Evaluation of ANN-Based Dynamic Modulus Models of Asphalt Mixtures
Publication: Journal of Materials in Civil Engineering
Volume 33, Issue 6
Abstract
Artificial neural network (ANN)-based dynamic modulus models were evaluated on South Carolina’s asphalt mixtures, the majority of which contained recycled asphalt pavement (RAP). These ANNs contained similar input variables as the NCHRP 1-40D and Hirsch regression models and were implemented in the neural network toolbox of MATLAB version R2018b. Two previously published ANN-based models were also evaluated on the same database. Most ANNs in the literature have been shown to predict with good success; however, they have not been validated outside of their original studies. The results showed that (1) ANN-based models performed significantly better than regression models; (2) ANNs with few input variables (either , , and or VMA, VFA, and ) highly predicted with on testing; (3) ANNs can accurately predict of recycled asphalt mixtures; (4) the validation performance of the two published ANNs on South Carolina’s asphalt mixtures was ranked fair; and (5) locally customized ANNs are more accurate in the estimation of than globally calibrated ANNs or regression models.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The HMA data referenced in this manuscript were obtained from the FHWA-SC-18-04 report. The views, opinions, and recommendations of the authors do not represent official statements and/or recommendations from the SCDOT.
References
AASHTO. 2017. Standard method of test for determining the dynamic modulus and flow number for asphalt mixtures using the asphalt mixture performance tester (AMPT). Washington, DC: AASHTO.
AASHTO. 2019. Standard method of test for determining dynamic modulus of hot-mix asphalt concrete mixtures. Washington, DC: AASHTO.
Al-Khateeb, G., A. Shenoy, N. Gibson, and T. Harman. 2006. “A new simplistic model for dynamic modulus predictions of asphalt paving mixtures.” J. Assoc. Asphalt Paving Technol. 75: 586.
Amirkhanian, S., F. Xiao, and M. Corley. 2018. Characterization of asphalt concrete dynamic modulus in South Carolina. Washington, DC: Federal Highway Administration.
Bari, J. 2005. “Development of a new revised version of the Witczak predictive models for hot mix asphalt mixtures.” Ph.D. thesis, Dept. of Civil and Environmental Engineering, Arizona State Univ.
Bennert, T. A. 2009. Dynamic modulus of hot mix asphalt. Washington, DC: FHWA.
Ceylan, H., K. Gopalakrishnan, and S. Kim. 2009a. “Looking to the future: The next-generation hot mix asphalt dynamic modulus prediction models.” Int. J. Pavement Eng. 10 (5): 341–352. https://doi.org/10.1080/10298430802342690.
Ceylan, H., C. W. Schwartz, S. Kim, and K. Gopalakrishnan. 2009b. “Accuracy of predictive models for dynamic modulus of hot-mix asphalt.” J. Mater. Civ. Eng. 21 (6): 286–293. https://doi.org/10.1061/(ASCE)0899-1561(2009)21:6(286).
Christensen, D., T. Pellinen, and R. Bonaquist. 2003. “Hirsch model for estimating the modulus of asphalt concrete.” J. Assoc. Asphalt Paving Technol. 72: 97–121.
Dongre, R., L. Myers, J. D’Angelo, C. Paugh, and J. Gudimettla. 2005. “Field evaluation of Witczak and Hirsch models for predicting dynamic modulus of hot-mix asphalt (with discussion).” J. Assoc. Asphalt Paving Technol. 74: 381–442.
El-Badawy, S., R. Abd El-Hakim, and A. Awed. 2018. “Comparing artificial neural networks with regression models for hot-mix asphalt dynamic modulus prediction.” J. Mater. Civ. Eng. 30 (7): 04018128. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002282.
El-Badawy, S., F. Bayomy, and A. Awed. 2012. “Performance of MEPDG dynamic modulus predictive models for asphalt concrete mixtures: local calibration for Idaho.” J. Mater. Civ. Eng. 24 (11): 1412–1421. https://doi.org/10.1061/(ASCE)MT.1943-5533.0000518.
Far, M. S. S. 2011. “Development of new dynamic modulus () predictive models for hot mix asphalt mixtures.” Ph.D. thesis, Dept. of Civil, Construction and Environmental Engineering, North Carolina State Univ.
