摘要
利用车线动力学模型构建监测节点布置方案。基于监测数据,通过研究服役状态数据与轨道故障特征关系,得到轨道振动在不同故障条件下的特征规律。提取主要特征,并对特征进行归一化处理,使用密度聚类用于诊断轨道服役状态,建立轨道故障诊断的分类器;采用具体仿真实验验证了本文轨道结构故障诊断方法的有效性;并由此验证了一种基于多源异构数据的故障诊断特征研究方法,实现了轨道故障的分类。
The layout scheme of monitoring nodes is constructed by using the vehicle-line dynamics model.Based on the monitoring data,the characteristics of track vibration under different fault conditions are obtained by studying the relationship between service state data and track fault characteristics.The main features are extracted,and the features are normalized.The density clustering is used to diagnose the track service state,and the track fault diagnosis classifier is established.The effectiveness of this method is verified by simulation experiments.A fault diagnosis feature research method based on multi-source heterogeneous data is verified and the classification of track faults is realized.
作者
石敏莲
许汪歆
Shi Minlian;Xu Wangxin(School of Urban Rail Transportation,Shanghai University of Engineering Science,Shanghai 201620,China)
出处
《农业装备与车辆工程》
2020年第12期119-123,共5页
Agricultural Equipment & Vehicle Engineering
关键词
轨道结构
动力学模型
故障诊断
服役状态
降维
分类器
track structure
dynamic model
fault diagnosis
service condition
dimension reduction
classifier
