Wilhelm Kirchgässner

Kontakt

Vita

Publikationen

Leistungselektronik und Elektrische Antriebstechnik (LEA)

Wissenschaftlicher Mitarbeiter - Maschinelles Lernen in der elektrischen Antriebstechnik

VCard

Telefon:

+49 5251 60-5048

Fax:

+49 5251 60-3443

E-Mail:

kirchgaessner(at)lea.upb(dot)de

Büro:

E4.324

Web:

Homepage

Besucher:

Pohlweg 55
33098 Paderborn

07/2018 - heute	Wissenschaftlicher Mitarbeiter/ Doktorand Maschinelles Lernen im Kontext elektrischer Antriebstechnik und Leistungselektronik
08/2016 - 06/2018	Software-Ingenieur Continental Automotive GmbH, Babenhausen. Entwicklung eingebetteter Systeme, Koordination von Entwickler-Hubs, Toolchain, Lasten- und Pflichtenheft-Pflege.
10/2015 - 03/2016	Studentische Hilfskraft Uni Paderborn, PB (Fachbereich Nachrichtentechnik). Unit-Tests, Algorithmen-Konversion Matlab <-> Python.
04/2014 - 09/2015	Werkstudent Wincor Nixdorf, Paderborn. Systemtest, Integrationstest, Installationsroutinen.
07/2009 - 08/2013	Dual-Student Elektrotechnik, B.Sc. & Facharbeiter Elektroniker für Geräte u. Systeme Phoenix Contact Electronics GmbH, Bad Pyrmont. Hochschule Ostwestfalen-Lippe, Lemgo.

Liste im Research Information System öffnen

2021

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), pp. 187-201

DOI

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 (2021), 36(3), pp. 2059 - 2067

DOI

gym-electric-motor (GEM): A Python toolbox for the simulation of electric drive systems

P. Balakrishna, G. Book, W. Kirchgässner, M. Schenke, A. Traue, O. Wallscheid, Journal of Open Source Software (2021), 2498

DOI

Thermal Neural Networks: Lumped-Parameter Thermal Modeling With State-Space Machine Learning

W. Kirchgässner, O. Wallscheid, J. Böcker, arXiv preprint arXiv:2103.16323 (2021)

2020

Toward a Reinforcement Learning Environment Toolbox for Intelligent Electric Motor Control

A. Traue, G. Book, W. Kirchgässner, O. Wallscheid, IEEE Transactions on Neural Networks and Learning Systems (2020), pp. 1-10

DOI

Estimating Electric Motor Temperatures with Deep Residual Machine Learning

W. Kirchgässner, O. Wallscheid, J. Böcker, IEEE Transactions on Power Electronics (2020), 36(7), pp. 7480-7488

DOI

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

W. Kirchgässner, O. Wallscheid, J. Böcker, arXiv preprint arXiv:2001.06246 (2020)

2019

Controller Design for Electrical Drives by Deep Reinforcement Learning: A Proof of Concept

M. Schenke, W. Kirchgässner, O. Wallscheid, IEEE Transactions on Industrial Informatics (2019), pp. 4650-4658

DOI

Empirical Evaluation of Exponentially Weighted Moving Averages for Simple Linear Thermal Modeling of Permanent Magnet Synchronous Machines

W. Kirchgässner, O. Wallscheid, J. Böcker, in: 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE), 2019

DOI

Deep Residual Convolutional and Recurrent Neural Networks for Temperature Estimation in Permanent Magnet Synchronous Motors

W. Kirchgässner, O. Wallscheid, J. Böcker, in: 2019 IEEE International Electric Machines & Drives Conference (IEMDC), 2019

DOI

2017

Investigation of long short-term memory networks to temperature prediction for permanent magnet synchronous motors

O. Wallscheid, W. Kirchgässner, J. Böcker, in: 2017 International Joint Conference on Neural Networks (IJCNN), 2017

DOI

Investigation of Long Short-Term Memorys to Temperature Prediction for Permanent Magnet Synchronous Motors

O. Wallscheid, W. Kirchgässner, J. Böcker, in: IEEE International Joint Conference on Neural Networks (IJCNN 2017), 2017

Liste im Research Information System öffnen