基于机器学习的铁路轨道打磨电动机故障诊断技术研究  

Research on fault diagnosis technology of railway track grinding motor based on machine learning

作　　者：周奇才[1] 黄杰武 熊肖磊[1] 赵炯[1] Zhou Qicai;Huang Jiewu;Xiong Xiaolei;Zhao Jiong

机构地区：[1]同济大学机械与能源工程学院,上海201800

出　　处：《起重运输机械》2022年第22期38-44,共7页Hoisting and Conveying Machinery

摘　　要：铁路轨道打磨车打磨电动机工作环境复杂恶劣,故障发生率相对较高,并且打磨电动机作为铁路轨道打磨车的关键部件,其运行状态直接关系到轨道打磨的效率与质量,故可靠的故障诊断技术是提高打磨效率与打磨质量的关键技术之一。文中研究基于数据驱动的方式,通过传感器采集不同打磨电动机数据构建数据集,采用不同的机器学习算法构建电动机智能故障诊断模型,对打磨电动机运行状态进行诊断,并通过对比不同算法的诊断准确率,探索更加适用于打磨电动机的故障诊断算法。结果表明,所研究的智能故障诊断技术准确度较高,对提高打磨电动机运行可靠性以及提高其工业智能化程度具有较大意义。The working environment of the grinding motor of the railway track grinding vehicle is complex and harsh,and the failure rate is high.As the key component of the railway track grinding vehicle,the running state of the grinding motor is directly related to the efficiency and quality of track grinding,so reliable fault diagnosis technology is one of the key factors to improve the grinding efficiency and quality.Based on the data-driven method,the data of different grinding motors are collected by sensors to build data sets,and different machine learning algorithms are used to build intelligent fault diagnosis models of motors to diagnose the running state of grinding motors.By comparing the diagnostic accuracy of different algorithms,a more suitable fault diagnosis algorithm for grinding motors is explored.The results show that the accuracy of the intelligent fault diagnosis technology studied is high,which is of great significance to improve the reliability of grinding motor operation and its industrial intelligence.

关 键 词：打磨电动机 机器学习 故障诊断 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]