harbin Institute of Technology, 2013.
[14] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321–357.
[15] BLAGUS R, LUSA L. Improved shrunken centroid classifiers for high-dimensional class-imbalanced data[J]. BMC Bioinformatics, 2013, 14: 64.
[16] 张家伟, 郭林明, 杨晓梅. 针对不平衡数据的过采样和随机森林改进算法[J]. 计算机工程与应用, 2020, 56(11): 39–45
ZHANG Jiawei, GUO Linming, YANG Xiaomei. Improved oversampling and random forest algorithm for imbalanced data[J]. Computer Engineering and Applications, 2020, 56(11): 39–45
[17] HART P. The condensed nearest neighbor rule (Corresp.)[J]. IEEE Transactions on Information Theory, 1968, 14(3): 515–516.
[18] 董冰. 基于贝叶斯网络的电力变压器故障诊断[D]. 抚顺: 辽宁石油化工大学, 2019.
DONG Bing. Synthesized diagnosis on transformer faults based on Bayes networks[D]. Fushun: Liaoning Petro Chemical University, 2019.
[19] DUVAL M, DEPABLA A. Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases[J]. IEEE Electrical Insulation Magazine, 2001, 17(2): 31–41.
[20] 方涛,钱晔,郭灿杰,等. 基于天牛须搜索优化支持向量机的变压器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(2): 90–96
FANG Tao, QIAN Ye, GUO Canjie, et al. Research on transformer fault diagnosis based on a beetle antennae search optimized support vector machine[J]. Power System Protection and Control, 2020, 48(2): 90–96
[21] 谢国民, 倪乐水. 基于IABC优化SVM的变压器故障诊断[J]. 电力系统保护与控制, 2020, 48(15): 156–163
XIE Guomin, NI Leshui. Transformer fault diagnosis based on an artificial bee colony-support vector machine optimization algorithm[J]. Power System Protection and Control, 2020, 48(15): 156–163
[22] 田凤兰,张恩泽,潘思蓉,等. 基于特征量优选与ICA-SVM的变压器故障诊断模型[J]. 电力系统保护与控制, 2019, 47(17): 163–170
TIAN Fenglan, ZHANG Enze, PAN Sirong, et al. Fault diagnosis model of power transformers based on feature quantity optimization and ICA-SVM[J]. Power System Protection and Control, 2019, 47(17): 163–170
[23] 康兵, 杨勇, 李振兴, 等. 基于实际运行数据的配电变压器故障原因多维度分析[J]. 智慧电力, 2019, 47(3): 66-70, 116.
KANG Bing, YANG Yong, LI Zhenxing, et al. Multidimensional analysis of causes of distribution transformer fault based on actual operation data[J]. Smart Power, 2019, 47(3): 66-70, 116.
[24] 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
[25] 张利伟. 油浸式电力变压器故障诊断方法研究[D]. 北京: 华北电力大学, 2014.
ZHANG Liwei. Study on fault diagnosis approaches for oil-immersed power transformers[D]. Beijing: North China Electric Power University, 2014.

基于混合采样和支持向量机的变压器故障诊断

Transformer Fault Diagnosis Based on Hybrid Sampling and Support Vector Machines

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郑涛, 于佳旭, 眭程曦, 申由, 薛玉石, 武剑. 基于磁路耦合的Sen变压器差动保护方案[J]. 中国电力, 2025, 58(3): 108-118.
[2]	宋许鹏, 杨小洋, 樊征臻. 基于电流合成矢量轨迹特性的双馈风电场主变压器差动保护[J]. 中国电力, 2025, 58(2): 9-21.
[3]	张旭, 王淳, 胡奕涛, 陈锐凯, 刘昆, 郭志东, 钟俊勋. 面向短时过载及长期轻载的配变侧储能配置与调度双层优化[J]. 中国电力, 2025, 58(1): 174-184.
[4]	彭寒梅, 尹棠, 肖千皓, 谭貌, 苏永新, 李辉. 高比例分布式电源配电网中低压柔性互联协调规划[J]. 中国电力, 2024, 57(8): 117-129.
[5]	郑鹏, 韩鹏程, 王国栋, 娄颖. 中压配电线路断线高阻接地故障精细化诊断方法[J]. 中国电力, 2024, 57(4): 220-228.
[6]	胡云鹏, 都成刚, 齐军, 郑日红, 阿敏夫, 张浩, 梁永亮. 基于D-S证据理论的配电网接地故障原因综合辨识模型[J]. 中国电力, 2024, 57(10): 133-142.
[7]	朱佳, 王峰, 李一泉, 焦邵麟, 徐晓春, 赵青春. 基于Tanimoto相似度的变压器零序差动保护约束方案[J]. 中国电力, 2023, 56(8): 193-199.
[8]	徐艳春, 范钟耀, 孙思涵, MI Lu. 基于去趋势分析的大规模双馈风电场送出变压器差动保护[J]. 中国电力, 2023, 56(7): 186-197.
[9]	辛全金, 李晓华, 杨义, 李俊聪, 夏能弘. 基于冗余卷积编解码器的变压器噪声抑制[J]. 中国电力, 2023, 56(4): 112-118.
[10]	黄辉, 杨智豪, 魏建国, 邓辉, 刘诣. 变压器套管局部放电射频信号在外部空间的分布特征[J]. 中国电力, 2023, 56(4): 175-183.
[11]	曹赋禄, 赵晋斌, 潘超, 毛玲, 屈克庆. 基于DFFT的低压直流线路主动式接地故障定位方法[J]. 中国电力, 2023, 56(4): 184-191.
[12]	田宇, 黄婧, 谢枭, 王若昕, 沈丹青, 何丽娜, 杨凯帆, 陈汝科. 主动配电网无功补偿和OLTC鲁棒多目标优化配置[J]. 中国电力, 2023, 56(3): 94-99.
[13]	李刚, 孟坤, 贺帅, 刘云鹏, 杨宁. 考虑特征耦合的Bi-LSTM变压器故障诊断方法[J]. 中国电力, 2023, 56(3): 100-108,117.
[14]	徐一伦, 张彬桥, 黄婧, 谢枭, 王若昕, 沈丹青, 何丽娜, 杨凯帆. 考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测[J]. 中国电力, 2023, 56(2): 143-149.
[15]	韩伟, 段文岩, 杜兴伟, 姚峰, 马伟东, 刘磊. 基于数字孪生的在运安控系统故障诊断方法[J]. 中国电力, 2023, 56(11): 121-127.

模态框（Modal）标题

基于混合采样和支持向量机的变压器故障诊断

Transformer Fault Diagnosis Based on Hybrid Sampling and Support Vector Machines

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics