摘要
针对环网柜电缆接头故障发生前后时刻的时间相关性较强,且故障的发生是一个非线性过程,将动态核主元分析应用于环网柜电缆接头故障检测并建立故障检测模型.该模型可以在解决非线性变量难以分离的同时提取变量之间的动态自相关特性,并通过建立动态核主元在线监测模型及时检测故障的发生.最后对采集的环网柜电缆接头故障数据进行实验分析,实验结果证明所提方法能有效地检测出环网柜电缆接头故障的发生,且检测精度和误报率均优于之前的算法.
Due to the time correlation and nonlinear characteristics of fault occurrence of cable joint in ring main unit,the dynamic kernel principal component analysis(DKPCA)is applied to the fault detection of cable joints in ring main unit and the fault detection model is established.The model can extract the dynamic autocorrelation between variables while solving the difficulty of separating nonlinear variables,and detect the occurrence of faults by establishing a dynamic kernel principal component online monitoring model.Finally,the proposed method is applied to the fault diagnosis of cable joints in ring main unit.The experimental results show that the method can effectively detect the cable joint failure of the ring main unit,and the detection accuracy and false alarm rate are better than the previous algorithm.
作者
张起
李学渊
李鹏
曹敏
ZHANG Qi;LI Xueyuan;LI Peng;CAO Min(School of Information Science and Engineering, Yunnan University, Kunming 650500, China;Yunnan Power Grid Corporation, Kunming 650011, China)
出处
《大连理工大学学报》
EI
CAS
CSCD
北大核心
2020年第3期300-305,共6页
Journal of Dalian University of Technology
基金
国家自然科学基金资助项目(61763049)
云南省应用基础研究计划重点项目(2018FA032)。
