数据不足条件下基于改进自动编码器的变压器故障数据增强方法

doi:10.19595/j.cnki.1000-6753.tces.L90083

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1868 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract There are few transformer faults, which makes the methods of transformer fault diagnosis based on machine learning lack of data. For this reason, a method based on improved auto-encoder (IAE) is proposed to augment transformer fault data. Firstly, to solve the problem of limited data and lack of diversity in the traditional automatic encoder, an improved strategy for generating samples for transformer faults is proposed. Secondly, considering that the traditional convolutional neural network will lose a lot of feature information in the pooling operation, the improved convolutional neural network (ICNN) is constructed as the classifier of fault diagnosis. Finally, the effectiveness and adaptability of the proposed method are verified by the actual data. The simulation results show that IAE can take into account the distribution and diversity of data at the same time, and the generated transformer fault data can improve the performance of the classifier better than the traditional augmentation methods such random over-sampling method, synthetic minority over-sampling technique, and auto-encoder. Compared with traditional classifiers, ICNN has higher fault diagnosis accuracy before and after data augmentation.

Key words： Insufficient data transformer fault diagnosis improved auto-encoder

Received: 18 June 2020

PACS:

TM721

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Ge Leijiao
	Liao Wenlong
	Wang Yusen
	Song Like

Cite this article:

Ge Leijiao,Liao Wenlong,Wang Yusen等. Data Augmentation Method for Transformer Fault Based on Improved Auto-Encoder Under the Condition of Insufficient Data[J]. Transactions of China Electrotechnical Society, 2021, 36(zk1): 84-94.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.L90083 OR https://dgjsxb.ces-transaction.com/EN/Y2021/V36/Izk1/84

