journal article·2025-02

Prediction of asphalt concrete energy release rate from Texas Overlay Test using machine learning

Fangyu Liu, Masih Beheshti, Hasan Ozer, Imad L. Al-Qadi

Publisher page

Abstract

This study aimed to apply machine learning (ML) models to predict the energy release rate (ERR) in the Texas Overlay Test (TXOT) for the reflective cracking of asphalt concrete (AC) overlay. The Generalised Finite Element Method model was developed with TXOT experimental results. Subsequently, a TXOT Finite Element database was constructed. Four different cases were formulated, each utilising distinct input variables and the same output variable (i.e. ERR). Five ML models were trained and evaluated for ERR prediction. The model performances were compared across four cases to determine the optimal set of input variables. Shapley Additive exPlanations methods were employed to interpret ML models. The results demonstrated that ML models performed differently across different cases. Artificial Neural Network achieved the highest accuracy in the case which included crack length, crack opening, AC modulus, and sigmoidal function parameters. Therefore, ML models prove to be accurate and reliable for predicting ERR.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Non-Destructive Testing Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

University of Illinois Urbana-Champaign

Arizona State University

Funding

Federal Aviation Administration

References (53)

Show source-provided references
1. 10.3390/su1414862710.3390/su14148627 ↗
2. Al-Qadi, I. L., Elseifi, M., & Leonard, D. (2003). Development of an overlay design model for reflective cracking with and without steel reinforcing nettings. Asphalt Paving Technology, 72, 388–423.
3. 10.1177/036119811875796910.1177/0361198118757969 ↗
4. Baek, J., & Al-Qadi, I. (2009). Reflective cracking: Modeling fracture behavior of hot-mix asphalt overlays with interlayer systems. Asphalt Paving Technology-Proceedings, 28, 789.
5. 10.1088/0965-0393/17/4/04300110.1088/0965-0393/17/4/043001 ↗
6. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
7. Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., … Zhou, T. (2015). Xgboost: Extreme gradient boosting. R package version 0.4-2, 1(4), 1–4.
8. 10.1007/BF0099401810.1007/BF00994018 ↗
9. 10.1016/S0045-7949(99)00211-410.1016/S0045-7949(99)00211-4 ↗
10. Federal Aviation Administration. (2020). Reflective cracking outdoor phase 1. https://www.airporttech.tc.faa.gov/Airport-Pavement/NAPTF/Reflective-Cracking-Program/Reflective-Cracking-Outdoor-Phase-1
11. Federal Highway Administration. (2012). Long term pavement performance program standard data release (SDR) 26.0.
12. 10.1016/j.engstruct.2021.11197910.1016/j.engstruct.2021.111979 ↗
13. 10.1016/j.tafmec.2023.10375910.1016/j.tafmec.2023.103759 ↗
14. General Dynamics Information Technology. (2020). Reflective cracking indoor phase 6 material characterization report. Federal Aviation Administration.
15. General Dynamics Information Technology, & Horizon Engineering Consulting. (2020). Reflective cracking outdoor phase 1 material characterization report. Federal Aviation Administration.
16. 10.1016/j.conbuildmat.2020.11991210.1016/j.conbuildmat.2020.119912 ↗
17. 10.1016/j.conbuildmat.2015.10.15910.1016/j.conbuildmat.2015.10.159 ↗
18. 10.1177/036119811878068110.1177/0361198118780681 ↗
19. 10.3141/2590-1210.3141/2590-12 ↗
20. 10.3141/2127-0910.3141/2127-09 ↗
21. 10.1007/s11709-020-0712-610.1007/s11709-020-0712-6 ↗
22. 10.1109/TITS.2022.314239310.1109/TITS.2022.3142393 ↗
23. 10.1016/j.autcon.2022.10457510.1016/j.autcon.2022.104575 ↗
24. 10.1016/j.autcon.2022.10438310.1016/j.autcon.2022.104383 ↗
25. 10.1016/j.autcon.2024.10535510.1016/j.autcon.2024.105355 ↗
26. 10.1016/j.conbuildmat.2022.12799710.1016/j.conbuildmat.2022.127997 ↗
27. 10.1016/j.conbuildmat.2022.12921110.1016/j.conbuildmat.2022.129211 ↗
28. 10.1080/10298436.2021.199028810.1080/10298436.2021.1990288 ↗
29. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4768–4777.
30. Lytton R. Tsai F. Lee S. Luo R. Hu S. & Zhou F. (2010). NCHRP report 669: Models for predicting reflection cracking of hot-mix asphalt overlays. Transportation research board of the national academies Washington DC.
31. 10.1016/j.conbuildmat.2020.11851310.1016/j.conbuildmat.2020.118513 ↗
32. 10.1016/j.measurement.2018.11.08110.1016/j.measurement.2018.11.081 ↗
33. Mirzaiyanrajeh, D., Dave, E. V., Sias, J. E., & Ramsey, P. (2022). Developing a prediction model for low-temperature fracture energy of asphalt mixtures using machine learning approach. International Journal of Pavement Engineering, 1–12.
34. Mitchell, T. M., & Mitchell, T. M. (1997). Machine learning (Vol. 1). McGraw-hill New York.
35. Molnar, C. (2020). Interpretable machine learning. Lulu. com.
36. 10.1111/mice.1253210.1111/mice.12532 ↗
37. 10.1080/10298436.2021.199321910.1080/10298436.2021.1993219 ↗
38. Ozer, H. (2011). Development of domain integral and generalized finite element methods for three dimensional analysis of near-surface cracking in flexible pavements. University of Illinois at Urbana-Champaign.
39. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., … Antiga, L. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32, 8026–8037.
40. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., … Dubourg, V. (2011). Scikit-learn: Machine learning in Python. the Journal of Machine Learning Research, 12, 2825–2830.
41. 10.1016/j.enganabound.2004.09.00710.1016/j.enganabound.2004.09.007 ↗
42. 10.1061/JPEODX.PVENG-121110.1061/JPEODX.PVENG-1211 ↗
43. Roylance D. (2001). Introduction to fracture mechanics.
44. 10.1016/S0045-7825(99)00072-910.1016/S0045-7825(99)00072-9 ↗
45. 10.1002/(SICI)1097-0207(20000320)47:8<1401::AID-NME835>3.0.CO;2-810.1002/(SICI)1097-0207(20000320)47:8<1401::AID-NME835>3.0.CO;2-8 ↗
46. 10.1016/S0045-7825(01)00188-810.1016/S0045-7825(01)00188-8 ↗
47. 10.1016/j.engfracmech.2007.04.00910.1016/j.engfracmech.2007.04.009 ↗
48. Texas DOT. (2019). Texas overlay test.
49. Tietz M. Fan T. J. Nouri D. Bossan B. & Developers S. (2017). Skorch: A scikit-learn compatible neural network library that wraps PyTorch: July.
50. 10.1016/j.conbuildmat.2018.08.20210.1016/j.conbuildmat.2018.08.202 ↗
51. 10.1016/j.istruc.2021.03.01110.1016/j.istruc.2021.03.011 ↗
52. 10.1016/0169-7439(87)80084-910.1016/0169-7439(87)80084-9 ↗
53. 10.1109/TITS.2022.315022410.1109/TITS.2022.3150224 ↗