Detection of the Presence of Rail Corrugation Using Convolutional Neural Network
[ 1 ] Instytut Mechaniki Stosowanej, Wydział Inżynierii Mechanicznej, Politechnika Poznańska | [ 2 ] Instytut Transportu, Wydział Inżynierii Lądowej i Transportu, Politechnika Poznańska | [ P ] employee
[2.7] Civil engineering, geodesy and transport[2.9] Mechanical engineering
2022
scientific article
english
- corrugation
- vibration and noise
- machine learning
- convolutional networks
EN Rail corrugation is a significant problem not only in heavy-haul freight but also in light rail systems. Over the last years, considerable progress has been made in understanding, measuring and treating corrugation problems also considered a matter of safety. In the presented research, convolutional neural networks (CNNs) are used to identify the occurrence of rail corrugation in light rail systems. The paper shows that by simultaneously measuring the vibration and the sound pressure, it is possible to identify the rail corrugation with a very small error.
339 - 353
CC BY-SA (attribution - share alike)
open journal
final published version
public
70