EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning for Process Monitoring and Defect Detection of Laser-Based Powder Bed Fusion of Polymers

Mohammadali Vaezi iD, Victor Klamert, Mugdim Bublin

Polymers · 03.03.2026 · 18 (5) · 629

DOI: 10.3390/polym18050629 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Polymers, online erschienen am 03.03.2026. Verfasst von Mohammadali Vaezi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Technical Management, Hochschule Campus Wien, University of Applied Sciences, Favoritenstrasse 226, 1100 Vienna, Austria. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MA23 City of Vienna, City of Vienna.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maintaining consistent part quality remains a critical challenge in industrial additive manufacturing, particularly in laser-based powder bed fusion of polymers (PBF-LB/P), where crystallization-driven thermal instabilities, governed by isothermal crystallization within a narrow sintering window, precipitate defects such as curling, warping, and delamination. In contrast to metal-based systems dominated by melt-pool hydrodynamics, polymer PBF-LB/P requires monitoring strategies capable of resolving subtle spatio-temporal thermal deviations under realistic industrial operating conditions. Although machine learning, particularly convolutional neural networks (CNNs), has demonstrated efficacy in defect detection, a structured evaluation of heterogeneous modeling paradigms and their deployment feasibility in polymer PBF-LB/P remains limited. This study presents a systematic cross-paradigm assessment of unsupervised anomaly detection (autoencoders and generative adversarial networks), supervised CNN classifiers (VGG-16, ResNet50, and Xception), hybrid CNN-LSTM architectures, and physics-informed neural networks (PINNs) using 76,450 synchronized thermal and RGB images acquired from a commercial industrial system operating under closed control constraints. CNN-based models enable frame- and sequence-level defect classification, whereas the PINN component complements detection by providing physically consistent thermal-field regression. The results reveal quantifiable trade-offs between detection performance, temporal robustness, physical consistency, and algorithmic complexity. Pre-trained CNNs achieve up to 99.09% frame-level accuracy but impose a substantial computational burden for edge deployment. The PINN model attains an RMSE of approximately 27 K under quasi-isothermal process conditions, supporting trend-level thermal monitoring. A lightweight hybrid CNN achieves 99.7% validation accuracy with 1860 parameters and a CPU-benchmarked forward-pass inference time of 1.6 ms (excluding sensor acquisition latency). Collectively, this study establishes a rigorously benchmarked, scalable, and resource-efficient deep-learning framework tailored to crystallization-dominated polymer PBF-LB/P, providing a technically grounded basis for real-time industrial quality monitoring.

Schlagwörter

Stichwörter der Autor:innen

additive manufacturing (AM)convolutional neural networks (CNN)deep learninglaser-based powder bed fusion of polymers (PBF-LB/P)physics-informed neural networks (PINNs)

Autor:innen und Institutionen

  • Department of Technical Management, Hochschule Campus Wien, University of Applied Sciences, Favoritenstrasse 226, 1100 Vienna, Austria.
  • Department of High Tech Manufacturing, Hochschule Campus Wien, University of Applied Sciences, Favoritenstrasse 226, 1100 Vienna, Austria.
  • Department of Computer Science and Digital Communications, Hochschule Campus Wien, University of Applied Sciences, Favoritenstrasse 226, 1100 Vienna, Austria.

ORCID-Profile: Mohammadali Vaezi

Förderung

  • MA23 City of Vienna
  • City of Vienna

Zitieren

APA

Vaezi, M., Klamert, V., & Bublin, M. (2026). Deep Learning for Process Monitoring and Defect Detection of Laser-Based Powder Bed Fusion of Polymers. Polymers, 18(5), 629. https://doi.org/10.3390/polym18050629

Vancouver

Vaezi M, Klamert V, Bublin M. Deep Learning for Process Monitoring and Defect Detection of Laser-Based Powder Bed Fusion of Polymers. Polymers. 2026;18(5):629. doi:10.3390/polym18050629

BibTeX
@article{Vaezi2026,
  author = {Vaezi, Mohammadali and Klamert, Victor and Bublin, Mugdim},
  title = {Deep Learning for Process Monitoring and Defect Detection of Laser-Based Powder Bed Fusion of Polymers},
  journal = {Polymers},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {629},
  doi = {10.3390/polym18050629}
}
Kostenlos starten →