Transformer Fault Diagnosis Based on Online Sequential Extreme Learning Machine

Abstract:

Experiment analyzed the main factors that affect the performance of Online Sequential Extreme Learning Machine (OS-ELM). And the experimental comparison show that the OS-ELM in classification performance is better than the support vector machine (SVM) and extreme learning machine (ELM). But there still is not a stable network output now. For this aspect, this article presents the optimization algorithm of integrated Ensemble of online sequential extreme learning machine (EOS-ELM). The algorithm using a limited number of sample data has been applied to transformer fault diagnosis. The time of training and testing can be shortened and the classification accuracy can be improved. The experimental results show that the OS-ELM has better performance in response to online monitoring and real-time data processing.

• Periodical: Applied Mechanics and Materials (Volume 721)
• Pages: 360-365
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.721.360
• Online since: December 2014
• Authors: Lin Lin Wang, Fei Pei, Yong Li Zhu
• Keywords: Ensemble of Online Sequential Extreme Learning Machine, On-Line Monitoring, Online Sequential Extreme Learning Machine, Transformer Fault Diagnosis

References

[1] P Mirowski, Y LeCun. Statistical Machine Learning and Dissolved Gas Analysis: A Review [J]. IEEE Transactions on Power Delivery, 2010, 27(4): 1-6.

DOI: 10.1109/tpwrd.2012.2197868

[2] Ronaldo R.B. de Aquino, Milde M.S. Lira. A fuzzy system for detection of incipient fault in power transformers based on gas-in-oil analysis[C]. Fuzzy Systems (FUZZ), 2010 IEEE International Conference on, 2010. 7: 1-6.

DOI: 10.1109/fuzzy.2010.5584511

[3] Du Wenxia, Lv Feng, Ju Xiyuan, et al. Fault Diagnosis of Power Transformer Based on BP Neural Network[J]. Transformer, 2007, 44(3): 45-47.

[4] Li Shuang, Wang Langzhu, Zhang Wei, et al. Fault Diagnosis Method of Transformer Based on Improved BP Neural Network of DGA[J]. Transformer, 2010, 47(12): 61-65.

[5] Zhao Wenqing, Zhu Yongli, Wang Xiaohui. Fault Diagnosis of Power Transformer Based on Combination of Bayesian Networks[J]. Electric Power Automation Equipment, 2009, 29(11): 6-9.

[6] Li Chunxiang, Zhang Weimin, Zhong Biliang, et al. Reserach On Parameter Optimization Algorithm of Least Squares Support Vector Machine[J]. Journal of Hangzhou Dianzi University, 2010, 30(4): 213-216. DOI: 10. 3969/j. issn. 1001-9146. 2010. 0406.

[7] Huang G B, Zhu Q Y, Siew C K. Extreme Leraning Maching: Theory and Application[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.

[8] Huang G B, Zhu Q Y, Siew C K. Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks[C]. Proceedings of the International Joint Conference on Neural Networks. Piscataway: Institute of Electrical and Electronics Engineers Inc, 2004: 985-990.

DOI: 10.1109/ijcnn.2004.1380068

[9] Liang Nanying, Huang Guang-bin, SaratchandranP, et al. A fast and accurate online sequential learning algorithm for feedforward networks[J]. IEEE Transaction on Neural Networks, 2006, 17(6): 1411-1423.

DOI: 10.1109/tnn.2006.880583

[10] Lan Y, Soh Y C, Huang G B. Ensemble of sequential extreme learning machine[J]. Neural Computation, 2009, 72: 3391-3395.

DOI: 10.1016/j.neucom.2009.02.013

[11] Zhao J W, Wang Z H, Park D S. Online sequential extreme learning machine with forgetting mechanism[J]. Neural Computation，2012，87: 79-89.

[12] Huynh H T, Won Y. Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks[J]. Pattern Recognition Letters, 2011, 32: 1930-(1935).

DOI: 10.1016/j.patrec.2011.07.016

[13] Hoang M T T, Huynh H T, Vo N H, et, al. A robust online sequential extreme learning machine[J]. LNCS, 2007, 4491: 1077-1086.

[14] Yuan Lan, Yeng Chai Soh, Guang-Bin Huang. Ensemble of online sequential extreme learning machine[J]. Neurocomputing, 2009, 72(13/14/15): 3391-3395.

DOI: 10.1016/j.neucom.2009.02.013