Transformers Fault Diagnosis Based on SVM for Unbalanced Data

LIU Chenfei; CUI Haoyang; LI Xin; SHU Jiang; LI Ya

doi:10.13296/j.1001-1609.hva.2019.07.031

您当前的位置：

首页 >

文章列表页 >

Transformers Fault Diagnosis Based on SVM for Unbalanced Data

更新时间：2025-04-26

- Transformers Fault Diagnosis Based on SVM for Unbalanced Data
- High VoltageApparatus Vol. 55, Issue 7, Pages: 216-220(2019)
- 作者机构：
  
  上海电力学院电子与信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2019.07.031
  CLC： TM407
- Published：2019
- 稿件说明：
移动端阅览
[1]刘晨斐,崔昊杨,李鑫,束江,李亚.不对称样本下基于支持向量机的变压器故障诊断[J].高压电器,2019,55(07):216-220.

LIU Chenfei, CUI Haoyang, LI Xin, et al. Transformers Fault Diagnosis Based on SVM for Unbalanced Data[J]. High VoltageApparatus, 2019, 55(7): 216-220.
[1]刘晨斐,崔昊杨,李鑫,束江,李亚.不对称样本下基于支持向量机的变压器故障诊断[J].高压电器,2019,55(07):216-220. DOI： 10.13296/j.1001-1609.hva.2019.07.031.

LIU Chenfei, CUI Haoyang, LI Xin, et al. Transformers Fault Diagnosis Based on SVM for Unbalanced Data[J]. High VoltageApparatus, 2019, 55(7): 216-220. DOI： 10.13296/j.1001-1609.hva.2019.07.031.

摘要

为解决基于支持向量机（SVM）的变压器故障诊断中因样本不对称导致诊断准确率降低的问题

提出了一种改进的向上采样策略和SVM结合的方法。首先通过K-近邻算法提取少数类样本数据中的边界数据集并生成新的少数类随机样本

在此基础上向少数类样本中添加人工生成的随机新样本使得两类样本数量达到基本均衡。对比均衡样本和不对称样本下的SVM分类模型的性能

结果表明:该方法能够有效降低SVM分类平面的偏移程度

进一步提高了SVM变压器故障诊断的准确率。

Abstract

In the process of power transformer fault diagnosis based on support vector machine（SVM）

unbalanceddata makes the classifying hyper plane of SVM shift to the minority samples

which decreases the diagnostic accura-cy. This paper proposed a method combining over sampling strategy and SVM to solve the problem. K-nearest neigh-bor algorithm is used to extract the boundary data sets from the minority samples. On this basis

the new random sam-ples are generated and added into the minority samples to make the two kinds of samples balanced consequently.Comparing the performance of SVM classification model with balanced data sets and unbalanced data sets

the exper-iment results show that the proposed method can reduce the deviation of SVM classifying hyper plane effectively.

关键词

Keywords

references

Views

194

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault Diagnosis of Power Transformer Based on DGA of Algorithm for SVM

Research on Fault Diagnosis of High Voltage Circuit Breaker Opening/Closing Coils Based on SVM Principal Component Analysis

Research on Influence of Crack Depth and Position on Vibration Detection of 220 kV Porcelain Post Insulators

Multi-signal Joint Identification and Intelligent Diagnosis of High Voltage Circuit Breaker Faults Based on VMD-BiLSTM

Design of a Digital Twin-oriented Integrated Monitoring System for Substation Switchgear

Related Author

JIA Lijing

ZHANG Jianwen

WANG Chuanlin

YAN Jiaming

ZHOU Xianjiao

CHEN Luna

PENG Zaixing

WANG Song

Related Institution

School of Information and Electrical Engineering,China University of Mining and Technology

China Southern Power Grid Co.,Ltd.

College of Electrical Engineering,Xi’an Jiaotong University

Shandong Taikai Company

Electrical Power Research Institute of CSG

⁰