Parametric model embedding

Methodologies for reducing the design-space dimensionality in shape optimization have been recently developed based on unsupervised machine learning methods. These methods provide reduced representations of design space, capable maintaining a certain degree original variability. Nevertheless, they usually do not allow to use directly parameterization method, representing limitation their widespread application industrial field, where parameters often pertain well-established parametric models, e.g. CAD (computer aided design) models. This work presents how embed parametric-model reduced-dimensionality representation space. The which takes advantage from definition newly-introduced generalized feature is demonstrated, as proof concept, reparameterization 2D Bezier curves and 3D free-form deformation spaces consequent solution simulation-driven problems subsonic airfoil naval destroyer calm water, respectively.