>> 自然科学版期刊 >> 2022 >> 2022年02期 >> 正文
基于多信息融合的塑壳断路器故障诊断方法研究
时间: 2022-03-10 次数:

李奎, 梁启明, 赵成晨,.基于多信息融合的塑壳断路器故障诊断方法研究[J].河南理工大学学报(自然科学版),2022,41(2):93-101.

LI K, LIANG Q M, ZHAO C C,et al. Research on fault diagnosis method of MCCB based on multi data fusion[J].Journal of Henan Polytechnic University(Natural Science) ,2022,41(2):93-101.

基于多信息融合的塑壳断路器故障诊断方法研究

李奎1,2, 梁启明1,2, 赵成晨1,2, 胡博凯1,2, 马典良1,2, 赵伟焯1,2

1.河北工业大学 河北省电磁场与电器可靠性重点实验室,天津 3001302.河北工业大学 省部共建电工装备可靠性与智能化国家重点 实验室,天津 300130

摘要:为了提高塑壳断路器故障诊断的正确率,根据D-S证据理论提出基于多信息融合的塑壳断路器故障诊断方法。首先,对断路器合闸声音信号和振动信号进行经验模态分解,提取不同信号的IMF包络能量熵,并作为特征向量输入LIBSVM library for support vector machines)进行诊断,依据内部投票规则获得基本概率分配;然后将LIBSVM测试样本总分类正确率作为固定权重,构成声振信号的加权概率分配;最后通过D-S证据理论对声振信号加权概率分配进行决策层融合,得到断路器故障诊断结果。在实验室条件下,进行塑壳断路器操作试验,获得安装正常、安装松动、主拉簧断裂3种不同状态下的试验数据,并进行诊断分析,结果表明,融合诊断比单信息诊断的正确率高。

关键词:塑壳断路器;经验模态分解;信息熵;LIBSVM;D-S证据理论

doi:10.16186/j.cnki.1673-9787.2021010112

基金项目:国家自然科学基金资助项目(51937004,51777056

收稿日期:2021/01/24

修回日期:2021/03/19

出版日期:2022/03/15

Research on fault diagnosis method of MCCB based on multi data fusion

LI Kui1,2, LIANG Qiming1,2, ZHAO Chengchen1,2, HU Bokai1,2, MA Dianliang1,2, ZHAO Weizhuo1,2

1.Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin  300130 , China2.State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin  300130 , China

Abstract: In order to improve the accuracy of MCCB fault diagnosis,a fault diagnosis method of MCCB based on multi information fusion was proposed. Firstly,empirical mode decomposition(EMD) was used to decompose the MCCB closing sound and vibration signals. Then,the IMF envelope energy entropy could be extracted as eigenvector and be put into LIBSVM(library for support vector machines) to obtain the basic probability assignment. The total classification accuracy of LIBSVM test samples was taken as a fixed weight to form the weighted probability assignment of sound and vibration signals. Finally,the weighted probability assignment of sound and vibration signals was integrated by using D-S evidence theory to obtain the fault diagnosis results of MCCB. Under laboratory conditions,the test data of MCCB in three different states including normal,loose installation and main spring fracture were obtained,and the diagnostic analysis was carried out. The results showed that the accuracy of fusion diagnosis was higher than that of single information diagnosis.

Key words:MCCB;empirical mode decomposition;information entropy;LIBSVM;D-S evidence theory

 基于多信息融合的塑壳断路器故障诊断方法研究_李奎.pdf

最近更新