基于深度迁移学习的提升机主轴故障在线诊断系统研究  

Online fault diagnosis system of hoist bearing based on deep transfer learning

作　　者：张宏乐 韩雪华 史凯 任贺贺 徐磊 钱恒昌 李灿 李方迪 黄璜 ZHANG Hong-le;HAN Xue-hua;SHI Kai;REN He-he;XU Lei;QIAN Heng-chang;LI Can;LI Fang-di;HUANG Huang(Jining No.2 Coal Mine,Yankuang Energy Group Co.,Ltd.,Jining 273599,China;Shandong Coal Science and Technology Research Institute Branch,Yankuang Energy Group Co.,Ltd.,Jinan 250117,China)

机构地区：[1]兖矿能源集团股份有限公司济宁二号煤矿,山东济宁273599 [2]兖矿能源集团股份有限公司山东煤炭科技研究院分公司,山东济南250117

出　　处：《煤炭工程》2022年第7期61-66,共6页Coal Engineering

摘　　要：实际工业场景下的提升机状态监测与在线故障诊断,存在缺少足量有标签故障样本以及变工况导致的测试样本与训练样本间分布差异的问题,限制了智能故障诊断算法应用于实际工程。文章提出一种面向实际提升机的融合边缘节点的迁移故障诊断架构,包括多源信息采集层,边缘节点层,网络层和中央云服务器层。以提升机轴承为对象,提出基于ResNet与多核联合分布差异的深度迁移故障诊断算法,实现变工况下的提升机轴承故障状态识别,采用两种轴承故障数据进行算法有效性与适应性验证,结果表明所提出算法能够达到理想的迁移故障诊断准确率。最后,设计构建了提升机检测诊断平台,部署于煤矿地面中央云服务器中心,实现了对矿井提升机运行状态的监测与在线诊断。In the condition monitoring and on-line fault diagnosis of hoist in the actual industrial scene,insufficient labeled fault samples and the distribution difference between testing and training samples caused by variable working conditions are important reasons that restrict the application of intelligent fault diagnosis algorithm in practical engineering.A transfer fault diagnosis architecture combined edge node for actual hoist is proposed,including multi-source data perception layer,edge node layer,network layer and central cloud server layer.Taking the hoist bearing as the object,a deep transfer fault diagnosis algorithm based on ResNet and multi-core joint distribution discrepancy is proposed to recognize the fault state of hoist under variable working conditions,two kinds of bearing fault data are used to verify the effectiveness and adaptability of the algorithm.The results show that the proposed algorithm can achieve an ideal transfer fault diagnosis accuracy.Finally,a hoist detection and diagnosis platform is designed and constructed,which is deployed in the coal mine ground central cloud server center to monitor and online diagnose the running state of the mine hoist.

关 键 词：提升机 故障诊断 深度学习 边缘节点 诊断平台 变工况 

分 类 号：TD534[矿业工程—矿山机电] TP391[自动化与计算机技术—计算机应用技术]