代价敏感VBGP在变压器故障诊断中的应用

Abstract
Figure/Table
References
Related Citation (6)

Download: PDF (585 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The traditional transformer fault diagnosis methods are typical evaluated by estimating their error rate. However this makes sense only if all errors have equal cost. But in practical problems, cost caused by different type of misdiagnosis is usually unequal. In order to overcome the shortcoming that only pursuit of low misdiagnosis may not bring about meaningful diagnosis results, cost-sensitive variational Bayesian treatment for gaussian process classification(CS-VBGP) is proposed and is applied to power transformer fault diagnosis. The method aims to minimize the misdiagnosis cost by introducing cost-sensitive learning mechanism. Class labels of new instances are predicted according to Bayesian risk theory. Experimental results show CS-VBGP is capable of high fault recognition rate and tends to improve the diagnostic accuracy of high misdiagnosis cost class and the diagnosis speed meets the engineering requirements of the transformer fault diagnosis.

Key words： Gaussian process misdiagnosis cost cost-sensitive learning transformer fault diagnosis

Received: 05 June 2012 Published: 17 June 2014

PACS:

TM411

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yin Jinliang
	Zhu Yongli
	Zheng Xiaoyu
	Wang Guoqiang

Cite this article:

Yin Jinliang,Zhu Yongli,Zheng Xiaoyu等. Cost-Sensitive Gaussian Process Classification with Variational Bayesian Treatment for Fault Diagnosis of Power Transformers[J]. Transactions of China Electrotechnical Society, 2014, 29(3): 222-227.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2014/V29/I3/222

[1] 朱德恒, 严璋, 谈克雄, 等. 电气设备状态监测与故障诊断技术[M]. 北京: 中国电力出版社, 2009.
[2] 吴立增, 朱永利, 苑津莎. 基于贝叶斯网络分类器的变压器综合故障诊断方法[J]. 电工技术学报, 2005, 20(4): 45-51.
Wu Lizeng, Zhu Yongli, Yuan Jinsha. Novel method for transformer faults integrated diagnosis based on Bayesian network classifie[J]. Transactions of China Electrotechnical Society, 2005, 20(4): 45-51.
[3] 章剑光, 周浩, 项灿芳. 基于Super SAB神经网络算法的主变压器故障诊断模型[J]. 电工技术学报, 2004, 19(7): 49-52, 58.
Zhang Jianguang, Zhou Hao, Xiang Canfang. Application of super SAB ANN model for transformer fault diagnosis[J]. Transactions of China Electrotech- nical Society, 2004, 19(7): 49-52, 58.
[4] Bishop C M. Pattern Recognition and Machine Learning[M]. Singapore: Springer, 2006.
[5] Rasmussen C E, Williams C K I. Gaussian processes for machine learning[M]. Cambridge/London: The MIT Press, 2006.
[6] Saitta L. Machine learning: a technological roadmap [R]. The Netherlands: Univ. of Amsterdam, 2000.
[7] Ling C X, Sheng V S. A comparative study of cost-sensitive classifiers[J]. Chinese J of Computers, 2007, 30(8): 1023-1211.
[8] Diamantini C, Potena D. Bayes vector quantizer for classimbalance problem[J]. IEEE Trans on Knowledge and Data Engineering, 2009, 21(5): 638-651.
[9] Girolami M, Rogers S. Variational Bayesian multino- mial probit regression with Gaussian process priors[J]. Neural Computation, 2006, 18(8): 1790- 1817.
[10] 赵文清, 朱永利, 张小奇. 应用支持向量机的变压器故障组合预测[J]. 中国电机工程学报, 2008, 28(25): 14-19.
Zhao Wenqing, Zhu Yongli, Zhang Xiaoqi. Combina- tional forecast for transformer faults based on support vector machine[J]. Proceedings of the CSEE, 2008, 28(25): 14-19.
[11] Tang W H, Wu Q H. Condition monitoring and assessment of power transformers using computational intelligence[M]. New York: Springer-Verlag Press, 2011, 95-104.
[12] Sheng Weifei, Xiao Binzhang. Fault diagnosis of power transformer based on support vector machine with genetic algorithm[J]. Expert Systems with Applications, 2009, 36(8): 11352-11357.
[13] 李中, 苑津莎, 张利伟. 基于自组织抗体网络的电力变压器故障诊断[J]. 电工技术学报, 2010, 25(10): 200-206.
Li Zhong, Yuan Jinsha, Zhang Liwei. Fault diagnosis for power transformer based on the self-organization antibody net[J]. Transactions of China Electrotechnical Society, 2010, 25(10): 200-206.
[14] Seeger M. Gaussian processes for machine learning[J]. International Journal of Neural Systems, 2004, 14(2): 69-106.
[15] Kuss M, Rasmussen C E. Assessing approximate inference for binary Gaussian process classification[J]. Journal of Machine Learning Research, 2005, 6: 1679-1704.
[16] Nickisch H, Rasmussen C E. Approximations for binary Gaussian process classification[J]. Journal of Machine Learning Research, 2008, 9: 2035-2078.
[17] Bermak A, Belhouari S B. Bayesian learning using gaussian process for gas identification[J]. IEEE Transactions on Instrumentation and Measurement, 2006, 55(3): 787-792.
[18] 郑海平, 孙才新, 李俭, 等. 诊断电力变压器故障的一种灰色关联度分析模式及方法[J]. 中国电机工程学报, 2001, 21(10): 106-109.
Zheng Haiping, Sun Caixin, Li Jian, et al. A model and method of degree of grey incidence analysis on transformer fault diagnosis[J]. Proceedings of the CSEE, 2001, 21(10): 106-109.
[19] 孙才新, 陈伟根, 李俭, 等. 电气设备油中气体在线监测与故障诊断技术[M]. 北京: 科学出版社, 2003.
[20] 张德明. 变压器分接开关状态监测与故障诊断[M]. 北京: 中国电力出版社, 2008.