Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA

ZHOU Guangyu; MA Songling

doi:10.13296/j.1001-1609.hva.2020.06.038

您当前的位置：

首页 >

文章列表页 >

Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA

更新时间：2025-04-26

- Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA
- High VoltageApparatus Vol. 56, Issue 6, Pages: 262-268(2020)
- 作者机构：
  
  西安建筑科技大学机电工程学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2020.06.038
  CLC： TM407
- Published：2020
- 稿件说明：
移动端阅览
[1]周光宇,马松龄.基于机器学习与DGA的变压器故障诊断及定位研究[J].高压电器,2020,56(06):262-268.

ZHOU Guangyu, MA Songling. Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA[J]. High voltageapparatus, 2020, 56(6): 262-268.
[1]周光宇,马松龄.基于机器学习与DGA的变压器故障诊断及定位研究[J].高压电器,2020,56(06):262-268. DOI： 10.13296/j.1001-1609.hva.2020.06.038.

ZHOU Guangyu, MA Songling. Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA[J]. High voltageapparatus, 2020, 56(6): 262-268. DOI： 10.13296/j.1001-1609.hva.2020.06.038.

摘要

变压器故障诊断特征信息繁多

且故障点难以确定

为有效利用故障信息提高故障诊断准确率

以及实现故障定位

提出一种基于粗糙集知识和优化支持向量机的变压器分层故障诊断及定位新方法。首先使用邻域粗糙集评估DGA样本重要度

并约简出优选故障诊断特征量。其次构建基于多分类支持向量机的分层故障诊断模型

采用粒子群算法优化模型参数以提高分类精度

实现了故障性质和故障定位的多层诊断。实例分析表明

新特征量可以提高机器学习的知识挖掘能力

不仅故障分类的精度增加

而且模型可以实现故障点的定位

综合诊断准确率达到88.4%。

Abstract

There are many fault diagnosis features of the transformer

and difficult to determine the point of failure.In order to effectively use fault information

improve the accuracy of fault diagnosis and achieve fault location

con-structed a new method for fault diagnosis stratified and location of transformers based on Rough set knowledge andoptimized Support Vector Machine. First

used the neighborhood rough set to assess DGA sample importance and re-duced to get optimal feature quantity. Secondly

built a hierarchical fault diagnosis model based on multi-class sup-port vector machine

used the particle swarm optimization parameter selection is used to improve the accuracy

achieved stratified multi-layered nature of the fault diagnosis and fault location. The example analysis shows that newfeature quantity can improve the knowledge mining ability of machine learning

not only increases the accuracy offault classification

and the model can realize the positioning of the fault point

comprehensive diagnostic accuracyreached 88.4%.

关键词

Keywords

references

Views

305

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transformer Winding Deformation Classification Method Based on Particle Swarm Algorithm Optimizing Support Vector Machine

Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology

Fault Diagnosis Model of Transformer Based on GJO Feature Optimization and AO-RF

Research on Diagnosis Method of Transformer Winding Deformation Fault Based on Dynamic Time Warping

New Approach to Transformer Fault Diagnosis Based on ANN

Related Author

LIU Wei

HAN Yanhua

WANG Jing

LIU Jiangnan

ZHAO Zhongyong

XU Aihua

ZANG Chunyan

LI Yishuo

Related Institution

State Grid Shaanxi Electric Power Company

State Grid Shanxi Electric Power Research Institute

College of Engineering and Technology,Southwest University

Hubei Institute of Measurement and Testing Technology

School of Electrical and Electronic Engineering, Huazhong University of Science and Technology

⁰