SpringerLink
Log in

Predictive Modeling of Modified Asphalt Mixture Rutting Potentials: Machine Learning Approach

  • Research Paper
  • Published:
Iranian Journal of Science and Technology, Transactions of Civil Engineering Aims and scope Submit manuscript

Abstract

The addition of polymer modifiers to bitumen has been discovered to effectively improve the rutting performance of asphalt mixtures. However, the understanding of the mechanism underlying its rutting resistance is of crucial importance. This study utilized an impressive machine learning approach based on Gaussian process regression (GPR) to predict the rutting potential of asphalt mixtures modified with polyethylene waste dust. To design the experimental setup, a Taguchi orthogonal array was utilized, incorporating three factors with three levels, to predict indirect tensile strength (ITS) and Marshall quotient (MQ) which simulate rutting potential. The results obtained from the performance evaluation of the GPR model indicated coefficient of determination (R2) and root mean square error values of 0.96 and 1.826 for MQ while ITS indicated 0.969 and 0.027 for testing sets. Moreover, the sensitivity analysis of the model showed that bitumen content is the most significant factor for predicting rutting performance of modified mixtures using MQ, while mixture type is the most sensitive variable when the ITS method is deployed to evaluate rutting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Germany)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  • Abtahi S, Sheikhzadeh M, Hejazi S (2010) Fibre-reinforced asphalt concrete—a review. Constr Build Mater 24(16):871–877

    Article  Google Scholar 

  • Abu Abdo A, Jung S (2016) Effects of asphalt mix design properties on pavement performance: a mechanistic approach. Adv Civ Eng. https://doi.org/10.1155/2016/9354058,1-7

    Article  Google Scholar 

  • Alatas T, Yilmaz M (2013) Effects of different polymers on mechanical properties of bituminous binders and hot mixtures. Constr Build Mater 42(16):1–7

    Google Scholar 

  • ASTM C1252 (2017) American society for testing and materials, Standard test method for uncompacted void content of fine aggregate. Pennsylvania

  • ASTM C127 (2016) American society for testing and materials, Standard test method for relative density and absorption of coarse aggregate. Pennsylvania, USA

  • ASTM C128 (2016) Americn society for testing and materials, Standard test method for density, relative density and absorption of fine aggregate. Pennsylvania, USA

  • ASTM C131 (2010) American society for testing and materials, Standard test method for resistance to degradation of small-size coarse aggregate by abrasion and impact in the Los Angeles machine. Pennsylvania, USA

  • ASTM C142 (2017) American society for testing and materials, Standard test method for clay lumps and friable particles. Pennsylvania

  • ASTM C88 (2018) American society for testing and materials, Standard test method for soundness of aggregates. Pennsylvania, USA

  • ASTM D1238 (2013) American society for testing and materials, Standard test method for melt flow rates of themoplastic by extrusion plastomer. Pennsylvania, USA

  • ASTM D2419 (2022) American society for testing and materials, Standard test method for equivalent value soil and fine aggregates. Pennsylvania

  • ASTM D3418 (2021) American society for testing and materials, Standard test methof for transition temperatures and enthalpies and fusion crystallization of polymers by differential scanning calorimetry. Pennsylvania, USA

  • ASTM D3515 (2021) American Society for Testing and Materials, Standard Test Method for Hot- Mixed, Bituminous Paving Mixtures. Pennsylvania, USA

  • ASTM D36 (2006) American Society for Testing and Materials, Standard test methods for softening point of bitumen (Fing and ball apparatus). Pennsylvania USA

  • ASTM D4402 (2022) American society for testing and materials, Standard test method for viscosity determination of asphalt at elevated temperatures using rotational viscometer. Pennsylvania

  • ASTM D4791 (2010) American society for testing and materials, Standard test method for flat particles, elongated particles. Pennsylvania, USA

  • ASTM D4883 (2018) American society for testing and materials, Standard test method for density of polyethylene by the ultrasound technique. Pennsylvania, USA

  • ASTM D5 (2006) American Society for Testing and Materials, Standard test methods for penetration of bituminous materials. Pennsylvania USA

