Architecture for Anomaly Localization: Concept and Implementation
Fraunhofer-Gesellschaft
full-time
Posted on:
Location Type: Office
Location: Stuttgart • Germany
Visit company websiteExplore more
Tech Stack
About the role
- Design, implementation, and evaluation of a modular system architecture for anomaly localization in compressed air systems based on Physics-Informed Neural Networks (PINNs)
- Structure sensor data acquisition, preprocessing, and modeling in a clear and reproducible way
- Explicitly incorporate physical system knowledge
- Integrate multiple modeling approaches (baseline and PINN-based methods)
- Enable robust and generalizable localization of anomalies
Requirements
- Enrolled at a German university or university of applied sciences (Fachhochschule)
- Strong analytical skills
- Programming experience in Python
- Interest in data-driven and physics-based methods
- Independent and structured working style
- Ability to design, implement, and evaluate innovative architecture and modeling approaches
Benefits
- Work in the exciting and innovative field of energy data analysis
- Pleasant working atmosphere within a motivated team
- Flexible working hours (e.g., to accommodate exam preparation)
- Home office available by arrangement
- If desired: close supervision with weekly coordination meetings
- Opportunity to contribute to publications
- Apply theoretical knowledge from your studies in practice and gain experience with the challenges of working with real-world data
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills & Tools
PythonPhysics-Informed Neural Networksdata acquisitiondata preprocessingmodelinganomaly localizationmodular system architecturemodeling approachesbaseline methodsgeneralizable localization
Soft Skills
analytical skillsindependent working stylestructured working styleability to designability to implementability to evaluateinnovative thinking