Combined DBN Diagnosis Method for Dissolved Gas Analysis of Power Transformer Oil

被引：0
|
作者：
Rong Z. [1 ]
Qi B. [1 ]
Li C. [1 ]
Zhu S. [1 ]
Chen Y. [2 ]
Gu C. [2 ]
机构：
[1] School of Electrical and Electronics Engineering, North China Electric Power University, Changping District, Beijing
[2] State Grid Shandong Electric Power Research Institute, Jinan, 250002, Shandong Province
来源：
Dianwang Jishu/Power System Technology | 2019年 / 43卷 / 10期
关键词：
Combined DBN; DBN; DGA; Power transformer fault diagnosis;
D O I：
10.13335/j.1000-3673.pst.2019.0422
中图分类号：
学科分类号：
摘要：
Dissolved gas analysis (DGA) of power transformer oil is an important method for power transformer insulation fault diagnosis. According to failure case analysis, traditional diagnosis methods based on deep belief network (DBN) may cause many misjudgments between partial discharge, low-temperature overheating, low-energy arc discharge, overheating, etc. To further improve the effect of DBN diagnosis, a combined DBN fault diagnosis method for dissolved gas analysis of power transformer oil is proposed. This method introduces DBN group to identify fault type and severity. In the diagnosis, the fault type recognition results of the first layer are used to activate the second layer's DBN to recognize fault severity. Then, the influences of different inputs, network layers and hidden units on accuracy of combined DBN fault diagnosis are studied. It is found out that when the input is non-code ratios with characteristic gas content and layer number is 3, the networks have the highest accuracy rate. When the number of network units is greater than 3, increasing the number of units cannot significantly improve identification accuracy. The accuracy rates and recall rates of the combined DBN are higher than that of single DBN and the overall accuracy increases from 80. 9% to 90. 1%. The impact of case data volume on the diagnosis result is analyzed. It is found out that the recall and accuracy rates increase with increase of data volume, and accuracy of fault type with more cases is higher than that with fewer cases. © 2019, Power System Technology Press. All right reserved.
引用
收藏
页码：3800 / 3807
页数：7
相关论文
共 23 条
  • [1] Yuan Q., Qi B., Zhang S., Et al., Gas generating characteristics of oil-paper defect models under composite AC-DC voltage, Power System Technology, 42, 9, pp. 3093-3099, (2018)
  • [2] Han S., Liu B., Ai X., Et al., Dynamic failure rate model for transformer considering insulation aging and oil chromatographic monitoring data, Power System Technology, 42, 10, pp. 3275-3281, (2018)
  • [3] Qi B., Zhang P., Xu R., Et al., Calculation method on dif-ferentiated warning value of power transformer based on distribution model, High Voltage Engineering, 42, 7, pp. 2290-2298, (2016)
  • [4] Rong Z., Qi B., Zhang P., Et al., Anomalous state detection of dissolved gases in transformer oil based on the canopy hyper sphere mod, Proceedings of the CSEE, 38, 13, (2018)
  • [5] Xiong H., Sun C., Liao R., Et al., Study on kernel-based possibilistic clustering an dissolved gas analysis for fault diagnosis of power transformer, Proceedings of the CSEE, 25, 20, pp. 162-166, (2005)
  • [6] Fu Q., Chen T., Zhu J., Transformer fault diagnosis using self-adaptive RBF neural network algorithm, High Voltage Engineering, 38, 6, pp. 1368-1375, (2012)
  • [7] Huang X., Liwen J., Song T., Et al., Application of bag-ging-CART algorithm optimized by genetic algorithm in transformer fault diagnosis, High Voltage Engineering, 42, 5, pp. 617-1623, (2016)
  • [8] Zhu Y., Yin J., Study on application of multi-kernel learning relevance vector machines in fault diagnosis of power transformers, Proceedings of the CSEE, 33, 22, pp. 68-74, (2013)
  • [9] Li Y., Shu N., Transformer fault diagnosis based on fuzzy clustering and complete binary tree support vector machine, Transactions of China Electrotechnical Society, 31, 4, pp. 64-70, (2016)
  • [10] Yu B., Zhu Y., Transformer fault diagnosis using weighted extreme learning machine, Computer Engineering and Design, 34, 12, pp. 4340-4344, (2013)
123