A point cloud reconstruction method based on uncertainty feature enhancement for aerodynamic shape optimization

The precision of shape representation and the dimensionality of the design space significantly influence the cost and outcomes of aerodynamic optimization. The design space can be represented more compactly by maintaining geometric precision while reducing dimensions, hence enhancing the cost-effectiveness of the optimization process. This research presents a new point cloud Autoencoder Based on Uncertainty Feature Enhancement (AE-BUFE) architecture, designed to attain efficient and precise generalized representations of 3D aircraft through uncertainty analysis of the deformation relationships among surface grid points. The deep learning architecture consists of two components: the uncertainty index-based feature enhancement module and the point cloud autoencoder module. It learns the shape features of the point cloud geometric representation to establish a low-dimensional latent space. To assess and evaluate the efficiency of the method, a comparison was conducted with the prevailing point cloud autoencoder architecture and the proper orthogonal decomposition linear dimensionality reduction method under conditions of complex shape deformation. The results show that the new architecture significantly improves the extraction effect of the low-dimensional latent space. Then, this paper developed the surrogate-based optimization framework based on the AE-BUFE parameterization method and completed a multi-objective aerodynamic optimization design for a wide-speed-range vehicle considering volume and moment constraints. While ensuring the take-off and landing performance, the aerodynamic performance is improved under transonic and hypersonic conditions, which verifies the efficiency and engineering practicability of this method.