基于大样本的土基模量反算方法  

Back calculation method of subgrade rebound modulus based on large sample

作　　者：高燕 英红 Gao Yan;Ying Hong(Hengshui Municipal Engineering Management Center,Hengshui Hebei 053000,China;College of Architecture and Transportation Engineering,Guilin University of Electronic Science and Technology,Guilin Guangxi 541004,China)

机构地区：[1]衡水市市政工程管理中心,河北衡水053000 [2]桂林电子科技大学建筑与交通工程学院,广西桂林541004

出　　处：《山西建筑》2023年第21期130-131,共2页Shanxi Architecture

基　　金：国家自然科学基金(51668012,51968011)。

摘　　要：针对土基模量反算的技术难题,提出了一种基于神经网络的大样本反算方法,该方法在利用Bisar软件进行正算时,使用了6种面层厚度、8种基层厚度、10种土基模量、面层和基层模量各15种,合计108 000个正算样本,基本涵盖了三层常用结构的各种工况,实验结果表明,误差满足工程实际需求。Aiming at the technical problem of subgrade rebound modulus back calculation,a large sample method based on neural network is proposed.When using BISAR software for forward calculation,this method uses 6 kinds of surface layer thickness,8 kinds of base layer thickness,10 kinds of soil foundation modulus,15 kinds of surface layer and base layer modulus,with a total of 108000 forward calculation samples,which basically covers various working conditions of three-layer common structures.The experimental results show that the error meets the actual needs of the project.

关 键 词：道路工程 沥青路面 模量反算 弯沉盆 

分 类 号：TU997[建筑科学—市政工程]