Damage identification of honeycomb sandwich structures based on Lamb waves and 1D-CNN

Abstract

A specific method combining Lamb waves and 1D-CNN is proposed in this paper for damage assessment of honeycomb sandwich structures, which can identify the location and degree of damage simultaneously. The applicability of the Lamb waves method is verified by simulating the interaction between the Lamb waves and different degrees of damage on the honeycomb panel. In the experiment, four identical piezoelectric wafers were placed on a honeycomb plate in a square shape, and a mass block was placed inside to simulate damage. One of the sensors was used as an actuator to generate the Lamb waves signal, and the remaining three sensors received the response signals after interacting with the damage. The collected signals were denoised by Kalman filter, and the time domain signals were transformed into the frequency domain signals by Fourier transform, so as to extract the feature more effectively. The amplitude frequency characteristics of Lamb wave signals were used as inputs to the 1D-CNN model, and the damage categories were used as outputs. 365 samples were used for model testing, 364 were correctly identified with a correct recognition rate of 99.7 %. The result shows that the proposed method is feasible for damage identification of honeycomb sandwich structures.