摘要
针对分布式配电网故障诊断过程中因信号丢失导致的诊断准确率下降问题,以分布式电源配电网络故障定位拓扑结构为基础,采集不同时段不同区段故障发生后的配电网络节点信息,形成故障信息数据集群,并对其数据特性进行分析,提取故障特征量,最后,采用粒子群寻优算法对支持向量机模型参数进行参数寻优,在Matlab仿真平台构建了分布式配电网络故障诊断算法模型,其中对区域故障信号因子进行反馈校正,剔除非区域故障的冗余计算。仿真结果表明,该故障诊断策略提升了配电网络的故障诊断运算速度和准确率。
In order to solve the problem that the accuracy of fault diagnosis in distributed distribution network is reduced due to signal loss,based on the fault location topology structure of distributed generation distribution network,the node information of distribution network after fault occurrence in different periods and sections was collected to form the fault information data cluster,the data characteristics were analyzed,and the fault feature quantity was extracted,finally,particle swarm optimization algorithm was used to optimize the parameters of support vector machine model.A distributed distribution network fault diagnosis algorithm model was built on the Matlab simulation platform.The regional fault signal factors are feedback corrected and the redundant calculation of non regional fault was eliminated.The simulation results showed that the fault diagnosis strategy improves the operation speed and accuracy of fault diagnosis of distribution network accuracy.
作者
刘小英
Liu Xiaoying(Mechanical and electrical College of Xianyang Vocational and Technical College,Xianyang 712000,China)
出处
《能源与环保》
2021年第9期229-233,239,共6页
CHINA ENERGY AND ENVIRONMENTAL PROTECTION
基金
国家“双高计划”建设学校课程思政研究与实践课题(SGKCSZ2020-1526)
咸阳职院2020年度课程思政建设研究与实践课题(2020KCSZ079)。
关键词
分布式配电网
故障诊断
拓扑结构
粒子群寻优
支持向量机
distributed distribution network
fault diagnosis
topology
particle swarm optimization
support vector machine
