Detection of anomalies in bridge waterproof membrane using artificial intelligence applied to GPR - Université Gustave Eiffel
Communication Dans Un Congrès Année : 2022

Detection of anomalies in bridge waterproof membrane using artificial intelligence applied to GPR

Résumé

Evaluation of bridge deck waterproofing membrane is essential to assess the durability of the whole structure from the surface (pavement) to the subsurface (bridge structure). Maintenance, rehabilitation and redesign strategies require road surface information for decisive actions by profound analysis. The objective of this project is to develop an innovative 3D electromagnetic mapping showing accurately water leakage in concrete layers of the bridge deck. Non-Destructive Testing (NDT) can detect critical damages that cannot be detected using visual inspection. In this scope, due to their sensitivity to water content, Electromagnetic waves, especially Ground Penetrating Radar (GPR) may provide a strong means to evaluate the safety and reliability of a bridge. The aim of the present work is to detect and characterize water leakage in a concrete bridge deck using detailed analysis of the radar signal from a Stepped-frequency Radar (SFR). We use an approach based on the coupling between the Full-Waveform Inversion (FWI) and a supervised learning method applied in local and global approaches to C-scans, obtained at first from SFR output data modelling.
Fichier principal
Vignette du fichier
DSPS_Abstract_Buliuk_V_cor.pdf (358.69 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04296197 , version 1 (20-11-2023)

Identifiants

  • HAL Id : hal-04296197 , version 1

Citer

V. Buliuk, C. Heinkele, Amine Ihamouten, R. Jaufer, Shreedhar Savant Todkar, et al.. Detection of anomalies in bridge waterproof membrane using artificial intelligence applied to GPR. Data Science in Pavement Symposium, Mar 2022, Mclean, United States. ⟨hal-04296197⟩
59 Consultations
46 Téléchargements

Partager

More