摘要
机械故障是高压断路器最常见的故障,研究高压断路器机械故障诊断方法对于提高电力系统可靠性具有重要意义。为提高高压断路器机械故障诊断的效率,文中提出一种基于S变换和极限学习机(ELM)的高压断路器机械故障诊断新方法。首先,对高压断路器动作期间产生的振动信号进行S变换处理,获得相应的时—频矩阵;然后,对S变换模值矩阵进行时域和频域划分,计算振动信号在不同时段和频段的局部奇异值,并选择各子矩阵的最大奇异值作为故障诊断的特征向量;最后,采用ELM对高压断路器机械状态进行分类。对高压断路器在正常和故障状态下进行诊断实例测试,实验结果表明,该方法能够快速准确地识别断路器机械状态,具有较高的诊断效率。
To improve the fault diagnosis efficiency of high voltage circuit breakers(HVCBs),a new mechanical fault diagnosis method for HVCBs based on S-transform and extreme learning machine(ELM) is proposed.Firstly,the vibration signal generated during the operation of HVCBs is processed by S-transform to get the corresponding time-frequency matrix. Then,the S-transform module matrix is divided into several submatrices in time domain and frequency domain to compute the local singular values of vibration signal in different time and frequency sections. And the largest singular value of each submatrix is selected to form the feature vector for fault diagnosis. Finally,ELM algorithm is used for classification of the high voltage circuit breaker’s mechanical state. In addition,diagnostic experiments are conducted on a real HVCB in respective normal and fault state,and the results show that the proposed method can quickly and accurately recognize mechanical status of HVCBs with high efficiency.
作者
黄南天
陈怀金
林琳
戚佳金
HUANG Nantian;CHEN Huaijin;LIN Lin;QI Jiajin(School of Electrical Engineering,Northeast Electric Power University,Jilin 132012,China;State Grid Jining Power Supply Company,Shangdong Jining 272000,China;College of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin 132022,China;State Grid Hangzhou Power Supply Company,Hangzhou 310009,China)
出处
《高压电器》
CAS
CSCD
北大核心
2018年第6期74-80,共7页
High Voltage Apparatus
基金
国家高技术研究发展计划(863计划)项目(SS2014AA052502)
吉林省科技发展计划项目(20160411003XH)
吉林省教育厅"十三五"科技项目(吉教科合字[2016]第90号)
吉林市科技发展计划项目(20156407)~~
关键词
高压断路器
机械故障诊断
S变换
局部奇异值
极限学习机
high voltage circuit breaker
mechanical fault diagnosis
S-transform
local singular value
extreme learning machine
