Concentration Prediction of Dissolved Gases in Transformer Oil Based on Deep Belief Networks

被引：0
|
作者：
Dai J. [1 ]
Song H. [1 ]
Yang Y. [2 ]
Chen Y. [2 ]
Sheng G. [1 ]
Jiang X. [1 ]
机构：
[1] Department of Electrical Engineering, Shanghai Jiaotong University, Minhang District, Shanghai
[2] Electric Power Research Institute of Shandong Power Supply Company of State Grid, Jinan, 250002, Shandong Province
来源：
Dai, Jiejie (secess@163.com) | 2017年 / Power System Technology Press卷 / 41期
基金：
中国国家自然科学基金;
关键词：
Correlation; Deep belief networks; Dissolved gas in oil; Predict; Transformer;
D O I：
10.13335/j.1000-3673.pst.2016.2623
中图分类号：
学科分类号：
摘要：
Prediction of development trend of gas concentration dissolved in transformer oil can provide important basis for transformer condition assessment. A new prediction model based on deep belief networks is proposed. Seven types of characteristic gas concentration combined with environment temperature and transformer oil temperature are fed to input layer. The model can automatically extract regulation of gas concentration development trend through training a multi-hidden-layer machine learning model based on restricted Boltzmann machine. Correlation between different types of gases and influence of temperatures is activated layer by layer. Irrelevant and redundant information is inhibited by the model. The proposed method has higher prediction accuracy. It overcomes drawbacks of low stability in traditional methods and shortcoming of considering only one characteristic gas. In addition, it avoids manual intervention in calculation process. Finally, case analysis verifies effectiveness and superiority of the proposed model. © 2017, Power System Technology Press. All right reserved.
引用
收藏
页码：2737 / 2742
页数：5
相关论文
共 22 条
  • [1] Wei Z., Qi B., Zuo J., Et al., A method to diagnose defects in oil-paper insulation of converter transformer based on image feature of partial discharge, Power System Technology, 39, 4, pp. 1160-1166, (2015)
  • [2] Liu K., Wang P., Wang W., Et al., Electric filed distribution in transformer oil under DC electric field, Power System Technology, 39, 6, pp. 1714-1718, (2015)
  • [3] Wu G., Yao M., Xin D., Et al., Experimental study on oil-impregnated paper with non-uniform thermal aging, Power System Technology, 39, 11, pp. 3298-3304, (2015)
  • [4] Xu Z., Wang K., Sun J., Et al., Research on characteristics during latent period of partial discharge developing process under direct voltage of oil-paper insulation, Power System Technology, 40, 2, pp. 614-619, (2016)
  • [5] Luo Y., Yu P., Song B., Et al., Prediction of the gas dissolved in power transformer oil by the grey model, Proceedings of the CSEE, 21, 3, pp. 65-69, (2001)
  • [6] Bian J., Liao R., Yang L., Concentration prediction of gases dissolved in transformer oil based on weakening buffer operator and least square support vector machine, Power System Technology, 36, 2, pp. 195-199, (2012)
  • [7] Yang T., Liu P., Li Z., Et al., A new combination forecasting model for concentration prediction of dissolved gases in transformer oil, Proceedings of the CSEE, 28, 31, pp. 108-113, (2008)
  • [8] Xiao Y., Zhu H., Chen X., Concentration prediction of dissolved gas-in-oil of a power transformer with the multivariable grey model, Automation of Electric Power Systems, 30, 13, pp. 64-67, (2006)
  • [9] Sima L., Shu N., Zuo J., Et al., Concentration prediction of dissolved gases in transformer oil based on grey relational analysis and fuzzy support vector machines, Power System Protection and Control, 40, 19, pp. 41-46, (2012)
  • [10] Lin X., Huang J., Xiong W., Et al., Interval prediction of dissolved-gas concentration in transformer oil, Electric Power Automation Equipment, 36, 4, pp. 73-77, (2016)
123