Dadoulis, GeorgiosGeorgiosDadoulisManolis, GeorgeGeorgeManolisKatakalos, KonstantinosKonstantinosKatakalosAl-Zuriqat, ThamerThamerAl-ZuriqatDragos, KosmasKosmasDragosSmarsly, KayKaySmarsly2024-09-192024-09-192024-07Proceedings of the European Conference on Computing in Construction, EC3 2024: 511-518978-90-834513-0-5https://hdl.handle.net/11420/49123Lightweight bridges are subjected to moving loads (vehicular traffic), with vehicular masses typically being comparable to structural masses. Moving loads are thus regarded as “traveling masses”, resulting in complex dynamic behavior, which is hardly covered by conventional damage detection strategies. This paper presents a concept towards damage detection in lightweight bridges with traveling masses using machine learning (ML). Specifically, a ML model for classifying structural damage is trained, using simulations, and applied using real-world structural response data. Preliminary tests of the proposed concept validate the power of the ML model in identifying structural damage, despite the non-stationarity of the problem.enMLE@TUHHTechnology::690: Building, ConstructionConference Paper10.35490/EC3.2024.224Conference Paper