Mandatory Internship Development and Validation of Conventional and AI-Based Electric Arc Detection Methods for Next-Generation Automotive Electrical Systems

Electric arc detection represents a critical safety and reliability challenge in modern and future automotive electrical systems. As vehicles transition to electrified powertrains with increasingly complex higher-voltage architectures (e.g. the new 48 V voltage level system) the risk of electrical arcing caused by various failure modes including electrode degradation connector faults wire damage and intermittent contacts poses a significant threat to vehicle safety and system performance. Undetected electrical arcs can lead to: safety hazards: fire risk thermal damage and potential harm to occupants; system reliability issues: component degradation unexpected system failures and reduced operational lifetime; performance degradation: power delivery interruptions electromagnetic interference affecting sensitive electronics. Current arc detection methods face limitations in accurately distinguishing between genuine arc events and normal operational transients across diverse load types (resistive inductive power electronics) and environmental conditions (noise impedance variations electromagnetic disturbances). The automotive industry urgently requires robust intelligent detection algorithms capable of operating reliably in real-world conditions while minimizing false positives and negatives. This internship addresses this critical need by combining cutting-edge AI/ML technologies with comprehensive experimental validation to develop next-generation arc detection solutions for future automotive electrical systems.

• During your internship you will establish a comprehensive arc detection database through systematic measurement and data collection across various load types: Resistive (R) Inductive (I) and Power electronic loads (P); arc types: series and parallel arcs; arc scenarios: electrode degradation plug/connector faults guillotine wire cuts pendulum-type contact and intermittent contacts; environmental conditions: various noise levels impedance variations and electromagnetic disturbances.
• You will benchmark existing arc detection methods (ZoneArc Vbased Ibased and other commercial solutions) through development and verification using collected data.
• In addition you will validate them under real test conditions using test bench infrastructure and assess their performance via Monte Carlo simulations for robustness analysis.
• Furthermore you will prototype novel AI/ML-based arc detection algorithms utilizing: Deep Learning (DL) Convolutional Neural Networks (CNN) Recurrent Neural Networks (RNN) Support Vector Machines (SVM) and AutoEncoder architectures AI-generative modelling to enhance and expand training datasets.
• Last but not least you will validate all methods using professional test bench equipment. The Standalone ArcBench with electronic loads (resistive power current PWM capabilities) and the Integrated with realistic load benches including ZoneECU EPS (steering system) brake systems and Cooling Fan components.

Qualifications :

• Education: Master studies in the field of Electrical Engineering Automotive Engineering or comparable
• Experience and Knowledge:
  • strong academic record with coursework in power electronics signal processing and/or Machine Learning
  • proficient programming skills in Python and/or MATLAB
  • familiarity with automotive electrical systems and safety standards
  • experience with experimental work and measurement equipment
• Personality and Working Practice: you are an adaptable self-motivated individual who can work independently; you have strong teamwork skills; you are detail-oriented committed to quality as well as eager to learn new technical domains
• Enthusiasm: for emerging automotive technologies
• Languages: business fluent in German and English

Additional Information :

Start: according to prior agreement
Duration: 3 - 6 months (confirmation of mandatory internship required)

Requirement for this internship is the enrollment at university. Please attach your CV transcript of records enrollment certificate 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

Work #LikeABosch starts here: Apply now!

#LI-DNI

Remote Work :

No

Employment Type :

Full-time