skip to main content
Show Results with: Show Results with:

Prediction of subgrade elastic moduli in different seasons based on BP neural network technology

Zhang, Haitao; Yu, Tengjiang

Road materials and pavement design: an international journal. Volume 19:Number 2 (2018, February 17th); pp 271-288 -- Taylor & Francis

Online access

  • Title:
    Prediction of subgrade elastic moduli in different seasons based on BP neural network technology
  • Author: Zhang, Haitao;
    Yu, Tengjiang
  • Found In: Road materials and pavement design: an international journal. Volume 19:Number 2 (2018, February 17th); pp 271-288
  • Journal Title: Road materials and pavement design: an international journal
  • Subjects: Highway engineering--Periodicals; Pavements--Design and construction--Periodicals; Road materials--Periodicals; asphalt pavement--subgrade elastic modulus--different seasons--influencing factors--BP neural network technology; Dewey: 625.805
  • Rights: Licensed
  • Publication Details: Taylor & Francis
  • Abstract:

    The asphalt pavement makes a higher demand on the subgrade load-carrying capacity. The subgrade elastic moduli in different seasons has not been predicted or evaluated at the specification in China or other countries, and there are no specific methods and standards for the accurate evaluations of the subgrade elastic moduli in different seasons. The project attempts to provide a fast and accurate method for predicting subgrade elastic moduli in different seasons of the year. The research contents include the data investigation on the subgrade elastic moduli at the different areas in China, the analysis of the annual influencing factors of the subgrade water content and temperature, and the prediction of the subgrade elastic moduli in different seasons at Harbin in China based on BP (back propagation) neural network technology. The research results can offer a viable method for the fast and accurate prediction of the subgrade elastic moduli in different seasons. The project has demonstrated that the BP neural network technology can more accurately predict the subgrade elastic moduli in different seasons, and the research results can lead to better economic benefit and social benefit.


  • Identifier: System Number: ETOCvdc_100063148177.0x000001; Journal ISSN: 1468-0629; doi/10.1080/14680629.2016.1259122
  • Publication Date: 2018
  • Physical Description: Electronic
  • Shelfmark(s): 7994.910000
  • UIN: ETOCvdc_100063148177.0x000001

Searching Remote Databases, Please Wait