@inproceedings{BertramJankeFlassigetal.2025, author = {Bertram, Hamun and Janke, Christian and Flassig, Robert and Flassig, Peter}, title = {Efficient ML-Based Prediction of Turbomachinery Blade Performance With B-Spline Surface Representation}, series = {ASME Turbo Expo 2025: Turbomachinery Technical Conference and Exposition, Memphis, Tennessee, USA, 2025}, booktitle = {ASME Turbo Expo 2025: Turbomachinery Technical Conference and Exposition, Memphis, Tennessee, USA, 2025}, publisher = {ASME}, isbn = {978-0-7918-8886-5}, doi = {10.1115/GT2025-152689}, pages = {13}, year = {2025}, abstract = {In turbomachinery blade design, rapid and accurate performance prediction is essential to accelerate optimization and reduce reliance on costly high-fidelity simulations. Traditional data-driven approaches often use dense surface point-cloud representations as input features, requiring extensive training datasets and computational resources. This work presents a more efficient methodology leveraging a compact B-Spline-based surface representation, where control points serve as input features, significantly reducing geometric dimensionality and computational overhead. A systematic Design of Experiments (DoE) is performed to generate a diverse set of blade geometries for NASA Rotor 67. Each design is evaluated via computational fluid dynamics (CFD) simulations in ANSYS CFX, providing key aerodynamic performance metrics such as isentropic efficiency. We train and compare Graph Convolutional Neural Networks (GCNN) and Random Forest Regression (RFR) models to predict blade performance directly from the reduced control-point parameterization. Incorporating first- and second-order geometric derivatives (gradients and Laplacians) into the feature set significantly enhances predictive accuracy and stability, capturing essential curvature-related flow physics. Results demonstrate that this B-Spline-based, CAD-centric methodology can achieve competitive accuracy in predictions with as few as 150-200 training simulations—comparable to other GCNN-based approaches. Consequently, the proposed framework reduces training overhead from days to minutes, enabling faster, more cost-effective turbomachinery design workflows and guiding optimization toward high-performing blade geometries.}, language = {en} } @inproceedings{MuellerMarkgrafVogeletal.2025, author = {M{\"u}ller, Katja and Markgraf, Klaus and Vogel, Andreas and Flassig, Peter and Flassig, Robert}, title = {Numerical Study of Ice Accretion on Fan Blades: Implications for the Design of Blade Geometries}, series = {ASME Turbo Expo 2025: Turbomachinery Technical Conference and Exposition, Memphis, Tennessee, USA, 2025}, booktitle = {ASME Turbo Expo 2025: Turbomachinery Technical Conference and Exposition, Memphis, Tennessee, USA, 2025}, publisher = {ASME}, isbn = {978-0-7918-8887-2}, doi = {10.1115/GT2025-152704}, pages = {12}, year = {2025}, abstract = {Ice formation on aircraft components due to the impact of supercooled droplets poses a severe safety risk. In particular, the formation of ice on the fan blades can lead to vibrations that affect the entire engine. While numerous studies have examined the effects of environmental conditions on ice accumulation, the influence of blade geometry has received little attention. This study investigates how variations in blade geometry affect ice accretion in a low-pressure compressor using a numerical approach. A Design of Experiments (DoE) is conducted on the NASA Rotor67, focusing on the sensitivity of ice formation to geometric modifications. The workflow includes geometry generation (ParaBlade), flow simulation (ANSYS CFX), and ice accretion modeling (ANSYS FENSAP-ICE) under rime ice conditions. The results reveal a strong correlation between the inlet metal angle and both accreted ice mass and maximum ice thickness. Furthermore, designs with good aerodynamic performance tend to exhibit higher ice accumulation. These findings enhance the understanding of icing behavior in low-pressure compressors and offer valuable insights for optimizing blade design in adverse environmental conditions.}, language = {en} }