EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Digital Twins, Machine Learning, and Advanced Process Control in Next-Generation Additive Manufacturing

S M Akib

Frontora · 2025

DOI: 10.70945/f.v03i02.0019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontora, 2025. Verfasst von S M Akib. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The incorporation of digital twins, machine learning, and advanced process control is transforming the landscape of AM, allowing for real-time monitoring, predictive quality analysis, and process optimization. It investigates a holistic system where digital twins create dynamic virtual models of the additive manufacturing systems, machine learning systems analyse and extract prediction information from heterogeneous sensor and process data, and advanced control systems such as model predictive control convert predictions into real-time process control. It can be used for a variety of applications, such as defect detection, optimizing process parameters, predictive maintenance, anomaly detection, material property prediction, and quality assurance. Digital twin architectures provide the ability to keep physical equipment in sync with virtual models, and machine learning and physics-based methods help forecast processes and eliminate the need for expensive and heavy computational simulations. Another advantage of using machine learning-based surrogate models is that they can help estimate future process states quickly, thus speeding up the process of predictive control. Clearly, digital representations can mimic the behavior of physical machines and facilitate better monitoring and decision-making, as demonstrated by digital applications. The implementation is, however, limited due to a lack of data, model generalisation, computational demands, interoperability, cybersecurity, model validation and regulatory certification. To realize the concepts of intelligent manufacturing in scalable industrial production, continued development of physics-informed modeling, multimodal sensor fusion, edge and cloud computing, uncertainty quantification and trustworthy governance will be crucial.

Zitieren

APA

Akib, S. M. (2025). Digital Twins, Machine Learning, and Advanced Process Control in Next-Generation Additive Manufacturing. Frontora. https://doi.org/10.70945/f.v03i02.0019

Vancouver

Akib SM. Digital Twins, Machine Learning, and Advanced Process Control in Next-Generation Additive Manufacturing. Frontora. 2025. doi:10.70945/f.v03i02.0019

BibTeX
@article{Akib2025,
  author = {Akib, S M},
  title = {Digital Twins, Machine Learning, and Advanced Process Control in Next-Generation Additive Manufacturing},
  journal = {Frontora},
  year = {2025},
  doi = {10.70945/f.v03i02.0019}
}
Kostenlos starten →