Sharif Journal of Civil Engineering

Sharif Journal of Civil Engineering

Neural Network Models for Predicting Fracture Energy and Toughness of Asphalt Mixtures Based on Semi-Circular Bending (SCB) Test Results

Document Type : Research Note

Authors
Mohammad Samanipour
Mohammad Zia Alavi
Abbas Babazadeh
School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran.
10.24200/j30.2025.64904.3353
Abstract
The measurement of failure characteristics in the semi-circular bending (SCB) test of asphalt mixtures has significantly expanded over the last decade, with laboratory study results being published in numerous studies. The purpose of this article is to develop neural network models to predict the fracture energy and fracture toughness of asphalt mixtures based on data mining principles. For this purpose, 3290 data points from SCB fracture test results of asphalt samples were collected from 102 credible articles. Out of these, 1627 data points are used to predict fracture energy and 1663 data points are used to predict fracture toughness.
The input layer of the neural networks includes data collected on fracture mode, loading rate, test temperature, sample thickness, notch dimension, presence of modifier, maximum nominal aggregate size, air void percentage, binder percentage, aging, and binder type of asphalt mixtures. The output layer generates fracture energy and fracture toughness for each assumed input. The results show that the constructed neural network models can predict fracture energy with 75% accuracy and fracture toughness with 70% accuracy.
The sensitivity analysis reveals that the loading rate, test temperature, air void percentage, and binder percentage are the most influential characteristics on the prediction models' results. The integration of data mining principles and neural network algorithms enhances the prediction accuracy of asphalt mixture properties, which can aid in designing more durable pavement materials.
The accuracy of the models was validated using metrics such as Root Mean Squared Error (RMSE) and Mean Squared Error (MSE), with RMSE values of 0.727 for fracture energy and 0.170 for fracture toughness. The regression analysis between actual and predicted values showed R² values of 0.75 for fracture energy and 0.70 for fracture toughness, indicating robust model performance.
In conclusion, the neural network models based on collected SCB test data exhibit acceptable performance in predicting the fracture energy and toughness of asphalt mixtures. The study's findings highlight the importance of considering key input variables such as air void percentage, binder percentage, test temperature, and loading rate in developing reliable predictive models for asphalt mixture behavior.
Keywords
Asphalt mixtures
semi-circular bending test
fracture energy
fracture toughness
neural network
Subjects
1.       Pirmohammad, S. and Ayatollahi, M., 2020. Fracture behavior of asphalt materials. http://dx.doi.org/10.1007/978-3-030-39974-0
 
2.       Huang, B., Shu, X. and Tang, Y., 2005. Comparison of semi-circular bending and indirect tensile strength tests for HMA mixtures. Advances in Pavement Engineering,pp.1–12. https://doi.org/10.1061/40776(155)14
 
3.       AASHTO, 2010. Determining the fracture energy of asphalt mixtures using the semi circular bend geometry (SCB). In Designation: TP 105-20, Washington, DC 20004.
 
4.       Lancaster, I. and Khalid, H., 2011. Crack growth analysis of polymer modified asphalt using linear and non linear fracture mechanics. Fifth International Conference on Bituminous Mixtures and Pavements, pp.612–623.
 
5.       Biligiri, K., Said, S. and Hakim, H., 2012. Asphalt mixtures crack propagation assessment using semi-circular bending tests. International Journal of Pavement Research and Technology, 5(4), pp.209–217.
 
6.       Im, S., Ban, H. and Kim, Y. R., 2014. Mode-dependent fracture behavior of asphalt mixtures with semicircular bend test. Transportation Research Record, Journal of the Transportation Research Board, 2447, pp.23–31.
 https://doi.org/10.3141/2447-03
 
7.       Mahmoud, E., Saadeh, S., Hakimelahi, H. and Harvey, J., 2014. Extended finite-element modelling of asphalt mixtures fracture properties using the semi-circular bending test. Road Materials and Pavement Design, 15, pp.153–166. https://doi.org/10.1080/14680629.2013.863737
 
8.       Pirmohammad, S. and Ayatollahi, M., 2015. Asphalt concrete resistance against fracture at low temperatures under different modes of loading. Cold Regions Science and Technology, 110, pp.149–159. https://doi.org/10.1016/j.coldregions.2015.03.001
 
