摘要
为评估SF_(6)断路器触头的烧蚀状态,对断路器进行模拟烧蚀试验,并采用3种不同测试电流分别测量动态电阻行程。结果表明:增大测试电流可以减少动态电阻曲线的波动;除电流烧蚀作用外,操动机构松动会造成触头分合闸不到位,导致动态电阻曲线中主触头行程不断减小。将触头烧蚀状态按照烧蚀次数划分为4个等级;从动态电阻行程曲线中提取5个状态参数作为输入参数,基于极限学习机建立触头烧蚀状态的评估模型,并使用人工鱼群算法对模型进行优化;建立未优化的极限学习机模型进行对比。结果表明:利用优化后的模型能够准确分类测试集样本的烧蚀等级,准确率为100%;人工鱼群算法可以提高模型的评估准确率,使模型具有更好的稳定性。
In order to evaluate the ablation state of the contacts of the SF_(6)circuit breaker,a simulated ablation test is carried out on the circuit breaker,and the dynamic resistance-travel curve is measured with three types of test currents.The results showed that increasing the test current can reduce the fluctuation of the dynamic resistance-travel curve;in addition to the ablation effect of current,the loosening of the operating mechanism will affect the accuracy of opening and closing action of the contact,resulting in the continuous reduction of the main contact stroke in the dynamic resistance-travel curve.The ablation state of contact is divided into four grades according to the number of ablations;five parameters are extracted from the dynamic resistance curve as a function of contact travel as input parameters,an evaluation model of contact ablation state is established based on extreme learning machine optimized by artificial fish swarm algorithm,and the model is optimized by using an artificial fish swarm algorithm.The results show that by using the optimized model,the ablation level of test samples can be accurately classified with an accuracy of 100%;by using the artificial fish algorithm,the evaluation accuracy can be improved and make the model more stable.
作者
周雄
彭彦军
潘宁波
庞建有
王璐
Zhou Xiong;Peng Yanjun;Pan Ningbo;Pang Jianyou;Wang Lu(Guilin Power Supply Bureau,Guangxi Power Grid Co.,Ltd.,Guilin,Guangxi 541002,China)
出处
《机电工程技术》
2023年第6期222-226,共5页
Mechanical & Electrical Engineering Technology
关键词
极限学习机
人工鱼群算法
SF_(6)断路器
触头烧蚀
动态电阻
extreme learning machine
artificial fish school algorithm
SF_(6)circuit breaker
contact ablation
dynamic resistance
