High-speed train surface sparse pressure field reconstruction method, device and electronic equipment

By generating a dense pressure field through a node selection network and a coordinate encoder, the problems of low reconstruction accuracy and insufficient generalization ability in existing technologies are solved, and high-precision reconstruction and robustness improvement are achieved under complex flow conditions.

CN122174610APending Publication Date: 2026-06-09INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
INST OF AUTOMATION CHINESE ACAD OF SCI
Filing Date
2026-01-28
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing deep learning-based methods for reconstructing the surface pressure field of high-speed trains suffer from low reconstruction accuracy under complex flow conditions, insufficient generalization ability when data is scarce, and a lack of perception of three-dimensional spatial geometric location information, resulting in local reconstruction distortion and poor physical consistency.

Method used

A pre-trained reconstruction model, including a node selection network, a coordinate encoder, and a pressure field reconstruction network, is used to generate a dense pressure field by selecting sampling nodes, encoding spatial relationship information, and using the Charbonnier loss function to optimize model parameters. The node selection network and coordinate encoder are combined to extract spatial features and generate a dense pressure field.

Benefits of technology

It significantly improves reconstruction accuracy and multi-condition generalization ability under complex flow conditions, avoids local reconstruction distortion and physical conservation violations, improves robustness and physical consistency, and can better adapt to complex flow conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122174610A_ABST
    Figure CN122174610A_ABST
Patent Text Reader

Abstract

This invention provides a method, apparatus, and electronic device for reconstructing a sparse pressure field on the surface of a high-speed train. The method employs a pre-trained reconstruction model, which includes a node selection network, a coordinate encoder, and a pressure field reconstruction network. The method includes: selecting multiple sampling nodes from the pressure field point cloud on the high-speed train surface using the node selection network as recommended sensor placement locations; generating a pressure field feature vector based on the selected sampling nodes and the input pressure field point cloud; acquiring the three-dimensional coordinates corresponding to the multiple sampling nodes and constructing a coordinate matrix; encoding the coordinate matrix using the coordinate encoder to extract spatial information feature vectors representing the spatial relationships between all sampling nodes; and generating a dense pressure field based on the pressure field feature vectors and the spatial information feature vectors using the pressure field reconstruction network. This invention improves the reconstruction accuracy of the pressure field on the surface of high-speed trains under complex operating conditions and enhances its multi-condition generalization capability.
Need to check novelty before this filing date? Find Prior Art