Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Physical and geometrical characterization of reinforced concrete using radar and artificial neural networks
Radar technology is increasingly implemented on reinforced concrete (RC) structures, but it is often limited to the assessment of concrete cover or element thickness. However, the electromagnetic response of the surveyed element encloses more information related to moisture content and also reinforcement diameter. Therefore, the purpose of this work is focused on the application of radar to the physical and geometrical characterization of reinforced concrete elements according to a statistical approach based on the concept of artificial neural networks. Radar measurements (B-scan) were carried out on RC specimens made and controlled in the laboratory. These experiments generated a statistical database composed of more than 500 patterns relating radar B-scan signatures to physical and geometrical characteristics of RC specimens. The database was used to train neural models able to recognize radar signatures and to extract information such as moisture content of concrete and reinforcement depth and diameter. The developed models were tested on a real concrete structure.
Physical and geometrical characterization of reinforced concrete using radar and artificial neural networks
Radar technology is increasingly implemented on reinforced concrete (RC) structures, but it is often limited to the assessment of concrete cover or element thickness. However, the electromagnetic response of the surveyed element encloses more information related to moisture content and also reinforcement diameter. Therefore, the purpose of this work is focused on the application of radar to the physical and geometrical characterization of reinforced concrete elements according to a statistical approach based on the concept of artificial neural networks. Radar measurements (B-scan) were carried out on RC specimens made and controlled in the laboratory. These experiments generated a statistical database composed of more than 500 patterns relating radar B-scan signatures to physical and geometrical characteristics of RC specimens. The database was used to train neural models able to recognize radar signatures and to extract information such as moisture content of concrete and reinforcement depth and diameter. The developed models were tested on a real concrete structure.
Physical and geometrical characterization of reinforced concrete using radar and artificial neural networks
Physikalische und geometrische Beschreibung von Stahlbeton mittels Radar und neuronalen Netzwerken
Laurens, Stephane (Autor:in) / Viriyametanont, Kriengkai (Autor:in) / Sbartai, Zoubir Mehdi (Autor:in) / Balyssac, Jean-Paul (Autor:in)
2009
6 Seiten, 11 Bilder, 2 Tabellen, 13 Quellen
(nicht paginiert)
Aufsatz (Konferenz)
Datenträger
Englisch
Non-destructive evaluation of concrete physical condition using radar and artificial neural networks
| Online Contents | 2009
Non-destructive evaluation of concrete physical condition using radar and artificial neural networks
| British Library Online Contents | 2009
Non-destructive evaluation of concrete physical condition using radar and artificial neural networks
| Online Contents | 2009
Prediction of Target Displacement of Reinforced Concrete Frames Using Artificial Neural Networks
| British Library Conference Proceedings | 2011