当前位置: X-MOL 学术Int. J. Pavement Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Application of a hybrid neural network structure for FWD backcalculation based on LTPP database
International Journal of Pavement Engineering ( IF 3.8 ) Pub Date : 2021-03-09 , DOI: 10.1080/10298436.2021.1883016
Chengjia Han 1 , Tao Ma 1, 2 , Siyu Chen 1 , Jianwei Fan 1
Affiliation  

ABSTRACT

The road layer modulus backcalculation based on the road deflection basin obtained by the Falling Weight Deflectometer is a key issue in road engineering. Traditional Falling Weight Deflectometer backcalculation method based on Artificial Neural Network has the disadvantages of poor generalisation ability and low convergence accuracy in terms of the dynamic modulus. In this paper, a hybrid neural network structure, combined with Residual Neural Network, Recurrent Neural Network and Wide & Deep (Abbreviated as ResRNN–W&D) structure, was proposed for Falling Weight Deflectometer deflection basin backcalculation. A case study using the United States Long-Term Pavement Performance database verified that the ResRNN–W&D structure can train Falling Weight Deflectometer data on multiple roads together and achieve fast and high-precision convergence, thereby greatly improving the availability of the multi-source heterogeneous data. Moreover, two transfer learning methods for the ResRNN–W&D structure were proposed to improve the divergence issue. It was found that the ResRNN–W&D structure has stronger generalisation ability than traditional Artificial Neural Network.



中文翻译:

基于LTPP数据库的混合神经网络结构在FWD反算中的应用,基于LTPP数据库的混合神经网络结构在FWD反算中的应用

摘要

基于落锤式挠度计获得的道路挠度盆地反算道路层模量是道路工程中的一个关键问题。传统的基于人工神经网络的落重式挠度计反算方法在动态模量方面存在泛化能力差、收敛精度低等缺点。本文提出了一种混合神经网络结构,结合残差神经网络、循环神经网络和Wide & Deep(简称ResRNN-W&D)结构,用于落锤式挠度计挠度盆反算。使用美国长期路面性能数据库的案例研究验证了 ResRNN–W& D结构可以将多条道路上的Falling Weight Deflectometer数据一起训练,实现快速、高精度的收敛,从而大大提高了多源异构数据的可用性。此外,针对 ResRNN-W&D 结构提出了两种迁移学习方法来改善分歧问题。发现ResRNN-W&D结构比传统人工神经网络具有更强的泛化能力。

,

抽象的

基于落锤式挠度计获得的道路挠度盆地反算道路层模量是道路工程中的一个关键问题。传统的基于人工神经网络的落重式挠度计反算方法在动态模量方面存在泛化能力差、收敛精度低等缺点。本文提出了一种混合神经网络结构,结合残差神经网络、循环神经网络和Wide & Deep(简称ResRNN-W&D)结构,用于落锤式挠度计挠度盆反算。使用美国长期路面性能数据库的案例研究验证了 ResRNN–W& D结构可以将多条道路上的Falling Weight Deflectometer数据一起训练,实现快速、高精度的收敛,从而大大提高了多源异构数据的可用性。此外,针对 ResRNN-W&D 结构提出了两种迁移学习方法来改善分歧问题。发现ResRNN-W&D结构比传统人工神经网络具有更强的泛化能力。

更新日期:2021-03-09
down
wechat
bug