Prediction of Asphalt Creep Compliance Using Artificial Neural Networks: Fid-Bau Portal

Prediction of Asphalt Creep Compliance Using Artificial Neural Networks

Zofka, A. / Yut, I.

Abstract Creep compliance of the hot-mix asphalt (HMA) is a primary input of the current pavement thermal cracking prediction model used in the US. This paper discusses a process of training an Artificial Neural Network (ANN) to correlate the creep compliance values obtained from the Indirect Tension (IDT) with similar values obtained on small HMA beams from the Bending Beam Rheometer (BBR). In addition, ANNs are also trained to predict HMA creep compliance from the creep compliance of asphalt binder and vice versa using the BBR setup. All trained ANNs exhibited a very high correlation of 97 to 99 percent between predicted and measured values. The binder creep compliance functions built on the ANN-predicted discrete values also exhibited a good correlation when compared with the laboratory experiments. However, the simulation of trained ANNs on the independent dataset produced a significant deviation from the measured values which was most likely caused by the differences in material composition, such as aggregate type and gradation, presence of recycled additives, and binder type.

Extended Abstract Creep compliance of the hot-mix asphalt (HMA) is a primary input of the pavement thermal cracking prediction model in the recently developed Mechanistic-Empirical Pavement Design Guide (M-EPDG) in the US. The HMA creep compliance is typically determined from the Indirect Tension (IDT) tests and requires complex experimental setup. On the other hand, creep compliance of asphalt binders is determined from a relatively simple three- point bending test performed in the Bending Beam Rheometer (BBR) device. This paper discusses a process of training an Artificial Neural Network (ANN) to correlate the creep compliance values obtained from the IDT with those from an innovative approach of testing HMA beams in the BBR. In addition, ANNs are also trained to predict HMA creep compliance from the creep compliance of asphalt binder and vice versa using the BBR setup. All trained ANNs exhibited a very high correlation of 97 to 99 percent between predicted and measured values. The binder creep compliance curves built on the ANN-predicted values also exhibited good correlation with those obtained from laboratory experiments. However, the simulation of trained ANNs on the independent dataset produced a significant deviation from the expected values which was most likely caused by the differences in material composition, such as aggregate type and gradation, presence of recycled additives, and binder type.