9.       Xiao, F. and Serji, N., 2009. Artificial neural network approach to estimating stiffness behavior of rubberized asphalt concrete containing reclaimed asphalt pavement. Journal of Transportation Engineering, 135, (8), pp.580–589. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000014
 
10.    Shafabakhsh, G. H., Jafrai Ani, O. and Talebsafa, M., 2015. Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates. Construction and Building Materials, 85, pp.136–143. https://doi.org/10.1016/j.conbuildmat.2015.03.060
 
11.    Mirabdolazimi, S. and Shafabakhsh, G., 2017. Rutting depth prediction of hot mix asphalts modified with forta fiber using artificial neural networks and genetic programming technique. Construction and Building Materials, 148, pp.666–674. https://doi.org/10.1016/j.conbuildmat.2017.05.088
 
12.    Leon, P. L. and Gay, D., 2019. Gene expression programming for evaluation of aggregate angularity effects on permanent deformation of asphalt mixtures. Construction and Building Materials, 211, pp.470–478. https://doi.org/10.1016/j.conbuildmat.2019.03.225
 
13.    Majdifard, H., Jahangiri, B., Buttlar, W. G. and Alavi, A. H., 2019. New machine learning-based prediction models for fracture energy of asphalt mixtures. Measurement, 135, pp.438–451. https://doi.org/10.1016/j.measurement.2018.11.081
 
14.    Yaro, N., Sutanto, M. H., Habib, N. Z., Napiah, M., Usman, A. and Muhammad, 2022. Comparison of response surface methodology and artificial neural network approach in predicting the performance and properties of palm oil clinker fine modified asphalt mixtures. Construction and Building Materials, 324,126618. https://doi.org/10.1016/j.conbuildmat.2022.126618
 
15.    Barghabany, P., Zhang, J., Mohammad, L. N. and Cooper, S. B., 2022. Novel model to predict critical strain energy release rate in semi-circular bend test as fracture parameter for asphalt mixtures using an artificial neural network approach. Journal of the Transportation Research Board. https://doi.org/10.1177/03611981211036357
 
16.    Abuawad, I., Al-Qadi, I. and Trepanier, J., 2015. Mitigation of moisture damage in asphalt concrete: testing techniques and additives/modifiers effectiveness. Construction and Building Materials, 84, pp.437–443. https://doi.org/10.1016/j.conbuildmat.2015.03.001
 
17.    Hamedi, G. H., Saedi, D. and Ghahremani, H., 2020. Effect of short-term aging on low-temperature cracking in asphalt mixtures using mechanical and thermodynamic methods. ASCE,­ 32. https://doi.org/10.1061/(ASCE)MT.1943-5533.0003388
 
18.    Malek, M. and Keymanesh, M., 2023. Impact of thickness, void content, temperature and loading rate on tensile fracture toughness and work of fracture of asphalt mixtures-an experimental study using the SCB test. Engineering Solid Mechanics, 11, pp.163–174. https://doi.org/10.5267/j.esm.2023.000015
 
19.    Nsengiyumva, G., You, T. and Kim, Y., 2017. Experimental-statistical investigation of testing variables of a semicircular bending (SCB) fracture test repeatability for bituminous mixtures. Journal of Testing and Evaluation, 45, pp.1691–1701. https://doi.org/10.1520/JTE20160103
 
20.    X., J. and Li, M., 2010. Using semi circular bending test to evaluate low temperature fracture resistance for asphalt concrete. Experimental Mechanics, 50, pp.867–876. https://doi.org/10.1007/s11340-009-9303-0
 
21.    Bui, H. and Mofreh, S., 2021. Effects of specimen size and loading conditions on the fracture behaviour of asphalt concretes in the SCB test. Engineering Fracture Mechanics, 242, 107452. https://doi.org/10.1016/j.engfracmech.2020.107452
 
22.    Arabani, M. and Ferdowsi, B., 2007. Evaluating the semi-circular bending test for HMA mixtures. International Journal of Engineering, 22, pp.47–58. https://doi.org/10.22068/ije.22.1.47