  • ASTM D5581 (2021) American Society for Testing and Materials, Standard Test Method for Resistance to Plastic Flow of Bituminous Mixtures Using Marshall Apparatus. Pennsylvania, USA

  • ASTM D5821 (2017) American society for testing and materials, Standard test method for determing the percentage of fractured particles in coarse aggregate. Pennsylvania, USA

  • ASTM D6927 (2017) American Society for Testing and Materials, Standard Test Method for Marshall Stability and Flow of Bituminous Mixtures. West Conshohocken, USA

  • ASTM D70 (2003) American society for testing and materials, Standard test method for density of semi solid bituminous materials (Pycnometer method). Pennsylvania, USA

  • ASTM D92 (2020) American society for testing and materials, Standard test method for determination of flash point using a Prensky-martens closed-up apparatus. Pennsylvania, USA

  • Azarhoosh A, Hamedi G, Abandansan H (2018) Providing laboratory rutting models for modified asphalt mixes with different waste materials. Periodica Polytech Civ Engineering 62(2):308–317

    Google Scholar 

  • Baghaee T, Karian M, Abdelaziz M (2011) A review on fatigue and rutting performance of asphalt mixtures. Sci Res Essays 6(4):670–682

    Google Scholar 

  • Baize A, Ahmadi H, Shariatmadari F, Karimi torshizi M (2020) A Gaussian process regression model to predict energy contents of corn for poultry. Poultry Sci. https://doi.org/10.1016/j.psj.2020.07.004

    Article  Google Scholar 

  • Behnood A, Ameri M (2012) Experimental investigation of stone matrix asphalt mixtures containing steel slag. Sci Iran 19:1214–1219. https://doi.org/10.1016/j.scient.2012.07.007

    Article  Google Scholar 

  • Behnood A, Gharehwaran M (2009) Morphology, rheology, and physical properties of polymer-modified asphalt binder. Eur Polym J 766–791

  • Chen Y, Yang H, Wang X, Zhang S, Chen H (2012) Biomass-base pyrolytic polygeneration system on cotton stalk pyrolysis : Influence of temperature. Bioresur Technol 107:411–418

    Article  Google Scholar 

  • Christensen D, Bonaquist R, Jack D (2000a) Evaluation of triaxial strength as a simple test for asphalt concrete rut resistance. Transportation Research Board, Pennsylvania

  • Christensen D, Bonaquist R, Jack D (2000b) Evaluation of triaxial strenth as a simple test for asphalt concrete rut resistance.Transportation Research Board, Pennsylvania

  • Esmaeil A, Majid Z, Mohamed R, Mahrez A, Payam S (2011) Using Waste Plastic bottles as additive for ston mastic asphalt. Mater Des 32(10):4844–4849

    Article  Google Scholar 

  • Fontes L, Triches G, Pais J, Pereira P (2010) Evaluating permanent deformation in asphalt rubber mixtures. Construc Build Mater 12: 1193–1200. https://doi.org/10.1016/j.combuildmat.2009.12.021

  • Gorkem C, Sengoz B (2009) Predicting strip** and moisture induced damage of asphalt concrete prepared with polymer modified bitumen and hydrated lime. Construct Build Mater 23(6):2227–2236

    Article  Google Scholar 

  • Isabona J, Ojuh D (2021) Machine learning based on kernel function controlled GAUSSIAN process regression method for in-depth extrapolative analysis of covid-19 daily cases drift rates. Int J Math Sci Comput 7(2):14–23

    Google Scholar 

  • Isacsson U, Zeng H (1998) Low-temperature cracking of polymer-modified asphalt. Mater Struct 31(1):58–63

    Article  Google Scholar 

  • Ismael M, Joni H, Fattah M (2022) Neural network modeling of rutting performance for sustainable asphalt mixtures modified by industrial waste alumina. Ain Shams Eng J. https://doi.org/10.1016/j.asej.2022.101972,101972

    Article  Google Scholar 

  • Jakel F, Scholkopf B, Wichmann F (2007) Atutorial on kernel methods for categorization. J Math Psychol 51(6):343–358

