Void Ratio of Porous Asphalt Mixtures as a Performance Determinant in Semi-Rigid Pavements: An Experimental and Artificial Neural Network (Ann) Approach

Abstract

Semi-rigid pavements are innovative composite systems formed by injecting highly flowable cement grout into the voids of a compacted porous asphalt skeleton with a void ratio between 25% and 35%. The effectiveness of grout infiltration and thus the mechanical performance of the pavement relies heavily on the adequacy of these voids. This study investigates the void content of porous asphalt mixtures forming the skeleton of semi-rigid pavements. Specimens were prepared using basalt and limestone aggregates across six gradations, with nine bitumen contents per combination, totaling 108 samples. Void ratios were determined empirically, and an artificial neural network (ANN) model was developed to predict them. The model utilized ten input variables, including aggregate gradation, specific gravities, and bitumen characteristics, with void ratio as the sole output. The ANN demonstrated excellent predictive accuracy (R² = 0.98), indicating its effectiveness as a reliable tool for estimating void content in porous asphalt mixtures used in semi-rigid pavement design.

Keywords

• Semi-rigid pavement
• porous asphalt
• void ratio
• artificial neural network (ANN)

References

1. Cai X, Leng Z, Ashish PK, Shi C, Yang J, Gong M. Temperature dependency analysis of the fracture characteristics of semi-flexible pavement (SFP) mixtures using acoustic emission technique. Int J Pavement Eng 2023;24. https://doi.org/10.1080/10298436.2023.2201903.
2. El AA, Yalçın E, Yılmaz M. Investigation of the Effects of Porous Asphalt Mixtures Prepared with Different Modified Binders on the Performance Characteristics of Semi-Rigid Pavements. Turkish J Civ Eng 2025;36(5).
3. Xiong Z, Gong M, Hong J, Zhang L, Jiang L, Xu Z. Correlation analysis of the gradation design parameters and mechanical performance of semi-flexible pavement. Constr Build Mater 2023;404. https://doi.org/10.1016/j.conbuildmat.2023.133206.
4. Hou S, Xu T, Huang K. Aggregate gradation influence on grouting results and mix design of asphalt mixture skeleton for semi-flexible pavement. J Test Eval 2017;45. https://doi.org/10.1520/JTE20150190.
5. Hassani A, Taghipoor M, Karimi MM. A state of the art of semi-flexible pavements: Introduction, design, and performance. Constr Build Mater 2020;253. https://doi.org/10.1016/j.conbuildmat.2020.119196.
6. Setyawan A. Design and Properties of Hot Mixture Porous Asphalt for Semi-Flexible Pavement Applications. Media Tek Sipil 2005.
7. An S, Ai C, Ren D, Rahman A, Qiu Y. Laboratory and Field Evaluation of a Novel Cement Grout Asphalt Composite. J Mater Civ Eng 2018;30. https://doi.org/10.1061/(asce)mt.1943-5533.0002376.
8. Ding Q, Sun Z, Shen F, Huang S. The performance analysis of semi-flexible pavement by the volume parameter of matrix asphalt mixture. Adv. Mater. Res., vol. 168–170, 2011. https://doi.org/10.4028/www.scientific.net/AMR.168-170.351.

