Karriere am WZL


Masterarbeit oder Bachelorarbeit oder Projektarbeit

am Forschungsbereich Technologie der Fertigungsverfahren, Abteilung Umformen, Gruppe Umformende Fertigungsverfahren

Data Science and Machine Learning in Manufacturing – PA/BA/MA

Fine blanking is a highly economical sheet metal cutting process for mass production of components with very high cutting surface quality and is commonly used in the automotive and aerospace industry.

Within the framework of the Internet of Production, which was approved as one of the two clusters of excellence of the RWTH, the potentials of a fine blanking press as a cyber-physical system are being researched. Various sensor systems were installed for the online recording of process forces, peripheral forces and acoustic emission signals, as well as material properties and environmental influences on the fine blanking process. The objective of this data acquisition is to detect machine faults at an early stage and to avoid downtimes. In addition to that deviations during the forming process are to be detected in order to react to them.

To achieve this goal, the reference state of the process must be detected. This allows deviations from the reference condition during the process to be quantified and correlated with external influences such as mate-rial properties or quality characteristics of the fine blanked workpiece. For this purpose data-driven models need to be derived, which can robustly record this reference state of the process and quantify deviations in real time.

Questions to be dealt with in this context include various areas of data processing. Both high frequency cy-cle based time series must be segmented and analysed, event based data sets processed and superordinate models derived. This requires basic methods of how to process larger datasets efficiently, but also includes methods from the fields of data science, data mining and machine learning to process the different data sets. These methods can be used in various problems both together and separately from one another for modelling. The scope of the investigated time series, as well as the applied methods of data-driven modeling can be individually adjusted, depending on your personal preferences.
– Motivation and commitment
– Interest in data analysis and machine learning in an industrial context

We offer
– Comprehensive support
– Familiarization with highly up-to-date methods for data analysis of large amounts of data in an industrial context
– Independent time management
– Familiarization with programming languages (Python, R)
– Familiarization with data analysis tools
Zeitaufwand: 11,00 Arbeitsstunden

Philipp Niemietz, M.Sc RWTH
Cluster Produktionstechnik 3A 328
Tel.: +49 241 80-28212
Fax: +49 241 80-628212
Mail: P.Niemietz@wzl.rwth-aachen.de