    Article  MATH  Google Scholar 

  • Khattak M, Baladi G (2001) Paving asphalt polymer blends: relationships between composition, structure and properties. Transportation Research Board Annual Meeting, Washington D.C

  • Kumar-Karna S, Sahai R (2012) An overview on Taguchi method. Int J Math Eng Manag Sci 1–7

  • Liang M, **n X, Fan W, Jiang H, Yao Z (2009) Comparison of rheological properties of compactibility of asphalt modified with various polyethylene. Int J Pavement Eng 22(2):1–10

    Google Scholar 

  • Liang M, **n X, Fan W, Jiang H, Yao Z (2019) Comparison of rheological properties of compactability of asphalt modified with various polyethylene. Int J Pavement Eng 22(2):1–10

    Google Scholar 

  • Lidia Sarah C, Palamara R, Leonardi GNM (2017) 3D-FEM analysis of geogrid reinforced flexible pavement roads. IOP Conf Ser Earth Environ Sci 95(2):022024

    Google Scholar 

  • Majidifard H, Jahangiri B, Rath P, Urra L, Buttlar W, Alavi A (2020) Develo** a prediction model for rutting depth of asphalt mixtures using gene expression programming. Construct Build Mater. https://doi.org/10.1016/j.conbuildmat.2020.120543

    Article  Google Scholar 

  • Mehta A, Siddique R, Pratap B, Aggoun S, Łagód G, Barnat-hunek D (2017) Influence of various parameters on strength and absorption properties of fly ash based geopolymer concrete designed by Taguchi method. Construct Build Mater 150:817–824

    Article  Google Scholar 

  • Nallamothu S (2003) Evaluation of binders grades on rutting performance. Morgantowm. Masters thesis Submitted to the Department of Civil Engineering, West Virginia University

  • Nandiyanto A, Oktiani R, Ragadhita R (2019) How to read and interpret FTIR spectroscope of organic material. Indones J Sci Technol 4:97–118

    Article  Google Scholar 

  • Ponniah J, Kennepohl G (1996) Polymer-modified asphalt pavements in Ontario: performance and cost-effectiveness. Transp Res Rec J Transp Res Board 1545(1):51–60

    Article  Google Scholar 

  • Prasad V, Prakash E, Abishek M, Dev K, Kiran C (2018) study on concrete containing waste foundry sand, fly ash and polypropylene fibre using Taguchi method. Mater Today Proc 23964–23973

  • Rafiqul A (2003a) Laboratory and model prediction of rutting in asphalt concrete. Oklahoma, Ph.d. thesis of University of Oklahoma Graduate College

  • Rafiqul AT (2003b) Laboratory and model prediction of rutting in asphalt concrete. Norman, Ph.d. thesis of University of Oklahoma Graduate College

  • Rasmussen P, Madsen K, Lund T, Hansen L (2011) Visualization of nonlinear kernel models in neuroimaging by sensitivity maps. Neuroimage 55:1120–1131

    Article  Google Scholar 

  • Roberts F, Kandhal P, Browm E (1996a) Hot mix asphalt materials, mixture design, and construction. NAPA Education Foundation, Maryland

    Google Scholar 

  • Roberts F, Kandhal P, Brown E (1996b) Hot mix asphalt materials, mixture design, and construction. NAPA Education Foundation, Lanhamn

    Google Scholar 

  • Shafabakhsh G, Ani O, Talebsafa M (2015) Artificial neural network modelling (Ann) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates. Construct Build Mater. https://doi.org/10.1016/j.conbuildmat.2015.03.060

    Article  Google Scholar 

  • Siti SL ( 2011) Styrofoam waste as bitumen modifier in hot mix asphaltic concrete. Petronas, Malaysia, Bachelor thesis, Universiti Teknologi Petronas, Malaysia

  • Speight J (2015) Asphalt materials science and technology. Elsevier, Chicago

    Google Scholar 

  • Stephanie F, Mike O, Ben T, John Z (2021) Design of experiments via taguchi methods-orthogonal arrays. University of Michigan, Michigan

