• 首页
  • 期刊介绍
  • 编委会
  • 征稿启事
  • 期刊订阅
  • 相关下载
  • 联系我们
橡胶沥青混合料疲劳损伤及全周期寿命预估
Fatigue Damage and Full Cycle Life Estimation of Rubber Asphalt Mixture
投稿时间:2017-10-01  修订日期:2017-11-20
DOI:103969/j.issn.1007 9629201804015
中文关键词:  橡胶沥青混合料  全周期  疲劳损伤  评价指标  神经网络  寿命预估
英文关键词:rubber asphalt mixture  full cycle  fatigue damage  evaluation index  neural network  life estimation
基金项目:陕西省自然科学基础研究计划项目(2017JQ5085)
              
作者单位
申爱琴
SHEN Aiqin
长安大学公路学院,陕西西安710064
School of Highway, Changan University, Xian 710064, China
喻沐阳
YU Muyang
长安大学公路学院,陕西西安710064
School of Highway, Changan University, Xian 710064, China
周笑寒
ZHOU Xiaohan
长安大学公路学院,陕西西安710064
School of Highway, Changan University, Xian 710064, China
吕政桦
L Zhenghua
长安大学公路学院,陕西西安710064
School of Highway, Changan University, Xian 710064, China
宋攀
SONG Pan
长安大学公路学院,陕西西安710064
School of Highway, Changan University, Xian 710064, China
摘要点击次数: 205
全文下载次数: 
中文摘要:
      针对橡胶沥青混合料疲劳性能评价指标单一,疲劳失效判定标准难以确定的问题,在研究橡胶沥青混合料疲劳损伤演化过程的基础上,计算损伤曲线特征值并将其作为疲劳性能的评价指标,同时建立BP神经网络全周期疲劳寿命预测模型.研究表明:橡胶沥青混合料疲劳损伤过程中材料劣化速度能够保持在稳定发展状态,未发生明显疲劳失效现象;无损劲度模量S0,失稳率V,疲劳稳定度K和转化劲度模量St可作为疲劳性能的评价指标,并具有明确的物理含义;采用BP神经网络模型进行预估全周期疲劳寿命可获得较高准确度,LevenbergMarquardt训练算法收敛速度快,泛化能力好,最大相对误差为170%~823%.
英文摘要:
      Due to scarcity of the evaluation index of rubber asphalt mixture fatigue performance, and the difficulty of determination of fatigue failure criterion, on the basis of research of fatigue damage evolution process of rubber asphalt mixture, the characteristic value of damage curve was taken as the evaluation index of fatigue performance, and the prediction model of BP neural network full cycle fatigue life was established. The results show that the deterioration rate of the material during the fatigue damage of the rubber asphalt mixture can be maintained in a stable state without obvious fatigue failure. The lossless stiffness modulus S0, instability rate V, fatigue stability K and transformation stiffness modulus St can be used as the evaluation index of fatigue performance with clear physical meanings. To obtain high accuracy, the BP neural network model is used to predict the full cycle fatigue life. The Levenberg Marquardt training algorithm has high convergence speed and great generalization ability with the maximum relative error between 170% and 823%.
查看全文  查看/发表评论  下载PDF阅读器
关闭