Machine learning-aided rheological prediction models of asphalt binders based on chemical properties

Zhang, F.; Wang, D.; Sun, Y.; Falchetto, A.C.

doi:10.34726/11001

Record link:

http://hdl.handle.net/20.500.12708/219654
https://doi.org/10.34726/11001

Title:

Machine learning-aided rheological prediction models of asphalt binders based on chemical properties

Citation:

Zhang, F., Wang, D., Sun, Y., & Falchetto, A. C. (2025). Machine learning-aided rheological prediction models of asphalt binders based on chemical properties. In L. Eberhardsteiner, B. Hofko, & R. Blab (Eds.), Advances in Materials and Pavement Performance Prediction IV : Contributions to the 4th International Conference on Advances in Materials and Pavement Performance Prediction (AM3P 2025), 7-9 May 2025, Vienna, Austria (pp. 583–586). TU Wien, E230-03 Road Engineering. https://doi.org/10.34726/11001

reposiTUm DOI:

10.34726/11001

Publication Type:

Inproceedings - Full-Paper Contribution

Language:

English

Authors:

Zhang, F.
Wang, D.
Sun, Y.
Falchetto, A.C.

Organisational Unit:

E000 - Technische Universität Wien

Published in:

Advances in Materials and Pavement Performance Prediction IV : Contributions to the 4th International Conference on Advances in Materials and Pavement Performance Prediction (AM3P 2025), 7-9 May 2025, Vienna, Austria

ISBN:

978-3-901912-99-3

Volume:

DOI of the book:

10.34726/9259

Date (published):

2025

Event name:

Advances in Materials and Pavement Performance Prediction 2025 (AM3P 2025)

Event date:

7-May-2025 - 9-May-2025

Event place:

Wien, Austria

Number of Pages:

Publisher:

TU Wien, E230-03 Road Engineering, Wien

Keywords:

asphalt binders; rheological properties; chemical composition; machine learning

Abstract:

This work aims to provide rapid rheological characterization of asphalt binders through their chemical properties based on advanced machine learning tools. With this objective, Fourier transform infrared spectroscopy (FTIR) and dynamic shear rheometer (DSR) are adopted to measure the chemical and rheological properties. Results indicate that the raw six FTIR features can be reduced to two principal components (PC 1 and PC 2), and the variance and role of PC 1 are more significant than PC 2. Multiple linear regression models can predict the phase angle accurately but not for modulus. Gaussian process regression model with higher R2 and lower RMSE values can accurately predict both modulus and phase angle.

Research Areas:

Modeling and Simulation: 35%
Structure-Property Relationsship: 30%
Computational System Design: 35%

Science Branch:

2011 - Bauingenieurwesen: 30%
2013 - Verkehrswesen: 70%

License:

CC BY 4.0