Transformer Fault Prediction Based on Time Series and Support Vector Machine

被引：0
|
作者：
Huang X. [1 ]
Jiang W. [1 ]
Zhu Y. [1 ]
Tian Y. [1 ]
机构：
[1] School of Electronics and Information, Xi'an Polytechnic University, Xi'an
来源：
Gaodianya Jishu/High Voltage Engineering | 2020年 / 46卷 / 07期
关键词：
ARIMA; Dissolved gas in oil; Fault prediction; Genetic algorithm; Support vector machine; Time series; Transformer;
D O I：
10.13336/j.1003-6520.hve.20191344
中图分类号：
学科分类号：
摘要：
The fault prediction of power transformer can realize the early warning of transformer fault, which is vital to ensure the normal operation of the electric power system. A transformer fault prediction model based on time series and support vector machine (SVM) is presented in this paper. The model is based on the autoregressive integral moving average (ARIMA) model in time series analysis, and the parameters p and q of ARIMA model are determined by genetic algorithm (GA). The dissolved gas in transformer oil is predicted by the time series model after parameter determination. Then the SVM model optimized by grid search algorithm (GS) is used to predict the dissolved gas in oil. The running results show that the accuracy of transformer fault prediction model can reaches 89.66%, while the prediction accuracy of GM-SVM, ARIMA-SVM and GA-ARIMA-ANN is 58.62%, 79.31% and 75.86%, respectively. So the method proposed in this paper has the higher prediction accuracy. © 2020, High Voltage Engineering Editorial Department of CEPRI. All right reserved.
引用
收藏
页码：2530 / 2538
页数：8
相关论文
共 19 条
  • [1] HUANG Xinbo, Online monitoring and fault diagnosis of transmission line, (2014)
  • [2] DAI Jiejie, SONG Hui, SHENG Gehao, Et al., Prediction method for power transformer running state based on LSTM network, High Voltage Engineering, 44, 4, pp. 1099-1106, (2018)
  • [3] WANG Youyuan, ZHOU Liwei, LIANG Xuanhong, Et al., Markov forecasting model of power transformer fault based on association rules analysis, High Voltage Engineering, 44, 4, pp. 1051-1058, (2018)
  • [4] TAN Jingbo, Research on fault prediction and diagnosis of power transformer based on dissolved gas analysis in oil, (2009)
  • [5] LI Long, ZHANG Di, TANG Jun, Et al., Application of unequal interval GM(1, 1) power model in prediction of dissolved gases for power transformer failure, Power System Protection and Control, 45, 15, pp. 118-124, (2017)
  • [6] ZHU Yongli, ZHANG Xiaoqi, Combinational forecast for transformer faults based on support vector machine, Proceedings of the CSEE, 28, 25, pp. 14-19, (2008)
  • [7] LIU Hang, WANG Youyuan, LIANG Xuanhong, Et al., Prediction method of the dissolved gas volume fraction in transformer oil based on multi factors, High Voltage Engineering, 44, 4, pp. 1114-1121, (2018)
  • [8] LIU Yunpeng, XU Ziqiang, DONG Wangying, Et al., Concentration prediction of dissolved gases in transformer oil based on empirical mode de-composition and long short-term memory neural networks, Proceedings of the CSEE, 39, 13, pp. 3998-4008, (2019)
  • [9] HUANG Xinbo, LI Hongbo, ZHU Yongcan, Et al., Short-term forecast for transmission line icing by time series analysis and Kalman filtering, High Voltage Engineering, 43, 6, pp. 1943-1949, (2017)
  • [10] PAN Difu, LIU Hui, LI Yanfei, A wind speed forecasting optimization model for wind farms based on time series analysis and Kalman filter algorithm, Power System Technology, 32, 7, pp. 82-86, (2008)
12