Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

Use of an artificial neural network to estimate the stiffness of asphalt pavement subgrade

Authors

[ 1 ] Instytut Inżynierii Lądowej, Wydział Inżynierii Lądowej i Transportu, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.7] Civil engineering, geodesy and transport

Year of publication

2024

Chapter type

chapter in monograph / paper

Publication language

english

Abstract

EN The paper presents the application of artificial neural networks (ANN) to estimate the stiffness of the pavement subgrade, expressed by the value of the modulus of elasticity. The basis for training the artificial neural network was a database of deflection values derived from calculations carried out using a static pavement model. The boundary conditions defined in the pavement model correspond to those occurring during measurements conducted with a dynamic deflectometer device of the FWD type. The artificial neural network trained in this way was used to estimate the value of the modulus of elasticity expressing the stiffness of the pavement subgrade of the test sections based on the results of pavement deflection measurements made with a FWD device under the dynamic load. Values obtained in this manner were subjected to frequency normalisation for better compliance with the assumptions of the static pavement model used at the stage of learning. The comparison of the results of ANN calculations with the results of backcalculations shows that the values of the modulus of elasticity obtained by both methods are consistent with each other at a satisfactory level of significance. An important applicable effect of the performed research and analysis is the fact that the stiffness estimated with the use of ANN can be an attractive addition to the backcalculation procedure at the stage of assuming the initial values in optimization algorithms.

Pages (from - to)

870 - 878

URL

https://www.taylorfrancis.com/chapters/edit/10.1201/9781003402541-102/use-artificial-neural-network-estimate-stiffness-asphalt-pavement-subgrade-po%C5%BCarycki-g%C3%B3rna%C5%9B-s%C5%82owik-bilski

Book

Bituminous Mixtures and Pavements VIII : Proceedings of 8th International Conference on Bituminous Mixtures and Pavements, ICONFBMP 8, 12–14 June 2024, Thessaloniki, Greece

Presented on

8th International Conference on Bituminous Mixtures and Pavements ICONFBMP 8, 12-14.06.2024, Thessaloniki, Greece

Ministry points / chapter

20

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.