Skip to main content

Advertisement

SpringerLink
Log in

Artificial Neural Network Modeling of Theoretical Maximum Specific Gravity for Asphalt Concrete Mix

  • Original Research Paper
  • Published:
International Journal of Pavement Research and Technology Aims and scope Submit manuscript

Abstract

The maximum specific gravity of asphalt concrete (AC) mix (\(G_{mm}\)) is an important parameter without which asphalt mix design cannot be realized. But the experimental procedure for measuring the \(G_{mm}\) requires time, consumes electric energy, and generates wastewater. Huge amount of experimental data that can enable the virtualization of the AC mix design process exists. But to date, all standardized AC mix-design procedures are mainly experimental. In this study, non-linear regression analysis and multi-layer Artificial Neural Network (ANN) were utilized to develop prediction models for the \(G_{mm}\) of AC mixes. The study utilized 4158 superpave mix-design data points from the Long-Term Pavement Performance (LTPP) information management system (IMS) database. The input variables are asphalt specific gravity \(G_{b}\), asphalt binder content \(P_{b}\), and combined bulk specific gravity of aggregates \(G_{sb}\). The ANN-model (\(R = 0.9843, MSE = 0.00016\)) performed better than the regression model (\(R = 0.9241, MSE = 0.00076\)). A standalone user-friendly MATLAB-based app was developed for the trained ANN-model. The ANN-model is capable of predicting \(G_{mm}\) within AASHTO and ASTM standard single-operator precision requirements (± 0.011) 85.9% of the time. The model can predict \(G_{mm}\) within a margin of ± 0.021 with a 95% success rate. The resulting air voids which were estimated using the predicted \(G_{mm}\) met air-void precision tolerance of ± 0.5 and ± 1.0% in 85.6 and 96.3% of the tests, respectively. The proposed model could minimize the time, energy, and material resources needed during the mix-design process of AC. Standards for AC mix-design should be revised to accommodate more use of prediction models so as to make the design process more sustainable.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

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

Data Availability

Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.

Abbreviations

ASTM:

American society for testing and materials

ANN:

Artificial neural network

AASHTO:

American association of state highway and transportation officials

DDE:

Dissipated damage energy

\(E^{*}\) :

Dynamic modulus

\(\varepsilon\) :

Applied strain

\(f\) :

Loading frequency

FWD:

Falling weight deflector meter

\(G_{mm}\) :

Theoretical maximum specific gravity of asphalt concrete mix

\(G_{mb}\) :

Bulk specific gravity (BSG)

\(G_{b}\) :

Asphalt binder specific gravity

\(G_{se}\) :

Effective specific gravity

GA:

Genetic algorithm

\(G_{ca}\) :

BSG of coarse aggregate

\(G_{fa}\) :

BSG of fine aggregate

\(G_{f}\) :

BSG of filler material

\(G_{sb}\) :

Combined bulk specific gravity of aggregates

IRI:

International roughness index

LTPP:

Long-term pavement performance

\(MSE\) :

Mean square error

\(n_{t}\) :

Total number of observed \(G_{mm}\)

\(n_{p}\) :

Number of model parameters

\(\eta\) :

Viscosity

\(N_{Ini}\) :

Initial number of gyrations

\(N_{des}\) :

Design number of gyrations

\(N_{max}\) :

Maximum number of gyrations

PG:

Performance grade

PC:

Portland cement

\(P_{b}\) :

Asphalt binder content

\(P_{fa}\) :

Percentage of fine aggregate by total mass of solid

\(P_{f}\) :

Percentage of filler by total mass of solid

\(P_{ca}^{^{\prime}}\) :

Percentage of coarse aggregate by total mass of mix,

\(P_{fa}^{^{\prime}}\) :

Percentage of fine aggregate by total mass of mix,

\(P_{f}^{^{\prime}}\) :

Percentage of filler by total mass of mix

Q1:

25th percentile

Q2:

50th percentile

Q3:

75th percentile

RNN:

Recurrent neural network

SG:

Specific gravity

SHRP:

Strategic highway research program

VFA:

Void filled with asphalt

\(V_{a}\) :

Air-voids

\(V_{beff}\) :

Effective binder content

\(\overline{{y_{a} }}\) :

Mean of observed \(G_{mm}\)

\(\overline{{y_{p} \left( {u_{i} } \right)}}\) :

Mean of predicted \(G_{mm}\)

\(\sigma_{a}\) :

