EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

AI-Driven Digital Twins for Manufacturing: A Review Across Hierarchical Manufacturing System Levels

Phat Nguyen, Minjung Kim iD, Elaina Nichols, Hwan-Sik Yoon iD

Sensors · 24.12.2025 · 26 (1) · 124

DOI: 10.3390/s26010124 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 24.12.2025. Verfasst von Phat Nguyen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, The University of Alabama, Tuscaloosa, AL 35487, USA. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 129 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital Twins (DTs) integrated with Artificial Intelligence (AI) are emerging as transformative tools in smart manufacturing. By bridging the physical and virtual domains, DTs enable real-time monitoring, predictive analytics, and autonomous decision-making. Originally conceived as advanced simulation models, DTs have evolved significantly with the incorporation of AI, which enhances their ability to acquire process knowledge, optimize scheduling, and autonomously control system variables. This evolution transforms DTs from passive representations into prescriptive, self-optimizing systems. AI-driven DTs support a wide range of applications, including predictive maintenance, process optimization, quality control, and dynamic scheduling, using techniques such as deep reinforcement learning and convolutional neural networks. These capabilities have been successfully deployed across industrial domains such as CNC machining, robotics, and industrial printing, yielding substantial improvements in efficiency, reliability, and responsiveness. Despite these advancements, the full realization of intelligent DTs relies heavily on the availability of high-fidelity, real-time data and a seamless alignment between physical systems and their digital counterparts. This literature survey provides a state-of-the-art review of AI-driven DTs in manufacturing, highlighting their key applications, challenges, and emerging research directions that will shape the future of intelligent and adaptive manufacturing systems. To present a structured perspective on the evolution and scalability of AI-driven DTs, the application case studies are organized according to four integration levels—machine, cell, shop floor, and enterprise—highlighting how these technologies scale from individual assets to fully interconnected manufacturing ecosystems.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencedigital twinpredictive maintenanceprocess optimizationquality controlsmart manufacturing

Autor:innen und Institutionen

  • Department of Mechanical Engineering, The University of Alabama, Tuscaloosa, AL 35487, USA.

ORCID-Profile: Minjung Kim, Hwan-Sik Yoon

Zitieren

APA

Nguyen, P., Kim, M., Nichols, E., & Yoon, H. S. (2025). AI-Driven Digital Twins for Manufacturing: A Review Across Hierarchical Manufacturing System Levels. Sensors, 26(1), 124. https://doi.org/10.3390/s26010124

Vancouver

Nguyen P, Kim M, Nichols E, Yoon HS. AI-Driven Digital Twins for Manufacturing: A Review Across Hierarchical Manufacturing System Levels. Sensors. 2025;26(1):124. doi:10.3390/s26010124

BibTeX
@article{Nguyen2025,
  author = {Nguyen, Phat and Kim, Minjung and Nichols, Elaina and Yoon, Hwan-Sik},
  title = {AI-Driven Digital Twins for Manufacturing: A Review Across Hierarchical Manufacturing System Levels},
  journal = {Sensors},
  year = {2025},
  volume = {26},
  number = {1},
  pages = {124},
  doi = {10.3390/s26010124}
}
Kostenlos starten →