针对轨道车辆走行部关键部件故障的智能识别研究
2021-08-17周宏祥尧辉明
周宏祥 尧辉明



摘 要:针对轨道车辆走行部关键部件的故障识别问题,本文提出了利用蚁群算法对弹簧的状态参数进行估计。通过对轨道车辆横向动力学方程建立的多元线性回归模型进行处理,得到约束模型。利用蚁群算法的寻优特性,在弹簧的正常、轻微故障和断裂的情况下对约束模型进行寻优计算,验证该算法的有效性。结果表明:该方法可以有效准确地估计轨道车辆走行部关键部件弹簧的实际参数值。通过比较估计值和正常值,可及时判断弹簧的状态,该参数估计方法可为轨道车辆悬挂系统关键部件状态监测提供重要的理论依据。
关键词:轨道车轮;动力学模型;蚁群算法;参数估计;寻优处理
中图分类号:TP391 文献标识码:A DOI:10.3969/j.issn.1003-6970.2021.03.024
本文著录格式:周宏祥,尧辉明.针对轨道车辆走行部關键部件故障的智能识别研究[J].软件,2021,42(03):086-089+102
Research on Intelligent Recognition of Failures of Key Components of Rail Vehicle Running Parts
ZHOU Hongxiang, YAO Huiming
(School of Urban Rail Transit, Shanghai University of Engineering Science, Shanghai 201620)
【Abstract】:Aiming at the problem of fault identification of the key components of the running part of rail vehicles, this paper proposes the use of ant colony algorithm to estimate the state parameters of the spring. By processing the multiple linear regression model established by the rail vehicle lateral dynamics equation, the constraint model is obtained. Using the optimization characteristics of the ant colony algorithm, the constraint model is optimized under the condition of normal, minor failure and breakage of the spring to verify the effectiveness of the algorithm. The results show that the method can effectively and accurately estimate the actual parameter values of the springs of the key components of the running gear of rail vehicles. By comparing the estimated value with the normal value, the state of the spring can be judged in time. This parameter estimation method can provide an important theoretical basis for the state monitoring of the key components of the rail vehicle suspension system.
【Key words】:rail wheel;dynamic model;ant colony algorithm;parameter estimation;optimization processing
0引言
目前,信号分析的方法是悬挂系统在线监测主要使用的方法,轨道车辆悬挂系统关键部件的幅值、频率特性以及对动力学参数的统计特征等关键部件的检测信号特性的突变是信号分析方法的主要研究对象,同时需要将较多的传感器安装在轨道车辆走行部的指定位置处。但是监测结果精度较低,有一定的局限性[1]。
相对于信号分析方法而言,参数估计以可操作性强等优点逐渐被广泛应用于故障状态监测领域中,为了达到估计轨道车辆关键部件的实际参数值的目的,仅需要通过安装在轨道车辆上的传感器获取车辆振动的信息,通过运算处理即可。……
