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

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (701 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对变压器油中溶解气体含量分布的长尾效应引起故障样本信息缺失,属于零样本问题,从而导致故障诊断准确率低的问题,提出一种基于变权属性矩阵的变压器零样本故障诊断技术。首先,采用改进的高效通道注意力网络-堆栈式自编码器（Improved Efficient Channel Attention Network-Stack Autoencoder, IECANet-SAE）网络构建特征提取模块,自适应地提取油中气体数据的关键特征信息;其次,利用基于潜在狄利克雷分布的主题建模方法构建变权属性矩阵;最后,提出基于神经网络的朴素贝叶斯（Neural Naive Bayes, NNB）方法学习已知故障特征信息与属性矩阵的空间映射关系,建立零样本故障诊断模型并依靠模型实现未知故障类型诊断。应用IEC TC 10故障数据库及典型故障数据对所提方法加以验证。试验结果表明,所提出的方法具有更佳的诊断效果,且在零样本条件下故障诊断平均准确率高达到83%,平均诊断时间达0.18s。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	雷蕾潇
	何怡刚
	姚其新
	邢致恺

关键词 ：零样本学习, 特征提取, 故障诊断, 变权属性矩阵

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

PACS:

TM407

基金资助:

国家重点研发计划“智能电网技术与装备”专项“电力物联网关键技术”项目(2020YFB0905900) ,国家自然科学基金(52207134、52207221)和武汉市局科技计划项目(20201G01)

通讯作者: 何怡刚男,1966年生,教授,博士生导师,研究方向为混合信号电路故障诊断、电子设备可靠性和通信信道建模与监测等。E-mail：yghe1221@whu.edu.cn

作者简介: 雷蕾潇女,1994年生,博士研究生,研究方向为变压器故障诊断。E-mail：leixiaolei@whu.edu.cn

引用本文:

雷蕾潇, 何怡刚, 姚其新, 邢致恺. 基于变权属性矩阵的变压器零样本故障诊断技术[J]. 电工技术学报, 0, (): 1335-1335. Lei Leixiao, He Yigang, Yao Qixin, Xing Zhikai. Zero-Shot Fault Diagnosis Technique of Transformer Based on Weighted Attribute Matrix. Transactions of China Electrotechnical Society, 0, (): 1335-1335.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.231335 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/1335