9. Hassan NA, Mahmud MZH, Jaya RP. Air void characterisation in porous asphalt using x-ray computed tomography. Adv. Mater. Res., vol. 911, 2014. https://doi.org/10.4028/www.scientific.net/AMR.911.443.
10. Król JB, Khan R, Collop AC. The study of the effect of internal structure on permeability of porous asphalt. Road Mater Pavement Des 2018;19. https://doi.org/10.1080/14680629.2017.1283355.
11. Hassn A, Aboufoul M, Wu Y, Dawson A, Garcia A. Effect of air voids content on thermal properties of asphalt mixtures. Constr Build Mater 2016;115. https://doi.org/10.1016/j.conbuildmat.2016.03.106.
12. Chen Z, Qiao J, Yang X, Sun Y, Sun D. A review of grouting materials for pouring semi-flexible pavement: Materials, design and performance. Constr Build Mater 2023;379. https://doi.org/10.1016/j.conbuildmat.2023.131235.
13. Abu Bakr M, Singh BK, Deifalla AF, Pandey S, Hussain A, Ragab AE, et al. Assessment of the mechanical and durability characteristics of bio-mineralized Bacillus subtilis self-healing concrete blended with hydrated lime and brick powder. Case Stud Constr Mater 2023;19. https://doi.org/10.1016/j.cscm.2023.e02672.
14. Luo M, Bai J, Jing K, Ding Z, Yang D, Qian C. Self-healing of early-age cracks in cement mortars with artificial functional aggregates. Constr Build Mater 2021;272. https://doi.org/10.1016/j.conbuildmat.2020.121846.
15. Gong M, Xiong Z, Deng C, Peng G, Jiang L, Hong J. Investigation on the impacts of gradation type and compaction level on the pavement performance of semi-flexible pavement mixture. Constr Build Mater 2022;324. https://doi.org/10.1016/j.conbuildmat.2022.126562.
16. Zarei S, Ouyang J, Zhao Y. Evaluation of fatigue life of semi-flexible pavement with cement asphalt emulsion pastes. Constr Build Mater 2022;349. https://doi.org/10.1016/j.conbuildmat.2022.128797.
17. Bakr MA, Hussain A, Singh PK, Singh BK, Prajakti. Effects of bacterial consortium enhanced recycled coarse aggregates on self-healing concrete immobilized with Bacillus megaterium MTCC 1684 and Bacillus subtilis NCIM 2193. Struct Concr 2024;25. https://doi.org/10.1002/suco.202301018.
18. Khan MI, Khan N, Hashmi SRZ, Yazid MRM, Yusoff NIM, Azfar RW, et al. Prediction of compressive strength of cementitious grouts for semi-flexible pavement application using machine learning approach. Case Stud Constr Mater 2023;19. https://doi.org/10.1016/j.cscm.2023.e02370.
19. Iqbal M, Zhao Q, Zhang D, Jalal FE, Jamal A. Evaluation of tensile strength degradation of GFRP rebars in harsh alkaline conditions using non-linear genetic-based models. Mater Struct Constr 2021;54. https://doi.org/10.1617/s11527-021-01783-x.
20. Jalal FE, Xu Y, Iqbal M, Jamhiri B, Javed MF. Predicting the compaction characteristics of expansive soils using two genetic programming-based algorithms. Transp Geotech 2021;30. https://doi.org/10.1016/j.trgeo.2021.100608.
21. Mohammed A, Rafiq S, Sihag P, Kurda R, Mahmood W, Ghafor K, et al. ANN, M5P-tree and nonlinear regression approaches with statistical evaluations to predict the compressive strength of cement-based mortar modified with fly ash. J Mater Res Technol 2020;9. https://doi.org/10.1016/j.jmrt.2020.08.083.
22. Liu JC, Zhang Z. A machine learning approach to predict explosive spalling of heated concrete. Arch Civ Mech Eng 2020;20. https://doi.org/10.1007/s43452-020-00135-w.
23. Sadowski L. Non-destructive investigation of corrosion current density in steel reinforced concrete by artificial neural networks. Arch Civ Mech Eng 2013;13. https://doi.org/10.1016/j.acme.2012.10.007.
24. Ahmadi M, Naderpour H, Kheyroddin A. Utilization of artificial neural networks to prediction of the capacity of CCFT short columns subject to short term axial load. Arch Civ Mech Eng 2014;14. https://doi.org/10.1016/j.acme.2014.01.006.
25. Seitlllari A, Naser MZ. Leveraging artificial intelligence to assess explosive spalling in fire-exposed RC columns. Comput Concr 2019;24. https://doi.org/10.12989/cac.2019.24.3.271.
26. Iqbal M, Zhang D, Jalal FE, Faisal Javed M. Computational AI prediction models for residual tensile strength of GFRP bars aged in the alkaline concrete environment. Ocean Eng 2021;232. https://doi.org/10.1016/j.oceaneng.2021.109134.
27. Onyelowe KC, Iqbal M, Jalal FE, Onyia ME, Onuoha IC. Application of 3-algorithm ANN programming to predict the strength performance of hydrated-lime activated rice husk ash treated soil. Multiscale Multidiscip Model Exp Des 2021;4. https://doi.org/10.1007/s41939-021-00093-7.
28. Mohammed AS. Vipulanandan model for the rheological properties with ultimate shear stress of oil well cement modified with nanoclay. Egypt J Pet 2018;27. https://doi.org/10.1016/j.ejpe.2017.05.007.
29. Lai S, Serra M. Concrete strength prediction by means of neural network. Constr Build Mater 1997;11. https://doi.org/10.1016/S0950-0618(97)00007-X.
30. Alaneme George U, Mbadike Elvis M. Modelling of the mechanical properties of concrete with cement ratio partially replaced by aluminium waste and sawdust ash using artificial neural network. SN Appl Sci 2019;1. https://doi.org/10.1007/s42452-019-1504-2.
31. Çolak AB, Akçaözoğlu K, Akçaözoğlu S, Beller G. Artificial Intelligence Approach in Predicting the Effect of Elevated Temperature on the Mechanical Properties of PET Aggregate Mortars: An Experimental Study. Arab J Sci Eng 2021;46. https://doi.org/10.1007/s13369-020-05280-1.
32. Ay M. Modeling and analysis of a modular-structured tendon-driven continuum robot for the three-dimensional end effector coordinate. Simul Model Pract Theory 2023;127. https://doi.org/10.1016/j.simpat.2023.102787.
33. Müdürlüğü KG. Highway Technical Specifications. Ankara, Turkey: KGM Publication; 2013.
34. Khan MI, Sutanto MH, Khan K, Iqbal M, Napiah M Bin, Zoorob SE, et al. Effective use of recycled waste PET in cementitious grouts for developing sustainable semi-flexible pavement surfacing using artificial neural network (ANN). J Clean Prod 2022;340. https://doi.org/10.1016/j.jclepro.2022.130840.
35. Alam MA, Ya HH, Azeem M, Hussain P Bin, Salit MS bin, Khan R, et al. Modelling and optimisation of hardness behaviour of sintered Al/SiC composites using RSM and ANN: A comparative study. J Mater Res Technol 2020;9. https://doi.org/10.1016/j.jmrt.2020.09.087.
36. Trong DK, Pham BT, Jalal FE, Iqbal M, Roussis PC, Mamou A, et al. On random subspace optimization-based hybrid computing models predicting the california bearing ratio of soils. Materials (Basel) 2021;14. https://doi.org/10.3390/ma14216516.
37. Babanajad SK, Gandomi AH, Alavi AH. New prediction models for concrete ultimate strength under true-triaxial stress states: An evolutionary approach. Adv Eng Softw 2017;110. https://doi.org/10.1016/j.advengsoft.2017.03.011.
38. Plug CP, de Bondt a. H, van der Woerd BJ, Steensma G. Improved performance of grouted macadams - High Performance Applications of Grouted Macadam. Ooms Ned Hold Bv 2006.