Master Thesis Data Augmentation with Physics-Guided Diffusion Models for Probabilistic Safety Assessment of Battery Diagnosis
Master Thesis Data Augmentation with Physics-Guided Diffusion Models for Probabilistic Safety Assessment of Battery Diagnosis
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
With the emerging technologies like autonomous driving and xbywire systems the vehicles onboard power supply system also known as the powernet is subject to stringent safety requirements. Failure of the powernet leads immediately to the loss of all the safetyrelated functions such as braking steering autonomous driving features etc. Among all the powernet components special attention shall be paid on batteries due to their complex electrochemical nature. However limited realworld data often hinders the development of reliable battery diagnostic models. To address this this project explores the use of diffusion models for data augmentation improving uncertainty quantification (UQ) and enabling probabilistic safety assessment. Diffusion models have demonstrated stateoftheart performance in highfidelity data generation making them a promising approach for enhancing battery diagnostics with synthetic but realistic data. The research questions are: how can diffusion models be used to generate high quality synthetic battery data how can we integrate diffusion models with physically informed priors for more realistic data generation using less data what is the impact of data augmentation on failure probability estimation in battery diagnostics.
- As part of your Master thesis you will assist us in conducting a comprehensive literature review on diffusion models and physicsguided generative models for data augmentation.
- You will implement a diffusion model (e.g. DDPM DDIM or conditional diffusion models) to generate battery data using PyTorch.
- In addition you will compare diffusion models with GANs in terms of data fidelity uncertainty quantification and robustness.
- Last but not least you will validate the impact of synthetic data on battery diagnostics and probabilistic safety assessment.
Qualifications :
- Education: Master studies in any field
- Experience and Knowledge: background in Machine Learning Deep Learning PhysicsInformed AI etc.; experience with PyTorch and deep generative models (GANs VAEs or diffusion models); knowledge of battery diagnostics or battery systems is a plus
- Personality and Working Practice: you are a selfmotivated and proactive person who is 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 the enrollment at university. Please attach your CV transcript of records examination regulations and if indicated a valid work and residence permit.
Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore we welcome all applications regardless of gender age disability religion ethnic origin or sexual identity.
Need further information about the job
Zhiyi Xu (Functional Department)
49 2
#LIDNI
Remote Work :
No
Employment Type :
Fulltime
Employment Type
Full-time