Standard deviation of the actual \(G_{mm}\)

\(\sigma_{p}\) :

Standard deviation of the predicted \(G_{mm}\)

\(R^{2}\) :

Coefficient of determination

\(R\) :

Coefficient of correlation

\(RI\) :

Relative importance

\(S\) :

Initial mix stiffness

References

  1. Rice, J. M. (1957). Maximum Specific Gravity of Bituminous Mixtures by Vacuum Saturation Procedure. In H. Williams (Ed.), Symposium on Specific Gravity of Bituminous Coated Aggregates (pp. 43–61). West Conshohocken PA: ASTM International. https://doi.org/10.1520/STP48029S

    Chapter  Google Scholar 

  2. ASTM:D2041, D2041M-19. (2019). Standard Test Method for Theoretical Maximum Specific Gravity and Density of Asphalt Mixtures. West Conshohocken PA: ASTM Int. https://doi.org/10.1520/D2041_D2041M-19

    Book  Google Scholar 

  3. AASHTO:T209–20. (2020). Theoretical Maximum Specific Gravity (Gmm) and Density of Asphalt Mixtures (p. 20004). Washington DC: American Association of State Highway and Transportation Officials.

    Google Scholar 

  4. Andrew, B., Buyondo, K. A., Kasedde, H., Kirabira, J. B., Olupot, P. W., & Yusuf, A. A. (2022). Investigation on the use of reclaimed asphalt pavement along with steel fibers in concrete. Case Studies in Construction Materials, 17, e01356. https://doi.org/10.1016/j.cscm.2022.e01356

    Article  Google Scholar 

  5. Buyondo, K. A., Olupot, P. W., Kirabira, J. B., & Yusuf, A. A. (2020). Optimization of production parameters for rice husk ash-based geopolymer cement using response surface methodology. Case Studies in Construction Materials, 13, e00461. https://doi.org/10.1016/j.cscm.2020.e00461

    Article  Google Scholar 

  6. ASTM:D6857, D6857M-18. (2018). Standard Test Method for Maximum Specific Gravity and Density of Asphalt Mixtures Using Automatic Vacuum Sealing Method. West Conshohocken PA: ASTM Int.

    Google Scholar 

  7. Spellerberg, P., Savage, D., Pielert, J. (2003). Precision Estimates of Selected Volumetric Properties of HMA Using Non-Absorptive Aggregate. NCHRP D9-26. http://onlinepubs.trb.org/onlinepubs/nchrp/nchrp_w54.pdf.

  8. FHWA. (2010). A Review of Aggregate and Asphalt Mixture Specific Gravity Measurements and Their Impacts on Asphalt Mix Design Properties and Mix Acceptance, WASHINGTON, DC 20590. https://www.fhwa.dot.gov/pavement/materials/pubs/hif11033/hif11033.pdf. Accessed 18 Sept 2022.

  9. Fred Martinez, D., & Bayoma, F. M. (1991). Selection of maximum theoretical specific gravity for asphalt mixture design. Transportation Research Record, 1300, 13–21.

    Google Scholar 

  10. Azari, H. (2010). REFINEMENT OF AASHTO T 209. NCHRP10-87. https://onlinepubs.trb.org/onlinepubs/nchrp/docs/NCHRP10-87_FR.pdf.

  11. da Silva, T. K., Pitanga, H. N., da Silva, T. O., de Marques, G. L. O., Causado-Mendoza, L. E., & de Lima, D. C. (2019). Sensitivity of the Superpave mix design method to different methods for determining the maximum specific gravity. DYNA, 86, 184–191.

    Article  Google Scholar 

  12. El Sayed, M. A. G. (2012). Effect of changing theoretical maximum specific gravity on asphalt mixture design. Engineering Journal, 16, 137–148.

