journal article·2009-02

Non-destructive evaluation of concrete physical condition using radar and artificial neural networks

Z.M. Sbartaï, S. Laurens, K. Viriyametanont, J.P. Balayssac, G. Arliguie

Publisher page

Abstract

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.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Geophysical Methods and Applications · Non-Destructive Testing Techniques · Ultrasonics and Acoustic Wave Propagation

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (37)

Show source-provided references
1. Relative humidity in interior of concrete exposed to natural and artificial weathering10.1016/S0008-8846(99)00123-4 ↗
2. Chlorides-induced macrocell corrosion of steel in concrete – theoretical background and practical consequences10.1016/0950-0618(95)00018-6 ↗
3. Moisture measurements in building materials with microwaves10.1016/S0963-8695(01)00005-6 ↗
4. Matthews S, Goodier A, Massey S. Permittivity measurements and analytical dielectric modelling of plain structural concretes. In: Proceedings of the seventh international conference on ground-penetrating radar, Kansas USA: Laurence; 1998. p. 363–8.
5. Laurens S. Aptitude de la technique radar à la caractérisation du béton d’enrobage-Aide au diagnostic de la corrosion des armatures. Civil engineering doctoral thesis, INSA de Toulouse (France), University of Sherbrooke, Sherbrooke (Québec, Canada); 2001.
6. Spectral analysis of radar surface waves for non-destructive evaluation of cover concrete10.1016/j.ndteint.2003.09.006 ↗
7. Sbartaï ZM. Caractérisation physique des bétons par radar – approche neuromimétique de l’inversion. Civil engineering doctoral thesis. Université Paul Sabatier, Toulouse III (France). University of Sherbrooke, Sherbrooke (Québec, Canada); 2005.
8. Ability of the direct wave of radar ground-coupled antenna for NDT of concrete structures10.1016/j.ndteint.2005.11.003 ↗
9. Effect of concrete moisture on radar signal amplitude
10. Detection of chlorides in concrete using low radio frequency10.1061/(ASCE)0899-1561(1997)9:1(29) ↗
11. Dielectric permittivity of concrete between 50MHz and 1GHz and GPR measurements for building materials evaluation10.1016/S0926-9851(98)00009-3 ↗
12. Dielectric properties of concrete and their influence on radar testing10.1016/S0963-8695(01)00009-3 ↗
13. Field pattern characteristics of GPR antennas10.1016/S0963-8695(02)00023-3 ↗
14. Simulation of direct wave propagation by numerical FDTD for a GPR coupled antenna10.1016/j.ndteint.2005.10.001 ↗
15. Modelling the electromagnetic properties of concrete
16. Analytical modelling of the dielectric properties of concrete for subsurface radar applications10.1016/S0950-0618(97)00033-0 ↗
17. Dreyfus G, Martinez J-M, Samuelides M, Gordon MB, Badran F, Thiria S, Hérault L. Réseaux de neurones, Méthodologie et applications. Edition Eyrolles; 2002.
18. Modelling of strength of high-performance concrete using artificial neural networks10.1016/S0008-8846(98)00165-3 ↗
19. Prediction of compressive strength of concrete by neural networks10.1016/S0008-8846(00)00345-8 ↗
20. Neural networks for predicting properties of concretes with admixtures10.1016/S0950-0618(01)00006-X ↗
21. Predicting performance of self-compacting concrete mixtures using artificial neural networks
22. Neural network model for performed-foam cellular concrete
23. Artificial neural networks in predicting of concrete strength reduction due to high temperature
24. Extracting dimensional information from steel reinforcing bars in concrete using neural networks trained on data from an inductive sensor10.1016/j.ndteint.2004.02.005 ↗
25. New technique of non-destructive assessment of concrete strength using artificial intelligence10.1016/j.ndteint.2004.08.002 ↗
26. Radar signal interpretation using neural network for detection in concrete
27. Radar assessment of structural concrete using neural networks10.1016/0963-8695(95)00027-U ↗
28. Location of steel reinforcement in concrete using ground penetrating radar and neural networks10.1016/j.ndteint.2004.06.011 ↗
29. Non-destructive inspection of overlaid bridge decks with ground penetrating radar
30. Daniels · 1996
31. Sub-surface radar testing of concrete: a review10.1016/S0950-0618(03)00093-X ↗
32. Neural network design for engineering applications10.1016/S0045-7949(01)00039-6 ↗
33. Jodouin J-F. Les réseaux de neurones principe et définitions. Edition Hermès, Paris; 1994.
34. Bishop · 1995
35. Learning internal representations by error propagation
36. Generalization by weight elimination with application to forecasting
37. Generalization and parameter estimation in feed-forward nets: some experiments