山西电子技术2024,Issue(5) :29-32.

基于樽海鞘群算法优化支持向量机的电缆故障诊断

Optimization of Support Vector Machine for Cable Fault Diagnosis Based on Salp Swarm Algorithm

吴志明
山西电子技术2024,Issue(5) :29-32.

基于樽海鞘群算法优化支持向量机的电缆故障诊断

Optimization of Support Vector Machine for Cable Fault Diagnosis Based on Salp Swarm Algorithm

吴志明1
扫码查看

作者信息

  • 1. 广州友智电气技术有限公司,广东 广州 510000
  • 折叠

摘要

为了提高高压电缆故障诊断精度,提出了一种基于樽海鞘群算法优化SVM的电缆故障诊断方法.利用余弦相似度对电缆故障时序特征进行分析,采用樽海鞘群算法对支持向量机进行优化,建立基于樽海鞘群算法优化SVM的电缆故障诊断模型,采用配电网电缆故障录波数据进行仿真分析,并同其他电缆故障模型对比,结果表明,SSA-SVM的诊断精度为97.5%,诊断精度高于其他模型,验证了本文所提电缆故障诊断方法的实用性和有效性.

Abstract

In order to improve the accuracy of high-voltage cable fault diagnosis,a cable fault diagnosis method based on the optimization of SVM using the bottle sea sheath swarm algorithm is proposed.It uses cosine similarity to analyze the temporal characteristics of cable faults,the salp swarm algorithm to optimize the support vector ma-chine,and establishes a cable fault diagnosis model based on the salp swarm algorithm to optimize SVM.The dis-tribution network cable fault recording data is used for simulation analysis,and comparing it with other cable fault models.The results show that the diagnostic accuracy of SSA-SVM is 97.5%,which is higher than other models,The practicality and effectiveness of the cable fault diagnosis method proposed in this article have been verified.

关键词

电缆/故障诊断/樽海鞘群算法/支持向量机/诊断精度

Key words

cable/fault diagnosis/salp swarm algorithm/support vector machine/diagnostic accuracy

引用本文复制引用

出版年

2024
山西电子技术
山西省电子工业科学研究院 山西省电子学会

山西电子技术

影响因子:0.197
ISSN:1674-4578
段落导航相关论文