DeepSHM: A deep learning approach for structural health monitoring based on guided Lamb wave technique

Adrianus Ewald, V.; Groves, R.M.; Benedictus, R.

doi:10.1117/12.2506794

DeepSHM

Title

DeepSHM: A deep learning approach for structural health monitoring based on guided Lamb wave technique

Author

Adrianus Ewald, V. (TU Delft Structural Integrity & Composites)
Groves, R.M. (TU Delft Structural Integrity & Composites)
Benedictus, R. (TU Delft Structural Integrity & Composites)

Contributor

Lynch, Jerome P. (editor)
Sohn, Hoon (editor)
Wang, Kon-Well (editor)
Huang, Haiying (editor)

Date

2019

Abstract

In our previous work, we demonstrated how to use inductive bias to infuse a convolutional neural network (CNN) with domain knowledge from fatigue analysis for aircraft visual NDE. We extend this concept to SHM and therefore in this paper, we present a novel framework called DeepSHM which involves data augmentation of captured sensor signals and formalizes a generic method for end-to-end deep learning for SHM. The study case is limited to ultrasonic guided waves SHM. The sensor signal response from a Finite-Element-Model (FEM) is pre-processed through wavelet transform to obtain 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 signals based on simulation and experimental testing within the framework of DeepSHM concept.

Subject

convolutional neural network (CNN)
damage classification
deep learning
Finite-Element-Modelling (FEM)
guided Lamb wave
signal processing
Structural Health Monitoring (SHM)

To reference this document use:

http://resolver.tudelft.nl/uuid:0ca117b3-6ee4-4267-a581-984fc108d37a

DOI

https://doi.org/10.1117/12.2506794

Publisher

SPIE

ISBN

9781510625952

Source

Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2019, 10970