Disconnector Fault Diagnosis Method Based on Autonomous-cognition Deep Temporal Clustering Representation

doi:10.11985/2024.01.030

Abstract

Abstract:

In order to accurately identify the fault of the disconnector, determine the fault type, and ensure the stable operation of the power grid, an autonomous-cognition deep temporal clustering representation model(AC-DTCR) is proposed to diagnose the fault of the disconnector. In the case of a small amount of data, and the class label information is not available, time series clustering is a very good unsupervised learning technology, and the AC-DTCR model integrates time reconstruction and K-means targets. In order to improve the ability of the encoder, a false sample generation strategy and auxiliary classification task are proposed to improve the cluster structure and obtain a cluster-specific time representation. According to the motor current data obtained from the fault simulation experiment of high voltage disconnector, the AC-DTCR model is divided into four parts to train the experimental data. The results show that the model has good classification performance. Compared with the traditional classification model and time series clustering model, it has higher accuracy and can be applied to the field of power equipment fault diagnosis.

Key words: Deep temporal clustering representation, self-attention, autonomous-cognition, fault diagnosis, K-means

CLC Number:

TM56

XIE Qian, XU Haolan, WANG Tong, ZHAO Fashou, ZHANG Gang, DANG Jian. Disconnector Fault Diagnosis Method Based on Autonomous-cognition Deep Temporal Clustering Representation[J]. Journal of Electrical Engineering, 2024, 19(1): 281-289.

Figures/Tables 14

References 20

[1]	构建基于“大云物移智”等现代信息通信技术的智能运检体系[J]. 电力设备管理, 2019,4:26-27.
	Construction of intelligent operation inspection system based on modern information and communication technologies such as “big cloud and object mobile intelligence”[J]. Electric Power Equipment Management, 2019,4:26-27.
[2]	邱志斌, 阮江军, 黄道春, 等. 高压隔离开关机械故障分析及诊断技术综述[J]. 高压电器, 2015, 51(8):171-179.
	QIU Zhibin, RUAN Jiangjun, HUANG Daochun, et al. Review of mechanical fault analysis and diagnosis technology of high voltage disconnector[J]. High Voltage Apparatus, 2015, 51(8):171-179.
[3]	KIM K, PARLOS A G, BHARADWAJ R M. Sensorless fault diagnosis of induction motors[J]. IEEE Transactions on Industrial Electronics, 2003, 50(5):1038-1051. doi: 10.1109/TIE.2003.817693
[4]	李少华, 张文涛, 宋亚凯, 等. 基于高压隔离开关振动信号的故障诊断方法分析[J]. 内蒙古电力技术, 2018, 36(1):89-92.
	LI Shaohua, ZHANG Wentao, SONG Yakai, et al. Analysis of fault diagnosis method based on vibration signal of high voltage disconnector[J]. Inner Mongolia Electric Power Technology, 2018, 36(1):89-92.
[5]	ZHAO Lihua, HONG Guo, WANG Zelong, et al. Research on fault vibration signal features of GIS disconnector based on EEMD and kurtosis criterion[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2021, 16(5):677-686. doi: 10.1002/tee.v16.5
[6]	王黎明, 何建明. 电动隔离开关机械故障状态监测的设想[J]. 浙江电力, 2006,3:56-59.
	WANG Liming, HE Jianming. Assumption of mechanical fault condition monitoring of electric disconnector[J]. Zhejiang Electric Power, 2006,3:56-59.
[7]	FUJITA A, SEVERINO P, KOJIMA K, et al. Functional clustering of time series gene expression data by Granger causality[J]. BMC Systems Biology, 2012,6:1-12.
[8]	CHAN P K, MAHONEY M V. Modeling multiple time series for anomaly detection[C]// Fifth IEEE International Conference on Data Mining(ICDM’05). IEEE,2005:8.
[9]	AGHABOZORGI S, SHIRKHORSHIDI A S, WAH T Y. Time-series clustering:A decade review[J]. Information Systems, 2015,53:16-38.
[10]	孙志鹏, 孙志龙, 魏建. 基于决策树支持向量机算法的电力变压器故障诊断研究[J]. 电气工程学报, 2019, 14(4):42-45.
	SUN Zhipeng, SUN Zhilong, WEI Jian. Research on fault diagnosis of power transformer based on decision tree support vector machine algorithm[J]. Journal of Electrical Engineering, 2019, 14(4):42-45.
[11]	于聪, 汤凯波, 李哲, 等. 基于BP神经网络与改进DS证据融合的GIS设备局放故障识别[J/OL]. 电气工程学报:1-9[2023-10-21]. http://kns.cnki.net/kcms/detail/10.1289.TM.20230725.1006.006.html.
	YU Cong, TANG Kaibo, LI Zhe, et al. PDS fault identification of GIS equipment based on BP neural network and improved DS evidence fusion[J/OL]. Journal of Electrical Engineering:1-9[2023-10-21]. http://kns.cnki.net/kcms/detail/10.1289.TM.20230725.1006.006.html.
[12]	LEI Huang, XIA Yingcun, QIN Xu. Estimation of semivarying coefficient time series models with ARMA errors[J]. The Annals of Statistics, 2016, 44(4):1618-1660.
[13]	CAI Zongwu, FAN Jianqing, YAO Qiwei. Functional-coefficient regression models for nonlinear time series[J]. Journal of the American Statistical Association, 2000, 95(451):941-956. doi: 10.1080/01621459.2000.10474284
[14]	YANG Yi, SHEN Hengtao, Ma Zhigang, et al. ℓ2, 1-norm regularized discriminative feature selection for unsupervised learning[C]// IJCAI International Joint Conference on Artificial Intelligence. 2011.
[15]	LI Zechao, YANG Yi, LIU Jing, et al. Unsupervised feature selection using nonnegative spectral analysis[C]// Proceedings of the AAAI Conference on Artificial Intelligence, 2012, 26(1):1026-1032.
[16]	钱明杰, 翟承祥. 鲁棒性的无监督特征选择[C]// 人工智能国际联合会议, 2013.
	QIAN Mingjie, ZHAI Chengxiang. Robust unsupervised feature selection[C]// International Joint Conference on Artificial Intelligence, 2013.
[17]	SHI Lei, DU Liang, SHEN Yidong. Robust spectral learning for unsupervised feature selection[C]// In 2014 IEEE International Conference on Data Mining,IEEE,2014: 977-982.
[18]	DU Xinlong, HAJJAR J F, BOND R B, et al. Clustering and selection of hurricane wind records using autoencoder and K-means algorithm[J]. Journal of Structural Engineering, 2023, 149(8):4023096. doi: 10.1061/JSENDH.STENG-12110
[19]	TJOSTHEIM D, AUESTAD B H. Nonparametric identification of nonlinear time series:Projections[J]. Journal of the American Statistical Association, 1994, 89(428):1398-1409.
[20]	MA Qianli, LI Sen, SHEN Lifeng, et al. End-to-end incomplete time-series modeling from linear memory of latent variables[J]. IEEE Transactions on Cybernetics, 2019, 50(12):4908-4920. doi: 10.1109/TCYB.6221036