EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Transfer Learning Approach for Localization of Damage Area in Composite Laminates Using Acoustic Emission Signal

Jingyu Zhao iD, Weihua Xie iD, Dong Yu iD, Qiang Yang, Songhe Meng, Qihui Lyu

Polymers · 19.03.2023 · 15 (6) · 1520

DOI: 10.3390/polym15061520 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Polymers, online erschienen am 19.03.2023. Verfasst von Jingyu Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Science and Technology on Advanced Composites in Special Environment Laboratory, Harbin Institute of Technology, Harbin 150080, China. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science Foundation of National Key Laboratory of Science and Technology on Advanced Com-posites in Special Environments, Science Foundation of National Key Laboratory of Science and Technology on Advanced Composites in Special Environments.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent composite structures with self-aware functions are preferable for future aircrafts. The real-time location of damaged areas of composites is a key step. In this study, deep transfer learning was used to achieve the real-time location of damaged areas. The sensor network obtained acoustic emission signals from different damaged areas of the aluminum alloy plate. The acoustic emission time-domain signal is transformed into the input image by continuous wavelet transform. The convolutional neural network-based model automatically localized the damaged area by extracting features from the input image. A small amount of composite acoustic emission data was used to fine-tune some network parameters of the basic model through transfer learning. This enabled the model to classify the damaged area of composites. The accuracy of the transfer learning model trained with 900 samples is 96.38%, which is comparable to the accuracy of the model trained directly with 1800 samples; the training time of the former is only 17.68% of that of the latter. The proposed method can be easily adapted to new composite structures using transfer learning and a small dataset, providing a new idea for structural health monitoring.

Schlagwörter

Stichwörter der Autor:innen

acoustic emissioncompositesdamage localizationdeep transfer learning

Autor:innen und Institutionen

  • Science and Technology on Advanced Composites in Special Environment Laboratory, Harbin Institute of Technology, Harbin 150080, China.
  • School of Science, Harbin Institute of Technology, Shenzhen 518055, China.

ORCID-Profile: Jingyu Zhao, Weihua Xie, Dong Yu

Förderung

  • National Natural Science Foundation of China
  • Science Foundation of National Key Laboratory of Science and Technology on Advanced Com-posites in Special Environments
  • Science Foundation of National Key Laboratory of Science and Technology on Advanced Composites in Special Environments

Zitieren

APA

Zhao, J., Xie, W., Yu, D., Yang, Q., Meng, S., & Lyu, Q. (2023). Deep Transfer Learning Approach for Localization of Damage Area in Composite Laminates Using Acoustic Emission Signal. Polymers, 15(6), 1520. https://doi.org/10.3390/polym15061520

Vancouver

Zhao J, Xie W, Yu D, Yang Q, Meng S, Lyu Q. Deep Transfer Learning Approach for Localization of Damage Area in Composite Laminates Using Acoustic Emission Signal. Polymers. 2023;15(6):1520. doi:10.3390/polym15061520

BibTeX
@article{Zhao2023,
  author = {Zhao, Jingyu and Xie, Weihua and Yu, Dong and Yang, Qiang and Meng, Songhe and Lyu, Qihui},
  title = {Deep Transfer Learning Approach for Localization of Damage Area in Composite Laminates Using Acoustic Emission Signal},
  journal = {Polymers},
  year = {2023},
  volume = {15},
  number = {6},
  pages = {1520},
  doi = {10.3390/polym15061520}
}
Kostenlos starten →