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

JIA Lijing; ZHANG Jianwen; WANG Chuanlin; YAN Jiaming; ZHOU Xianjiao; CHEN Luna

doi:10.13296/j.1001-1609.hva.2015.04.003

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2025-04-26

- Fault Diagnosis of Power Transformer Based on DGA of Algorithm for SVM
- High VoltageApparatus Vol. 51, Issue 4, Pages: 13-18(2015)
- 作者机构：
  
  中国矿业大学信息与电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2015.04.003
  CLC： TM41
- Published：2015
- 稿件说明：
移动端阅览
[1]贾立敬,张建文,王传林,严家明,周贤娇,陈鲁娜.基于DGA的差分进化支持向量机电力变压器故障诊断[J].高压电器,2015,51(04):13-18.

JIA Lijing, ZHANG Jianwen, WANG Chuanlin, et al. Fault Diagnosis of Power Transformer Based on DGA of Algorithm for SVM[J]. High voltageapparatus, 2015, 51(4): 13-18.
[1]贾立敬,张建文,王传林,严家明,周贤娇,陈鲁娜.基于DGA的差分进化支持向量机电力变压器故障诊断[J].高压电器,2015,51(04):13-18. DOI： 10.13296/j.1001-1609.hva.2015.04.003.

JIA Lijing, ZHANG Jianwen, WANG Chuanlin, et al. Fault Diagnosis of Power Transformer Based on DGA of Algorithm for SVM[J]. High voltageapparatus, 2015, 51(4): 13-18. DOI： 10.13296/j.1001-1609.hva.2015.04.003.

摘要

针对支持向量机中参数选择严重影响分类效果的特点

提出采用差分进化算法对核函数g和惩罚因子c进行优化

得到最优的支持向量机模型

用于变压器的故障诊断。在简单介绍支持向量机的基础上

分析了采用差分进化算法对支持向量机优化的可行性。通过将收集的数据样本进行预处理

再利用差分进化的变异、交叉和选择对高斯径向基核函数进行优化

搜索出最优（c

g）

并对得到的参数进行验证

获得最优的支持向量机模型。仿真实验表明

与SVM、GRID-SVM、GA-SVM、PSO-SVM相比

该方法误判率最低、全局寻优能力及鲁棒性较好。

Abstract

In response to parameter selection seriously affect classification results in SVM

this paper proposes a method using differential evolution optimizes on parameter of kernel function g and penalty parameter c

aiming to getting the SVM machine model for the fault diagnosis of transformer. Firstly

this paper analyzes the feasibility of using differential evolution algorithm for SVM optimization based on the brief introduction of SVM. Through pretreating the collecting data samples and using the mutation

crossover and selection of differential evolution optimizes on RBF

the best parameters c and g are found out

and the parameters to obtain the SVM model are verified. The results show that

compared with non-optimized SVM

GRID-SVM

GA-SVM and PSO-SVM

this method has the lowest misjudgment rate and good global search ability and better robustness.

关键词

Keywords

references

Views

399

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transformers Fault Diagnosis Based on SVM for Unbalanced Data

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

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

Fault Diagnosis of High Voltage Disconnector Based on Attitude Angle and Speed Curves

Related Author

LIU Chenfei

CUI Haoyang

LI Xin

SHU Jiang

LI Ya

PENG Zaixing

WANG Song

YI Lin

Related Institution

College of Electronics and Information Engineering,Shanghai University of Electric Power

China Southern Power Grid Co.,Ltd.

College of Electrical Engineering,Xi’an Jiaotong University

Shandong Taikai Company

Electrical Power Research Institute of CSG

⁰