EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

From Pixels to Predictions: Integrating Machine Learning and Digital Image Correlation for Damage Identification in Engineering Materials

Mostafa Sadeghian, Arvydas Palevicius iD, Jokubas Sablinskas, Paulius Griskevicius iD

Materials · 24.12.2025 · 19 (1) · 77

DOI: 10.3390/ma19010077 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Materials, online erschienen am 24.12.2025. Verfasst von Mostafa Sadeghian und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical Engineering and Design, Kaunas University of Technology, Studentu 56, 51424 Kaunas, Lithuania. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 290 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lietuvos Mokslo Taryba.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Damage assessment in engineering materials is essential for structural reliability and safety. While traditional imaging techniques and Digital Image Correlation (DIC) provide valuable insights into deformation and crack evolution, they often require significant manual effort and suffer from accuracy limitations under complex loading conditions. Recent advances in Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), have enabled the development of automated, high-resolution, and near real-time damage assessment techniques. This paper reviews methods that integrate ML with DIC to assess damage in composites, metals, and other engineering materials. We compare conventional ML models with modern DL architectures, discuss key challenges, and propose future research directions. The findings demonstrate that coupling DIC with ML significantly improves the accuracy, speed, and reliability of damage identification in engineering materials.

Schlagwörter

Stichwörter der Autor:innen

damage identificationdigital image correlationmachine learning

Autor:innen und Institutionen

  • Faculty of Mechanical Engineering and Design, Kaunas University of Technology, Studentu 56, 51424 Kaunas, Lithuania.

ORCID-Profile: Arvydas Palevicius, Paulius Griskevicius

Förderung

  • Lietuvos Mokslo Taryba

Zitieren

APA

Sadeghian, M., Palevicius, A., Sablinskas, J., & Griskevicius, P. (2025). From Pixels to Predictions: Integrating Machine Learning and Digital Image Correlation for Damage Identification in Engineering Materials. Materials, 19(1), 77. https://doi.org/10.3390/ma19010077

Vancouver

Sadeghian M, Palevicius A, Sablinskas J, Griskevicius P. From Pixels to Predictions: Integrating Machine Learning and Digital Image Correlation for Damage Identification in Engineering Materials. Materials. 2025;19(1):77. doi:10.3390/ma19010077

BibTeX
@article{Sadeghian2025,
  author = {Sadeghian, Mostafa and Palevicius, Arvydas and Sablinskas, Jokubas and Griskevicius, Paulius},
  title = {From Pixels to Predictions: Integrating Machine Learning and Digital Image Correlation for Damage Identification in Engineering Materials},
  journal = {Materials},
  year = {2025},
  volume = {19},
  number = {1},
  pages = {77},
  doi = {10.3390/ma19010077}
}
Kostenlos starten →