Details
| Original language | English |
|---|---|
| Journal | e-Journal of Nondestructive Testing |
| Volume | 29 |
| Issue number | 7 |
| Publication status | Published - Jul 2024 |
Abstract
Keywords
- composite, damage localization, domain adaptation, structural health monitoring, transfer learning
ASJC Scopus subject areas
- Health Professions(all)
- Health Information Management
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: e-Journal of Nondestructive Testing, Vol. 29, No. 7, 07.2024.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Exploring transfer learning for improving ultrasonic guided wave-based damage localization
AU - Lomazzi, Luca
AU - Pinello, Lucio
AU - Abbassi, Abderrahim
AU - Giglio, Marco
AU - Cadini, Francesco
N1 - Publisher Copyright: © 2024 11th European Workshop on Structural Health Monitoring, EWSHM 2024. All rights reserved.
PY - 2024/7
Y1 - 2024/7
N2 - Designing maintenance strategies to reduce the failure risk of plated structures is paramount for increasing the safety level of aerospace, civil and mechanical systems. Although traditional time-scheduled maintenance policies are reliable, they come with costly operations and avoidable downtimes. Recently, more complex condition-based strategies have been studied in the literature. This class of maintenance actions rely on structural health monitoring (SHM) frameworks: a sensor network is installed on the structure diagnostic data are processed to monitor the health state of the structure. The high dimensionality of data and the limitations of model-based SHM algorithms have led researchers to investigate data-driven solutions for improving the reliability of condition-based strategies. So far, supervised machine learning strategies have mainly been considered. However, since the cost of generating labeled datasets usually turns out to be prohibitive, two alternative solutions have gained attention: unsupervised methods and transfer learning (TL). While the former approach has been proved to provide satisfactory damage detection performance, it requires external knowledge sources to also localize and quantify damage. Instead, transfer learning could be used for performing all the damage diagnosis tasks, without the need for coupling the data-driven method with complex algorithms to restore the information lost by using smaller datasets for training. TL allows adapting pre-trained ML tools to new situations, new tasks and new environments. Moreover, TL can be leveraged when few labeled data are available, or to adapt efficient tools that have already been trained on a slightly different task. In this work, TL and convolutional neural networks (CNNs) were leveraged for performing damage localization and quantification in metal and composite plated structures. That is, an in-house CNN-based framework for localizing and quantifying structural damage was considered, and the fine-tuning TL technique was employed to make the framework flexible enough to work in different domains.
AB - Designing maintenance strategies to reduce the failure risk of plated structures is paramount for increasing the safety level of aerospace, civil and mechanical systems. Although traditional time-scheduled maintenance policies are reliable, they come with costly operations and avoidable downtimes. Recently, more complex condition-based strategies have been studied in the literature. This class of maintenance actions rely on structural health monitoring (SHM) frameworks: a sensor network is installed on the structure diagnostic data are processed to monitor the health state of the structure. The high dimensionality of data and the limitations of model-based SHM algorithms have led researchers to investigate data-driven solutions for improving the reliability of condition-based strategies. So far, supervised machine learning strategies have mainly been considered. However, since the cost of generating labeled datasets usually turns out to be prohibitive, two alternative solutions have gained attention: unsupervised methods and transfer learning (TL). While the former approach has been proved to provide satisfactory damage detection performance, it requires external knowledge sources to also localize and quantify damage. Instead, transfer learning could be used for performing all the damage diagnosis tasks, without the need for coupling the data-driven method with complex algorithms to restore the information lost by using smaller datasets for training. TL allows adapting pre-trained ML tools to new situations, new tasks and new environments. Moreover, TL can be leveraged when few labeled data are available, or to adapt efficient tools that have already been trained on a slightly different task. In this work, TL and convolutional neural networks (CNNs) were leveraged for performing damage localization and quantification in metal and composite plated structures. That is, an in-house CNN-based framework for localizing and quantifying structural damage was considered, and the fine-tuning TL technique was employed to make the framework flexible enough to work in different domains.
KW - composite
KW - damage localization
KW - domain adaptation
KW - structural health monitoring
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85202638448&partnerID=8YFLogxK
U2 - 10.58286/29685
DO - 10.58286/29685
M3 - Conference article
VL - 29
JO - e-Journal of Nondestructive Testing
JF - e-Journal of Nondestructive Testing
SN - 1435-4934
IS - 7
ER -