doiSerbia

Modeling the surface stored thermal energy in asphalt concrete pavements

Matić Bojan J. (Faculty of Technical Sciences, Novi Sad)
Salem Hasan Awadat (Faculty of Technical Sciences, Novi Sad)
Radonjanin Vlastimir S. (Faculty of Technical Sciences, Novi Sad)
Radović Nebojša M. (Faculty of Technical Sciences, Novi Sad)
Sremac Siniša R. (Faculty of Technical Sciences, Novi Sad)

Regression analysis is used to develop models for minimal daily pavement surface temperature, using minimal daily air temperature, day of the year, wind speed and solar radiation as predictors, based on data from Awbari, Lybia,. Results were compared with existing SHRP and LTPP models. This paper also presents the models to predict surface pavement temperature depending on the days of the year using neural networks. Four annual periods are defined and new models are formulated for each period. Models using neural networks are formed on the basis of data gathered on the territory of the Republic of Serbia and are valid for that territory.

Keywords: pavement, temperature, model, predicting, ANN, regression analysis, thermal energy

Projekat Ministarstva nauke Republike Srbije, br. TR 36017