This master thesis presents an exciting opportunity to validate AI-based temperature field predictions and thermal mechanical fatigue (TMF) life predictions for head valve seat bridges. As the internal combustion engine (ICE) continues to evolve, accurately predicting thermal conditions and fatigue life is essential for enhancing reliability and performance while minimizing costly physical prototype testing. The thesis provides a unique platform to engage in cutting-edge research that integrates numerical modeling and AI methodologies. This project will leverage sophisticated simulation tools to compare AI predictions against established data, thereby enhancing the fidelity of thermal simulations. By analyzing key factors such as temperature, geometry, and coolant flow, the student will contribute to the understanding of how these elements affect the life cycle of valve seat bridges.
* Review and analyze existing simulation and test data from AVL iCA FE and powertrain databases
* Validate AI-based temperature field predictions compared to virtual simulations
* Validate AI-based TMF predictions against thermal shock tests and virtual simulations
* Identify key parameters (e.g., temperature, geometry, coolant flow) influencing temperature and TMF life prediction
* Develop and train an AI model to predict temperature and TMF of valve seat bridges
* Confirm simulation accuracy by identifying and validating key parameters influencing thermal fatigue life
* Bachelor of Science in domains similar to Mechanical Engineering, Physics or a related field
* Interest in Internal Combustion Engine (ICE) technology and conducting mechanical analysis using numerical modeling and simulation techniques
* Familiarity with structural mechanics principles and 3D Finite Element Analysis (FEA) simulation methods is appreciated
* Strong interest in AI methodologies and programming, particularly with Python, for developing and automating various aspects of the project