DeepSHM: A Deep Learning Approach for Structural Health　Monitoring Based on Guided Lamb Wave Techniques

摘要

In our previous work, we demonstrated how to use inductive bias to infuse a convolutional neural network (CNN) withdomain knowledge from fatigue analysis for aircraft visual NDE. We extend this concept to SHM and therefore in thispaper, we present a novel framework called DeepSHM which involves data augmentation of captured sensor signals andformalizes a generic method for end-to-end deep learning for SHM. The study case is limited to ultrasonic guided wavesSHM. The sensor signal response from a Finite-Element-Model (FEM) is pre-processed through wavelet transform toobtain the wavelet coefficient matrix (WCM), which is then fed into the CNN to be trained to obtain the neural weights.In this paper, we present the results of our investigation on CNN complexities that is needed to model the sensor signalsbased on simulation and experimental testing within the framework of DeepSHM concept.