矿用电连接器串联型故障电弧诊断方法研究

发布时间：2018-04-27 16:34

  本文选题：矿用电连接器 + 串联型故障电弧　； 参考：《电子测量与仪器学报》2017年08期

【摘要】：为提高煤矿井下供电系统的可靠性,在不同电压、电流、功率因数、环境相对湿度条件下,开展了因机械振动引发的串联型故障电弧模拟实验。分析了不同实验参数对故障电弧的影响;提取串联型故障电弧相邻五周期电流信号中的过零点数、归一化后的方差、协方差构成特征向量;建立了基于随机森林分类算法的串联型故障电弧诊断模型,以正常运行及故障电弧电流信号的特征向量构成训练样本和测试样本作为随机森林模型的输入,对样本进行分类,进而诊断是否发生串联型故障电弧。结果表明,该方法能够有效地实现矿用电连接器串联型故障电弧的诊断。
[Abstract]:In order to improve the reliability of underground power supply system in coal mine, the series fault arc simulation experiment caused by mechanical vibration was carried out under different voltage, current, power factor and relative humidity. The influence of different experimental parameters on the fault arc is analyzed, and the number of zero-crossing points in the adjacent five-period current signal of the series fault arc is extracted, and the normalized variance and covariance constitute the eigenvector. A series fault arc diagnosis model based on stochastic forest classification algorithm is established. The training samples and test samples are used as input to the random forest model to classify the samples, which are composed of characteristic vectors of normal operation and fault arc current signals. Then diagnose whether the series fault arc occurs. The results show that the method can effectively diagnose the series fault arc of mine electrical connectors.
【作者单位】： 辽宁工程技术大学电气与控制工程学院;辽宁工程技术大学安全学院;国网葫芦岛供电公司;
【基金】：国家自然科学基金(51674136) 辽宁工程技术大学市场调研基金(20160067T) 国家大学生创新创业计划训练项目(201610147000028)资助
【分类号】：TD611.3
，

本文编号：1811481