    Google Scholar 

  • Sultan S, Guo Z (2017) Evaluating the performance of sustainable perpetual pavements using recycled asphalt pavement in China. Int J Transp Sci Technol 5(3):200–209

    Article  Google Scholar 

  • Taherkhani H (2006) Experimental characterisation of the compressive permanent deformation behaviour in asphaltic mixtures. Nottingham, Doctoral dissertation submitted to the Department of Civil Engineering, University of Nottingham

  • Tapkin S, Cevik A, Ozcan S (2012a) Utilizing neural networks and closed form solutions to determine Static creep behaviour and optimal polypropylene amount in Bituminious mixtures. Mater Res 15(6):865–883

    Article  Google Scholar 

  • Tapkin S, Cevik A, Usar U (2012b) Prediction of rutting potential of dense bituminous mixtures with polypropylene fibre via repeated creep test by using neuro-fuzzy. Periodica Polytech Civ Eng 56(2):253–266

    Article  Google Scholar 

  • Tapkin S, Cevik A, Usar U, Gulsan E (2013) Rutting prediction of asphalt mixtures modified by polyproylene fibres via repeated creep testing by utilising genetic programming. Mater Res 16(2):277–292

    Article  Google Scholar 

  • Usman G (2020) How to use Residual Plots for regression model validation. Towards Data Science

  • Uwanuakwa I, Ali S, Hasan M, Akpinar P, Sani A, Shariff K (2020) Artificial intelligence prediction of rutting and fatigue parameters in modified asphalt binders. Appl Sci. https://doi.org/10.3390/app10217764

    Article  Google Scholar 

  • Von Quintus H, Mallela J, Buncher M (2007) Quantification of effect of polymer-modified asphalt on flexible Pavement performance. Transp Res Rec J Transp Res Board 2001(1):41–54

    Google Scholar 

  • **ongwei D, Yanshun J, Shaoquan W, Ying G (2020a) Evaluation of rutting performance of field specimen using the hamburg wheel-tracking test and dynamic modulus test. Adv Civ Eng Article ID 9525179

  • **ongwei D, Yanshun J, Shaoquan W, Ying G (2020b) Evaluation of rutting performance of field specimen using the hamburg wheel-tracking test and dynamic modulus test. Adv Civ Eng. https://doi.org/10.1155/2020/9525179

    Article  Google Scholar 

  • **-zhao W, Qing-Yan S, Qing M, Jun-hai Z (2013) Arhitectural Selection for networks trained with extreme learning machine using localized generalization error model. Neurocomputing 102:3–9. https://doi.org/10.1016/j.neucom.2011.12.053

    Article  Google Scholar 

  • Zieliński P (2019) Indirect tensile test as a simple method for rut resistance evaluation of asphalt concrete. Arch Civ Eng 65:31–44. https://doi.org/10.2478/ace-2019-0032

    Article  Google Scholar 

Download references

Acknowledgements

The authors acknowledge support from Cafmeg Laboratory, Shelter Afrique, Nigeria through the use of their laboratory in conducting this research.

Author information

Authors and Affiliations

  1. Department of Civil Engineering, Akwa Ibom State University, Ikot Akpaden, Nigeria

    Idorenyin Ndarake Usanga, Roland Kufre Etim & Imoh Christopher Attah

  2. Department of Civil Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria

    Chijioke Christopher Ikeagwuani

Authors
  1. Idorenyin Ndarake Usanga
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chijioke Christopher Ikeagwuani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Roland Kufre Etim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Imoh Christopher Attah
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Idorenyin Ndarake Usanga.

Ethics declarations

Conflict of interest

The Authors declare that there is no conflict of interest.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Usanga, I.N., Ikeagwuani, C.C., Etim, R.K. et al. Predictive Modeling of Modified Asphalt Mixture Rutting Potentials: Machine Learning Approach. Iran J Sci Technol Trans Civ Eng 47, 4087–4101 (2023). https://doi.org/10.1007/s40996-023-01192-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40996-023-01192-w

Keywords

Search

Navigation