EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parametric Optimization of Artificial Neural Networks and Machine Learning Techniques Applied to Small Welding Datasets

Vinícius Resende Rocha, Fran Sérgio Lobato, Pedro Augusto Queiroz de Assis, Carlos Roberto Ribeiro, Sebastião Simões da Cunha, Louriel Oliveira Vilarinho, João Rodrigo Andrade, Leonardo Rosa Ribeiro da Silva, Luiz Eduardo dos Santos Paes

Processes · 25.08.2025 · 13 (9) · 2711

DOI: 10.3390/pr13092711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 25.08.2025. Verfasst von Vinícius Resende Rocha und 8 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Petrobras, ANP, CAPES.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Establishing precise welding parameters is essential to achieving the desired bead geometry and ensuring consistent quality in manufacturing processes. However, determining the optimal configuration of parameters remains a challenge, particularly when relying on limited experimental data. This study proposes the use of artificial neural networks (ANNs), with their architecture optimized via differential evolution (DE), to predict key MAG welding parameters based on target bead geometry. To address data limitations, cross-validation and data augmentation techniques were employed to enhance model generalization. In addition to the ANN model, machine learning algorithms commonly recommended for small datasets, such as K-nearest neighbors (KNNs) and support vector machines (SVMs), were implemented for comparative evaluation. The results demonstrate that all models achieved good predictive performance, with SVM showing the highest accuracy among the techniques tested, reinforcing the value of integrating traditional ML models for benchmarking purposes in low-data scenarios.

Förderung

  • Petrobras
  • ANP
  • CAPES
  • CNPq
  • FAPEMIG

Zitieren

APA

Rocha, V. R., Lobato, F. S., Assis, P. A. Q. D., Ribeiro, C. R., Cunha, S. S. D., Vilarinho, L. O., Andrade, J. R., Silva, L. R. R. D., & Paes, L. E. D. S. (2025). Parametric Optimization of Artificial Neural Networks and Machine Learning Techniques Applied to Small Welding Datasets. Processes, 13(9), 2711. https://doi.org/10.3390/pr13092711

Vancouver

Rocha VR, Lobato FS, Assis PAQD, Ribeiro CR, Cunha SSD, Vilarinho LO, et al. Parametric Optimization of Artificial Neural Networks and Machine Learning Techniques Applied to Small Welding Datasets. Processes. 2025;13(9):2711. doi:10.3390/pr13092711

BibTeX
@article{Rocha2025,
  author = {Rocha, Vinícius Resende and Lobato, Fran Sérgio and Assis, Pedro Augusto Queiroz de and Ribeiro, Carlos Roberto and Cunha, Sebastião Simões da and Vilarinho, Louriel Oliveira and Andrade, João Rodrigo and Silva, Leonardo Rosa Ribeiro da and Paes, Luiz Eduardo dos Santos},
  title = {Parametric Optimization of Artificial Neural Networks and Machine Learning Techniques Applied to Small Welding Datasets},
  journal = {Processes},
  year = {2025},
  volume = {13},
  number = {9},
  pages = {2711},
  doi = {10.3390/pr13092711}
}
Kostenlos starten →