Modern test benches for experimental validation provide extremely large, mostly time-based and usually heterogeneous amounts of data, the processing and, above all, the evaluation of which is hardly possible with conventional knowledge-based methods or, due to the size and complexity, not possible at all. In particular, unknown correlations and error models elude analysis. For the use of AI methods, e.g. from the field of deep learning, this offers an extremely interesting, still little researched and, above all, future-relevant application.

A new, high-performance test bench for electric drive machines has recently been in use at the University of Kassel, which uses extensive measurement technology to generate very large heterogeneous data volumes of time-based electromagnetic, electrical, acoustic, mechanical and thermal variables, as well as non-time-based, characterizing or parametric data, and also allows measurements in previously little-researched border areas.

The BMBF joint project AIMEE addresses the processing and evaluation of heterogeneous, high-volume data sets from the test bench in order to make the applicability of innovative methods directly tangible and interpretable for students using practical examples in the AI lab. This creates the necessary conditions for students (undergraduates, doctoral students and professionals in further education) to study and apply the various AI methods with extensive and defined data sets using practical examples. It also opens up the highly interesting and rare opportunity for teaching and research to create new data sets at will and to adapt the boundary conditions of data creation, i.e. the measurement runs and structure, to the requirements of AI methods and method development. The close cooperation between software, hardware and application provides an excellent basis for teaching, is of great interest to the regional economy and has a high scientific connectivity.