Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM

YANG Xu; ZHOU Wen; CHENG Lin; LUO Chuanxian; ZHNAG Jing; JIANG Yi

doi:10.13296/j.1001-1609.hva.2025.02.007

您当前的位置：

首页 >

文章列表页 >

Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM

Research & Analysis | 更新时间：2025-05-25

- Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM
- High Voltage Apparatus Vol. 61, Issue 2, Pages: 54-62(2025)
- 作者机构：
  
  1.南瑞集团（国网电力科学研究院）有限公司，南京　 211006
  2.国网电力科学研究院武汉南瑞有限责任公司，武汉　 30074
  3.国网新疆电力有限公司检修公司，乌鲁木齐　 830000
- 作者简介：
- 基金信息：
  
  the State Grid Corporation Limited Headquarters Management Technology (Research on the Key Technology of Fault Detection and Diagnosis of Oil Paper Insulation of Super and UHV Transformers)
- DOI：10.13296/j.1001-1609.hva.2025.02.007
  CLC：
- Received：18 September 2024，
  
  Revised：25 November 2024，
  
  Published：16 February 2025
- 稿件说明：
移动端阅览
YANG Xu, ZHOU Wen, CHENG Lin, et al. Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM[J]. High voltage apparatus, 2025, 61(2): 54-62.
DOI：

YANG Xu, ZHOU Wen, CHENG Lin, et al. Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM[J]. High voltage apparatus, 2025, 61(2): 54-62. DOI： 10.13296/j.1001-1609.hva.2025.02.007.

摘要

变压器作为电力系统中最主要的输变电设备之一，其绝缘状态监测与故障识别对于电力系统安全稳定的运行具有重要意义。变压器内部绝缘劣化所产生的局部放电信号是目前对其内绝缘状态评判以及故障类型识别的最为有效的判据之一。文中通过构建4种典型的变压器绝缘缺陷模型，搭建试验平台测量得到了局部放电下的特高频信号和超声波信号。通过对2种信号的分析，对于特高频信号在TRTD模式下和PRPD模式下提取了两组特征参量，对于超声波信号在TRTD模式下提取了一组特征参量。经过核主成分分析联合支持向量机（KPCA-SVM）的特征融合方法进行信息融合后，发现相较于单一信息的识别效果，信息融合的识别率有显著的提升。

Abstract

Transformer is one of the most important power transmission and transformation equipment in power system and its insulation status monitoring and fault identification are of great significance to the safe and stable operation of power system. The partial discharge signal generated by the internal insulation deterioration of the transformer is currently one of the most effective criteria for evaluating the internal insulation status and identifying the fault type. In this paper

the ultrahigh frequency signal and ultrasonic signal under partial discharge are obtained by constructing four typical insulation defect models of transformer and setting up test platform for measurement. Throughout the analysis of two kinds of signals

two sets of characteristic parameters are extracted for ultrahigh frequency signals in both TRTD and PRPD modes

and a set of characteristic parameters are extracted for ultrasonic signals in TRTD mode. It is found after the feature fusion method of kernel principal component analysis together with support vector machine (KPCA-SVM) for information fusion that the recognition rate of information fusion is significantly improved compared to that of single information.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

APPLICATION OF INFORMATION FUSION TECHNIQUE TO TRANSFORMER FAULT DIAGNOSIS

APPLICATION OF INFORMATION FUSION BASED ON DEMPSTER-SHAFER’S EVIDENCE THEORY TO THE DIAGNOSIS OF TRANSFORMER’S FAULT POSITION

Fault Diagnosis of Transformer Based on Multi-information Fusion

SA-APSO Algorithm and Its Application in Ultrasonic Location of Partial Discharge in Transformer Oil

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

Related Author

DENG Yu

LUO An

XIA Xiang-yang

WANG Bei-bei

GUO Ji-wei

XIE Jing-dong

ZHOU Jian-hua

TANG Guo-qing

Related Institution

Central South University

中南大学信息科学与工程学院湖南长沙410083

Southeast University

东南大学电气工程系江苏南京210096

School of Electrical Engineering, Southwest Jiaotong University

⁰