Article de journal
Using artificial neural network and non-destructive test for crack detection in concrete surrounding the embedded steel reinforcement

Domaines de Recherche
Currently no objects available

Détails sur la publication
Liste des auteurs: Muhammad Saleem,Hector Gutierrez,
Editeur: Thomas Telford (ICE Publishing) / Wiley-VCH Verlag / Ernst und Sohn: OnlineOpen
Année de publication: 2021
Journal: Structural Concrete
Numéro du volume: 1
Numéro de publication: 1
Page d'accueil: 1
Dernière page: 19
Nombre de pages: 19
ISSN: 1464-4177
Web of Science ID: 000662871700001
Scopus ID: 85107746587
eISSN: 1751-7648

Bond between steel and concrete is one of the key aspects of structural design and its performance evaluation. In the past much research work has been focused on understanding bond deterioration owing to corrosion of reinforcement, however, there exists no nondestructive method to access the bond condition. In this regard, the presented experimental research work details the development of a nondestructive testing method to estimate the crack condition of concrete surrounding the steel reinforced by using ultrasonic pulse velocity test. In addition, a multilayer feedforward back propagation perceptron artificial neural network (ANN) is developed in order to avoid simplification assumptions for developing models to predict the cracking, owing to the nonlinear complex stress distribution at the steel-concrete interface. The ANN is used to predict the crack width and to conduct sensitivity analysis of the various factors influencing the bond deterioration. A high accuracy level is achieved between the predicted and the experimental values with R2 of 0.97 and the most influential parameter is highlighted.

Currently no objects available

Currently no objects available

Currently no objects available

Dernière mise à jour le 2021-13-09 à 10:03