Incipient fault diagnosis based on improved principal component analysis for power transformer

被引：0
|
作者：
Yang, Tingfang [1 ]
Zhang, Hang [1 ]
Huang, Libin [2 ]
Zeng, Xiangjun [1 ]
机构：
[1] School of Electrical & Information Engineering, Changsha University of Science and Technology, Changsha
[2] Electric Power Research Institute, China Southern Power Grid, Guangzhou
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2015年 / 35卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Cluster analysis; Dissolved gas analysis; Fault diagnosis; Power transformers; Principal component;
D O I：
10.16081/j.issn.1006-6047.2015.06.023
中图分类号：
学科分类号：
摘要：
Based on the transformer DGA(Dissolved Gas Analysis), an improved PCA(Principal Component Analysis) is proposed to diagnose the incipient fault of transformer. Different from the traditional PCA, it standardizes the sample indices with the sum of their absolute values, which eliminates the numeric magnitude difference between indices while keeps their information differences. The principal components are selected according to the cumulative contribution rate and the Euclidean distances between them are clustered to determine the fault state of transformer. Diagnosis instances show that, the proposed method effectively improves the diagnosis accuracy of transformer incipient faults. ©, 2015, Electric Power Automation Equipment Press. All right reserved.
引用
收藏
页码：149 / 153and165
相关论文
共 17 条
  • [1] Tang W.H., Wu Q.H., Condition Monitoring and Assessment of Power Transformers Using Computational Intelligence, pp. 95-104, (2011)
  • [2] Liang Y., Li K., Niu L., Et al., A multilayer uncertain transformer condition assessment model, Automation of Electric Power Systems, 37, 22, pp. 73-78, (2013)
  • [3] IEC60599-1999 Mineral oil-impregnated electrical equipment in service-guide to the interpretation of dissolved and free gases analysis, (1999)
  • [4] Guardado J.L., Naredo J.L., Moreno P.A., Comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis, IEEE Transactions on Power Delivery, 16, 4, pp. 643-647, (2001)
  • [5] Li J., Sun C., A method of synthesis based on the grey cluster and fuzzy cluster about internal fault diagnosis of transformer, Proceedings of the CSEE, 23, 2, pp. 112-115, (2003)
  • [6] Xiong H., Sun C., Zhang Y., Et al., A hierarchical grey evaluation model for operation condition of power transformers, Automation of Electric Power Systems, 31, 7, pp. 55-60, (2007)
  • [7] Dong M., Yan Z., Yang L., An evidential reasoning approach to transformer fault diagnosis, Proceedings of the CSEE, 26, 1, pp. 106-114, (2006)
  • [8] Zhu Y., Wu L., Li X., Synthesized diagnosis on transformer faults based on bayesian classifier and rough set, Proceedings of the CSEE, 25, 10, pp. 159-165, (2005)
  • [9] Shu H., Sun X., Yu J., A survey on the application of rough set theory in power systems, Automation of Electric Power Systems, 28, 3, pp. 90-95, (2004)
  • [10] Yang T., Zhou L., Li J., Et al., Power transformer fault diagnosis based on fuzzy immune recognition approach, Power System Technology, 37, 1, pp. 190-194, (2013)
12