[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(02):337-348.
Liu Yunpeng, Xu Qiang, Li Gang, et al.Application Review of Arti-ficial Intelligence Driven Data Analytics Technology in Power Trans-former State Maintenance. High Voltage Technology, 2019, 45(2): 337-348.
[2] .变压器油中溶解气体分析和判断导则:DL/T 722 2014[S].北京:国家能源局,2014.
Guide to the analysis and the diagnosis of gases dissolved in transformer oil:DL/T 722 2014[S]. Beijing, China: National Energy Adminis-tra-tion,2014.
[3] .TAHAI B, HOBALLAH A, GHONEIM S S. 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): 222-230.77
[4] .SOUAHLIA S,BACHA K, CHAARI A.MLP neural network-based decision for power transformers fault diagnosis using an improved com-bination of Rogers and Doernenburg ratios DGA([J]. International Journal of Electrical Power and Energy Systems, 2012,43(l):1346-1353
[5] .XING Z, He Y.Multi-modal information analysis for fault diagnosis with time-series data from power transformer[J]International Journal of Electrical Power & Energy Systems,2022,144.
[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(01):83-94.
Du Houxian, Liu Hao, Lei Longwu et al.Research on Power transformer fault Detection based on Multi-characteristic value of Vibration Signal[J]. Transactions of China Electrotechnical Society,2023,38(01):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(03):667-675.
Li Dianyang, Zhang Yujie, Feng Jian et al.Multi-dimensional Diagnosis of Transformer Fault Samples and Reliability Analysis of Results[J]. Transactions of China Electrotechnical Society,2022,37(03):667-675.
[8] .HONG C, QIU S, GAO W. fault Diagnosis of Distribution Trans-formers by Combining EEMDAN and GCN[J]. Journal of Elec-tronic 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.Fault diagnosis method of transformer Machinery based on point symmetry transformation and image matching[J]. Transactions of China Electrotechnical Society, 2019,36(17):3614-3626.
[10] .XU Y, BAO L, GUAN Zh, 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(S2):467-476.
ZHANG Lishi, LIANG Deliang, LIU Hua et al. Hybrid distribution transformer fault identification based on wavelet transform and logistic steele regression[J]. Journal of Electrotechnology,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(S1):84-94.
Ge Leijiao, Liao Wenlong, Wang Yusen et al.Transformer fault data enhancement method based on improved autoencoder with insufficient data[J].Transactions of China Electrotechnical Society, 21,36(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, Zhong Hongshan, Ma Libo et al. A Multi-depth Neural Network Integrated Fault Recognition Method for Transformers[J]. Journal of China Institute of Electrical Engineers, 2021, 41(23):823-821.
[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 Jiakang, Wu Weimei, Liang Haohao et al. Fault Recognition Method for Transformers Based on Adaptive Limit Learning Machine[J]. 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(04):32-42.
Wang Yan, Li Wei, Zhao Hongshan et al. Transformer Fault Diagnosis Method Based on DBN-SSAELM and Oil Soluble Gas Analysis[J]. Protective and Control of Power Systems, 2023, 51(4):32-42.
[16] .C. H. Lampert, H. Nickisch,S. Harmeling, “Learning to detect unseen object classes by between-class attribute transfer,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, Jun. 2009. doi: 10.1109/cvpr.2009.5206594.
[17] .C. H. Lampert, H. Nickisch,S. Harmeling, “Attribute-Based Classification for Zero-Shot Visual Object Categorization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 453-465, Mar. 2014, doi: 10.1109/tpami.2013.140.
[18] .P. Gong, X. Wang, Y. Cheng, Z. J. Wang,Q. Yu, “Zero-Shot Classification Based on Multitask Mixed Attribute Relations and Attribute-Specific Features,” IEEE Transactions on Cognitive and Developmental Systems, vol. 12, no. 1, pp. 73-83, Mar. 2020, doi: 10.1109/tcds.2019.2902250.
[19] .F. SHEN and Z.-M. LU, “A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning,” IEICE Transactions on Information and Systems, vol. E103.D, no. 6, pp. 1419-1422, Jun. 2020, doi: 10.1587/transinf.2019edl8176.
[20] .XU J, ZHOU L, ZHAO W, et al.Zero-shot learning for compound fault diagnosis of bearings[J]. Expert Systems With Applications,2022,190.
[21] .GAO Y, GAO L, LI X, et al.A zero?shot learning method for fault diagnosis under unknown working loads[J].Journal of Intelligent Manu-facturing,2020,31:899-909
[22] .GUPTA A, GUPTA H, BISWAS B, et al.An Unseen fault Classification Approach for Smart Appliances Using Ongoing Multivariate Time Se-ries[J].IEEE TRANSACTIONS ON INDUSTRIAL INfOR-MAT-ICS,2021,17(6).
[23] .PAN T, CHEN J, XIE J, et al.Deep feature Generating Network: A New Method for Intelligent fault Detection of Mechanical Systems Under Class Imbalance[J]. IEEE TRANSACTIONS ON INDUSTRIAL IN-FORMATICS,2021,17(9).
[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 Cluster Analysis of transformer oil chromatographic Data based on Chaotic sequence[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(07):1505-1515.
Yang Zhichun, Shen Yu, Yang Fan et al.Transfer learning fault diagnosis Model of distribution transformer considering multi-factor situation evolution[J].Transactions of China Electrotechnical Society,2019,34(07):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,2022,37(06):1572-1582.
JIANG Yanan, YU Yongjin, LI Changyun.Evaluation method of insulating paper machine-thermal aging state based on improved TOPSIS model[J]. Electrotechnology,2022,37(06):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(05):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 Edition), 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(09):974-983.
Xi Xiaowen, Guo Ying, Song Xina et al. Visualization Study of Technical Similarity Based on Word2Vec and LDA Topic Model[J]. Journal of Intelligence, 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].华中科技大学,2022.
Shi Hui.Research on Text Vectorization and Classification Based on TF-IDF and Machine Learning [D]. Huazhong University of Science and Technology, 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]. 中国电力出版社, 北京, 2014.
Operation and Maintenance Department of State Grid Corporation. Typical application Cases of Power Grid equipment condition Detection Tech-nology (2011-2013) [M]. China Electric Power Press, Beijing, 2014.
[31] .国家电网公司运维检修部. 变压器类设备典型故障案例汇编(2006~2010年)[M]. 中国电力出版社, 北京, 2012.
Operation and Maintenance Department of State Grid Corporation. Typical fault Case Compilation of Transformer Equipment (2006~2010) [M]. China Electric Power Press, Beijing, 2012.
[32] .X. Ma, Y. Hu, M. Wang, F. Li,Y. Wang, Degradation State Partition and Compound Fault Diagnosis of Rolling Bearing Based on Personalized Multilabel Learning[J], IEEE Transactions on Instrumentation and Measurement,2021,36:1-11