Wilhelm Kirchgässner

Leistungselektronik und Elektrische Antriebstechnik (LEA)

Ehemaliger

Maschinelles Lernen in der elektrischen Antriebstechnik

Büro­anschrift:
Pohlweg 55
33098 Paderborn
Raum:
E4.324

Publikationen

Aktuelle Publikationen

Thermal neural networks: Lumped-parameter thermal modeling with state-space machine learning

W. Kirchgässner, O. Wallscheid, J. Böcker, Engineering Applications of Artificial Intelligence 117 (2022).


Learning Thermal Properties and Temperature Models of Electric Motors with Neural Ordinary Differential Equations

W. Kirchgässner, O. Wallscheid, J. Böcker, in: 2022 International Power Electronics Conference (IPEC-Himeji 2022- ECCE Asia), IEEE, 2022.


Application of Thermal Neural Networks on a Small-Scale Electric Motor

W. Kirchgässner, D. Wöckinger, O. Wallscheid, G. Bramerdorfer, J. Böcker, in: IKMT 2022; 13. GMM/ETG-Symposium, 2022, pp. 1–6.


Transferring Online Reinforcement Learning for Electric Motor Control From Simulation to Real-World Experiments

G. Book, A. Traue, P. Balakrishna, A. Brosch, M. Schenke, S. Hanke, W. Kirchgässner, O. Wallscheid, IEEE Open Journal of Power Electronics (2021) 187–201.


Data-Driven Permanent Magnet Temperature Estimation in Synchronous Motors with Supervised Machine Learning: A Benchmark

W. Kirchgässner, O. Wallscheid, J. Böcker, IEEE Transactions on Energy Conversion 36 (2021) 2059–2067.


Alle Publikationen anzeigen