Methods, systems, equipment and storage media for generating aerodynamic shapes of aircraft

By combining diffusion models and deep learning models, multiple complete aerodynamic parameter matrices are generated and shape representation data is predicted, solving the problems of high computational cost and unstable generation in aircraft aerodynamic shape design, and realizing efficient and diverse aerodynamic shape generation.

CN122087941APending Publication Date: 2026-05-26CHINA ACAD OF AEROSPACE AERODYNAMICS
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA ACAD OF AEROSPACE AERODYNAMICS
Filing Date
2025-12-30
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

In existing technologies, the aerodynamic shape design of aircraft relies on empirical formulas and parametric modeling, which has high computational costs and unstable and undiversifiable results. Direct mapping is prone to ill-conditioned problems, and existing generative models lack structural awareness.

Method used

Multiple sets of complete aerodynamic parameter matrices are generated through a diffusion model. After filtering, the data is input into a deep learning model to predict the shape representation data. The shape representation is performed using structure-aware models such as the Transformer architecture, convolutional neural networks, and graph neural networks, supporting multiple representation methods such as explicit parameters, latent space encoding, and point cloud data.

Benefits of technology

It achieves efficient and stable aerodynamic shape generation of aircraft, avoids the problems of direct mapping, improves the diversity and physicality of the generated results, and reduces computational costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122087941A_ABST
    Figure CN122087941A_ABST
Patent Text Reader

Abstract

This application provides a method, system, device, and storage medium for generating the aerodynamic shape of an aircraft. The method includes: receiving aerodynamic parameter setting requirements input by a user; inputting the aerodynamic parameter setting requirements into a diffusion model to generate multiple sets of complete aerodynamic parameter matrices, wherein the complete aerodynamic parameter matrices include parameters under different flight conditions; filtering the multiple sets of complete aerodynamic parameter matrices based on differences in aerodynamic characteristics to obtain a filtered matrix scheme; inputting the filtered matrix scheme into a deep learning model to predict the aircraft's shape representation data; and drawing the final aerodynamic shape based on the shape representation data. This application proposes a transparent process including key parameter setting, complete aerodynamic parameter matrix generation, and shape representation data generation; first, the complete aerodynamic parameter matrix is ​​generated from the key aerodynamic parameter setting requirements, and then the shape representation data is predicted by a deep learning model using the final filtered scheme, effectively avoiding the problems of direct mapping.
Need to check novelty before this filing date? Find Prior Art