EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of a Deep Learning-Based Decision Framework for Optimal Process Parameter Selection in Metal Additive Manufacturing

Min Seop So, Duck Bong Kim iD, Duncan Kibet iD, Jong-Ho Shin iD

Sensors · 09.02.2026 · 26 (4) · 1124

DOI: 10.3390/s26041124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.02.2026. Verfasst von Min Seop So und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Industrial Engineering, Chosun University, Gwangju 61452, Republic of Korea. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chosun University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional subtractive manufacturing methods, such as cutting, often result in material waste and limitations in geometric complexity. To address these challenges, Wire Arc Additive Manufacturing (WAAM), in which components are built through successive weld bead deposition, has attracted increasing attention across various industrial fields. However, WAAM-fabricated components typically exhibit significant surface irregularities, necessitating additional post-processing that reduces overall productivity. Improving productivity therefore requires effective control and optimization of deposition parameters. This task is particularly challenging in multilayer WAAM processes, as the geometry of previously deposited layers varies with operating conditions. To address this challenge, this study proposes an AI-based framework for controlling surface roughness by rapidly identifying near-optimal process parameters in response to evolving bead geometry. A large-scale simulation dataset was generated by applying a pre-trained deep neural network (DNN) surface roughness predictor to one million bead geometry variations under 72 process parameter combinations. The resulting optimal parameter labels were used to train a classification model that recommends process conditions based on the current bead geometry. Model performance was evaluated using predictor-estimated surface roughness values, achieving Weighted Precision, Recall, and F1-score of 0.98, with an average AUC of 0.977. Five previously generated WAAM specimens were used for comparative analysis between AI-recommended and conventional process conditions using the previously developed and validated surface roughness prediction model, rather than direct physical measurements. This predictor-based feasibility analysis showed that AI-recommended conditions consistently reduced the predicted surface roughness, indicating the potential of AI-driven process optimization to improve surface quality in WAAM and reduce reliance on post-processing.

Schlagwörter

Stichwörter der Autor:innen

arc weldingdeep neural networksurface roughnesswire + arc additive manufacturing

Autor:innen und Institutionen

  • Department of Industrial Engineering, Chosun University, Gwangju 61452, Republic of Korea.
  • School of Environmental, Civil, Agricultural, and Mechanical Engineering, University of Georgia, Athens, GA 30602, USA.

ORCID-Profile: Duck Bong Kim, Duncan Kibet, Jong-Ho Shin

Förderung

  • Chosun University

Zitieren

APA

So, M. S., Kim, D. B., Kibet, D., & Shin, J. H. (2026). Development of a Deep Learning-Based Decision Framework for Optimal Process Parameter Selection in Metal Additive Manufacturing. Sensors, 26(4), 1124. https://doi.org/10.3390/s26041124

Vancouver

So MS, Kim DB, Kibet D, Shin JH. Development of a Deep Learning-Based Decision Framework for Optimal Process Parameter Selection in Metal Additive Manufacturing. Sensors. 2026;26(4):1124. doi:10.3390/s26041124

BibTeX
@article{So2026,
  author = {So, Min Seop and Kim, Duck Bong and Kibet, Duncan and Shin, Jong-Ho},
  title = {Development of a Deep Learning-Based Decision Framework for Optimal Process Parameter Selection in Metal Additive Manufacturing},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {4},
  pages = {1124},
  doi = {10.3390/s26041124}
}
Kostenlos starten →