    Article  Google Scholar 

  13. Ozturk, H. I., & Kutay, M. E. (2014). An artificial neural network model for virtual Superpave asphalt mixture design. International Journal of Pavement Engineering, 15, 151–162. https://doi.org/10.1080/10298436.2013.808341

    Article  CAS  Google Scholar 

  14. Sebaaly, H., Varma, S., & Maina, J. W. (2018). Optimizing asphalt mix design process using artificial neural network and genetic algorithm. Construction and Building Materials, 168, 660–670. https://doi.org/10.1016/j.conbuildmat.2018.02.118

    Article  Google Scholar 

  15. Fadhil, T. H., Ahmed, T. M., & Al Mashhadany, Y. I. (2022). Application of artificial neural networks as design tool for hot mix asphalt. International Journal of Pavement Research and Technology., 15, 269–283. https://doi.org/10.1007/s42947-021-00065-7

    Article  Google Scholar 

  16. Zheng, D., Qian, Z., Liu, Y., & Liu, C. (2018). Prediction and sensitivity analysis of long-term skid resistance of epoxy asphalt mixture based on GA-BP neural network. Construction and Building Materials, 158, 614–623. https://doi.org/10.1016/j.conbuildmat.2017.10.056

    Article  CAS  Google Scholar 

  17. Dharamveer, S., Musharraf, Z., & Sesh, C. (2013). Artificial neural network modeling for dynamic modulus of hot mix asphalt using aggregate shape properties. Journal of Materials in Civil Engineering, 25, 54–62. https://doi.org/10.1061/(ASCE)MT.1943-5533.0000548

    Article  Google Scholar 

  18. Jun, L., Kezhen, Y., Jenny, L., & Xiaowen, Z. (2018). Using artificial neural networks to predict the dynamic modulus of asphalt mixtures containing recycled asphalt shingles. Journal of Materials in Civil Engineering, 30, 4018051. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002242

    Article  Google Scholar 

  19. Hamim, A., Yusoff, N. IMd., Omar, H. A., Jamaludin, N. A. A., Hassan, N. A., El-Shafie, A., & Ceylan, H. (2020). Integrated finite element and artificial neural network methods for constructing asphalt concrete dynamic modulus master curve using deflection time-history data. Construction and Building Materials., 257, 119549. https://doi.org/10.1016/j.conbuildmat.2020.119549

    Article  Google Scholar 

  20. You, L., Yan, K., & Liu, N. (2020). Assessing artificial neural network performance for predicting interlayer conditions and layer modulus of multi-layered flexible pavement. Frontiers of Structural and Civil Engineering., 14, 487–500. https://doi.org/10.1007/s11709-020-0609-4

    Article  Google Scholar 

  21. Han, C., Ma, T., Chen, S., & Fan, J. (2021). Application of a hybrid neural network structure for FWD backcalculation based on LTPP database. International Journal of Pavement Engineering. https://doi.org/10.1080/10298436.2021.1883016

    Article  Google Scholar 

  22. Andrew, L., Kim, Y. R., & Ranjithan, S. R. (2008). Backcalculation of dynamic modulus from resilient modulus of asphalt concrete with an artificial neural network. Transportation Research Record, 2057, 107–113. https://doi.org/10.3141/2057-13

    Article  Google Scholar 

  23. Shafabakhsh, G. H., Ani, O. J., & Talebsafa, M. (2015). 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, 136–143. https://doi.org/10.1016/j.conbuildmat.2015.03.060

    Article  Google Scholar 

  24. Mirabdolazimi, S. M., & Shafabakhsh, G. (2017). Rutting depth prediction of hot mix asphalts modified with forta fiber using artificial neural networks and genetic programming technique. Construction and Building Materials., 148, 666–674. https://doi.org/10.1016/j.conbuildmat.2017.05.088

    Article  Google Scholar 

  25. Shan, A., Hafeez, I., Hussan, S., & Jamil, M. B. (2020). Predicting the laboratory rutting response of asphalt mixtures using different neural network algorithms. International Journal of Pavement Engineering. https://doi.org/10.1080/10298436.2020.1830282

    Article  Google Scholar 

  26. Haddad, A. J., Chehab, G. R., & Saad, G. A. (2021). The use of deep neural networks for developing generic pavement rutting predictive models. International Journal of Pavement Engineering. https://doi.org/10.1080/10298436.2021.1942466

    Article  Google Scholar 

  27. Pourtahmasb, M. S., Karim, M. R., & Shamshirband, S. (2015). Resilient modulus prediction of asphalt mixtures containing recycled concrete aggregate using an adaptive neuro-fuzzy methodology. Construction and Building Materials., 82, 257–263. https://doi.org/10.1016/j.conbuildmat.2015.02.030

    Article  Google Scholar 

  28. Hu, J., & Qian, Z. (2018). The prediction of adhesive failure between aggregates and asphalt mastic based on aggregate features. Construction and Building Materials, 183, 22–31. https://doi.org/10.1016/j.conbuildmat.2018.06.145

