Master Thesis Reliability Analysis and Uncertainty Quantification Using Generative AI for Batte[...]

Bosch Group; Stuttgart; Vor Ort; EUR 60.000 - 80.000; Vollzeit

Zusammenfassung

An innovative company is seeking a motivated Master's student for a thesis on uncertainty quantification in battery diagnostics. This exciting opportunity involves developing generative AI models to assess predictive uncertainties and improve battery diagnostic accuracy. You'll engage in state-of-the-art research, implementing and comparing various models while preparing synthetic data for study. Join a forward-thinking team committed to fostering diversity and inclusion, where your contributions will directly impact the future of autonomous driving technologies. If you're passionate about machine learning and eager to make a difference, this role is for you!

Qualifikationen

• Master studies in any field are required.
• Background in Machine Learning and Deep Learning is essential.

Aufgaben

• Review methodologies for uncertainty quantification based on generative AI.
• Develop a probabilistic surrogate model for battery diagnostics.

Kenntnisse

Machine Learning

Deep Learning

Reliability Engineering

Uncertainty Quantification

Communication Skills

Ausbildung

Master's Degree

Tools

PyTorch

Generative AI Models

Jobbeschreibung

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

With emerging technologies like autonomous driving and x-by-wire systems, the vehicle's onboard power supply system, known as the powernet, must meet stringent safety requirements. Failure of the powernet results in the loss of all safety-related functions such as braking, steering, and autonomous driving features. Special attention is given to batteries within the powernet due to their complex electrochemical nature. Accurate battery diagnosis is essential to predict performance, and safety validation ensures deviations are low under real-world conditions. To ensure robustness, uncertainty quantification (UQ) is necessary to assess prediction deviations. This thesis aims to develop a probabilistic surrogate model using generative AI models (e.g., Conditional Generative Adversarial Networks (cGAN), Conditional Normalizing Flows (cNF)) to quantify and distinguish different sources of uncertainty. It will also explore strategies to estimate failure probabilities with limited data while maintaining accuracy. Key research questions include how to quantify and separate epistemic and aleatory uncertainties, which generative AI models are best suited for capturing aleatory uncertainties, how to evaluate and calibrate the reliability of predicted uncertainties, the impact of data volume on uncertainty quantification accuracy, and effective failure probability estimation with small datasets.

• As part of your Master thesis, you will review state-of-the-art methodologies for uncertainty quantification (UQ) based on generative AI.
• You will prepare synthetic data for study.
• You will implement and compare different UQ models to evaluate their ability to accurately capture predictive uncertainty and distinguish between epistemic and aleatory uncertainty.
• You will improve prediction interval calibration to ensure robust and reliable uncertainty estimates.
• Finally, you will develop an approach to estimate battery diagnostic failure probability with minimal data using probabilistic surrogate models.

Qualifications

• Education: Master studies in any field.
• Experience and Knowledge: Background in Machine Learning, Deep Learning, Reliability or Uncertainty quantification; experience with PyTorch and deep generative models (cGANs, cNF); knowledge of battery diagnostics or systems is a plus.
• Personality and Working Practice: Self-motivated, proactive, and able to work independently.
• Languages: Very good communication skills in written and spoken German or English.

Additional Information

Start: According to prior agreement.
Duration: 3 - 6 months.

Requirement for this thesis is enrollment at a university. Please attach your CV, transcript of records, examination regulations, and if applicable, a valid work and residence permit.

Diversity and inclusion are integral to our culture. We welcome all applications regardless of gender, age, disability, religion, ethnicity, or sexual identity.

Need further information about the job?
Zhiyi Xu (Functional Department)
[phone]

#LI-DNI