Physics-InspiRed AI Models for Engineering Design (PIRAMED)
This project combines AI techniques with physics-based models to accelerate and improve the design of complex mechanical, electronic and photonic systems.
This project focuses on the enrichment of physics-inspired models with novel AI techniques. It will advance and automate the design of engineering devices (e.g. mechanical, electronic, photonic), which are essential for a wide range of applications. There's a significant gap between the capabilities of available technology and the functionalities engineers require. Designing these devices is often complex and time-consuming, and involves lengthy cycles of simulation, measurement, optimization, and testing. This iterative work can slow down innovation and increase costs. By unifying advanced AI approaches with fundamental physics principles, the performance of the design process can be further enhanced. The added value lies in its potential to make the design task faster, more accurate, and less costly, thereby accelerating technological advancements. As such, the enriched tools could lead to the development of innovative, high-performance products with applications in various fields.
Downloads
Toolbox - https://sumo.ilabt.imec.be/home/software/piramed
Tutorial - EUMW-2025_Full-Programme-250909-14-interactiv-Compressed.pdf
Contacts
Philip Leroux (UGent)- Philip.leroux@ugent.be
Research
Tom DHaene (UGent): Tom.Dhaene@ugent.be
Dirk Deschryver (UGent): Dirk.deschryver@ugent.be
Research group
Ugent - IDLab