Masood, Z.; Kostas, K.V.; Khan, S.; Kaklis, P.D. Shape-Informed Dimensional Reduction in Airfoil/Hydrofoil Modeling. J. Mar. Sci. Eng.2023, 11, 1851.
Masood, Z.; Kostas, K.V.; Khan, S.; Kaklis, P.D. Shape-Informed Dimensional Reduction in Airfoil/Hydrofoil Modeling. J. Mar. Sci. Eng. 2023, 11, 1851.
Masood, Z.; Kostas, K.V.; Khan, S.; Kaklis, P.D. Shape-Informed Dimensional Reduction in Airfoil/Hydrofoil Modeling. J. Mar. Sci. Eng.2023, 11, 1851.
Masood, Z.; Kostas, K.V.; Khan, S.; Kaklis, P.D. Shape-Informed Dimensional Reduction in Airfoil/Hydrofoil Modeling. J. Mar. Sci. Eng. 2023, 11, 1851.
Abstract
Parametric models have been widely used in pertinent literature for reconstructing, modifying and representing a wide range of airfoil and/or hydrofoil profile geometries. Design spaces corresponding to these models can be exploited for modeling and profile-shape optimization under various performance criteria. Accuracy requirements, along with the need for modeling local features, often lead to high-dimensional design spaces that hinder the process of shape optimization and design through analysis. In this work, we propose a shape-informed dimensional reduction approach that attempts to tackle this deficiency by producing low-dimensional latent design spaces that can be efficiently used in shape representation and optimization. Furthermore, geometric moments are introduced in an attempt to cost-effectively capture analysis-relevant information that is generally expensive to produce. Specifically, geometric integral properties, although intrinsic features of the shape, are quite commonly related to performance indicators employed in performance optimization and therefore provide a cost-effective physics-informed component in the description of the design in the latent space. To this end, we employ the generalized Karhunen-Loeve expansion to produce a shape- and physics-informed subspace retaining the highest possible geometric variance and robustness, that is, lack of invalid designs. At the same time, a series of shape discretizations, encoding the foil's shape profile, are examined with regards to their effect on the resulting latent space's quality and efficiency. Our results demonstrate a significant reduction in the dimensionality of the original design space while maintaining a high representational capacity and a large percentage of valid geometries that facilitate fast convergence to optimal solutions in performance-based optimization.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