    Article  Google Scholar 

  29. Feipeng, X., Serji, A., & Hsein, J. C. (2009). Prediction of fatigue life of rubberized asphalt concrete mixtures containing reclaimed asphalt pavement using artificial neural networks. Journal of Materials in Civil Engineering, 21, 253–261. https://doi.org/10.1061/(ASCE)0899-1561(2009)21:6(253)

    Article  CAS  Google Scholar 

  30. Gong, H., Sun, Y., Hu, W., & Huang, B. (2021). Neural networks for fatigue cracking prediction using outputs from pavement mechanistic-empirical design. International Journal of Pavement Engineering, 22, 162–172. https://doi.org/10.1080/10298436.2019.1580367

    Article  CAS  Google Scholar 

  31. Nivedya, M. K., & Mallick, R. B. (2020). Artificial neural network-based prediction of field permeability of hot mix asphalt pavement layers. International Journal of Pavement Engineering, 21, 1057–1068. https://doi.org/10.1080/10298436.2018.1519189

    Article  CAS  Google Scholar 

  32. Xiao, F., Putman, B. J., & Amirkhanian, S. N. (2011). Viscosity prediction of CRM binders using artificial neural network approach. International Journal of Pavement Engineering, 12, 485–495. https://doi.org/10.1080/10298430903578903

    Article  Google Scholar 

  33. Hussain, F., Ali, Y., & Irfan, M. (2021). Quantifying the differential phase angle behaviour of asphalt concrete mixtures using artificial neural networks. Int. J. Pavement Res. Technol. https://doi.org/10.1007/s42947-021-00042-0

    Article  Google Scholar 

  34. Khasawneh, M. A., & Al-Oqaily, D. M. (2022). Development of analytical models to predict the dynamic shear rheometer outcome—phase angle. International Journal of Pavement Research and Technology. https://doi.org/10.1007/s42947-021-00141-y

    Article  Google Scholar 

  35. Upadhya, A., Thakur, M. S., Sharma, N., & Sihag, P. (2021). Assessment of soft computing-based techniques for the prediction of marshall stability of asphalt concrete reinforced with glass fiber. International Journal of Pavement Research and Technology. https://doi.org/10.1007/s42947-021-00094-2

    Article  Google Scholar 

  36. Khasawneh, M. A., Taamneh, M. M., & Albatayneh, O. (2019). Evaluation of static creep of FORTA-FI strengthened asphalt mixtures using experimental, statistical and feed-forward back-propagation ANN techniques. International Journal of Pavement Research and Technology, 12, 43–53. https://doi.org/10.1007/s42947-019-0006-3

    Article  Google Scholar 

  37. Duan, Z. H., Kou, S. C., & Poon, C. S. (2013). Using artificial neural networks for predicting the elastic modulus of recycled aggregate concrete. Construction and Building Materials, 44, 524–532. https://doi.org/10.1016/j.conbuildmat.2013.02.064

    Article  Google Scholar 

  38. Getahun, M. A., Shitote, S. M., & Abiero Gariy, Z. C. (2018). Artificial neural network based modelling approach for strength prediction of concrete incorporating agricultural and construction wastes. Construction and Building Materials., 190, 517–525. https://doi.org/10.1016/j.conbuildmat.2018.09.097

    Article  Google Scholar 

  39. Bellary, A., & Suresha, S. N. (2022). ANN model to predict joint stiffness of white-topped pavements using falling weight deflectometer (FWD) data. International Journal of Pavement Research and Technology. https://doi.org/10.1007/s42947-021-00137-8

    Article  Google Scholar 

  40. Hossain, M., Gopisetti, L. S. P., & Miah, M. S. (2020). Artificial neural network modelling to predict international roughness index of rigid pavements. International Journal of Pavement Research and Technology, 13, 229–239. https://doi.org/10.1007/s42947-020-0178-x

    Article  Google Scholar 

  41. Mohammadi Golafshani, E., Behnood, A., & Karimi, M. M. (2021). Predicting the dynamic modulus of asphalt mixture using hybridized artificial neural network and grey wolf optimizer. International Journal of Pavement Engineering. https://doi.org/10.1080/10298436.2021.2005056

    Article  Google Scholar 

  42. Hussan, S., Kamal, M. A., Hafeez, I., & Ahmad, N. (2019). Evaluation and modelling of permanent deformation behaviour of asphalt mixtures using dynamic creep test in uniaxial mode. International Journal of Pavement Engineering, 20, 1026–1043. https://doi.org/10.1080/10298436.2017.1380805

