EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantitative Damage Detection and Evolution in Composite Structures Using Digital Image Correlation, Machine Learning, and Peridynamics

Tomas Vaitkūnas iD, Elena Jasiūnienė iD, Justas Griškevičius iD, Vykintas Samaitis iD, Paulius Griškevičius iD

Materials · 07.05.2026 · 19 (10) · 1917

DOI: 10.3390/ma19101917 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 07.05.2026. Verfasst von Tomas Vaitkūnas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Kaunas University of Technology, Studentu Str. 56, LT-51424 Kaunas, Lithuania. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Lithuania (LMTLT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structural health monitoring (SHM) of composite structures using surface strain fields measured by digital image correlation (DIC) has been widely demonstrated; however, accurate damage quantification remains challenging. This study proposes a hybrid framework integrating finite element (FE) modeling, machine learning (ML), and peridynamics (PD). A CFRP specimen with a notch was subjected to cyclic loading, and damage evolution was monitored using DIC and validated by ultrasound measurements. A validated FE model generated synthetic strain-field datasets for ML training, enabling defect detection and quantitative characterization directly from surface strains. The trained models achieved high accuracy, including perfect notch detection and low prediction errors. A calibrated PD model captured internal damage evolution and fatigue behavior. The combined DIC–ML–PD approach enables accurate, non-contact damage identification and prognosis, supporting physics-informed digital twins for composite structures.

Schlagwörter

Stichwörter der Autor:innen

composite materialsdamage detectiondamage evolutiondigital image correlationfatigueinverse identificationmachine learningperidynamicsstructural health monitoring

Autor:innen und Institutionen

  • Department of Mechanical Engineering, Kaunas University of Technology, Studentu Str. 56, LT-51424 Kaunas, Lithuania.
  • Department of Electronics Engineering, Kaunas University of Technology, Studentu Str. 50, LT-51368 Kaunas, Lithuania.
  • Prof. K. Barsauskas Ultrasound Research Institute, Kaunas University of Technology, K.Baršausko St. 59, LT-51423 Kaunas, Lithuania.
  • Department of Applied Informatics, Kaunas University of Technology, Studentu str.50, LT-51368 Kaunas, Lithuania.

ORCID-Profile: Tomas Vaitkūnas, Elena Jasiūnienė, Justas Griškevičius, Vykintas Samaitis, Paulius Griškevičius

Förderung

  • Research Council of Lithuania (LMTLT)

Zitieren

APA

Vaitkūnas, T., Jasiūnienė, E., Griškevičius, J., Samaitis, V., & Griškevičius, P. (2026). Quantitative Damage Detection and Evolution in Composite Structures Using Digital Image Correlation, Machine Learning, and Peridynamics. Materials, 19(10), 1917. https://doi.org/10.3390/ma19101917

Vancouver

Vaitkūnas T, Jasiūnienė E, Griškevičius J, Samaitis V, Griškevičius P. Quantitative Damage Detection and Evolution in Composite Structures Using Digital Image Correlation, Machine Learning, and Peridynamics. Materials. 2026;19(10):1917. doi:10.3390/ma19101917

BibTeX
@article{Vaitknas2026,
  author = {Vaitkūnas, Tomas and Jasiūnienė, Elena and Griškevičius, Justas and Samaitis, Vykintas and Griškevičius, Paulius},
  title = {Quantitative Damage Detection and Evolution in Composite Structures Using Digital Image Correlation, Machine Learning, and Peridynamics},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {10},
  pages = {1917},
  doi = {10.3390/ma19101917}
}
Kostenlos starten →