Prediction Model for Dissolved Gases Content in Transformer Oil Based on Twice Dimensionality Reduction

被引：0

作者：

Tang Y. ^{[1
,2
]}

Xiong Y. ^{[1
]}

机构：

[1] School of Physical Science and Engineering, Yichun University, Yichun

[2] School of Information Science and Engineering, Central South University, Changsha

来源：

Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | 2017年 / 32卷 / 21期

关键词：

Dissolved gases in oil; Feature extraction; Kernel extreme learning machine; Kernel principal component analysis; Renyi entropy; Variable selection;

D O I：

10.19595/j.cnki.1000-6753.tces.160867

中图分类号：

学科分类号：

摘要：

Aiming at the testing problem of dissolved gases content in transformer oil, a new prediction model based on twice dimensionality reduction was proposed.Firstly, mutual information variable selection method was used to select relevant input variables of the prediction model; Secondly, the relevant variables were reconstructed in the phase space where feature extraction was carried out by using kernel principal component analysis (KPCA) for the purpose of data dimension reduction, denoising and eliminating relativity of variables, meanwhile, the parameters of KPCA were determined by Renyi information entropy.At last, kernel extreme learning machine (KELM) was employed to forecast dissolved gases content in transformer oil, and kernel principal components were used as the inputs of KELM.Compared with gray model and the prediction model which only adopt variable selection method or feature extraction method, experimental results show that the proposed prediction model has a better prediction and generalization. © 2017, The editorial office of Transaction of China Electrotechnical Society. All right reserved.

引用

页码：194 / 202

页数：8

共 20 条

[1] Shi X., Zhu Y., Sa C., Et al., Power transformer fault classifying model based on deep belief network, Power System Protection and Control, 44, 1, pp. 71-76, (2016)
[2] Lu B., Zhao S., Tian Y., Et al., Mid-long term electricity consumption forecasting based on improved NGM(1, 1, k) gray model, Power System Protection and Control, 43, 12, pp. 98-103, (2015)
[3] 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)
[4] Qiu S., Yang H., Assessment method of harmonic emission level based on the improved weighted support vector machine regression, Transactions of China Electrotechnical Society, 31, 5, pp. 85-90, (2016)
[5] Fei S., Sun Y., Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm, Electric Power Systems Research, 78, 3, pp. 507-514, (2008)
[6] Liao R., Zheng H., Grzybowski S., Et al., Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers, Electric Power Systems Research, 81, 12, pp. 2074-2080, (2011)
[7] Tang Y., Gui W., Peng T., Et al., Prediction method for dissolved gases content in transformer oil based on variable selection of mutual information, Chinese Journal of Scientific Instrument, 34, 7, pp. 1492-1498, (2013)
[8] Han M., Wang Y., Prediction of multivariate time series based on reservoir principal component analysis, Control and Decision, 24, 10, pp. 1526-1530, (2009)
[9] Choi S.W., Lee C., Lee J.M., Et al., Fault detection and identification of nonlinear processes based on kernel PCA, Chemometrics and Intelligent Laboratory Systems, 75, 1, pp. 55-67, (2005)
[10] Jin L., Zhang D., Duan S., Et al., Recognition of contamination grades of insulators based on IR and UV image information fusion, Transactions of China Electrotechnical Society, 29, 8, pp. 309-318, (2014)

← 1 2 →