Transformer Fault Analysis Based on Bayesian Networks and Importance Measures

doi:10.1007/s12204-015-1636-5

Abstract

Abstract: Complex environment stresses bring many uncertainties to transformer fault. The Bayesian network (BN) can represent prior knowledge in the form of probability which makes it an effective tool to deal with the uncertain problems. This paper established a BN model for the transformer fault diagnosis with practical operation dataset and expert knowledge. Then importance measures are introduced to indentify the key attributes which affect the results of transformer diagnosis most. Moreover, a strategy was proposed to reduce the number of attribute in transformer fault detection and the resource cost was saved. At last, a diagnosis case of practical transformer was implemented to verify the effectiveness of this method.

Key words: transformer| fault diagnosis| Bayesian network (BN)| importance measures

摘要： Complex environment stresses bring many uncertainties to transformer fault. The Bayesian network (BN) can represent prior knowledge in the form of probability which makes it an effective tool to deal with the uncertain problems. This paper established a BN model for the transformer fault diagnosis with practical operation dataset and expert knowledge. Then importance measures are introduced to indentify the key attributes which affect the results of transformer diagnosis most. Moreover, a strategy was proposed to reduce the number of attribute in transformer fault detection and the resource cost was saved. At last, a diagnosis case of practical transformer was implemented to verify the effectiveness of this method.

关键词: transformer| fault diagnosis| Bayesian network (BN)| importance measures

CLC Number:

TB 114.3

REN Fang-yu (任方宇), SI Shu-bin* (司书宾), CAI Zhi-qiang (蔡志强), ZHANG Shuai (张帅). Transformer Fault Analysis Based on Bayesian Networks and Importance Measures[J]. Journal of shanghai Jiaotong University (Science), 2015, 20(3): 353-357.

References 10

[1]	Shrivastava K, Choubey A. Data mining approach with IEC based dissolved gas analysis for fault diagnosis of power transformer [J]. International Journal of Engineering Research and Technology, 2013,2(3): 1-11.
[2]	Liu C H, Chen T L, Yao L T, et al. Using data mining to dissolved gas analysis for power transformer fault diagnosis [C]//Proceedings of the 2012 International Conference on Machine Learning and Cybernetics.Xi’an, China: IEEE, 2012: 1952-1957.
[3]	Zhu Y L, Huo L M, Lu J L. Bayesian networks-based approach for power systems fault diagnosis [J]. IEEE Transactions on Power Delivery, 2006, 21(2): 634-639.
[4]	Xie S Y, Peng X F, Zhong X Y, et al. Fault diagnosis of the satellite power system based on the Bayesian network [C]//Proceedings of the 8th International Conference on Computer Science and Education. Colombo,Sri Lanka: IEEE, 2013: 1004-1008.
[5]	Li S M, Si S B, Xing L D, et al. Integrated importance of multi-state fault tree based on multi-state multi-valued decision diagram [J]. Journal of Risk and Reliability, 2014, 228(2): 200-208.
[6]	Si S B, Liu G M, Cai Z Q, et al. Using Bayesian networks to build a diagnosis and prognosis model for breast cancer [C]//Proceedings of the 18th International Conference on Industrial Engineering and Engineering Management. Changchun, China: IEEE, 2011:1795-1799.
[7]	Xie Q, Zeng H, Ruan L, et al. Transformer fault diagnosis based on Bayesian network and rough set reduction theory [C]//Proceedings of the 2013 IEEE TENCON Spring Conference. Sydney, Australia:IEEE, 2013: 262-266.
[8]	Baesens B, Vertraeten G, van den Poel D, et al.Bayesian network classifiers for identifying the slope of the customer lifecycle of long-life customers [J]. European Journal of Operational Research, 2004, 156(2):508-523.
[9]	Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers [J]. Machine Learning, 1997, 29(2-3): 131-163.
[10]	Kuo W, Zhu X Y. Some recent advances on importance measure in reliability [J]. IEEE Transactions on Reliability, 2012, 61(2): 344-360.

