Geometry-augmented machine learning for drawability assessment across dissimilar U-shaped geometries under sparse data

Machine learning for drawability prediction in industrial settings faces significant challenges due to the high diversity of real-world geometries and the limited availability of directly usable historical data. Existing models often overfit to a limited family of geometries sharing the same parametrization, and consequently fail to generalize beyond that group to geometrically more diverse components. We propose geometry-based data augmentation methods and synthetic data generation to address generalization limitations. Both augmentation and machine learning model development utilize a base dataset derived from 90 real-world U-shaped parts, reflecting industry-relevant shape variability, within the common class of U-shaped deep drawing geometries. Evaluations with graph and point cloud models indicate that our geometry augmentation improves classification accuracy and reduces test accuracy variance, outperforming the isolated use of synthetic data and enabling improved generalization to unseen U-shaped geometries. Our best drawability classifier achieves almost 90% cross-validated accuracy by using augmented and synthetic data to expand a training set originally limited to 60 samples. Although the augmented geometries require simulation-based labeling and are loosely tailored to U-shaped sheet metal geometries, they contribute to more robust and generalizable model performance, with gains that can exceed the impact of the model choice in a sparse-data scenario. Hence, geometry data augmentation appears to emerge as a key enabler for foundation models capable of geometric generalization for data-driven tasks such as the drawability assessment investigated here. This, in turn, helps accelerate development processes.