Identification of complex crack damage for honeycomb sandwich plate using wavelet analysis and neural networks

In this study, crack damage detection for a honeycomb sandwich plate is studied using the energy spectrum of dynamic response decomposed by wavelet transform and the artificial neural network (NN). The results show that taking the energy spectrum of the decomposed wavelet signals of dynamic responses as the inputs of the NN can simplify the NN design for structural damage detection and it possesses a high sensitivity to small damage. Experimental results also show that the NN designed in this study can accurately detect multiple damage parameters or give some significant reference range of the damage parameters.