基于神经网络有限元策略的弓网耦合振动研究  

Research on pantograph-catenary coupling vibration based on neural network finite element strategy

作　　者：欧志新[1] 邓春兰 OU Zhixin;DENG Chunlan(Department of Urban Rail Transit and Information Engineering,Anhui Communications Vocational&Technical College,Hefei 230051,China)

机构地区：[1]安徽交通职业技术学院城市轨道交通与信息工程系,安徽合肥230051

出　　处：《湖南文理学院学报(自然科学版)》2025年第2期27-33,39,共8页Journal of Hunan University of Arts and Science(Science and Technology)

基　　金：安徽省高校自然科学研究重大项目(2024AH040053);安徽省青年骨干教师境内访学项目(JNFX2024143)。

摘　　要：针对复杂的外部振动干扰对弓网系统的影响进行分析,围绕弓网机械振动造成接触力下降而发生脱弓,耦合模型参数失调带来电流传输不稳定等问题进行研究。考虑将基于神经网络有限元控制策略的方法应用在弓网系统整体耦合建模中,建立基于动态受电弓自调节的匹配模型,并利用神经网络的预测理论,对误差参数自修正与拟合。实验与仿真结果显示,弓网输出结果与振动量存在非线性关系,由机械振动造成的垂直接触力电弧和水平滑动摩擦均满足弓网参数自修正,误差调节后列车能保持良好的电流传输和稳定性。To analyze the impact of complex external vibration interference on the pantograph-catenary system,the research is conducted on the problems of pantograph detachment caused by contact force reduction due to mechanical vibration,as well as the instability of current transmission caused by parameter imbalance in the coupling model.A neural network-based finite element control strategy is applied to the overall coupling modeling of the pantograph-catenary system.A matching model based on dynamic pantograph adjustment is established,and a neural network prediction theory is used for autonomous error parameters correction and fitting.The experimental and simulation results show that there is a nonlinear relationship between the output of the pantograph and the vibration intensity,both the vertical contact force arc and horizontal sliding friction caused by mechanical vibration meet the requirements for autonomous correction of pantograph parameters,and after error adjustment,the train can maintain good current transmission and stability.

关 键 词：弓网耦合系统 振动模型 神经网络 有限元策略 数据拟合和整定 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]