Stuttgart, Baden-Württemberg, Germany
Engineer combining physical system expertise with AI & data-driven methods to solve complex challenges in automotive and energy. 🔋Current focus: - Industry PhD on State-of-Health (SoH) battery modeling using large-scale telematics data. Contributing to a standardized European framework for predictive battery analytics. ⚡Core expertise & impact: - Real-time simulation of fuel cell systems (Hardware-in-the-Loop): Reduced complex fuel cell simulation runtime by 97.8% through ANN-based hybrid modeling. - Predictive maintenance using machine learning: Predicted valve failures 300 cycles in advance via ML-based time-series analysis. - Smart factory solutions and digitalized production: Implemented MES/SAP-based traceability systems at Bosch, enabling transparent prototype production. 💡Strength: Combining physical system knowledge (thermodynamics, electrochemistry, mechanics) with AI and big data, enabling reliable, scalable and industry-ready solutions for next-generation energy and mobility technologies.
- Conducting an industry-focused PhD on State-of-Health (SoH) battery modeling using large-scale telematics data. - Bridging deep learning, advanced data analytics and engineering expertise in electrochemistry and degradation mechanisms. - Delivering standardized, actionable outputs for a Europe-wide predictive battery analytics framework, enabling scalable and industry-ready solutions.
- Developing real-time capable fuel cell simulation for Hardware-in-the-Loop (HIL) testing in automotive and energy applications - Hybrid approach combining Artificial Neural Networks (ANN), physics-based simplifications & lookup tables - Achieved 97.8 % reduction in simulation runtime compared to full physical/mathematical models, maintaining high fidelity to original prototypes - Focused on electrochemistry, thermodynamics and system integration to ensure industrial-grade, scalable solutions - Validated models against prototype data for real-world reliability and applicability
- Executed prototype manufacturing for ESP and ABS systems, integrating digital production workflows - Led and coordinated digitalization projects, from planning to implementation - Applied Industry 4.0 solutions to enhance production transparency and efficiency - Conducted advanced data analysis and predictive modeling - Bridged academic knowledge in engineering with hands-on industrial challenges
- Conducted a feasibility study on predicting unexpected valve failures using large-scale data - Implemented Artificial Neural Networks (ANN) to anticipate failures up to 300 cycles in advance - Achieved cost reduction and prevented faulty tests through early detection - Demonstrated practical applications of predictive modeling to solve industrial challenges