基于机器学习方法的轨道车辆悬挂元件状态监测研究  

Condition Monitoring of Rail Vehicle Suspension Elements:A Machine Learning Approach

作　　者：Henrik Karlsson Alireza Qazizadeh Sebastian Stichel  刘晓艳(翻译) 刘宏友(校) Henrik Karlsson;Alireza Qazizadeh;Sebastian Stichel;Mats Berg

机构地区：[1]不详

出　　处：《智慧轨道交通》2022年第2期72-76,共5页SMART RAIL TRANSIT

摘　　要：状态修利用数据采集、数据处理和决策分析,并根据部件的实际状态安排维修计划。采用状态修技术可以提高铁路系统的可靠性。本文针对不同运行工况下一系悬挂和二系悬挂系统减振器性能已经衰减的轨道车辆进行了仿真分析,生成了一个大型仿真数据库,并用于训练和测试分类算法,以检测面临的减振器故障。把车体、转向架构架和轮对的加速度计信号之间的频率响应函数作为故障指标和预测根据,并提供给分类算法。研究结果表明,1-紧邻分类器和线性支持向量机分类器对减振器性能衰减的预判均具有较高的分类能力。Condition maintenance utilizes data collecting,data processing and decision making to schedule maintenance based on the actual condition of components.Applying condition based maintenance technology can increase the reliability of railway systems.In this paper a rail vehicle is simulated at varying operational conditions,and with degraded dampers in the primary and secondary suspension.A large database of simulations is generated and is used to train and test classification algorithms to detect upcoming damper faults.Frequency response functions between accelerometer signals in the carbody,bogieframes and axles are used as fault indicators,predictors,fed to the classification algorithms.The research results show that the 1-Nearest-Neighbour classifier and the linear Support Vector Machine classifier both have high classification capability in predicting damper performance degradations.

关 键 词：状态监测 分类算法 机器学习 减振器故障 悬挂元件 

分 类 号：U270.331[机械工程—车辆工程]