Student (f/m/x) - Explainable AI for Deep Learning-based Remaining Useful Life Prediction

Welcome to the Institute of Flight Systems Engineering. Our work focuses on the interaction between aircraft configuration, pilots and modern flight system technology. From flight dynamics to unmanned aerial vehicles, from simulation to real flight tests - we analyse, test and develop innovations that will shape the flying of the future.

What To Expect

To predict the Remaining Useful Life (RUL) of electromechanical flight control actuators (EMA) it is necessary to monitor mechanical components such as the ball bearings, e.g. by using acceleration measurements on the EMA housing. Due to continuous flight control surfaces adjustments combined with excessive loads during flight operation, the degradation behavior of the ball bearings becomes apparent in the monitored data. This degradation can then be modelled using deep learning-based health indicators as a basis for the RUL prediction.

However, due to the black box characteristics of deep learning models, the trustworthiness of the results is limited. Improving this trustworthiness is particularly relevant for such safety-critical systems. As part of a master's thesis, explainability approaches are therefore to be investigated.

Your tasks

• Literature review of existing deep learning-based health indicator construction methods
• Identification, preprocessing and preparation of existing databases
• Implementation of explainable AI methods in Python for run-to-failure data sets of rotating ball bearings
• Visualization of the results
• Characterization of the degradation behavior and the inherent uncertainties of the estimation process

Your profile

• Current enrollment in a Master’s program in Mechanical Engineering, Computer Science, Safety Engineering or a related field
• Good programming skills in Python
• Good knowledge in the field of artificial intelligence
• Good knowledge in the field of mechatronic systems and their dynamic behavior
• Very good English language skills

We look forward to getting to know you!

If you have any questions about this position (Vacancy-ID 2397) please contact:

Lauri Bodenröder
Tel.: