Prediction of asphalt concrete flexibility index and rut depth utilising deep learning and Monte Carlo Dropout simulation

ABSTRACT

Asphalt concrete (AC) balanced mix design (BMD) relies on laboratory testing to meet both the Illinois Flexibility Index Test (I-FIT) and the Hamburg Wheel Tracking Test (HWTT) by varying aggregate gradations and asphalt cement contents. AC mix designers would benefit from estimating the impact of constituent materials’ properties on I-FIT and HWTT before conducting a BMD trial. This study focused on the development of two deep learning models to predict I-FIT flexibility index (FI) and HWTT rut depth. The models were created based on a I-FIT database of 19,138 datasets and a HWTT database of 7602 datasets (after data preprocessing was conducted). Two deep neural networks (DNNs) were then trained to predict FI and rut depth. Monte Carlo Dropout simulations were then used in the DNN models to compute a distribution of predicted FI and rut depth. The distribution of predicted FI and rut depth provides a best estimate and range of FI and rut depth. The developed models provide a distribution of predictions with a coefficient of variation (CoV) lower than 30% for both the I-FIT and HWTT models, respectively.

KEYWORDS:

• Asphalt concrete
• flexibility index
• rut depth
• machine learning
• deep learning

Acknowledgements

The research was conducted in cooperation with the Illinois Department of Transportation. The authors appreciate the help of IDOT Materials technicians and engineers in all District and Central Bureau of Materials laboratories for providing the data used to build the database. The contents of this paper reflect the views of the authors, who are responsible for the facts and the accuracy of the data presented herein. The contents do not necessarily reflect the official views or policies of the Illinois Center for Transportation or the Illinois Department of Transportation. The authors acknowledge the support of Dr. Egemen Okte and Qingwen Zhou during the model development. The authors confirm that all authors contributed contribution to the paper as follows: study conception and design: José Rivera-Pérez and Imad L. Al-Qadi; data collection: José Rivera-Pérez; analysis and interpretation of results: José Rivera-Pérez and Imad L. Al-Qadi; draft manuscript preparation: José Rivera-Pérez and Imad L. Al-Qadi. All authors reviewed the results and approved the final version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

All data, models, and code used during the study are proprietary or confidential in nature. The data are owned and managed by the Illinois Department of Transportation. The data may only be provided with restrictions (e.g. anonymised data) upon reasonable request and with the authorisation of both stakeholders. For more information of how the data can be requested contact the corresponding José Rivera-Pérez author at: [email protected].