Developing a prediction model for rutting depth of warm mix asphalt mixture using neural network

Document Type : Original Article


1 Faculty of Civil Engineering -Shahrood university of technology

2 Faculty of Civil Engineering , Shahrood university of technology

3 Civil Engineering Faculty of K.N. Toosi University of Technology.


Researchers and engineers are constantly working to improve the performance of asphalt pavements. Pavements, as surfaces that are often loaded by heavy axles, must have sufficient resistance to fatigue, cracking and rutting. In this paper, using the data obtained from the laboratory results of the previous study that warm mix asphalt modified with glass fibers and 0, 20, 40 and 50% recycled asphalt pavement (RAP) were made to evaluate the resistance of the mixture against rutting, rutting depth of the mixtures was determined by multilayer perceptron neural network (MLP) and radial basis function neural network (RBF) and the results were compared with each other. The prediction model of post compaction and rutting depth showed good agreement with the experimental results. To evaluate the generalizability of the neural network using data that were not used during modeling, the multilayer perceptron neural network (MLP) performed better than the radial basis function neural network (RBF).


[1] M.Fakhri, S.M.Karimi, M. Qorbani Nik,” Estimation of Pavement Roughness Based on Surface Distresses Using Artificial Neural Network (case study: Iran’s arterial roads),” Journal of Transportation Engineering, vol.  12, no. 48, pp. 697-713(2021) (In Persian)
[2] M.Fakhri, E. Shahebrahimi, F. Chavoshian nain,” Study Rutting and Effect of Self-healing on Fatigue Behavior of Modified Asphalt Mixtures,” Journal of Transportation Research, vol.  1, no. 67, pp. 143-156(2019) (In Persian)
[3] A.Tarek,  A. Amr, H. Mahgoub, Asphalt crack detection using thermography,: university of central florida, center for advanced transportation systems simulation (CATSS) infra mation, 2005.
[4] S.M.Mirabdolazimi, Gh. Shafabakhsh, "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, 2017.
[5] M.Fakhri, S.A. Hosseini, "Laboratory evaluation of rutting and moisture damage resistance of glass fiber modified warm mix asphalt incorporating high RAP proportion," Construction and Building Materials, 134, pp. 626-640, 2017.
[6] A. Choubdar, A. Farajollahi, A. Ameli,” Experimental Evaluation of Rutting Performance of Polymer Modified Binders and Its Relation to Rutting Resistance of Mixture,” Journal of Transportation Research, vol.  17, no. 64, pp. 91-102(2020) (In Persian)
[7] N. Kamboozia, H. Ziari, H. Behbahani, "Artificial neural networks approach to predicting rut depth of asphalt concrete by using of visco-elastic parameters," Construction and Building Materials, 158, pp. 873-882, 2018.
[8] G.H. Shafabakhsh, O. Jafari Ani, M. Talebsafa, "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, 2015.
[9] M. Fakhri, R. Shahni Dezfoulian,” Determination of Effective Structural Number based on IRI and Surface Distress Using Regression and Neural Network Model,” Journal of Transportation Research, vol.  15, no. 57, pp. 207-221(2019) (In Persian)
[10] H. Ziari, A. Amini, A. Goli, & D. Mirzaiyan, "Predicting rutting performance of carbon nano tube (CNT) asphalt binders using regression models and neural networks," Construction and Building Materials, 160, pp.415-426, 2018.
[11] G. Sollazzo, T.F. Fwa, G. Bosurgi, "An ANN model to correlate roughness and structural performance in asphalt pavements," Construction and Building Materials, 134, pp. 684-693, 2017.
[12] H. Fizza, A. Yasir, I. Muhammad, A. Murtaza, A. Shafeeq, "A data-driven model for phase angle behaviour of asphalt concrete mixtures based on convolutional neural network," Construction and Building Materials, 269, p.121235, 2020.
[13] E. Ozgan, "Artificial neural network based modelling of the Marshall Stability of asphalt concrete," Expert Systems with Applications, 38, pp. 6025-6030, 2011.
[14] R.Hecht-Neilsen, Neurocomputing,: Addison-Wesley, Boston, 1989.
[15] Gupta, M,. Jin, L,. & Homma, N., Static and Dynamic Neural Network,: Hobokon, New Jersey, 2004.
[16] H. Taherkhani, A. Ebrahimimoghadam,” Prediction of the Fatigue Life of Asphalt Mixtures using Artificial Neural Networks  ,” Journal of Transportation Research, vol.  4, no. 1, pp. 45-58(2013) (In Persian)
[17] M. Saltan, T. Mesut, K. Mustafa, "Artificial neural networks application for flexible pavements thickness modeling," Turkish Journal of Engineering & Environmental Sciences, vol. 26, pp. 243-248. 2002.
[18] K. Suzuki, Artificial Neural Networks - Methodological Advances and Biomedical Applications,: Apr. 2011,
doi: 10.5772/644.