RADAR ASSESSMENT OF STRUCTURAL CONCRETE USING NEURAL NETWORKS

An assessment of the capability of artificial neural networks to interpret radar images of reinforced concrete is presented. The capability of three-layer, fully connected networks to detect the presence of a bar, the size of a bar, and the depth of a bar is examined. The study demonstrates that the use of a neural network approach to interpret complex sub-surface radar results of embedded reinforcing bars is promising. The neural network approach is successful in locating reinforcing bars over a range of embedment depths on almost all occasions. In addition it is shown to be possible to place each bar into a depth category with a high degree of success.