Large Power Transformer Fault Diagnosis and Prognostic Based on DBNC and D-S Evidence Theory
- 1 School of Control and Computer Engineering, North China Electric Power University, Baoding, China
- 2 School of Control and Computer Engineering, North China Electric Power University, Baoding, China
- 3 State Grid Hebei Electric Power Research Institute, Shijiazhuang, China
- 4 State Grid Hebei Electric Power Research Institute, Shijiazhuang, China
- 5 School of Control and Computer Engineering, North China Electric Power University, Baoding, China
- 6 School of Electrical and Electronic Engineering, North China Electric Power University, Baoding, China
Abstract
Power transformer is a core equipment of power system, which undertakes the important functions of power transmission and transformation, and its safe and stable operation has great significance to the normal operation of the whole power system. Due to the complex structure of the transformer, the use of single information for condition-based maintenance (CBM) has certain limitations, with the help of advanced sensor monitoring and information fusion technology, multi-source information is applied to the prognostic and health management (PHM) of power transformer, which is an important way to realize the CBM of power transformer. This paper presents a method which combine deep belief network classifier (DBNC) and D-S evidence theory, and it is applied to the PHM of the large power transformer. The experimental results show that the proposed method has a high correct rate of fault diagnosis for the power transformer with a large number of multi-source data.
- Wu, K., Kang, J.S. and Chi, K. (2016) Fault Diagnosis Method of Power Transformers Using Improved Multi-class Classification Algorithm and Relevance Vector Machine.High Voltage Engineering, 42, 3011-3017.
- Zhao, W.Q. and ZhuY.L. (2007) Summary of condition assessment for Power Transformer. Transformer, 44, 9-12.
- Cui Y., Ma, H. and Saha, T. (2016) Multi-source information fusion for power transformer condition assessment. Power and Energy Society General Meeting. Boston, 17-21, July 2016, 1-5.
- Gao, Z.X., Guo, C.G. and Yu, B. (2011) Study of A Fault Diagnosis Approach for Power Grid with Information Fusion Based on Multi-Data Resources. Power System Protection and Control, 39, 17-23.
- Dai, J. F. (2010) On-Line Fault Detection for Transformers Based on Information Fusion. Electrotechnics Electric, 51-55.
- Li, Y.W., Li, W. and Han, X.D. (2009) Application of Multi-Sensor Information Fusion Technology in the Power Transformer Fault Diagnosis. International Conference on Machine Learning and Cybernetics. Baoding, 12-15, July 2009, 29-33.
- Javed, K. (2014) ARobust And Reliable Data-Driven Prognostics Approach Based on Extreme Learning Machine and Fuzzy Clustering. Université de Franche-Comté.
- Tsui, K.L., Chen, N. and Zhou, Q. (2015) Prognostics and Health Management: A Review on Data Driven Approaches. Mathematical Problems in Engineering, 1-17. https://doi.org/10.1155/2015/793161
- Shi, X., Zhu, Y.L. and Sa, C. (2016) Power Transformer Fault Classifying Model Based on Deep Belief Network. Power System Protection and Control, 44, 71-76.
- Hinton, G.E., Osindero, S. and The, Y.W. (2006)A Fast Learning Algorithm for Deep Belief Nets. Neural computation, 18, 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
- Dempster, A. P. (1967) Upper and Lower Probabilities Induced by a Multivalued Mapping. The Annals of Mathematical Statistics,38, 325–339. https://doi.org/10.1214/aoms/1177698950