[1]	XU Yong, CAI Yunze, SONG Lin. Review of Research on Condition Assessment of Nuclear Power Plant Equipment Based on Data-Driven [J]. Journal of Shanghai Jiao Tong University, 2022, 56(3): 267-278.
[2]	LIU Xiuli, XU Xiaoli. A Fault Diagnosis Method Based on Feature Pyramid CRNN Network [J]. Journal of Shanghai Jiao Tong University, 2022, 56(2): 182-190.
[3]	NIE Rui, WANG Hongru. Fault Diagnosis of UAV Formation Actuator Based on Neural Network Observer [J]. Air & Space Defense, 2022, 5(2): 32-41.
[4]	MA Hangyu, ZHOU Di, WEI Yujie, WU Wei, PAN Ershun. Intelligent Bearing Fault Diagnosis Based on Adaptive Deep Belief Network Under Variable Working Conditions [J]. Journal of Shanghai Jiao Tong University, 2022, 56(10): 1368-1377.
[5]	MA Guohong (马国红), LI Jian (李健), HE Yinshui (何银水), XIAO Wenbo (肖文波). Weld Geometry Monitoring for Metal Inert Gas Welding Process with Galvanized Steel Plates Using Bayesian Network [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(2): 239-244.
[6]	HU Xiaoqiang,ZHONG Xunyu,ZHANG Xiaoli,PENG Xiafu,HE Ying. A Two-Level Fault Diagnosis Method for Gyro-Quadruplet Assisted by Support Vector Machine [J]. Journal of Shanghai Jiaotong University, 2020, 54(11): 1151-1156.
[7]	SONG Simeng (宋思蒙), CHEN Xiaoxin (陈孝信), QIAN Yong (钱勇), WANG Hui (王辉), ZHANG Yue (张悦), SHENG Gehao (盛戈皞), JIANG Xiuchen (江秀臣). Research on Time-Domain Transfer Impedance Measurement Technology for High Frequency Current Transformers in Partial Discharge Detection of Cables [J]. J Shanghai Jiaotong Univ Sci, 2020, 25(1): 10-17.
[8]	LI Dan (李丹), WANG Hongdong (王鸿东), LIANG Xiaofeng *(梁晓锋). Bayesian Network Based Approach for Diagnosis of Modified Sequencing Batch Reactor [J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(4): 417-429.
[9]	LU Cheng,XU Tingxue,WANG Hong. Fault Diagnosis of Terminal Guidance Radar Based on Attribute Granulation Clustering and Echo State Network [J]. Journal of Shanghai Jiaotong University, 2018, 52(9): 1112-1119.
[10]	YU Kun (俞昆), TAN Jiwen (谭继文), LIN Tianran (林天然). Fault Diagnosis of Rolling Element Bearing Using Multi-Scale Lempel-Ziv Complexity and Mahalanobis Distance Criterion [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(5): 696-701.
[11]	DENG Shijie (邓士杰), TANG Liwei (唐力伟), ZHANG Xiaotao (张晓涛). Research of Adaptive Neighborhood Incremental Principal Component Analysis and Locality Preserving Projection Manifold Learning Algorithm [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(2): 269-275.
[12]	JIN Zhijian,HONG Zhiyong,ZHAO Yue,LI Zhuyong,HUANG Zhen,WU Wei,ZHANG Zhiwei,LI Xiaofen,YAO Linpeng,SHENG Jie. Review of Technology and Development in the Power Applications Based on Second-Generation High-Temperature Superconductors [J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1155-1165.
[13]	JIA Lei,DONG Wei，SUN Xinya，JI Yindong，CHEN Hua. Soft Faults Diagnosis of Track Circuit with Tolerance Based on NodeVoltage Increments [J]. Journal of Shanghai Jiaotong University, 2017, 51(6): 679-685.
[14]	WU Bin1* (吴斌), XI Lifeng2 (奚立峰), FAN Sixia1 (范思遐), ZHAN Jian1 (占健). Fault Diagnosis for Wind Turbine Based on Improved Extreme Learning Machine [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(4): 466-473.
[15]	LIU Yinhua1* (刘银华), YE Xialiang1 (叶夏亮), JIN Sun2 (金隼). A Bayesian Based Process Monitoring and Fixture Fault Diagnosis Approach in the Auto Body Assembly Process [J]. Journal of shanghai Jiaotong University (Science), 2016, 21(2): 164-172.