Experimental measurements and mathematical model of vehicle noise using artificial neural network

The road transport sector plays a vital role in economic development. Although it is an essential element in regional development schemes, it generates negative externalities, thus constituting one of the most important sources of environmental pollution. Indeed, noise pollution will continue to increase in magnitude and severity as a result of population growth, urbanisation and growth associated with automobile use. In this paper, we propose to model vehicle noise based on an experimental study of vehicle noise in three different sites. We implement an artificial neural network (ANN) to model vehicle and traffic noise. The results demonstrate that vehicle characteristics, traffic flow and infrastructure have an important influence on the noise level of road traffic. It is observed that the ANN model can predict traffic noise with a correlation coefficient in the range of 0.98-0.99, which demonstrates the efficiency of the developed model to estimate vehicle noise. © 2021 Inderscience Enterprises Ltd.. All rights reserved.