Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2019 2019
DOI: 10.1117/12.2506794
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: A deep learning approach for structural health monitoring based on guided Lamb wave technique Ewald, Vincentius; Groves, Roger M.; Benedictus, Rinze ABSTRACTIn 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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
40
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
5
3

Relationship

1
7

Authors

Journals

citations
Cited by 48 publications
(40 citation statements)
references
References 30 publications
0
40
0
Order By: Relevance
“…By using decision tree methods or random cross-validation with different features combinations, one could rank the most important features, and use these to inform the approach taken, saving time and providing simpler solutions. From the ML viewpoint, a data augmentation approach [41], [66] can be addressed for both the simulated and experimental datasets of this work. Another approach would be addressing each of the mode separation datasets…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…By using decision tree methods or random cross-validation with different features combinations, one could rank the most important features, and use these to inform the approach taken, saving time and providing simpler solutions. From the ML viewpoint, a data augmentation approach [41], [66] can be addressed for both the simulated and experimental datasets of this work. Another approach would be addressing each of the mode separation datasets…”
Section: Discussionmentioning
confidence: 99%
“…Melville et al [40] employed convolutional neural networks to estimate the damage level of a thin metal plate, emulated by a steel washer, using full wavefield measured data. DL is also explored with Lamb waves, in which, wavelet coefficients are extracted and used as inputs of the models [41]. Moreover, Hesser et al [42] have proposed an active source localization to predict the impact position of a steel ball in an aluminium plate, using numerical simulations to train and experimental data to validate ML models.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…In addition to CS, other techniques in data science and engineering also attract attention in the field of structural health monitoring [31]. A novel framework called DeepSHM was presented to classify damage using deep learning (DL) [32]. It trained the neural weights by wavelet coefficient matrix and extracted feature patterns.…”
Section: Related Workmentioning
confidence: 99%
“…existence, location, size, and type of damage) which is dependent on the captured signal X Π , T , Ψ , Ω , and influenced by parameter tuples Π , T , Ψ , Ω , which correspond to actor, transitional, medium, and environmental domain, respectively. A detailed explanation of these parameters can be found in Ewald et al, 25 and to summarize we depict the above-mentioned parameters in Figure 1. Equation (1) can be understood by considering that the posterior belief P ( h θ ( X Π , T , Ψ , Ω )| X Π , T , Ψ , Ω ) is equal to the multiplication of the prior belief P ( X Π , T , Ψ , Ω ) by the likelihood P ( X Π , T , Ψ , Ω | h θ ( X Π , T , Ψ , Ω) ) that X Π , T , Ψ , Ω will occur given that h θ is true.…”
Section: Theorymentioning
confidence: 99%