Using Physics-Informed Machine Learning for reusing power system components
| Reference number | |
| Coordinator | Kungliga Tekniska Högskolan - Skolan för elektroteknik och Skolan f elektroteknik & datavetens |
| Funding from Vinnova | SEK 3 800 000 |
| Project duration | November 2021 - November 2025 |
| Status | Ongoing |
| Venture | Circular and biobased economy |
| Call | Increased resource efficiency for a circular industry |
Important results from the project
Yes, we have met our goal of using PINNs to aid understanding on how power components can be used and designed more sustainably.
Expected long term effects
The project will improve understanding of insulation aging and expand research into new materials. Using Physics-Informed Neural Networks (PINNs), it aims to optimize power system components and explore sustainable production methods. Future steps include developing digital twins and simulating alternative materials, like natural ester oils, to enhance equipment upcycling, efficiency, and sustainability in the power industry.
Approach and implementation
The project was carried out according to the plan. Some difficulties have occurred due to limited data availability. But since we have also joined the CIGRE working group on a similar topic (PhD student Federica Bragone is the part of the working group) we saw that this is common issue for the international industry community. Making the final results of the project even more meaningful. Hence the non-anticipated challenge has actually led to a more important discovery.