A Proposed Machine Learning Model for Forecasting Impact of Traffic-Induced Vibrations on Buildings

Traffic-induced vibrations may cause various damages to buildings located near the road, including cracking of plaster, cracks in load-bearing elements or even collapse of the whole structure. Measurements of vibrations of real buildings are costly and laborious. Therefore the aim of the research is to propose the original numerical algorithm which allows us to predict, with high probability, the negative dynamic impact of traffic-induced vibrations on the examined building. The model has been based on machine learning. Firstly, the experimental tests have been conducted on different buildings using specialized equipment taking into account six factors: distance from the building to the edge of the road, type of surface, condition of road surface, condition of the building, the absorption of soil and the type of vehicle. Then, the numerical algorithm based on machine learning (using support vector machine) has been created. The results of the conducted analysis clearly show that the method can be considered as a good tool for predicting the impact of traffic-induced vibrations on buildings, being characterized by high reliability.