摘要
高压SF6断路器弧触头的接触电阻和质量损失预测在断路器状态评估中起着重要作用。该文提出了一种基于量子粒子群优化和支持向量回归(quantum particle swarms optimization and support vector regression,QPSO-SVR)的方法,能够有效预测断路器弧触头在不同电弧电流条件下的接触电阻增量和质量损失,并结合实验数据获得了SVR算法的最佳训练参数。将该文方法与其他预测方法进行比较,QPSO-SVR方法对不同电弧电流条件下的实验数据表现出良好的预测能力。其中,对于接触电阻增量的预测相对误差为3.023%,而对于质量损失的预测相对误差为4.61%,均表现出较好的鲁棒性。最后将QPSO-SVR预测得到的质量损失和接触电阻增量以及监测到的累积电弧能量进行模糊逻辑推理,构建了基于QPSO-SVR算法的触头烧蚀状态评估系统,将触头烧蚀状态分为O级烧蚀、Ⅰ级烧蚀、Ⅱ级烧蚀、Ⅲ级烧蚀4等级,可为高压SF6断路器检修提供参考。
The prediction of contact resistance and mass loss of contacts plays an important role in the condition assessment of high-voltage SF_(6)circuit breakers.In this paper,a method based on quantum particle swarms optimization and support vector regression(QPSO-SVR)is proposed to effectively predict the incremental contact resistance and mass loss of arc contacts under different arc ablation conditions.The optimum training parameters for the SVR algorithm are obtained by combining the experimental data.The QPSO-SVR method has shown good prediction capability for different arc ablation conditions when compared with other prediction methods.The relative error of prediction for the incremental contact resistance is 3.023%,while the relative error of prediction for the mass loss is 4.61%,both of which show good robustness.Finally,the mass loss and contact resistance increments obtained from QPSO-SVR prediction and the monitored accumulated arc energy are subjected to fuzzy logic inference to construct a contact ablation state assessment system based on QPSO-SVR algorithm,which classifies the contact ablation state into four classes:class O,class I,class II and class III.The method can provide reference for high-voltage SF_(6)circuit breaker maintenance.
作者
王振兴
刁目鑫
肖光宇
闫静
陈道品
陈邦发
WANG Zhenxing;DIAO Muxin;XIAO Guangyu;YAN Jing;CHEN Daopin;CHEN Bangfa(State Key Library of Electrical Insulation and Power Equipment,Xi’an Jiaotong University,Xi’an 710049,China;Foshan Power Supply Bureau,Guangdong Power Grid Corporation,Foshan 528010,China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2023年第9期3907-3917,共11页
High Voltage Engineering
基金
国家自然科学基金(51937009)
中国南方电网公司科技项目(GDKJXM20184109)。
关键词
SF_(6)断路器
触头烧蚀
状态评估
支持向量回归
量子粒子群优化
模糊逻辑推理
SF_(6)circuit breaker
contact ablation
state assessment
support vector regression
quantum particle swarm optimization
fuzzy logic inference
