Master's Thesis Student: Automated Plausibility Checking of 1-D Simulation Results for Dynamic Load Cases

As part of the thesis, approaches for automated error detection in 1D simulation results (time series) will be developed further and evaluated. The question is whether detection is also possible for dynamic load cases with vehicles of different drive topologies. A previous thesis already developed an autoencoder method that reliably detects anomalies in BEV vehicles performing acceleration maneuvers. These methods are to be extended to more dynamic load cases such as the WLTP or circuit maneuvers and to further vehicle topologies, and integrated into a data pipeline so the baseline behavior can be updated continuously. Finally, feasibility is checked in a proof of concept.

• Literature research on the state of the art (unsupervised machine learning, clustering, anomaly detection, autoencoders)
• Review of existing methods
• Extension of existing methods
• Development of a comprehensive validation concept
• Confirming feasibility in a proof of concept
• Documentation of results

• Fields of study: Computer Science or similar, technical degree programs focused on software development and machine learning
• Study focus: ML, AI, data analytics
• Technical skills: TensorFlow, PyTorch, RayTune or similar
• IT skills: Python, MATLAB (desirable)
• Language skills: German (B2) and English (B2)
• Independent and structured way of working, teamwork and communication skills