Thesis - Adaptive Surrogate Modeling for Vehicle Dynamics

We are Geely Technology Europe. A unified European R&D centre within Geely Auto Group, where world-class engineers, developers and innovators push the boundaries of intelligent mobility. Our mission is to shape the next generation of vehicle architectures, digital technologies and intelligent systems for global markets. We integrate European customer and regulatory requirements early in the development process and support multiple brands within the Geely portfolio, including Zeekr, Lynk & Co and Geely. With nearly two decades of engineering experience in Europe, we continue to build smart, sustainable and user‑centric mobility solutions. Thesis title: Development of a Reusable Multi-Fidelity and Adaptive Surrogate Modeling Framework for Vehicle Dynamics Applications Project Description: High-fidelity vehicle dynamics simulations are essential for evaluating and optimizing vehicle performance, but they can require significant computational effort, especially when large design spaces and multiple parameter combinations need to be investigated. The objective of this thesis is to investigate and develop a reusable framework for multi-fidelity surrogate modelling and adaptive sampling in vehicle dynamics engineering. The framework shall combine information from simulation models with different levels of fidelity and computational cost in order to reduce the number of expensive high-fidelity simulations required for design exploration and optimization. The work will include the definition of a generic architecture for handling design variables, simulation models, fidelity levels, sampling strategies, surrogate models, uncertainty estimation and optimization workflows. Adaptive sampling methods shall be investigated to identify the most informative additional simulation points during the surrogate model development process. The framework should be designed to remain independent of one specific vehicle dynamics problem and should therefore support different simulation models and engineering use cases through configurable interfaces or adapters. The developed methodology shall be demonstrated and evaluated using representative vehicle dynamics applications, for example suspension K&C, ride, handling or suspension parameter optimization. The evaluation should focus on prediction accuracy, robustness, computational efficiency and the reduction in required high-fidelity simulation effort compared with conventional DOE-based approaches. The expected outcome is a functional prototype and an evaluated methodology that can serve as a reusable foundation for future surrogate-based vehicle dynamics development and optimization workflows. Key focus areas: - Multi-fidelity modelling for vehicle dynamics applications - Definition and management of low-, medium- and high-fidelity simulation models - Surrogate modelling and machine learning for engineering simulation - Adaptive sampling and active learning strategies - Uncertainty estimation and model confidence assessment - Efficient exploration of high-dimensional design spaces - Integration of different simulation environments through configurable interfaces or adapters - Automated generation and management of simulation datasets - Sensitivity analysis and identification of relevant design variables - Surrogate-based optimization and design-space exploration - High-fidelity verification of surrogate-based predictions and optimization results - Comparison with conventional DOE and single-fidelity surrogate modelling approaches - Evaluation of framework reusability across different vehicle dynamics use cases Your skills and background - Suitable for Master’s students in Mechanical Engineering, Automotive Engineering, Mechatronics, Applied Mathematics, Computer Science, Data Science or a related field. - A strong interest in combining vehicle dynamics simulation, machine learning and engineering optimization is particularly important. Relevant knowledge or interest in several of the following areas would be beneficial: - Vehicle dynamics and automotive simulation - Adams/Car, MATLAB/Simulink or comparable CAE tools - Python or MATLAB for scientific computing and automation - Machine learning and regression methods - Surrogate modelling or reduced-order modelling - Design of Experiments and statistical analysis - Optimization methods - Sensitivity analysis and uncertainty quantification - Software development and modular software architecture - Data processing and visualization of engineering simulation results - Version control and reproducible simulation workflows Why you should join Geely Tech Eu We are engineers, developers, and innovators from around the world. Joined together by entrepreneurship, our unique blend of global culture, and a belief in a smarter more sustainable future. At Geely Tech Eu we fast-track innovation and transform ideas into pioneering technology solutions, doing your master thesis here is no different. We are convinced that a thesis project is a major contribution to our innovation capabilities and long-term development. You'll have a great opportunity to use your skills and creativity to push the boundaries of what´s possible. What happens when you apply If this sounds interesting and you match the requirements, please don't hesitate to submit your application with a CV and cover letter. Shortlisted candidates will be contacted for an interview to further discuss the project's details and expectations. This thesis project is intended for 1-2 student Supervisor: Mingji Fang, Senior Specialist AI, mingji.fang@zeekrtech.eu, please contact for more information about the project Starting date: January 2027 Last application date: 2026-11-25 Apply today. We will perform ongoing selection during the application period. We look forward to hearing from you! Please note that due to GDPR regulations, we can only accept applications sent through the recruitment system, not via email or other channels.