电测与仪表2017，Vol.54Issue(16)：7-13,7.
基于代价敏感组合核相关向量机的电力变压器故障诊断
Transformer fault diagnosis based on cost-sensitive multi-kernel learning relevance vector machine
高国强 1杨飞豹 1尹豪杰 1宋臻杰 1高波1
作者信息
- 1. 西南交通大学 电气工程学院,成都 610031
- 折叠
摘要
Abstract
Multi-Kernel learning relevance vector machine can integrate multiple feature spaces, and output the probability belonging to each state.In this paper, cost-sensitive mechanism was integrated into the multi-Kernel learning relevance vector machine (MKL-RVM), and constructed the cost-sensitive multi-Kernel learning relevance vector machine.The algorithm is based on Bayesian risk theory to predict the fault category of samples, reaching the goal of minimum cost of misdiagnosis, and overcomes the problem of not taking account of the difference cost of misdiagnosis.To solve the problem of its kernel function parameters need to be set artificially, K-fold cross validation combined particle swarm optimization was adapted to optimize the kernel function parameters.Case analysis based on dissolved gas analysis (DGA) data shows that CS-MKL-RVM not only has higher diagnosis accuracy, but also has lowest misdiagnosis cost, when compared with BP neural network, support vector machine and multi-Kernel learning relevance vector machine.关键词
电力变压器/组合核相关向量机/参数优化/代价敏感学习/DGA/故障诊断Key words
power transformer/MKL-RVM/parameter optimization/cost-sensitive learning/DGA/fault diagnosis分类
信息技术与安全科学引用本文复制引用
高国强,杨飞豹,尹豪杰,宋臻杰,高波..基于代价敏感组合核相关向量机的电力变压器故障诊断[J].电测与仪表,2017,54(16):7-13,7.
