Redevelopment of Artificial Neural Networks for Predicting the Response of Bonded Concrete Overlays of Asphalt for use in a Faulting Prediction Model

Abstract

Transverse joint faulting is a common distress in bonded concrete overlays of asphalt pavements (BCOAs), also known as whitetopping. However, to date, there is no predictive faulting model available for these structures. Therefore, the intended research is to develop a predictive faulting model for BCOAs. In addition, it is important to be able to account for conditions unique to BCOA when characterizing the response in a faulting prediction model. To address this, computational models were developed using a three-dimensional finite element program, ABAQUS, to accurately predict the response of these structures. These models account for different depths of joint activation, as well as full and partial bonding between the concrete overlay and existing asphalt pavement. The models were validated with falling weight deflectometer (FWD) data from existing field sections at the Minnesota Road Research Facility (MnROAD) as well as at the University of California Pavement Research Center (UCPRC). A fractional factorial analysis was executed using the computational models to generate a database to be used in the development of the predictive models. The predictive models, based on artificial neural networks (ANNs), are used to rapidly estimate the structural response at the joint in BCOA to environmental and traffic loads so that these responses can be incorporated into the design process. The structural response obtained using the ANNs is related to damage using the differential energy concept. Future work includes the implementation of the ANNs developed in this study into a faulting prediction model for designing BCOA.