An intelligent tap test as an inspection tool for corrosion in chequer plate floors

The coin-tap test has the ability to indicate damage in a structural element due to a localized change of stiffness or damping. The change in vibration signature may be detected by ear or more precisely by measurement of the dynamic contact force. A method for discriminating between measurements made on sound and damaged structures is presented. An unsupervised neural network algorithm is used for recognizing the differences between contact force patterns. The method is used for non-destructive inspection of corrosion damage to steel chequer plate floors in industrial buildings. It is shown that the intelligent tap test is a useful and practical diagnostic tool for detecting localized damage in structures. © 2002 Elsevier Science Ltd. All rights reserved