Development of Artificial Neural Networks Based Predictive Models for Dynamic Modulus of Airfield Pavement Asphalt Mixtures

Thumbnail Image
Date
2018-07-11
Authors
Kaya, Orhan
Garg, Navneet
Ceylan, Halil
Kim, Sunghwan
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Person
Ceylan, Halil
Professor Professor
Research Projects
Organizational Units
Journal Issue
Is Version Of
Versions
Series
Department
Civil, Construction and Environmental EngineeringInstitute for TransportationInstitute for Transportation
Abstract

As part of asphalt mix design for flexible airfield pavements, the Federal Aviation Administration (FAA) collects asphalt volumetric mixture properties and aggregate gradations. Binder properties as well as laboratory dynamic modulus |E*| measurements for asphalt mixes are performed for flexible airfield pavements research. An artificial neural networks (ANN) model was developed using collected volumetric properties, aggregate gradation, and binder properties as well as laboratory |E*| measurements from seven hot-mix asphalt (HMA) and warm mix asphalt (WMA) mixtures. ANN model predictions were compared with the modified Witczak predictive model calculations for the same mixtures, and it was found that the developed ANN model successfully predicted |E*| for airfield pavement asphalt mixtures.

Comments

This proceeding is published as Kaya, Orhan, Navneet Garg, Halil Ceylan, and Sunghwan Kim. "Development of Artificial Neural Networks Based Predictive Models for Dynamic Modulus of Airfield Pavement Asphalt Mixtures." In International Conference on Transportation and Development (2018): 1-7. doi: 10.1061/9780784481554.001. Posted with permission.

Description
Keywords
Citation
DOI
Copyright