SVD在串联故障电弧检测及选相中的应用

Application of SVD in series fault arc detection and phase selection

煤矿井下发生串联故障电弧易引发火灾等安全事故,为了预防电气火灾、指导线路维修,利用三相电动机及变频器负载开展不同线路、不同电流条件下的串联故障电弧实验,研究三相串联故障电弧的检测及选相方法。首先,对单相电流进行一阶差分处理后,建立改进的吸引子轨迹矩阵作为故障特征矩阵;其次,对故障特征矩阵进行奇异值分解,采用特征矩阵的奇异值构建串联故障电弧检测及选相的特征向量;最后,利用极限学习机建立故障电弧检测及选相模型,并测试检测及选相准确率。研究结果表明:提出的SVD方法可以利用单相电流实现三相电动机及变频器负载回路中的串联故障电弧检测及选相。

The series arc fault in coal mine is easy to cause fires and other safety accidents,in order to prevent fires and guide line maintenance,three-phase motor and inverter load were used to carry out series arc fault experiments under different lines and currents,and the detection and phase selection methods of three-phase series arc fault were studied.Firstly,the improved attractor trajectory matrix was established the fault feature matrix after the first-order difference processing of single-phase current.Secondly,the singular value decomposition of the fault characteristic matrix was carried out,and the singular value was used to construct the feature vectors.Finally,an arc fault detection and phase selection model was established by the limit learning machine,and the accuracy of detection and phase selection was tested.The results show that the proposed method can realize the series arc fault detection and phase selection in the load circuit of the three-phase motor and inverter through the single-phase current.