Research Associate (f/m/d) Research focus: AI in the context of holistic turbine design, HAP2

Modern // regional // industry-oriented: The Brandenburg University of Applied Sciences (Technische Hochschule Brandenburg, THB) is a young and dynamic university with approximately 3,200 students enrolled in 26 study programmes across the Departments of Computer Science & Media, Engineering, and Business Administration, located in the city of Brandenburg an der Havel — directly at the doorstep of Potsdam and Berlin. As a family-friendly university on a green campus, we offer attractive working conditions.

Within the Department of Engineering, as part of the research project DaHKIZ (Data-based Holistic AI-supported Civil Engine Development), the following position with the opportunity to pursue a doctoral degree is to be filled at the earliest possible date, initially limited until 30 April 2029: in cooperation with Rolls-Royce Dtl.

Research Associate (f/m/d) Research focus: AI in the context of holistic turbine design, HAP2 The main focus of your work lies in the industrial research of Main Work Package HAP2 – AI in the context of holistic turbine design. You investigate original methods of Machine Learning (ML) and Artificial Intelli-gence (AI) for the multidisciplinary, robustness-oriented optimization (MDO) of high-pressure turbine components. As current approaches are not yet sufficiently robust for industrial use — due to the geomet-ric complexity of turbine blades (gas path and internal cooling channels) — data-driven methods shall enable a paradigm shift in holistic turbine design.

Your main responsibility

• Investigation of ML and AI strategies for the MDO of a turbine blade: down-selection and evaluation of original methods (e.g. Kolmogorov-Arnold Networks, bootstrapping ensembles, explainable AI) with sparse data sets., reduced order modeling ROM
• Investigation of ML and AI strategies for the dimensionality reduction of heterogeneous design spaces: analysis of methods (e.g. Kernel SVD, autoencoders) for high-dimensional, mixed continuous-discrete design parameter spaces including topological variations.
• Investigation of ML and AI strategies for robustness and reliability analysis: direct transformation of uncertainties into deterministic design parameters and data-driven ROM approaches for robustness-based optimisation.