Konferenzbeitrag
A Proposal for Physics-Informed Quantum Graph Neural Networks for Simulating Laser Cutting Processes
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2023
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Simulations are crucial for production monitoring and planning in manufacturing. Still, the performance of simulations based on mathematical modeling and machine learning methods is limited and opaque to widespread application. Quantum computing offers the potential for exponential acceleration of these tools, while physically informed neural networks (PINN) improve learning and reduce ambiguity. Objective of this paper is to explore the concept of developing a tool for laser cutting simulation based on a quantum neural network that can be trained on thermal physics principles.