[1] 齐波, 王一鸣, 张鹏, 等. 基于自决策主动纠偏的电力变压器油色谱诊断模型[J]. 高电压技术, 2020, 46(1): 23-32.
Qi Bo, Wang Yiming, Zhang Peng, et al.Oil chroma- tography diagnosis model of power transformer based on self-decision active rectification[J]. High Voltage Engineering, 2020, 46(1): 23-32.
[2] 齐波, 王一鸣, 张鹏, 等. 面向变压器油色谱趋势预测的深度递归信念网络[J]. 电网技术, 2019, 43(6): 1892-1900.
Qi Bo, Wang Yiming, Zhang Peng, et al.Deep recurrent belief network model for trend prediction of transformer oil chromatography data[J]. Power System Technology, 2019, 43(6): 1892-1900.
[3] 李恩文, 王力农, 宋斌, 等. 基于混沌序列的变压器油色谱数据并行聚类分析[J]. 电工技术学报, 2019, 34(24): 5104-5114.
Li Enwen, Wang Linong, Song Bin, et al.Parallel clustering analysis of dissolved gas analysis data based on chaotic sequences[J]. Transactions of China Electrotechnical Society, 2019, 34(24): 5104-5114.
[4] 张燕, 方瑞明. 基于油中溶解气体动态网络标志物模型的变压器缺陷预警与辨识[J]. 电工技术学报, 2020, 35(9): 2032-2041.
Zhang Yan, Fang Ruiming.Fault detection and identification of transformer based on dynamical network marker model of dissolved gas in oil[J]. Transactions of China Electrotechnical Society, 2020, 35(9): 2032-2041.
[5] Senoussaoui M E, Brahami M, Fofana I, et al.Combining and comparing various machine-learning algorithms to improve dissolved gas analysis interpretation[J]. IET Generation Transmission & Distribution, 2018, 12(15): 3673-3679.
[6] Benmahamed Y, Teguar M, Boubakeur A, et al.Application of SVM and KNN to duval pentagon 1 for transformer oil diagnosis[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(6): 3443-3451.
[7] 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.
[8] Aizpurua J I, Catterson V M, Stewart B G, et al.Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2018, 25(2): 494-506.
[9] Punnappurath A, Brown M S.Learning raw image reconstruction-aware deep image compressors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(4): 1013-1019.
[10] Guo Zhe, Li Xiang, Huang Heng, et al.Deep learning-based image segmentation on multimodal medical imaging[J]. IEEE Transactions on Radiation and Plasma Medical Sciences, 2019, 3(2): 162-169.
[11] 石鑫, 朱永利, 萨初日拉, 等. 基于深度信念网络的电力变压器故障分类建模[J]. 电力系统保护与控制, 2016, 44(1): 71-76.
Shi Xin, Zhu Yongli, Sa Churila, et al.Power transformer fault classifying model based on deep belief network[J]. Power System Protection and Control, 2016, 44(1): 71-76.
[12] 代杰杰, 宋辉, 杨祎, 等. 基于油中气体分析的变压器故障诊断ReLU-DBN方法[J]. 电网技术, 2018, 42(2): 658-664.
Dai Jiejie, Song Hui, Yang Yi, et al.Dissolved gas analysis of insulating oil for power transformer fault diagnosis based on ReLU-DBN[J]. Power System Technology, 2018, 42(2): 658-664.
[13] Afrasiabi S, Afrasiabi M, Parang B, et al.Integration of accelerated deep neural network into power transformer differential protection[J]. IEEE Transa- ctions on Industrial Informatics, 2020, 16(2): 865-876.
[14] 谢桦, 陈俊星, 赵宇明, 等. 基于SMOTE和决策树算法的电力变压器状态评估知识获取方法[J]. 电力自动化设备, 2020, 40(2): 137-142.
Xie Hua, Chen Junxing, Zhao Yuming, et al.Knowledge acquisition method of power transformer condition assessment based on SMOTE and decision tree algorithm[J]. Electric Power Automation Equipment, 2020, 40(2): 137-142.
[15] 刘云鹏, 和家慧, 许自强, 等. 基于SVM SMOTE的电力变压器故障样本均衡化方法[J]. 高电压技术, 2020, 46(7): 2522-2529.
Liu Yunpeng, He Jiahui, Xu Ziqiang, et al.The equalization method of power transformer fault sample based on SVM SMOTE[J]. High Voltage Engineering, 2020, 46(7): 2522-2529.
[16] 刘云鹏, 许自强, 和家慧, 等. 基于条件式Wasserstein生成对抗网络的电力变压器故障样本增强技术[J]. 电网技术, 2020, 44(4): 1505-1513.
Liu Yunpeng, Xu Ziqiang, He Jiahui, et al.Data augmentation method for power transformer fault diagnosis based on conditional Wasserstein gener- ative adversarial network[J]. Power System Tech- nology, 2020, 44(4): 1505-1513.
[17] Lee J, Sun S, Yang S, et al.Bidirectional recurrent auto-encoder for photoplethysmogram denoising[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(6): 2375-2385.
[18] Kingma D P, Welling M.Auto-encoding variational bayes[C]//International Conference on Learning Representations, Banff, Canada, 2014: 1-14.
[19] 王丙参, 魏艳华, 孙永辉. 利用舍选抽样法生成随机数[J]. 重庆师范大学学报: 自然科学版, 2013, 30(6): 86-91.
Wang Bingcan, Wei Yanhua, Sun Yonghui, et al.Generate random number by using acceptance rejection method[J]. Journal of Chongqing Normal University: Natural Science Edition, 2013, 30(6): 86-91.
[20] Sabour S, Frosst N, Hinton G E, et al.Dynamic routing between capsules[C]//Neural Information Pro- cessing Systems, California, USA, 2017: 3856-3866.
[21] 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/OL]. 高电压技术: 1-11 [2020-12-30]. https://doi.org/10.13336/j.1003-6520.hve.20200577.
Yang Dechang, Liao Wenlong, Ren Xiang, et al. Fault diagnosis of transformer based on capsule network[J/OL]. High Voltage Engineering: 1-11 [2020-12-30].https://doi.org/10.13336/j.1003-6520. hve.20200577.
[22] 尹金良. 基于相关向量机的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, 2013.
[23] Li Enwen. Dissolved gas data in transformer oil-fault diagnosis of power transformers with membership degree[J/OL]. IEEE Dataport: 1-4[2020-05-31]. http:// dx.doi.org/10.21227/h8g0-8z59.