基于变权属性矩阵的变压器零样本故障诊断技术

doi:10.19595/j.cnki.1000-6753.tces.231335

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2531 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In actual engineering applications, transformer failure is a small probability event, so there is little fault data and low data quality, and the actual data distribution often exhibits a long tail effect. However, traditional data-driven fault diagnosis methods require a large amount of fault data for sample training, which leads to problems such as low model accuracy and model failure in the actual application of traditional supervised models. To address this type of problem, this article proposes a zero-shot fault diagnosis technology for transformers based on variable weight attribute matrix. The spatial mapping function between known fault attribute matrices and dissolved gas data is learned to achieve accurate identification of unknown faults.
Firstly, an improved efficient channel attention network-stack autoencoder (IECANet-SAE) network is used to construct a data feature extraction network. Among them, convolutional neural networks extract local important information from input data through convolutional operations, while efficient channel attention networks focus on important information by learning attention weights between channels. The use of feature extraction networks solves the problem of quality and quantity of fault sample data, while adaptively extracting key feature information from dissolved gas data. Secondly, based on the description information of transformer faults, a variable weight attribute matrix is constructed using a topic modeling method based on potential Dirichlet distribution. This includes fault type classification, topic word extraction, similarity calculation, and matrix construction. By enhancing the connection between fault labels and fault information through the fault attribute matrix, data sharing between known and unknown class faults can be achieved. Then, the neural network-based Naive Bayes (NNB) method is used to learn the mapping function between each attribute vector in the fault attribute matrix and the important feature information of known class faults in the feature space. Based on the mapping function, the unknown class feature information is mapped to the same feature space to obtain the corresponding attribute vector. Finally, based on Bayesian principle, the maximum likelihood estimation formula is used to obtain the most likely fault type for unknown class faults.
The proposed method was validated using the IEC TC 10 fault database and relevant authoritative literature that has been publicly published. From the accuracy of fault diagnosis results, it can be seen that data-driven fault diagnosis models are difficult to achieve fault diagnosis without sample training, so the diagnostic accuracy of this type of algorithm is 0. On the basis of the transformer fault attribute matrix proposed in this article, zero-shot fault diagnosis is achieved, which has a higher accuracy of up to 0.83 compared to direct attribute prediction (DAP) and indirect attribute prediction (IAP) methods. From the fault diagnosis time, it can be seen that the DAP and IAP methods analyze the original data, so the calculation time is slightly longer due to the large amount of data. The method in this article retains some important features in the data, reducing computational time to a certain extent. The diagnostic time is about 0.18 seconds, which is slightly faster than other methods.
The following conclusions can be drawn through experimental analysis: (1) The use of LDA based topic modeling method effectively enhances the correlation between fault information and fault sample labels, solving the problem of difficult fault diagnosis under the condition of no training samples. (2) Extracting the main features of dissolved gas data through the IECANet-SAE network has better fault feature separation performance compared to other methods, which helps to improve transformer fault diagnosis performance. (3) The NNB algorithm is used to construct the mapping relationship between important feature data and fault attribute matrix, efficiently and accurately identifying unknown fault types. The average accuracy and diagnostic time of the diagnostic results are superior to other methods.

Key words： Zero-shot learning feature extraction fault diagnosis weighted attribute matrix

Received: 17 August 2023

PACS:

TM407

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Lei Leixiao
	He Yigang
	Yao Qixin
	Xing Zhikai

Cite this article:

Lei Leixiao,He Yigang,Yao Qixin等. Zero-Shot Fault Diagnosis Technique of Transformer Based on Weighted Attribute Matrix[J]. Transactions of China Electrotechnical Society, 2024, 39(20): 6577-6590.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.231335 OR https://dgjsxb.ces-transaction.com/EN/Y2024/V39/I20/6577

