Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks

Gdańsk University of Technology, Faculty of Civil and Environmental Engineering, Narutowicza 11/12, 80-233 Gdańsk, Poland

^* Corresponding author: annjakub@pg.gda.pl

Abstract

Traffic–induced vibrations may constitute a considerable load to a building, cause cracking of plaster, cracks in load–bearing elements or even a global structural collapse of the whole structure [1-4]. Vibrations measurements of real structures are costly and laborious, not justified in all cases. The aim of the paper is to create an original algorithm, to predict the negative dynamic impact on the examined residential building with a high probability. The model to forecast the impact of vibrations on buildings is based on artificial neural networks [5]. The author’s own field studies carried out according to the Polish standard [6] and literature examples [7-10] have been used to create the algorithms. The results of the conducted analysis show that an artificial neural network can be considered a good tool to predict the impact of traffic–induced vibrations on residential buildings, with a sufficiently high reliability.