Equalization Method of Power Transformer Fault Sample Based on SVM SMOTE

LIU Yunpeng; HE Jiahui; XU Ziqiang; WANG Quan; LI Zhe; GAO Shuguo

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Equalization Method of Power Transformer Fault Sample Based on SVM SMOTE

更新时间：2025-12-08

- Equalization Method of Power Transformer Fault Sample Based on SVM SMOTE
- Vol. 46, Issue 7, Pages: 2522-2529(2020)
- 作者机构：
  
  1. 华北电力大学河北省输变电设备安全防御重点实验室
  2. 华北电力大学新能源电力系统国家重点实验室
  3. 国网河北省电力有限公司电力科学研究院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：31 July 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
LIU Yunpeng, HE Jiahui, XU Ziqiang, et al. Equalization Method of Power Transformer Fault Sample Based on SVM SMOTE[J]. 2020, 46(7): 2522-2529.
DOI：

LIU Yunpeng, HE Jiahui, XU Ziqiang, et al. Equalization Method of Power Transformer Fault Sample Based on SVM SMOTE[J]. 2020, 46(7): 2522-2529. DOI：

摘要

在变压器故障诊断领域

数据集不平衡性带来的极端值、噪声等问题严重影响了分类算法的故障识别能力。为此

提出了一种基于支持向量机（supportvectormachine

SVM）合成少数类过采样（syntheticminority over-samplingtechnique

SMOTE）算法的电力变压器故障样本均衡化方法

并结合机器学习进行故障诊断

以解决不平衡数据集下变压器故障诊断整体精度低的问题。首先

从原理、特点、应用等方面对传统SMOTE算法和SVM SMOTE算法进行了大量研究和分析;然后

以变压器油中溶解气体为样本集

构建了基于故障样本均衡化的变压器故障诊断模型;最后

对所提方法进行了算例仿真。结果显示:相较于传统变压器故障诊断算法

采用SVMSMOTE算法对故障样本进行均衡化后

各评价指标均有大幅提升

其中整体分类准确度αmacro-F1提升了18.9%。研究结果证明所提方法可以有效解决不平衡数据集下变压器故障样本漏判率高的问题

并在其分类上具有更高的精度。

Abstract

In the field of transformer fault diagnosis

the extreme values and noise caused by the imbalance of a data set have seriously affected the fault recognition ability of the classification algorithm. Therefore

a method of power transformer fault sample equalization based on the support vector machine（SVM） synthetic minority over-sampling technique（SMOTE） algorithm is proposed

and machine learning is combined for fault diagnosis to effectively solve the problem of low overall-precision of transformer fault diagnosis under the unbalanced data set. Firstly

the traditional SMOTE algorithm and SVM SMOTE algorithm from the aspects of principle

characteristics

and application were researched and analyzed in detail Then

the gas concentration dissolved in transformer oil was taken as a sample set

and the transformer fault diagnosis model based on fault sample equalization was constructed. Finally

simulation study was carried out.The result shows that

compared with traditional transformer fault diagnosis

the evaluation indexes have been greatly improved after fault sample equalization with SVM SMOTE

and the αmacro-F1

namely

overall accuracy

has increased by nearly 18.9%. The research results prove that the proposed method can be adopted to effectively solve the problem of high missing report ratio of transformer fault sample under unbalanced data set

and outperform traditional classification algorithms with respect to accuracy.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Diagnosis Method of Internal Fault for Transformers Based on Information Fusion

Diagnosis Model for Transformer Fault Based on CRO-BP Neural Network and Fusion DGA Method

Application of Bagging-CART Algorithm Optimized by Genetic Algorithm in Transformer Fault Diagnosis

Fault Diagnosis for Power Transformer Based on Rough Set and Multi-class Support Vector Machine

Method for State Evaluation of Transformer Winding Deformation Based on Information Fusion

Related Author

CHEN Weigen

LIU Juan

CAO Min

ZHANG Kefei

GUO Jiang

NIE Dexin

YUAN Fang

XIAO Zhihuai

Related Institution

State Key Laboratory of Power Transmission Equipment & System Security, Chongqing University

Electric Power Research Institute, Yunnan Electric Power Test & Research Group Co., Ltd.

College of Power & Mechanical Engineering, Wuhan University

State Grid Electric Power Research Institute

School of Electronic Information, Xi’an Polytechnic University

AI问答

⁰