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.

Pavements are layered systems from both the geometrical and physical points of view. Flexible pavements most often include a sequence of asphalt layers, typically composed of the wearing course, binder course and base course. So far, there is no definite analytical solution of such a layered system in relation to the temperature distribution that would consider different thermal properties of the respective layers and follow the physical laws of the thermal wave nature of heat propagation. This being so, we are unable to assess the effect of the thermal properties of the respective pavement courses on the overall temperature distribution in the asphalt portion. In multi-layer pavement systems also important are the phenomena taking place at the interfaces between the pavement courses which have a bearing on the service life of pavement. This article presents a newanalytical solution to the problem of heat conduction and refraction in a multi-layer pavement. The solution was used to investigate and determine the effect of wave mode of heat propagation on the vertical temperature distribution, this considering that the pavement system is a sequence of layers comprising the soil subgrade, the base course and the wearing course. Moreover, the classical heat conduction equation is compared with the wave mode equation for a multi-layer pavement system and the temperature distribution in a layered system is compared with the temperature distribution in its homogenized equivalent. The solution of the heat conduction problem in a layered system showed a considerable effect of the thermal compatibility coefficients introduced by the authors and of the thermal refraction of the respective layers on the temperature distribution throughout the multi-layer pavement system. The output of this research includes prediction of the vertical temperature distribution in the pavement and definition of guidelines for reducing the effect of changing climatic conditions on the operation of layered flexible road and airfield pavements. In addition, the research results expand the toolkit for assessing the thermal effect on the actual pavements.