Far, M. S. S., B. S. Underwood, S. R. Ranjithan, Y. R. Kim, and N. Jackson. 2009. “Application of artificial neural networks for estimating dynamic modulus of asphalt concrete.” Transp. Res. Rec. 2127 (1): 173–186. https://doi.org/10.3141/2127-20.
Galeshchuk, S. 2016. “Neural networks performance in exchange rate prediction.” Neurocomputing 172 (Jan): 446–452. https://doi.org/10.1016/j.neucom.2015.03.100.
Gong, H., Y. Sun, Y. Dong, B. Han, P. Polaczyk, B. Hu, and B. Huang. 2020. “Improved estimation of dynamic modulus for hot mix asphalt using deep learning.” Constr. Build. Mater. 263 (Jan): 119912. https://doi.org/10.1016/j.conbuildmat.2020.119912.
Khattab, A., S. El-Badawy, A. Al Hazmi, and M. Elmwafi. 2015. “Comparing Witczak NCHRP 1-40D with Hirsh E* predictive models for Kingdom of Saudi Arabia asphalt mixtures.” In Proc., 3rd Middle East Society of Asphalt Technologists (MESAT) Conf., 6–8. Dubai, United Arab Emirates: American Univ. in Dubai.
Kim, Y. R., B. Underwood, M. S. Far, N. Jackson, J. Puccinelli, and N. C. Engineers. 2011. LTPP computed parameter: Dynamic modulus. Washington, DC: Federal Highway Administration.
Kutay, M. E., and A. Jamrah. 2013. Preparation for implementation of the mechanistic-empirical pavement design guide in Michigan: Part 1-HMA mixture characterization. Lansing, MI: Michigan DOT.
Liu, J., K. Yan, J. Liu, and X. Zhao. 2018. “Using artificial neural networks to predict the dynamic modulus of asphalt mixtures containing recycled asphalt shingles.” J. Mater. Civ. Eng. 30 (4): 04018051. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002242.
Liu, J., K. Yan, L. You, P. Liu, and K. Yan. 2017. “Prediction models of mixtures’ dynamic modulus using gene expression programming.” Int. J. Pavement Eng. 18 (11): 971–980. https://doi.org/10.1080/10298436.2016.1138113.
Pellinen, T. K. 2001. “Investigation of the use of dynamic modulus as an indicator of hot-mix asphalt performance.” Ph.D. thesis, Dept. of Civil and Environmental Engineering, Arizona State Univ.
Rahman, A. A., M. R. Islam, and R. A. Tarefder. 2018. “Assessment and modification of nationally-calibrated dynamic modulus predictive model for the implementation of Mechanistic-Empirical design.” Int. J. Pavement Res. Technol. 11 (5): 502–508. https://doi.org/10.1016/j.ijprt.2018.03.008.
SC-M-407 (06/11). 2011. Supplemental technical specification for recycled asphalt pavement (RAP) and recycled asphalt shingles (RAS). Columbia, SC: South Carolina DOT.
Szoplik, J. 2015. “Forecasting of natural gas consumption with artificial neural networks.” J. Energy 85 (Jun): 208–220. https://doi.org/10.1016/j.energy.2015.03.084.
Thodesen, C., F. Xiao, and S. N. Amirkhanian. 2009. “Modeling viscosity behavior of crumb rubber modified binders.” Constr. Build. Mater. 23 (9): 3053–3062. https://doi.org/10.1016/j.conbuildmat.2009.04.005.
Wang, W., M. Wang, H. Li, H. Zhao, K. Wang, C. He, J. Wang, S. Zheng, and J. Chen. 2019. “Pavement crack image acquisition methods and crack extraction algorithms: A review.” J. Traffic Transp. Eng. 6 (6): 535–556. https://doi.org/10.1016/j.jtte.2019.10.001.
Yu, H., and S. Shen. 2012. An investigation of dynamic modulus and flow number properties of asphalt mixtures in Washington State. Seattle: Transportation Northwest Regional Center X.
Zhao, S., J. Liu, P. Li, and S. Saboundjian. 2017. “Dynamic modulus characterization of Alaskan asphalt mixtures for mechanistic-empirical pavement design.” J. Mater. Civ. Eng. 29 (11): 04017213. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002069.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Jul 31, 2020
Accepted: Oct 21, 2020
Published online: Mar 23, 2021
Published in print: Jun 1, 2021
Discussion open until: Aug 23, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.