    Article  CAS  Google Scholar 

  43. FHWA. (2021). Long Term Pavement Performance (LTPP). https://infopave.fhwa.dot.gov/Data/DataSelection. Accessed 10 June 2021

  44. Gong, H., Sun, Y., Hu, W., Polaczyk, P. A., & Huang, B. (2019). Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests. Construction and Building Materials, 204, 203–212. https://doi.org/10.1016/j.conbuildmat.2019.01.198

    Article  Google Scholar 

  45. AASHTO T 228. (2022). Standard method of test for specific gravity and density of semi-solid asphalt materials. AASHTO. 4

  46. ASTM D70/D70M-21. (2021). Standard test method for specific gravity and density of semi-solid asphalt binder (Pycnometer Method). ASTM, 04(03), 5. https://doi.org/10.1520/D0070_D0070M-21

  47. Gevrey, M., Dimopoulos, I., & Lek, S. (2003). Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modelling, 160, 249–264. https://doi.org/10.1016/S0304-3800(02)00257-0

    Article  Google Scholar 

  48. Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J., & Aulagnier, S. (1996). Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling, 90, 39–52. https://doi.org/10.1016/0304-3800(95)00142-5

    Article  Google Scholar 

  49. Olden, J. D., Joy, M. K., & Death, R. G. (2004). An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecological Modelling., 178, 389–397. https://doi.org/10.1016/j.ecolmodel.2004.03.013

    Article  Google Scholar 

  50. Garson, G. D. (1991). Interpreting neural-network connection weights. AI Expert, 6, 46–51. https://doi.org/10.5555/129449.129452

    Article  Google Scholar 

  51. ASTM D2041/D2041M-19, (2019). Standard test method for theoretical maximum specific gravity and density of asphalt mixtures. ASTM, 04(03), 4. https://doi.org/10.1520/D2041_D2041M-19

  52. AASHTO T 209, (2022). Standard method of test for theoretical maximum specific gravity (gmm) and density of asphalt mixtures. AASHTO, 11

  53. Shi, D., Maydeu-Olivares, A., & DiStefano, C. (2018). The relationship between the standardized root mean square residual and model misspecification in factor analysis models. Multivariate Behavioral Research, 53, 676–694. https://doi.org/10.1080/00273171.2018.1476221

    Article  PubMed  Google Scholar 

  54. Vasquez, V. R., & Whiting, W. B. (2005). Accounting for both random errors and systematic errors in uncertainty propagation analysis of computer models involving experimental measurements with monte carlo methods. Risk Analysis, 25, 1669–1681. https://doi.org/10.1111/j.1539-6924.2005.00704.x

    Article  PubMed  Google Scholar 

  55. Weiguang, Z., Shihui, S., Shenghua, W., Xiao, C., Jiayue, X., & Mohammad, L. N. (2019). Effects of in-place volumetric properties on field rutting and cracking performance of asphalt pavement. Journal of Materials in Civil Engineering, 31, 4019150. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002767

    Article  Google Scholar 

  56. ASTM-D70, D70M-21. (2021). Standard Test Method for Specific Gravity and Density of Semi-Solid Asphalt Binder (Pycnometer Method). West Conshohocken PA: ASTM Int.

    Google Scholar 

  57. AASHTO:T228–18. (2018). Specific Gravity of Semi-Solid Bituminous Materials. USA: American Association of State Highway and Transportation Officials.

    Google Scholar 

Download references

Acknowledgements

The authors acknowledge the support provided by Imam Abdulrahman Bin Faisal University, Dammam, KSA, in carrying out this research.

Author information

Authors and Affiliations

  1. Transportation and Traffic Engineering Department, College of Engineering, Imam Abdulrahman Bin Faisal University, PO Box 1982, Dammam, 31451, Saudi Arabia

    M. A. Dalhat & Sami A. Osman

Authors
  1. M. A. Dalhat
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sami A. Osman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. A. Dalhat.

Ethics declarations

Conflict of Interest

The authors wish to declare that they have 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

Dalhat, M.A., Osman, S.A. Artificial Neural Network Modeling of Theoretical Maximum Specific Gravity for Asphalt Concrete Mix. Int. J. Pavement Res. Technol. 17, 406–422 (2024). https://doi.org/10.1007/s42947-022-00244-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s42947-022-00244-0

Keywords

Search

Navigation