EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Damage detection and localization in composite plates using mode shapes and artificial intelligence: from numerical models to experimental validation

Ronny Francis Ribeiro Junior, Guilherme Ferreira Gomes

Journal of the Brazilian Society of Mechanical Sciences and Engineering · 2026-10 · 48 (11)

DOI: 10.1007/s40430-026-06747-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Society of Mechanical Sciences and Engineering, online erschienen am 03.10.2026. Verfasst von Ronny Francis Ribeiro Junior und 1 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade Federal De Itajubá.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a simulation-driven deep learning framework for vibration-based damage detection and localization in composite structures using mode shape images. CNNs are trained exclusively on numerically simulated data and directly validated against experimental measurements, addressing the domain gap between numerical models and real-world structural behavior without requiring experimentally labeled data for training. The proposed approach is evaluated on the challenging task of detecting and localizing small damages in a large composite plate, with defect-to-structure area ratios as low as $$0.004\%.$$ A binary classification model is first developed to distinguish between damaged and undamaged conditions, achieving 100% accuracy on simulated data and 90% accuracy on experimental data. In addition, regression-based CNN models are employed to estimate damage location and size under two distinct boundary conditions: free–free and fully clamped. The models demonstrate consistent and accurate localization performance across both scenarios, with improved results in the free–free condition. Despite being trained solely on simulated data, the models generalize effectively to experimental mode shapes, capturing spatial damage features and providing physically meaningful predictions. Overall, the results demonstrate that simulation-driven CNN frameworks can achieve robust cross-domain performance. This significantly reduces the dependence on costly experimental datasets and highlights the practical potential of the proposed approach for real-world Structural Health Monitoring applications in composite structures.

Förderung

  • Universidade Federal De Itajubá

Zitieren

APA

Junior, R. F. R., & Gomes, G. F. (2026). Damage detection and localization in composite plates using mode shapes and artificial intelligence: from numerical models to experimental validation. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 48(11). https://doi.org/10.1007/s40430-026-06747-2

Vancouver

Junior RFR, Gomes GF. Damage detection and localization in composite plates using mode shapes and artificial intelligence: from numerical models to experimental validation. Journal of the Brazilian Society of Mechanical Sciences and Engineering. 2026;48(11). doi:10.1007/s40430-026-06747-2

BibTeX
@article{Junior2026,
  author = {Junior, Ronny Francis Ribeiro and Gomes, Guilherme Ferreira},
  title = {Damage detection and localization in composite plates using mode shapes and artificial intelligence: from numerical models to experimental validation},
  journal = {Journal of the Brazilian Society of Mechanical Sciences and Engineering},
  year = {2026},
  volume = {48},
  number = {11},
  doi = {10.1007/s40430-026-06747-2}
}
Kostenlos starten →