Better measurement thanks to AI

When electrical machines are tested, huge amounts of data are generated - temperature, load, magnetic, electrical and acoustic properties are just some of the parameters that can be collected on modern test benches. This often generates several gigabytes of data. "A human being can hardly evaluate this amount of information - for this we need the support of intelligent software," says Prof. Ludwig Brabetz.

He coordinates the AIMEE research project, which aims to investigate the use of AI methods such as deep learning for test benches. Together with two partners, who also come from the Department of Electrical Engineering/Computer Science at the University of Kassel, the aim is to create the possibility of evaluating so-called "heterogeneous high-volume data sets" by computer over the next two years.

In addition to the Department of "Vehicle Systems and Fundamentals of Electrical Engineering" led by Prof. Brabetz, the Department of "Intelligent Embedded Systems" led by Professor Bernhard Sick and the Department of "Digital Technology" led by Prof. Peter Zipf are also involved in the project. The funding from the German Federal Ministry of Education and Research (BMBF) amounts to around one million euros, and the project is scheduled to run until Oct. 31, 2021.

Further info at: https://www.uni-kassel.de/eecs/fachgebiete/fsg/forschung/aimee.html

Contact person:

Prof. Dr. rer. nat. Ludwig Brabetz
Department of "Vehicle Systems and Fundamentals of Electrical Engineering" (FSG)
Tel.  (49) 561 804 6232
E-mail brabetz[at]uni-kassel[dot]de