[1] 刘云鹏, 许自强, 李刚, 等. 人工智能驱动的数据分析技术在电力变压器状态检修中的应用综述[J]. 高电压技术, 2019, 45(2): 337-348.
Liu Yunpeng, Xu Ziqiang, Li Gang, et al.Review on applications of artificial intelligence driven data analysis technology in condition based maintenance of power transformers[J]. High Voltage Engineering, 2019, 45(2): 337-348.
[2] 国家能源局. DL/T 722-2014 变压器油中溶解气体分析和判断导则[S]. 北京: 中国电力出版社, 2015.
[3] Taha I B M, Hoballah A, Ghoneim S S M. Optimal ratio limits of Rogers' four-ratios and IEC 60599 code methods using particle swarm optimization fuzzy-logic approach[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2020, 27(1): 222-230.
[4] Souahlia S, Bacha K, Chaari A.MLP neural network-based decision for power transformers fault diagnosis using an improved combination of Rogers and Doernenburg ratios DGA[J]. International Journal of Electrical Power & Energy Systems, 2012, 43(1): 1346-1353.
[5] Xing Zhikai, He Yigang.Multi-modal information analysis for fault diagnosis with time-series data from power transformer[J]. International Journal of Electrical Power & Energy Systems, 2023, 144: 108567.
[6] 杜厚贤, 刘昊, 雷龙武, 等. 基于振动信号多特征值的电力变压器故障检测研究[J]. 电工技术学报, 2023, 38(1): 83-94.
Du Houxian, Liu Hao, Lei Longwu, et al.Power transformer fault detection based on multi-eigenvalues of vibration signal[J]. Transactions of China Electrotechnical Society, 2023, 38(1): 83-94.
[7] 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.
[8] Hong Cui, Qiu Shida, Gao Wei.Fault diagnosis of distribution transformers by combining EEMDAN and GCN[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(12): 86-96.
[9] 赵莉华, 徐立, 刘艳, 等. 基于点对称变换与图像匹配的变压器机械故障诊断方法[J]. 电工技术学报, 2021, 36(17): 3614-3626.
Zhao Lihua, Xu Li, Liu Yan, et al.Transformer mechanical fault diagnosis method based on symmetrized dot patter and image matching[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3614-3626.
[10] Xu Yaosong, Bao Liming, Guan Zhifeng, et al.Research on transformer fault diagnosis based on IPPA optimized PNN[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(10): 138-145.
[11] 张立石, 梁得亮, 刘桦, 等. 基于小波变换与逻辑斯蒂回归的混合式配电变压器故障辨识[J]. 电工技术学报, 2021, 36(增刊2): 467-476.
Zhang Lishi, Liang Deliang, Liu Hua, et al.Fault identification of hybrid distribution transformer based on wavelet transform and logistic regression[J]. Transactions of China Electrotechnical Society, 2021, 36(S2): 467-476.
[12] 葛磊蛟, 廖文龙, 王煜森, 等. 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[J]. 电工技术学报, 2021, 36(增刊1): 84-94.
Ge Leijiao, Liao Wenlong, Wang Yusen, et al.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(S1): 84-94.
[13] 曲岳晗, 赵洪山, 马利波, 等. 多深度神经网络综合的电力变压器故障识别方法[J]. 中国电机工程学报, 2021, 41(23): 8223-8231.
Qu Yuehan, Zhao Hongshan, Ma Libo, et al.Multi-depth neural network synthesis method for power transformer fault identification[J]. Proceedings of the CSEE, 2021, 41(23): 8223-8231.
[14] 吴杰康, 覃炜梅, 梁浩浩, 等. 基于自适应极限学习机的变压器故障识别方法[J]. 电力自动化设备, 2019, 39(10): 181-186.
Wu Jiekang, Qin Weimei, Liang Haohao, et al.Transformer fault identification method based on self-adaptive extreme learning machine[J]. Electric Power Automation Equipment, 2019, 39(10): 181-186.
[15] 王艳, 李伟, 赵洪山, 等. 基于油中溶解气体分析的DBN-SSAELM变压器故障诊断方法[J]. 电力系统保护与控制, 2023, 51(4): 32-42.
Wang Yan, Li Wei, Zhao Hongshan, et al.Transformer DGA fault diagnosis method based on DBN-SSAELM[J]. Power System Protection and Control, 2023, 51(4): 32-42.
