Master Thesis (f/m/x) Feature Engineering for Machine Learning-based Robotic SEAM Trajectory Tuning Job Details

We are currently reorganising our job portal. During the transition phase, you can find more jobs here: previous DLR job portal

Master Thesis (f/m/x) Feature Engineering for Machine Learning-based Robotic SEAM Trajectory Tuning

Job Description

Req ID: 1987

Place of work: Stuttgart

Starting date: schnellstmöglich

Career level: Graduates, Internship

Type of employment: Part time

Duration of contract: 3-6 Monate

Remuneration: Remuneration is in accordance with the Collective Agreement for the Public Sector - Federal Government (TVöD-Bund)

Enter the fascinating world of the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt e. V.; DLR) and help shape the future through research and innovation! We offer an exciting and inspiring working environment driven by the expertise and curiosity of our 11,000 employees from 100 nations and our unique infrastructure. Together, we develop sustainable technologies and thus contribute to finding solutions to global challenges. Would you like to join us in addressing this major future challenge? Then this is your place!

The Institute of Vehicle Concepts (FK) of the German Aerospace Centre (DLR) is internationally recognised for the design of future road and rail vehicles that enable climate and environmentally friendly mobility while being affordable and user-friendly at the same time.

We research and demonstrate the required key technologies and maintain close cooperation with other scientific institutions as well as industrial and political bodies.

What to expect

The DLR Institute of Vehicle Concepts researches novel vehicle structures. Certain structural parts for these vehicles are manufactured with Robotic Screw Extrusion Additive Manufacturing (SEAM). Robotic SEAM is a novel 3D printing process facilitated by Yizumi Space A hybrid manufacturing cell.
Space A system enables processing of standard granules as a raw product with high build-up rates and is used, for example, in the production of structural parts for the DLR Next Generation Car family. Space A employs two 6-Axis High Accuracy KUKA robots as positioning system to the screw extruder print module and a 2-Axis KUKA DKP as a build platform.
In order to increase the production quality of the structural parts with Space A, it is critical to realize the inaccuracies and anomaly of the overall production process so that it can be studied and if possible tuned to desired. A heterogenous dataset that capsulate data from pre-production, production and post-production phase all together can help to realize anomalies within overall production. Pre-production data mainly involves CAD data, CAM parameters etc. whereas production data is majorly (positioning) timeseries data that is fetched with high frequency through the production line.

The part of your work would be to at first get familiar with the Space A Robotic SEAM production line, production dataset and data acquisition techniques. Then you must learn, tune and employ the inhouse heterogenous data management system to record data and engineer features that can narrate the production with respect to the trajectory. Finally, you must thoroughly analyze the feature vectors via machine learning models to draw a comparative conclusion.

Your tasks

thorough literature review
understanding the process chain, process parameters and data acquisition techniques (KUKA RSI and OPC UA)
working with heterogeneous research data management system
organizing data for consistency and completeness
synchronize time series data for integrated process analysis and then engineer features
train ML model/s and analyze results through plots
document the decisions, challenges and results

Your profile

Masters Student majoring in Data Science, Machine Learning, Computer Science, Informatics, Mechatronics, Robotics or relevant
proficiency in Python programming language and ML libraries
familiarity with data processing and feature engineering
structured and responsible way of working

We offer

DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified.

We look forward to getting to know you!

If you have any questions about this position (Vacancy-ID 1987) please contact:

Mr. Pradnil Kamble
Phone: 0711/6862-8471