高压电器2018，Vol.54Issue(5)：236-241,247,7.DOI:10.13296/j.1001-1609.hva.2018.05.037
基于粒子群与多分类相关向量机的变压器故障诊断
Transformer Fault Diagnosis Based on Particle Swarm Optimization and Multi-classification Correlation Vector Machine
摘要
Abstract
In order to improve the accuracy of transformer fault diagnosis effectively, this paper combines particle swarm optimization (PSO) with multi-classification correlation vector machine to construct a method based on multi-classification correlation vector machine of particle swarm optimization for transformer fault diagnosis. The method firstly combines the dissolved gas in oil with the ratio of four characteristic gases as fault characteristic variables to further enrich the fault information. Secondly, the kernel parameters of the multi-classification correlation vector ma-chine are optimized by PSO algorithm and training sample data to obtain the parameters which are optimal and can improve the efficiency of fault classification effectively. Finally, nine characteristic variables are used as feature in-puts, and the trained multi-classification correlation vector machines are used for fault diagnosis. The case analysis shows that this method can effectively supplement and improve the fault characteristic variables and fault classification model, and its fault diagnosis efficiency is more advantageous.关键词
变压器/故障诊断/粒子群/多分类相关向量机Key words
transformer/fault diagnosis/particle swarm optimization/multi-classification correlation vector machine引用本文复制引用
刘益岑,袁海满,范松海,李帅兵,甘德刚,高波..基于粒子群与多分类相关向量机的变压器故障诊断[J].高压电器,2018,54(5):236-241,247,7.基金项目
国家电网公司科技项目(521997140005).Project Supported by Science and Technology Project of State Grid Corp.(521997140005). （521997140005）
