Enhancing Pavement Performance through Balanced Mix Design: A Comprehensive Field Study in Oklahoma
Publication: International Conference on Transportation and Development 2024
ABSTRACT
The Oklahoma Department of Transportation (ODOT) embarked on a phased implementation of balanced mix design (BMD) starting in 2018. This involved initial shadow projects (Phase I) and a proof of concept stage (Phase 2) with pilot projects, followed by long-term evaluation and implementation in Phase 3 and Phase 4, respectively. The goal of this study is to evaluate the field performance of BMD mixes used in Oklahoma. Cutting-edge 3D laser imaging technology was used to collect pavement condition data from various BMD sites, including metrics such as percentage cracking, international roughness index (IRI), rut depth, and mean profile depth. Firstly, a comparative analysis directly compared traditional Superpave mixes to BMD mixes using hypothesis testing. Secondly, among BMD mixes, the study analyzed performance variations resulting from different mix constituents. Lastly, statistical regression analysis and machine learning techniques (gradient boosting algorithm and random forest models) were used to pinpoint the most influential factors affecting field performance. The findings are expected to offer insights into the successful application of BMD while contributing to a deeper understanding of pavement design and performance on a broader scale.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Breiman, L. (2001). Random forests. Machine learning, 45, 5–32.
Cross, S. A., and Li, J. (2019). Implement a balanced asphalt mix design in Oklahoma (No. FHWA-OK-19-01). Oklahoma. Department of Transportation.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 1189–1232.
Hajj, E. Y., Aschenbrener, T., and Nener-Plante, D. (2022). Examples of Successful Practices with State Implementation of Balanced Design of Asphalt Mixtures. Transportation Research Record, 2676(5), 44–66.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., and Grisel, O. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(Oct), 2825–2830.
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., and Van Mulbregt, P. (2020). SciPy 1.0: fundamental algorithms for scientific computing in Python. Nature Methods, 17(3), 261–272.
Zhou, F., Hu, S., and Newcomb, D. (2020). Development of a performance-related framework for production quality control with ideal cracking and rutting tests. Construction and Building Materials, 261, 120549.
Information & Authors
Information
Published In
History
Published online: Jun 13, 2024
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.