Non-destructive evaluation of concrete physical condition using radar and artificial neural networks
Autor: | K. Viriyametanont, G. Arliguie, Zoubir Mehdi Sbartaï, Stéphane Laurens, J.P. Balayssac |
---|---|
Přispěvatelé: | LABORATOIRE DE RHEOLOGIE DU BOIS DE BORDEAUX (LRBB), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Recherche Agronomique (INRA)-Université Sciences et Technologies - Bordeaux 1, Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées |
Jazyk: | angličtina |
Rok vydání: | 2009 |
Předmět: |
Engineering
[SDV]Life Sciences [q-bio] 0211 other engineering and technologies 02 engineering and technology Machine learning computer.software_genre 01 natural sciences WATER CONTENT RÉSEAU NEURONAL ARTIFICIEL law.invention CONCRETE law Non destructive 021105 building & construction 0103 physical sciences [SDV.IDA]Life Sciences [q-bio]/Food engineering CHLORIDE CONTENT General Materials Science [SPI.GPROC]Engineering Sciences [physics]/Chemical and Process Engineering TENEUR EN CHLORURE Radar 010301 acoustics Physics::Atmospheric and Oceanic Physics Civil and Structural Engineering Artificial neural network business.industry ARTIFICIAL NEURAL NETWORKS Statistical model ÉVALUATION NON DESTRUCTRICE Building and Construction Structural engineering Inverse problem RADAR NON-DESTRUCTIVE EVALUATION TECHNOLOGIE RADAR Artificial intelligence business computer |
Zdroj: | Construction and Building Materials Construction and Building Materials, Elsevier, 2009, 23 (2), pp.837-845. ⟨10.1016/j.conbuildmat.2008.04.002⟩ |
ISSN: | 0950-0618 |
Popis: | International audience; This paper deals with the combination of radar technology and artificial neural networks (ANN) for the non-destructive evaluation of the water and chloride contents of concrete. Two networks were trained and tested to predict these concrete properties. Input data to the statistical models were extracted from time-domain signals of direct and reflected radar waves. ANN training and testing were implemented according to an experimental database of 100 radar measurements performed on concrete slabs having various water and chloride contents. Both networks were multi-layer-perceptrons trained according to back-propagation algorithm. The results of this research highlight the potential of artificial neural networks for solving the inverse problem of concrete physical evaluation using radar measurements. It was found that the optimized statistical models predicted water and chloride contents of concrete laboratory slabs with maximum absolute errors of about 2% and 0.5 kg/m3 of concrete, respectively. |
Databáze: | OpenAIRE |
Externí odkaz: |