Life-cycle reliability estimation of asphalt pavement based on machine learning approach

J. Xin, M. Zhang, M. Akiyama, D. M. Frangopol, J. Pei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Asphalt pavement is a complex engineering system which deteriorates due to several mechanical and environmental stressors (e.g. moisture damage, freeze-thaw cycles and traffic load). To predict the time-dependent performance of asphalt pavement, it is necessary to develop a deterioration model incorporating the associated variables under uncertainty. Artificial Neural Networks (ANNs) are effective intelligence technologies to develop an accurate prediction model with a large amount of data. In this paper, a time-dependent reliability assessment method based on the ANNs model is presented. ANNs are used to develop the performance prediction model of asphalt pavement according to the training data selected from the Long-term Pavement Performance database. The life-cycle reliability of asphalt pavement is calculated using the ANNs model based on Monte Carlo simulation with Importance Sampling. Two case studies are presented to investigate the effects of sublayers thickness and traffic levels on the life-cycle reliability.

Original languageEnglish
Title of host publicationLife-Cycle Civil Engineering
Subtitle of host publicationInnovation, Theory and Practice - Proceedings of the 7th International Symposium on Life-Cycle Civil Engineering, IALCCE 2020
EditorsAirong Chen, Xin Ruan, Dan M. Frangopol
PublisherCRC Press/Balkema
Pages246-251
Number of pages6
ISBN (Electronic)9780367360191
DOIs
Publication statusPublished - 2020
Event7th International Symposium on Life-Cycle Civil Engineering, IALCCE 2020 - Shanghai, China
Duration: 2020 Oct 272020 Oct 30

Publication series

NameLife-Cycle Civil Engineering: Innovation, Theory and Practice - Proceedings of the 7th International Symposium on Life-Cycle Civil Engineering, IALCCE 2020

Conference

Conference7th International Symposium on Life-Cycle Civil Engineering, IALCCE 2020
Country/TerritoryChina
CityShanghai
Period20/10/2720/10/30

ASJC Scopus subject areas

  • Computational Mechanics
  • Civil and Structural Engineering

Fingerprint

Dive into the research topics of 'Life-cycle reliability estimation of asphalt pavement based on machine learning approach'. Together they form a unique fingerprint.

Cite this