Location of steel reinforcement in concrete using ground penetrating radar and neural networks: Fid-Bau Portal

Location of steel reinforcement in concrete using ground penetrating radar and neural networks

Shaw, M.R. / Millard, S.G. / Molyneaux, T.C.K. / Taylor, M.J. / Bungey, J.H.

Ground-penetrating radar is becoming increasingly popular for use as a non-destructive assessment method for investigating reinforced concrete structures. The amount of data collected however can be very large and take a significant level of subjective experience to interpret. This study focuses upon the use of a neural network approach to automate and facilitate the post-processing of ground penetrating radar results. The radar data is reduced to a simplified data set by using an edge detection routine. Signal reflections from reinforcing bars displaying a hyperbolic image format are detected using a multi-layer perceptron (MLP) network with a single hidden layer containing 8 nodes to recognise a simplified hyperbolic shape. Training and testing of the network was carried out making use of an emulsion analogue tank, simulating the properties of concrete, and using real concrete specimens. The potential for automatic neural network analysis of GPR results from steel reinforcing bars embedded in concrete has been demonstrated. The large amount of data generated by a typical GPR image cannot be directly applied to a neural network, and a pre-processing procedure to reduce this to a manageable level has been proposed. This reduced data can then be analysed by a MLP network that has been developed, coupled to an artificial intelligence inference strategy. An encouraging level of success has been achieved in terms of bar identification, lateral positioning and depth estimation. The evaluation of the depth of a bar may potentially be improved by a more reliable knowledge of in situ dielectric properties resulting from development of the horn antenna system. This yields promising results but requires further development and refinement.