基于改进蜣螂算法优化LSSVM的断路器故障诊断方法研究

扫码查看

原文链接

国家科技期刊平台
NETL
NSTL
万方数据

中文摘要：为了使断路器故障诊断结果更可靠,笔者提出一种基于改进蜣螂算法(improved dung beetle optimizer,IDBO)优化最小二乘支持向量机(least squares support vector machine,LSSVM)的断路器故障诊断方法.通过采取Circle混沌映射、莱维飞行和T分布扰动等策略对蜣螂优化算法进行改进,以改善 IDBO 的寻优效果.采用IDBO搜索LSSVM关键参数最优值,建立基于IDBO-LSSVM的断路器故障诊断模型,并通过算例进行仿真实验分析.结果表明,IDBO-LSSVM模型、DBO-LSSVM模型和GA-BPNN模型在进行断路器故障诊断时的平均正确率分别为 97.44%、91.25%和 90.00%,IDBO-LSSVM模型具有更高的诊断精度,验证了所提断路器故障诊断方法的优越性.

外文标题：Fault Diagnosis Method of Circuit-Breaker Based on LSSVM Optimized by Improved Dung Beetle Optimizer

外文摘要：In order to make the fault diagnosis results of circuit-breakers more reliable,a fault diagnosis method of circuit-breakers based on improved dung beetle optimizer(IDBO)optimized least squares support vector machine(LSSVM)is proposed.In order to improve the optimization effect of IDBO,the dung beetle optimization algorithm is improved by adopting the strategies of Circle chaotic mapping,Levy flight and T distribution disturbance.IDBO is used to search the optimal value of the key parameters of LSSVM,and the fault diagnosis model of circuit-breaker based on IDBO-LSSVM is established,and the simulation experiment analysis is carried out through an example.The results show that the average correct rates of IDBO-LSSVM model,DBO-LSSVM model and GA-BPNN model in fault diagnosis of circuit-breakers are 97.44%,91.25%and 90.00%,respectively.The IDBO-LSSVM model has higher diagnostic accuracy,which verifies the superiority of the proposed fault diagnosis method for circuit breakers.

外文关键词：

circuit-breakerfault diagnosisleast squares support vector machineimproving dung beetle optimizer

作者：

尤敬尧、段洁、伍瑞泽

展开 >

作者单位：

国网湖北省电力有限公司荆门供电公司,湖北荆门 448001

关键词：

断路器故障诊断最小二乘支持向量机改进蜣螂优化算法

出版年：

2024

DOI：