Generative Modeling for Flap Kinematics: Enhancing Design Pipelines with Variational Autoencoders

The preliminary design of high-lift configurations for fixed-wing aircraft is a complex, multi-disciplinary task usually relying on extensive Design of Experiment (DoE) studies. This work presents a Variational Autoencoder (VAE)-based pipeline for generating Adaptive Dropped-Hinge Flap (ADHF) concepts that satisfy engineering constraints on cruise drag, separation behavior, and actuation efficiency. Trained on a curated set of desirable designs, the VAE produces novel configurations with characteristics similar to proven solutions, enabling efficient exploration of the design space. A post-processing framework evaluates these candidates and relates them to the original user input. The ADHF-VAE pipeline delivers a broader and higher-quality range of designs in significantly fewer iterations than standard DoE, providing improved starting points for downstream aerodynamic, kinematic, and integration analyses. This framework represents a first step towards automated, data-driven synthesis of high-lift systems for future aircraft design.