Abstract

The study aimed to investigate the rutting behaviour of the flexible pavement layers. Rutting is a significant distress mode in asphalt pavements, leading to severe serviceability issues. Understanding the rutting mechanisms in various pavement layers is crucial for improving pavement design and maintenance strategies. A three-dimensional finite element model (FEM) was constructed using the software ABAQUS to simulate the behaviour of flexible pavement layers under wheel loads. The study employed finite element analysis (FEA) to assess the rutting in different layers of the pavement structure. Additionally, support vector machine (SVM) models were constructed using the radial basis function (RBF) kernel to predict rutting behavior based on displacement data. The analysis revealed that the top layer of the pavement experienced a 3.8% reduction in rutting loss, while the subgrade layer showed only a 0.31% reduction. The top surface of the flexible (asphalt) pavement under the wheel load path experienced higher rutting than compressive stresses, which decreased laterally with horizontal distance. The critical rut depth was measured as 5.73 mm for the top layer and 3.8 mm for the base layer. The SVM models constructed with the RBF kernel function demonstrated superior performance, achieving R² values of 0.999 and 0.997 for displacement prediction at the center and edge of the pavement, respectively, under training conditions. The study demonstrated the effectiveness of FEA in evaluating the rutting behaviour of flexible pavement layers. The results highlighted the greater rutting in the top layer compared to the subgrade, emphasizing the need for focused attention on the top layers during pavement design and maintenance. Additionally, the SVM models with the RBF kernel accurately predicted pavement displacement, providing a valuable tool for future pavement analysis and optimization.

Keywords

Flexible pavement, Rutting behavior, ABAQUS, Finite element analysis (FEA), Support vector machine (SVM), Radial basis function (RBF) kernel.

References

[1] Mensahn ES, Wada SA, Lugeiyamu L. Structural evaluation of conventional and modified flexible pavement performance. Arid Zone Journal of Engineering, Technology and Environment. 2021; 17(4):535-46.

[2] Al-taher MG, Sawan AM, Solyman ME, El-sharkawi Attia MI, Ibrahim MF. Evaluating the durability of asphalt mixtures for flexible pavement using different techniques: a review. International Journal of Pavement Research and Technology. 2024:1-27.

[3] Kou B, Cao J, Huang W, Ma T, Shi Z. Rutting prediction model of asphalt pavement based on RIOHTrack full-scale ring road. Measurement. 2025; 242:115915.

[4] Alamnie MM. Laboratory-based study of viscoelastic, viscoplastic and fatigue damage of asphalt concrete. Doctoral Thesis, University of Agder. 2024.

[5] Patel VJ, Juremalani J, Kumavat HR. Incorporation of high volume ground granulated slag from blast furnaces in pavement quality concrete. Engineering, Technology & Applied Science Research. 2024; 14(4):14888-93.

[6] Zhang AA, Shang J, Li B, Hui B, Gong H, Li L, et al. Intelligent pavement condition survey: overview of current researches and practices. Journal of Road Engineering. 2024; 4(3): 257-81.

[7] Li Q, Xiao DX, Wang KC, Hall KD, Qiu Y. Mechanistic-empirical pavement design guide (MEPDG): a bird’s-eye view. Journal of Modern Transportation. 2011: 114-33.

[8] Gong H, Sun Y, Hu W, Huang B. Neural networks for fatigue cracking prediction using outputs from pavement mechanistic-empirical design. International Journal of Pavement Engineering. 2021; 22(2):162-72.

[9] Kang J. Pavement performance prediction using machine learning and instrumentation in smart pavement. Master's Thesis, University of Waterloo. 2022.

[10] Liu Y, You Z, Li L, Wang W. Review on advances in modeling and simulation of stone-based paving materials. Construction and Building Materials. 2013; 43:408-17.

[11] Deng Y, Shi X. Short-term predictions of asphalt pavement rutting using deep-learning models. Journal of Transportation Engineering, Part B: Pavements. 2024; 150(2):04024004.

[12] Bayat R, Talatahari S, Gandomi AH, Habibi M, Aminnejad B. Artificial neural networks for flexible pavement. Information. 2023; 14(2):1-23.

[13] Yang X, Guan J, Ding L, You Z, Lee VC, Hasan MR, et al. Research and applications of artificial neural network in pavement engineering: a state-of-the-art review. Journal of Traffic and Transportation Engineering (English Edition). 2021; 8(6):1000-21.

[14] Mikels N, Kassem E, Muftah A, Sufian AA. The Use of Artificial Intelligence in Pavement Engineering. Pacific Northwest Transportation Consortium (PacTrans) (UTC); 2023.

[15] Kotb MM. Prediction of distresses in pavement networks: a machine learning approach. Master's Thesis, The American University in Cairo (Egypt). 2024.

[16] Karadag H, Firat S, Isik NS, Yilmaz G. Determination of permanent deformation of flexible pavements using finite element model. Građevinar. 2022; 74(6):471-80.

[17] Pandey AK, Mathur D. Finite element analysis and optimization of flexible pavement. International Journal of Civil Engineering Applications Research. 2023; 4(1):6-25.

