Prediction of Air Voids in Asphalt Mixtures on In-Service Roads Using Artificial Neural Networks

Document Type : Scientific - Research

Author
Ali Heidaripanah
Assistant Professor, Materials Research Institute, Advanced Science and Technology and Environmental Sciences Research Center, Graduate University of Advanced Technology, Kerman, Iran
10.22119/jte.2025.506203.2732
Abstract
The void of the asphalt mixtures is a crucial parameter in design and performance of asphalt mixes. Changes in this parameter after road construction under traffic and over time, cause changes in the performance of asphalt mixtures. Therefore, predicting the void of asphalt mixes in the roads under service is an essential requirement for assessing asphalt performance. In this research, an AAN-based model with the high accuracy of R2 =0.97 has been developed to predict the void of asphalt mixes using feed-forward Artificial Neural Networks (ANNs) with the Levernberg-Marquardt Back Propagation (LMBP) training algorithm. The LMBP algorithm is a dynamic technique that combines the speed of the Gauss-Newton method with the convergence guarantee of the Steepest Decent method. Furthermore, the method of adjusting the training parameters of the ANN models is presented to increase the possibility of achieving higher accuracies in the process of reinitializing the weights and retraining the ANN models.
Keywords
Artificial Neural Network
Asphalt
Asphalt Air Voids
Subjects
- فخری م. و محمودی نیا ن. (1390) ، "ارزیابی مقاومت شیارافتادگی مخلوط های آسفالتی گرم با مصالح سنگی درشت دانه"، نشریه مهندسی عمران، دانشگاه فردوسی مشهد، دوره 23، شماره 1، صفحه 123-135.
 
- AASHTO    M 323-22 (2022) “Standard Specification for Superpave Volumetric Mix Design”.
 
- MS-2 (2014) “Mix Design Methods for Asphalt Concrete and Other Hot-Mix Types”. 7th Edition, 2014.
 
- AASHTO (2025), “Mechanistic-Empirical Pavement Design Guide”. (MEPDG). 
 
- Harvey J. T. and Tsai TB. W. (2025) “Effect of Asphalt content and Air Void Content on Mix fatigue and Stiffness”. Transportation Research Record, Journal of Transportation Research Board, 1996, Vo. 1543, No. 1, pp. 38-45. https://doi.org/10.3141/1543-05
- Zeiada W., Dabous S. A., Ruzouq R. A., Hamed Kh, Souliman M. I., Mirou  Sh. (2022) “Effect of air voids and asphalt content changes on laboratory and simulated long-term fatigue performance of asphalt concrete pavements”. Springer, Journal of Innovative Infrastructure Solutions, Vol. 8, No. 1. DOI:  10.1007/s41062-022-01023-3
 
- FHWA-HRT-21-044 (2021), Corrigan M. and Underwood Sh. “Rutting Strain Index (RSI) Parameter for Asphalt Performance Engineered Mixture Design”. DOI:  https://highways.dot.gov/research/publications/infrastructure/FHWA-HRT-21-044
- Hagan M. T. , Demuth H. B.,  Beale M. H., De Jesús O. (2014) “Neural Network Design” . 2nd Edition, eBook. 
 
- Heidaripanah A. and Hassani A. (2021), “Adaptive Neuro Fuzzy Inference System (ANFIS) approach to predict the dynamic modulus of Hot Mix Asphalt” ASCE, Journal of Transportation Engineering, Part B: Pavements, Vol 147, No. 3.  DOI: https://doi.org/10.1061/JPEODX.0000269
- Izadi  A., Jamshidpour F., Bargegol I. (2023) “Study of Urban Taxi-related Accident Analysis Using the Multiple Logistic Regression and Artificial Neural Network Models”. Vol. 10, No. 4, pp.  1163-1173. DOI: 10.22119/ijte.2022.292868.1578
 
- Mirbaha B., Kordani A.A., Salehikalam A., Zareyi M.  (2018). “Analyzing Stop Time Phase Leading to Congestion Based on Drivers’ Behavior Patterns”. Vol. 5, No. 20, pp. 383-400, DOI: 10.22119/ijte.2018.49734
 
- Heidaripanah A. and Hassani A. (2021) “A fundamental multiple-stage ANN-based sensitivity analysis to predict the dynamic modulus of Hot Mix Asphalt considering the effect of confining stress”. Springer, Martials and Structures, Vol. 54, No. 15. DOI: 10.1617/s11527-020-01581-x
 
- LTPP Info pave (2025) “Long Term Pavement Performance Project”. FHWA, https://infopave.fhwa.dot.gov/
Quarterly Journal of Transportation Engineering
Volume 17, Issue 2 - Serial Number 67
Winter 2026
Pages 5359-5371

  • Receive Date 14 February 2025
  • Revise Date 13 April 2025
  • Accept Date 13 April 2025