Fault Diagnosis of Transformer Using Relevance Vector Machine with Particle Swarm Optimization Based on DGA

YUAN Haiman; LEI Fan; CHEN Yu; CHEN Mingxing; JIANG Danyu; GAO Bo; WU Guangning

doi:10.13296/j.1001-1609.hva.2017.02.017

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis of Transformer Using Relevance Vector Machine with Particle Swarm Optimization Based on DGA

更新时间：2025-04-26

- Fault Diagnosis of Transformer Using Relevance Vector Machine with Particle Swarm Optimization Based on DGA
- High VoltageApparatus Vol. 53, Issue 2, Pages: 108-112+119(2017)
- 作者机构：
  
  西南交通大学电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2017.02.017
  CLC： TP18;TM407
- Published：2017
- 稿件说明：
移动端阅览
[1]袁海满,雷帆,陈宇,陈明星,江丹宇,高波,吴广宁.基于DGA的粒子群相关向量机变压器故障诊断[J].高压电器,2017,53(02):108-112+119.

YUAN Haiman, LEI Fan, CHEN Yu, et al. Fault Diagnosis of Transformer Using Relevance Vector Machine with Particle Swarm Optimization Based on DGA[J]. High voltageapparatus, 2017, 53(2): 108-112+119.
[1]袁海满,雷帆,陈宇,陈明星,江丹宇,高波,吴广宁.基于DGA的粒子群相关向量机变压器故障诊断[J].高压电器,2017,53(02):108-112+119. DOI： 10.13296/j.1001-1609.hva.2017.02.017.

YUAN Haiman, LEI Fan, CHEN Yu, et al. Fault Diagnosis of Transformer Using Relevance Vector Machine with Particle Swarm Optimization Based on DGA[J]. High voltageapparatus, 2017, 53(2): 108-112+119. DOI： 10.13296/j.1001-1609.hva.2017.02.017.

摘要

传统智能算法中因算法自身的固有缺陷

从而导致变压器故障诊断结果不理想。为此

针对相关向量机中核函数参数的选取对分类效果产生影响的问题

笔者在对运用粒子群算法优化相关向量机的可行性进行充分分析的基础上

构建了粒子群优化的相关向量机方法

以DGA作为特征输入

利用粒子群优化算法对核函数参数σ进行优化

以获得最优的相关向量机故障诊断方法

从而提高变压器的故障诊断精度。实例对比分析表明

与SVM、RVM方法相比

粒子群相关向量机方法具有更高的诊断精度。

Abstract

The inherent defects of the traditional intelligent algorithm results in unsatisfactory result of transformer fault diagnosis. In this paper

to eliminate the effect of parameter selection in relevance vector machine on classification results

the feasibility of using particle swarm optimization algorithm to optimize the relevance vector machine is analyzed

and a relevance vector machine method with particle swarm optimization is constructed. While DGA was considered as feature input

The particle swarm optimization algorithm is employed to optimize the kernel function parameter σ

hence to obtain an optimal fault diagnosis method with relevance vector machine and improve the precision of transformer fault diagnosis. Examples contrast and analysis show that

compared with support vector machine and relevance vector machine methods

the relevance vector machine method with particle swarm optimization has higher diagnostic accuracy.

关键词

Keywords

references

Views

368

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

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

Prediction Model for Dissolved Gas in Transformer Oil Based on Policy Gradient Optimization

Research on Hybrid Finite Element Method Based on Triangle Mesh and Its Application in Fluid-heat Coupled Calculation of Transformer

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

Related Author

LIU Wei

HAN Yanhua

WANG Jing

LIU Jiangnan

ZHAO Zhongyong

ZHOU Guangyu

MA Songling

TANG Jian

Related Institution

State Grid Shaanxi Electric Power Company

State Grid Shanxi Electric Power Research Institute

College of Engineering and Technology,Southwest University

School of Mechanical and Electrical Engineering,Xi’an University of Architecture and Technology

Department of Electrical Engineering, Shanghai Jiao Tong University

⁰