[18] Deng Y, Zhang Y, Shi X, Hou S, Lytton RL. Stress–strain dependent rutting prediction models for multi-layer structures of asphalt mixtures. International Journal of Pavement Engineering. 2022; 23(8):2728-45.

[19] Liu L, Hao P. ABAQUS program-based numerical analysis on U-shaped cracking of asphalt pavement. In international conference on remote sensing, environment and transportation engineering 2011 (pp. 2861-4). IEEE.

[20] Arabani M, Jamshidi R, Sadeghnejad M. Using of 2D finite element modeling to predict the glasphalt mixture rutting behavior. Construction and Building Materials. 2014; 68:183-91.

[21] Al-khateeb LA, Saoud A, Al-msouti MF. Rutting prediction of flexible pavements using finite element modeling. Jordan Journal of Civil Engineering. 2011; 5(2):173-90.

[22] Imaninasab R, Bakhshi B, Shirini B. Rutting performance of rubberized porous asphalt using finite element method (FEM). Construction and Building Materials. 2016; 106:382-91.

[23] Alnaqbi AJ, Zeiada W, Al-khateeb G, Abttan A, Abuzwidah M. Predictive models for flexible pavement fatigue cracking based on machine learning. Transportation Engineering. 2024; 16:1-24.

[24] Cano-ortiz S, Pascual-muñoz P, Castro-fresno D. Machine learning algorithms for monitoring pavement performance. Automation in Construction. 2022; 139:1-16.

[25] Cheng C, Wang L, Zhou X, Wang X. Predicting rutting development using machine learning methods based on RIOCHTrack data. Applied Sciences. 2024; 14(8):1-21.

[26] Alwan DS, Joni HH, Hilal MM. Deformation behavior of flexible pavements by finite element simulation. Periodicals of Engineering and Natural Sciences (PEN). 2022; 10(6):142-50.

[27] Kumar P, Kiran KBV, Manjunatha S, Subramanya KG. Finite element modeling by ABAQUS for rutting in flexible pavement. Civil Engineering and Architecture. 2024; 12(3):1576-84.

[28] Kothai R, Prabakaran N, Murthy YS, Cenkeramaddi LR, Kakani V. Pavement distress detection, classification and analysis using machine learning algorithms: a survey. IEEE Access. 2024; 12:126943-60.

[29] Deng Y, Shi X. Modeling the rutting performance of asphalt pavements: a review. Journal of Infrastructure Preservation and Resilience. 2023; 4(1):1-21.

[30] Alnaqbi AJ, Zeiada W, Al-khateeb GG, Hamad K, Barakat S. Creating rutting prediction models through machine learning techniques utilizing the long-term pavement performance database. Sustainability. 2023; 15(18):1-31.

[31] Hu X, Ishaq A, Khattak A, Chen F. Assessment of factors affecting pavement rutting in Pakistan using finite element method and machine learning models. Sustainability. 2024; 16(6):1-24.

[32] Li L, Huang X, Han D, Dong M, Zhu D. Investigation of rutting behavior of asphalt pavement in long and steep section of mountainous highway with overloading. Construction and Building Materials. 2015; 93:635-43.

[33] Patel A, Singh V, Shanker R. FEM based parametric analysis for investigating effect of wheel base characteristics and axle configurations on flexural stresses in rigid pavements. Materials Today: Proceedings. 2022; 65:1280-9.

[34] Akram HA, Hilal MM, Fattah MY. Numerical simulation of the effect of repeated load and waste polypropylene on the behavior of asphalt layers. In conference series: earth and environmental science 2022 (pp. 1-13). IOP Publishing.

[35] Li H, Guo R, Wang W. A multiphase hybrid-stress finite element method for macroscopic and microscopic modeling of composites: an element with multiple interfaces. Applied Mathematical Modelling. 2023; 116:147-67.

[36] Congress IR. IRC: 37: 2018-guidelines for the design of flexible pavements. IRC, New Delhi, India. 2018.

[37] Kumar A, Sinha S. Support vector machine-based prediction of unconfined compressive strength of multi-walled carbon nanotube doped soil-fly ash mixes. Multiscale and Multidisciplinary Modeling, Experiments and Design. 2024; 7(6):5365-86.

[38] Kashyap R, Chauhan VB, Kumar A, Jaiswal S. Machine learning-based stability assessment of unlined circular tunnels under surcharge loading. Asian Journal of Civil Engineering. 2024; 25(3):2553-66.

[39] Kumar A, Sinha S, Saurav S. Random forest, CART, and MLR-based predictive model for unconfined compressive strength of cement reinforced clayey soil: a comparative analysis. Asian Journal of Civil Engineering. 2024; 25(2):2307-23.

[40] Kumar A, Sinha S, Pandey D, Maurya MC, Chauhan VB. Advanced regression models for assessing the strength of multi-walled carbon nanotube-modified high-volume fly ash concrete. Asian Journal of Civil Engineering. 2024; 25(2):2247-68.

[41] Kumar A, Sinha S, Saurav S, Chauhan VB. Prediction of unconfined compressive strength of cement–fly ash stabilized soil using support vector machines. Asian Journal of Civil Engineering. 2024; 25(2):1149-61.

Cite this article