Computer Science ›› 2015, Vol. 42 ›› Issue (10): 251-255.

Previous Articles     Next Articles

DGA Fault Diagnosis Based on CBR Method with Feature Transformation

GAO Ming-lei, ZHANG Zhong-jiang and JI Bo   

  • Online:2018-11-14 Published:2018-11-14

Abstract: Pearson correlation coefficient is a way to measure the linear relationship between two variables,which is widely used as CBR matching algorithm for DGA fault diagnosis.However,the traditional application has two problems:discriminating in favor of the features which have larger data range and regarding equally the contributions of all features.To address these issues,the paper proposed the log-function feature transforming method to narrow the data range to solve the discrimination problem and proposed the mean square deviation feature weighting method to distinguish the contribution levels to improve the accuracy of DGA fault diagnosis.Experimental results show that the proposed FTW_Pearson algorithm is superior to David triangle method which is popularly used in real applications,the traditional Pearson algorithm without feature transforming/feature weighting,the Bayes algorithm and the BPNN algorithm.

Key words: Pearson correlation coefficient,DGA,Feature transforming,Feature weighting,CBR

[1] 蔡红梅,陈剑勇,苏浩益.基于灰云模型的电力变压器故障诊断[J].电力系统保护与控制,2012,0(12):151-155 Cai Hong-mei,Chen Jian-yong,Su Hao-yi.Fault diagnosis of power transformer based on grey cloud model[J].Power System Protection and Control,2012,0(12):151-155
[2] 朱继,喻瑛,王辰炜,等.基于粗糙集和自适应遗传算法的电力变压器故障诊断[J].电测与仪表,2012,9(6):47-51 Zhu Ji,Yu Ying,Wang Chen-wei,et al.Application of Rough Set and Adaptive Genetic Algorithm to Transformer Fault Diagnosis[J].Electrical Measurement & Instrumentation,2012,9(6):47-51
[3] 白翠粉,高文胜,金雷,等.基于3层贝叶斯网络的变压器综合故障诊断[J].高电压技术,2013,9(2):330-335 Bai Cui-fen,Gao Wen-shen,Jin Lei,et al.Integrated Diagnosis of Transformer Faults Based on Three-layer Bayesian Network[J].High Voltage Engineering,2013,9(2):330-335
[4] 尹金良,朱永利.支持向量机参数优化及其在变压器故障诊断中的应用[J].电测与仪表,2012,9(5):11-16 Yin Jin-liang,Zhu Yong-li.Parameter Optimization for Support Vector Machine and Its Application to Fault Diagnosis of Power Transformers[J].Electrical Measurement & Instrumentation,2012,9(5):11-16
[5] 张思扬,匡芳君,徐蔚鸿.混沌动态模糊神经网络及变压器故障诊断的应用[J].湖南科技大学学报(自然科学版),2012,7(1):35-39 Zhang Si-yang,Kuang Fang-jun,Xu Wei-hong.Chaotic dynamic fuzzy neural network and its application in power transformer fault Diagnosis[J].Journal of Hunan University of Science & Technology(Natural Science Edition),2012,7(1):35-39
[6] 赵小霞,苑津莎,刘磊,等.基于CBR与RBR变压器检修策略专家系统设计[J].电子科技,2012,5(7):31-34 Zhao Xiao-xia,Yuan Jin-sha,Liu Lei,et al.Transformer Maintenance Strategy Expert System Based on CBR And RBR[J].Electronic Science and Technology,2012,5(7):31-34
[7] 高俊杰,邓贵仕.基于本体的范例推理系统研究综述[J].计算机应用研究,2009,6(2):406-410,418 Gao Jun-jie,Deng Gui-shi.Survey on ontology-based CBR system[J].Application Research of Computers,2009,6(2):406-410,418
[8] Negar A,Jean R.An application of multi-criteria decision aids models for Case-Based Reasoning[J].Information Sciences,2012,0(22):55-66
[9] Wang J,Zheng N.A Novel Fractal Image Compression Scheme With Block Classification and Sorting Based on Pearson’s Correlation Coefficient[J].IEEE Transactions on Image Processing,2013,2(9):3690-3702
[10] Wang Gang-jin,Xie Chi,Chen Shou,et al.Random matrix theory analysis of cross-correlations in the US stock market:Evidence from Pearson’s correlation coefficient and detrended cross-correlation coefficient[J].Physica A:Statistical Mechanics and its Applications,2013,392(17):3715-3730
[11] 王骏,王士同,邓赵红.特征加权距离与软子空间学习相结合的文本聚类新方法[J].计算机学报,2012,35(8):1655-1665 Wang Jun,Wang Shi-tong,Deng Zhao-hong.A Novel Text Clustering Algorithm Based on Feature Weighting Distance and Soft Subspace Learning[J].Chinese Journal of Computers,2012,35(8):1655-1665
[12] He Z Y,Xu X F,Deng S C.Attribute Value Weighting in k-Modes Clustering [J].Expert Systems with Applications,2011,38(12):15365-15369

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!