摘要
针对电力系统故障诊断的不确定性,以及保护开关和断路器动作信息中常出现的误动、拒动等问题,笔者提出一种基于蝴蝶优化算法的电力系统故障诊断方法,重点分析了该方法在解析大数据模型中对目标问题快速求解的特点,给出了数据引入时的预处理过程,充分利用蝴蝶优化算法在寻迹方面的推理能力,根据报警信息搜索电网数据库,提出故障假设及诊断结果。采用IEEE-39节点进行验证,并与人工神经网络方法进行比较。结果表明,该方法目标更加明确,且收敛速度更快,适用于网络规模大的电力系统故障诊断。
Aiming at the uncertainty of power system fault diagnosis and the problems of misoperation and rejection in the action information of protection switches and circuit breakers,the authors propose a power system fault diagnosis method based on butterfly optimization algorithm.The characteristics of fast solution of the target problem in the analytical big data model are analyzed.The preprocessing process of data introduction is given.By making full use of the reasoning ability of butterfly optimization algorithm in tracing,the fault hypothesis and diagnosis results are proposed by searching the power grid database according to the alarm information.The IEEE-39 node is used for verification and compared with the artificial neural network method.The results show that the proposed method has clearer objectives and faster convergence speed,which is suitable for fault diagnosis of power system with large network scale.
作者
王致诚
李致远
邵长春
WANG Zhicheng;LI Zhiyuan;SHAO Changchun(Liuzhou Railway Vocational Technical College,Liuzhou 545616,China;Liuzhou Key Laboratory of Intelligent Mobile Robot,Liuzhou 545005,China)
出处
《红水河》
2024年第1期91-95,115,共6页
Hongshui River
基金
2021年度广西高校中青年教师科研基础能力提升项目(2021KY1392)。
关键词
故障诊断
电力系统
蝴蝶优化算法
故障识别
机器学习
fault diagnosis
power system
butterfly optimization algorithm
fault identification
machine learning