[16] Lampert C H, Nickisch H, Harmeling S.Learning to detect unseen object classes by between-class attribute transfer[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 951-958.
[17] Lampert C H, Nickisch H, Harmeling S.Attribute-based classification for zero-shot visual object categorization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(3): 453-465.
[18] Gong Ping, Wang Xuesong, Cheng Yuhu, et al.Zero-shot classification based on multitask mixed attribute relations and attribute-specific features[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(1): 73-83.
[19] Shen Fengli, Lu Zheming. A semantic similarity supervised autoencoder for zero-shot learning[J]. IEICE Transactions on Information and Systems, 2020, E103.D(6): 1419-1422.
[20] Xu Juan, Zhou Long, Zhao Weihua, et al.Zero-shot learning for compound fault diagnosis of bearings[J]. Expert Systems with Applications, 2022, 190: 116197.
[21] Gao Yiping, Gao Liang, Li Xinyu, et al.A zero-shot learning method for fault diagnosis under unknown working loads[J]. Journal of Intelligent Manufacturing, 2020, 31(4): 899-909.
[22] Gupta A, Gupta H P, Biswas B, et al.An unseen fault classification approach for smart appliances using ongoing multivariate time series[J]. IEEE Transactions on Industrial Informatics, 2021, 17(6): 3731-3738.
[23] Pan Tongyang, Chen Jinglong, Xie Jingsong, et al.Deep feature generating network: a new method for intelligent fault detection of mechanical systems under class imbalance[J]. IEEE Transactions on Industrial Informatics, 2021, 17(9): 6282-6293.
[24] 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.
[25] 杨志淳, 沈煜, 杨帆, 等. 考虑多元因素态势演变的配电变压器迁移学习故障诊断模型[J]. 电工技术学报, 2019, 34(7): 1505-1515.
Yang Zhichun, Shen Yu, Yang Fan, et al.A transfer learning fault diagnosis model of distribution transformer considering multi-factor situation evolution[J]. Transactions of China Electrotechnical Society, 2019, 34(7): 1505-1515.
[26] 姜雅男, 于永进, 李长云. 基于改进TOPSIS模型的绝缘纸机-热老化状态评估方法[J]. 电工技术学报, 2022, 37(6): 1572-1582.
Jiang Yanan, Yu Yongjin, Li Changyun.Evaluation method of insulation paper deterioration status with mechanical-thermal synergy based on improved TOPSIS model[J]. Transactions of China Electrotechnical Society, 2022, 37(6): 1572-1582.
[27] 李松, 舒世泰, 郝晓红, 等. 融合文本描述和层次类型的知识表示学习方法[J]. 浙江大学学报(工学版), 2023, 57(5): 911-920.
Li Song, Shu Shitai, Hao Xiaohong, et al.Knowledge representation learning method integrating textual description and hierarchical type[J]. Journal of Zhejiang University(Engineering Science), 2023, 57(5): 911-920.
[28] 席笑文, 郭颖, 宋欣娜, 等. 基于word2vec与LDA主题模型的技术相似性可视化研究[J]. 情报学报, 2021, 40(9): 974-983.
Xi Xiaowen, Guo Ying, Song Xinna, et al.Research on the technical similarity visualization based on word2vec and LDA topic model[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(9): 974-983.
[29] 石慧. 基于TF-IDF和机器学习的文本向量化与分类研究[D]. 武汉: 华中科技大学, 2022.
[30] 国家电网公司运维检修部. 电网设备状态检测技术应用典型案例: 2011~2013年[M]. 北京: 中国电力出版社, 2014.
[31] 国家电网公司运维检修部. 高压开关设备典型故障案例汇编: 2006~2010年[M]. 北京: 中国电力出版社, 2012.
[32] Ma Xin, Hu Yu, Wang Menghui, et al.Degradation state partition and compound fault diagnosis of rolling bearing based on personalized multilabel learning[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3520711.