EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Stacking Ensemble Neural Network and Stochastic Optimization Framework for Ultrasonic Welding

Patrik Gašparovič, Martin Juhás, Milan Daňo, Bohuslava Juhásová, Fedor Burčiar

Applied Sciences · 19.05.2026 · 16 (10) · 5058

DOI: 10.3390/app16105058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.05.2026. Verfasst von Patrik Gašparovič und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Grant Agency of the Ministry of Education, Research, Development and Youth of the Slovak Republic and the Slovak Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The reliable joining of thermoplastic composites is a critical requirement in modern manufacturing, where achieving zero-leakage joints is essential. For this application, ultrasonic welding is a highly efficient technology. Traditionally, standard heuristic methods and static experimental designs are used to optimize machine parameters. However, the process exhibits high stochastic variability due to complex, nonlinear thermomechanical interactions, which significantly influence the final seal quality and the reliability of the entire production system. This paper presents a practical prediction-optimization framework using a hybrid stacking ensemble neural network to process welding data. To improve the accuracy and stability of the manufacturing process, the predictive model is integrated with a Monte Carlo simulation. Evaluation showed that the proposed framework achieved the best performance among the evaluated benchmark models, with a coefficient of determination R2 = 0.8523 and a mean absolute error MAE = 0.7224. The proposed framework identifies candidate optimized machine parameters in a simulation-based workflow and defines stable operating conditions for subsequent experimental validation, providing a bounded data-driven approach for minimizing leakage in ultrasonic welding.

Förderung

  • Scientific Grant Agency of the Ministry of Education, Research, Development and Youth of the Slovak Republic and the Slovak Academy of Sciences

Zitieren

APA

Gašparovič, P., Juhás, M., Daňo, M., Juhásová, B., & Burčiar, F. (2026). A Hybrid Stacking Ensemble Neural Network and Stochastic Optimization Framework for Ultrasonic Welding. Applied Sciences, 16(10), 5058. https://doi.org/10.3390/app16105058

Vancouver

Gašparovič P, Juhás M, Daňo M, Juhásová B, Burčiar F. A Hybrid Stacking Ensemble Neural Network and Stochastic Optimization Framework for Ultrasonic Welding. Applied Sciences. 2026;16(10):5058. doi:10.3390/app16105058

BibTeX
@article{Gaparovi2026,
  author = {Gašparovič, Patrik and Juhás, Martin and Daňo, Milan and Juhásová, Bohuslava and Burčiar, Fedor},
  title = {A Hybrid Stacking Ensemble Neural Network and Stochastic Optimization Framework for Ultrasonic Welding},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {5058},
  doi = {10.3390/app16105058}
}
Kostenlos starten →