EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Inverse Neural Network Approach for Optimizing Chemical Composition in Shielded Metal Arc Weld Metals

Taehyun Yoon iD, Young Il Park iD, Jaewoong Kim, Jeong-Hwan Kim iD

Materials · 01.06.2025 · 18 (11) · 2592

DOI: 10.3390/ma18112592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 01.06.2025. Verfasst von Taehyun Yoon und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Naval Architecture and Offshore Engineering, Dong-A University, Busan 49315, Republic of Korea. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Industrial Technology, the Ministry of Trade, Industry and Energy, Ministry of Trade, Industry and Energy.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a hybrid machine learning framework combining an artificial neural network and a genetic algorithm to optimize chemical compositions of shielded metal arc weld metals for achieving targeted mechanical properties. First, a neural network model was trained using a large experimental database provided by Dr. Glyn M. Evans, which includes the chemical compositions and mechanical properties of over 950 shielded metal arc weld metals. The neural network model, optimized via Bayesian optimization, demonstrated high predictive accuracy for properties such as yield strength, ultimate tensile strength, and Charpy impact transition temperatures. To enable inverse design, a genetic algorithm-based optimization was applied to the trained neural network model, iteratively exploring the composition space to find optimal elemental combinations that match predefined mechanical property targets. The proposed hybrid approach successfully identified multiple feasible compositions that closely match the desired mechanical behavior, demonstrating the potential of neural network-assisted inverse design in welding alloy development.

Schlagwörter

Stichwörter der Autor:innen

chemical compositiongenetic algorithminverse neural networkshielded metal arc weld

Autor:innen und Institutionen

  • Department of Naval Architecture and Offshore Engineering, Dong-A University, Busan 49315, Republic of Korea.
  • Gwangju Ppuri Technology Support Center, Korea Institute of Industrial Technology, Gwangju 11109, Republic of Korea.

ORCID-Profile: Taehyun Yoon, Young Il Park, Jeong-Hwan Kim

Förderung

  • Korea Institute of Industrial Technology
  • the Ministry of Trade, Industry and Energy
  • Ministry of Trade, Industry and Energy

Zitieren

APA

Yoon, T., Park, Y. I., Kim, J., & Kim, J. H. (2025). Inverse Neural Network Approach for Optimizing Chemical Composition in Shielded Metal Arc Weld Metals. Materials, 18(11), 2592. https://doi.org/10.3390/ma18112592

Vancouver

Yoon T, Park YI, Kim J, Kim JH. Inverse Neural Network Approach for Optimizing Chemical Composition in Shielded Metal Arc Weld Metals. Materials. 2025;18(11):2592. doi:10.3390/ma18112592

BibTeX
@article{Yoon2025,
  author = {Yoon, Taehyun and Park, Young Il and Kim, Jaewoong and Kim, Jeong-Hwan},
  title = {Inverse Neural Network Approach for Optimizing Chemical Composition in Shielded Metal Arc Weld Metals},
  journal = {Materials},
  year = {2025},
  volume = {18},
  number = {11},
  pages = {2592},
  doi = {10.3390/ma18112592}
}
Kostenlos starten →