A型地铁车体结构疲劳寿命分析  

Fatigue Life Analysis of Type A Metro Car Body Structure

作　　者：王亚平[1] 钱凯杰 邢宗义[2] 苏钊颐 WANG Ya-ping;QIAN Kai-jie;XING Zong-yi;SU Zhao-yi(School of Mechanical Engineering,Nanjing University of Science and Technology,Jiangsu Nanjing 210094,China;Guangzhou Metro Corporation,Guangdong Guangzhou 510335,China)

机构地区：[1]南京理工大学机械工程学院,江苏南京210094 [2]南京理工大学自动化学院,江苏南京210094 [3]广州地铁集团有限公司,广东广州510335

出　　处：《机械设计与制造》2023年第1期203-207,共5页Machinery Design & Manufacture

基　　金：国家重点研发计划—复杂环境下轨道车辆全生命周期能力保持与优化研究(2017YFB1201201)。

摘　　要：在轨道循环交变应力作用下地铁车体易产生疲劳损伤。获得车体的载荷-时间历程,进行了强度校核;利用雨流计数法获得了循环载荷谱,根据累积损伤理论对A型地铁车体疲劳寿命进行分析,研究了列车速度、二系弹簧垂向刚度与二系弹簧垂向阻尼系数等对车体关键部位疲劳寿命的影响,分别采用逐步回归法和BP神经网络模型对车体关键部位—枕梁疲劳寿命进行拟合与分析。结果表明,BP神经网络模型具有更高的拟合精度。为A型地铁车体结构疲劳寿命的预测提供理论依据。The subway car body is prone to fatigue damage under the cyclic alternating stress. The load in time domain of car body was obtained. The strength check was conducted. The influence of different factors on the fatigue life of the car body structure of the A-type subway car body was studied,which provided a theoretical basis for the prediction of the fatigue life of the A-type subway car body structure. The cyclic load spectrum was obtained by rain flow counting method. The fatigue life of the vehicle body was predicted according to Miner damage theory. The stepwise regression method and BP neural network model were used to fit and analyze the fatigue life of the key part of the car body. The results show that the BP neural network model is better than the stepwise regression method.

关 键 词：地铁车体 疲劳寿命 代理模型 BP神经网络模型 逐步回归法 

分 类 号：TH16[机械工程—机械制造及自动化]