Damage identification in a ship's structure using neural networks

Visual inspection of large and complex structures such as a ship is difficult and costly due to problems of accessibility. In this paper, a neural network technique is developed for identifying the damage occurrence in the side shell of a ship's structure. The side shell is modeled as a stiffened plate. The input to the network is the autocorrelation function of the vibration response of the structure. The response was obtained using a finite element model of the structure. The output is a single function G(r)(z(r),z(r)), which was formed by adding together the damping and a part of the restoring forces. The function is used to identify not only the damage occurrence in the model but also its extent and location. The results show that the method presented in this work is successful in identifying the occurrence of damage. The detection of the extent and location of damage is promising, however, more work has to be done in this area. (C) 2002 Elsevier Science Ltd. All rights reserved.