基于多信息融合的塑壳断路器故障诊断方法研究

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

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。

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.