Implementation of the modal flexibility variation to fault identification in thin plates

In this study a new two-stage procedure has been presented to localize various faults and their corresponding severity in thin plate structures. In the first stage, the variation of modal flexibility and the load-deflection differential equation of plate in conjunction with the invariant expression for the sum of transverse load are utilized to formulate the damage indicator; then an artificial neural network technique is employed to estimate the fault severity of identified parts. The validity of the proposed method is supported by the good correlation obtained between the results of the parametric study and experimental data.