Delamination Detection Framework for the Imbalanced Dataset in Laminated Composite Using Wasserstein Generative Adversarial Network-Based Data Augmentation
Applied Sciences · 29.10.2023 · 13 (21) · 11837
DOI: 10.3390/app132111837 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.10.2023. Verfasst von Sungjun Kim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Fostering Global Talents for Innovative Growth Program.
Abstract (Originalsprache)
As laminated composites are applied more commonly, Prognostics and Health Management (PHM) techniques for the maintenance of composite systems are also attracting attention. However, applying PHM techniques to a composite system is challenging due to the data imbalance problem from the lack of failure data and unpredictable failure cases. Despite numerous studies conducted to address this limitation, including techniques like data augmentation and transfer learning, significant challenges remain. In this study, the Wasserstein Generative Adversarial Network (WGAN) model using a time-series data augmentation technique is proposed as a solution to the data imbalance problem. To ensure the performance of the WGAN model, time-series data augmentation of experimental data is executed with a frequency analysis. After that, a One-Dimensional Convolutional Neural Network (1D CNN) is used for fault diagnosis in laminated composites, validating the performance improvement after data augmentation. The proposed data augmentation significantly elevated the performance of the 1D CNN classification model compared to its non-augmented counterpart. Specifically, the accuracy increased from 89.20% to 91.96%. The precision improved remarkably from 29.76% to 74.10%, and its sensitivity rose from 33.33% to 94.39%. Collectively, these enhancements highlight the vital role of data augmentation in improving fault diagnosis performance.
Förderung
- National Research Foundation of Korea
- Fostering Global Talents for Innovative Growth Program
Zitieren
APA
Kim, S., Azad, M. M., Song, J., & Kim, H. (2023). Delamination Detection Framework for the Imbalanced Dataset in Laminated Composite Using Wasserstein Generative Adversarial Network-Based Data Augmentation. Applied Sciences, 13(21), 11837. https://doi.org/10.3390/app132111837
Vancouver
Kim S, Azad MM, Song J, Kim H. Delamination Detection Framework for the Imbalanced Dataset in Laminated Composite Using Wasserstein Generative Adversarial Network-Based Data Augmentation. Applied Sciences. 2023;13(21):11837. doi:10.3390/app132111837
BibTeX
@article{Kim2023,
author = {Kim, Sungjun and Azad, Muhammad Muzammil and Song, Jinwoo and Kim, Heungsoo},
title = {Delamination Detection Framework for the Imbalanced Dataset in Laminated Composite Using Wasserstein Generative Adversarial Network-Based Data Augmentation},
journal = {Applied Sciences},
year = {2023},
volume = {13},
number = {21},
pages = {11837},
doi = {10.3390/app132111837}
}
EUVIMED