A Predictive Effect of Additives on Asphalt Mixture Performance by Using Artificial Neural Network

Authors

1 Associate Professor, Department of Transportation Engineering and Planning, Technical and Engineering Faculty, Imam Khomeini International University, Qazvin, Iran.

2 M.Sc., Grad., Engineering Faculty, Kermanshah Razi University, Kermanshah, Iran.

10.22034/road.2020.114378

Abstract

The low resistance of asphalt mixtures to dynamic loads results in fatigue cracks, rutting, and ultimately reduced service life of the pavement. Hence, advanced countries are looking for new ways to build and maintain roads, as well as efforts to use new technologies to upgrade old pavements, indicating the attention of these countries to maintaining the status of roads at the optimum level. One of the methods for modifying bituminous and asphalt mixtures is the use of a variety of additives. The additives are used because bitumen cannot be used in all Weather and loading conditions. Iran, with its four season climate, experiences special weather effects on most of the development projects. Road pavement is one of the most influential projects in this regard. In addition to testing, using an artificial neural network can be a good solution to reduce costs and time to results evaluation. In this paper, along with the study of the effects of various additives on the functional properties of asphalt mixtures, the use of artificial neural network to predict the different properties of asphalt mix is also discussed.

Keywords

References

-بهبهانی، ح.، ایازی، م. ج.، و شجاعی، م. ح.، (1395)، "ارزیابی آزمایشگاهی حساسیت رطوبتی و پتانسیل شیار شدگی مخلوطهای آسفالتی نیمه گرم"، مهندسی حمل و نقل­، سال هفتم­، بهار، ص.418-405.
 
- McCulloch, D. and K, Vukadinovic, (2012), "Trafiic Control and Transport Planning: A Fuzzy Sets and Neural Networks Approach",
­Vol. 13, Springer Science & Business Media.
 
-­M. Lazarevska, M. Knezevic, M. Cvetkovska, A.G. Trombeva, (2014), “Application of artificial neural networks in civil engineering”, Tech. Gazette 21 (6),
 pp. 1353-1359.
 
-­I. Flood, (1990), “Simulating the construction process using neural networks, in: Proceedings of the 7th ISARC – International Association for Automation and Rrobotics in Construction/Bristol”,
pp. 374-382.
 
-­D.S. Jeng, D.H. Cha, m. Blumenstein, (2003), “Application of neural networks in civil engineering problems, in: Proceeding of the International Conference on Advance in the Internet, Processing, Systems and Interdisciplinary Research”.
 
-­S.M. Mirabdolazimi, Gh.Shafabakhsh, (2017), “Rutting depth prediction of hot mix asphalts modified with forta fiber using artificial neural networks and genetic programming technique, Construction and Building Materials, Vol. 148, 1 September, pp. 666-674.
-­E. Ozgan, (2011), “Artificial neural network based modelling of the Marshall Stability of asphalt concrete, Expert Systems with Applications”, 38(2011), pp.6025-6030.
-­Gh.Shafabakhsh, O. Jafari Ani, M. Talebsafa,  (2015), “artificial neural network modeling (ANN) for predicring rutting performance of nano-modified hot-mix asphalt mixtures containing Steel slag aggregates, Construction and Building Materials”, pp.­136-143.
-­F. Xiao, S. Amirkhanian, C. Hsein, (2009), “prediction of fatigue life of rubberized asphalt concrete mixtures containing reclaimed asphalt pavement using artificial neural network, J. Master. Civ. Eng. 21 (6),  pp.253-261.
- F. Xiao, S., (2015), “Amirkhanian, artificial neural network approach to estimating stiffness behaviour of rubberized asphalt concrete mixtures containing reclaimed asphalt pavement,, J. Transp. Eng. 59 (3),
pp. 249-264.
-­M. Firouzinia, Gh. Shafabakhsh, (2018), “Investigation of the effect of nano-silica on thermal sensitivity of HMA using artificial neural network, Construction and Building Materials 170, pp.527–53.
- Serkan Tapkın, Abdulkadir Çevik, Ün Usar, (2010), “Prediction of Marshall test results for polypropylene modified dense bituminous mixtures using neural networks, Expert Systems with Applications 37,
pp. 4660–4670
- Halil Ceylan , Alper Guclu , Erol Tutumluer & Marshall R. Thompson, (2005), “Back calculation of full-depth asphalt pavement layer moduli considering nonlinear
stress-dependent subgrade behaviour”, International Journal of Pavement Engineering, 6:3, pp.171-182.
-­Eldin, N. N., & Senouci, A. B., (1995), “A pavement condition rating model using back propagation neural network. Microcomputers in Civil Engineering, 10(6), pp.433-441.
-­Ivica Androjic, Zlata Dolacˇek-Alduk, (2018), “Artificial neural network model for forecasting energy consumption in hot mix asphalt (HMA) production”, Construction and Building Materials 170, pp.424–43.
-­Golzar, K., A. Jalali.arami, and M., (2012), “Nematollahi, Statistical investigation on physical-mechanical properties of base and polymer modified bitumen using Artificial Neural Network’, Construction and Building Materials, 37, pp. 822-831.
- Shi, X., et al., (2011), “Exploring the interactions of chloride deicer solutions with nanomodified and micromodified asphalt mixtures using artificial neural networks”, Journal of Materials in Civil Engineering, 24(7): pp. 805-815.

Files

Share

How to cite

Statistics