A large-scale three-dimensional flow field-oriented computing method, system and medium

By constructing a training dataset and modifying the input and output of a point cloud neural network, combined with a sampling method without replacement, the problems of grid size and accuracy in 3D flow field prediction in existing technologies are solved, and efficient and reliable prediction of complex 3D flow fields is achieved.

CN121902706BActive Publication Date: 2026-05-26CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
Filing Date
2026-03-23
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing intelligent CFD methods are difficult to directly transfer to 3D scenes, cannot handle 3D flow fields with complex shapes, have limited mesh size, and have uncontrollable prediction errors, which cannot meet the engineering accuracy requirements of the aerospace field.

Method used

A training dataset is constructed, the input and output dimensions and loss function of the point cloud neural network are modified, and the point cloud neural network is trained using a sampling-without-replacement method. This method is applicable to 3D spatial meshes of any size and type, and is combined with CFD software for flow field prediction.

Benefits of technology

It enables efficient prediction of three-dimensional flow fields of arbitrary type and scale, improves prediction accuracy and reliability, and meets the engineering needs of the aerospace field.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121902706B_ABST
    Figure CN121902706B_ABST
Patent Text Reader

Abstract

This application relates to the field of three-dimensional flow field technology, and discloses a computational method, system, and medium for large-scale three-dimensional flow fields. The method includes: constructing a training dataset; modifying the input and output dimensions and loss function of a point cloud neural network; inputting the coordinates of each point in the point cloud of the training dataset and the flight state of the aircraft into the modified point cloud neural network for training; minimizing the final loss function to obtain a trained point cloud neural network model; and outputting the physical quantities corresponding to the training dataset. For a three-dimensional spatial grid of arbitrary size, the point cloud neural network model is used to predict the physical quantities corresponding to the three-dimensional spatial grid of arbitrary size to obtain the three-dimensional flow field. The obtained three-dimensional flow field is then read using CFD software and used as the initial flow field to obtain the final three-dimensional flow field corresponding to the three-dimensional spatial grid of arbitrary size. This application can improve the computational efficiency of three-dimensional flow fields while ensuring reliability.
Need to check novelty before this filing date? Find Prior Art