电子测量与仪器学报

李黄曼,张勇,张瑶.基于ISSA优化SVM的变压器故障诊断研究[J].电子测量与仪器学报,2021,35(3):123-129

基于ISSA优化SVM的变压器故障诊断研究

Study of transformer fault diagnosis based on improved sparrow search algorithm optimized support vector machine

DOI：

英文关键词:sparrow search algorithm support vector machines fault diagnosis transformer opposition based learning

基金项目:国家自然科学基金青年科学基金（51806133)项目资助

作者	单位
李黄曼	陕西科技大学机电工程学院西安710021
张勇	陕西科技大学机电工程学院西安710021
张瑶	陕西科技大学机电工程学院西安710021

Author	Institution
Li Huangman	School of Mechanical and Electrical Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China
Zhang Yong	School of Mechanical and Electrical Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China
Zhang Yao	School of Mechanical and Electrical Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China

摘要点击次数: 1121

全文下载次数: 964

中文摘要:

针对传统的变压器故障诊断方法准确率较低的问题，提出了改进麻雀搜索算法（improved sparrow search algorithm，ISSA）优化支持向量机（SVM）的变压器故障诊断方法。首先引入动态反向学习因子对种群进行优化选择以提高麻雀搜索算法（SSA）全局寻优能力，其次用ISSA优化SVM的核函数参数和惩罚系数，建立基于油中溶解气体分析（DGA）的ISSA算法优化SVM的故障诊断模型。然后采用核主成分分析法(KPCA)对故障数据进行非线性降维。将经过KPCA处理后的数据输入ISSA SVM进行故障诊断。并与灰狼算法支持向量机（GWO SVM），粒子群算法支持向量机（PSO SVM）诊断结果进行对比。结果表明，ISSA SVM故障诊断率为92%，比GWO SVM, PSO SVM，SSA SVM分别提高了1067%、8%、533%，可以更精准的预测变压器运行状态。

英文摘要:

To solve the problem of low accuracy of tradition transformer fault diagnosis methods, a transformer fault diagnosis method based on the improved sparrow search algorithm was proposed. First, the opposition based learning (OBL) is introduced to optimize the selection of the population to improve the global optimization ability of the sparrow search algorithm.Then use the ISSA to dynamically optimize the kernel function parameters and penalty coefficients of the support vector machine, and obtain the fault diagnosis model of the support vector machine optimized by the ISSA based on DGA. The original data is processed through very sparse random projection to remove redundant features. At last input the processed data into ISSA SVM for fault diagnosis, and compare it with GWO SVM, PSO SVM and SSA SVM. The results show that the fault diagnosis rate of the ISSA SVM is 92%, which is 1067%, 8% and 533% higher than that of GWO SVM, PSO SVM and SSA SVM. So it can predict the operating status of the transformer more accurately.

查看全文查看/发表评论下载PDF阅读器