EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-objective process parameter optimization using a hybrid reinforcement/machine learning model in metal additive manufacturing

Arash Seifoddini, Arefeh Azad, Mohammad Hossein Mosallanejad, Abdollah Saboori

Advances in Manufacturing · 2026-12 · 14 (4) · 829-849

DOI: 10.1007/s40436-026-00596-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Manufacturing, online erschienen am 20.03.2026. Verfasst von Arash Seifoddini und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Politecnico di Torino.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Additive manufacturing enables the production of complex geometries and lightweight structures. However, producing defect-free components fundamentally depends on the careful optimization of process parameters that influence critical factors, such as melt pool depth, in laser powder bed fusion (L-PBF), an important class of metal additive manufacturing methods. Hence, for the first time, this paper presents a novel data-driven framework that integrates machine learning (ML) with reinforcement learning (RL) to optimize process parameters, ensuring the desired melt pool characteristics while meeting multi-objective design criteria. Experimental data from the literature were extracted to train several ML models, with Gaussian process regression (GPR) featuring a Matérn kernel proved to be the most accurate predictor. This model served as the digital twin of the L-PBF process and was integrated with a Q -learning-based RL agent to derive the optimal process parameters. The GPR model achieved a high prediction accuracy (root mean squared error (RMSE): 34 µm, the coefficient of determination R 2 : 96.05%) for L-PBF Ti6Al4V alloy using minimal training data. Integrating a Q -learning framework with ML demonstrated superior performance in deriving process parameters that achieved the target melt pool depth while minimizing the normalized enthalpy, directly impacting the formation of the keyhole defect.

Förderung

  • Politecnico di Torino

Zitieren

APA

Seifoddini, A., Azad, A., Mosallanejad, M. H., & Saboori, A. (2026). Multi-objective process parameter optimization using a hybrid reinforcement/machine learning model in metal additive manufacturing. Advances in Manufacturing, 14(4), 829-849. https://doi.org/10.1007/s40436-026-00596-x

Vancouver

Seifoddini A, Azad A, Mosallanejad MH, Saboori A. Multi-objective process parameter optimization using a hybrid reinforcement/machine learning model in metal additive manufacturing. Advances in Manufacturing. 2026;14(4):829-849. doi:10.1007/s40436-026-00596-x

BibTeX
@article{Seifoddini2026,
  author = {Seifoddini, Arash and Azad, Arefeh and Mosallanejad, Mohammad Hossein and Saboori, Abdollah},
  title = {Multi-objective process parameter optimization using a hybrid reinforcement/machine learning model in metal additive manufacturing},
  journal = {Advances in Manufacturing},
  year = {2026},
  volume = {14},
  number = {4},
  pages = {829--849},
  doi = {10.1007/s40436-026-00596-x}
}
Kostenlos starten →