Scholarlink

Dissolved gas analysis (DGA) in oil has some problems in reflecting and accurately diagnosing transformer faults. In order to solve these problems, We use the Neighborhood Rough Set technique to approximate a large number of transformer fault data ratios and reduce redundant data. This approximation technique resulted in a new set of ratios as our samples for fault diagnosis. In this study, a high-precision transformer fault diagnosis model combining the Gray Wolf Algorithm (GWO) and Support Vector Machine (SVM) has been successfully established.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on the Application of Support Vector Machine in Transformer Fault Diagnosis Based on Neighborhood Rough Set Theory and Gray Wolf Optimizer

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Guoyou Wang,
  • Weijin Xu,
  • Zhenyu Xu,
  • Xingguang Cheng,
  • Zeyi Yuan,
  • Renhui Chen

摘要

Dissolved gas analysis (DGA) in oil has some problems in reflecting and accurately diagnosing transformer faults. In order to solve these problems, We use the Neighborhood Rough Set technique to approximate a large number of transformer fault data ratios and reduce redundant data. This approximation technique resulted in a new set of ratios as our samples for fault diagnosis. In this study, a high-precision transformer fault diagnosis model combining the Gray Wolf Algorithm (GWO) and Support Vector Machine (SVM) has been successfully established.