Particle trajectory reconstruction method and device based on flow state perception implicit neural representation, equipment and medium
By employing a particle trajectory reconstruction method based on flow-perception implicit neural representation, and combining multilayer perceptron and implicit neural representation models with Taylor expansion and automatic differentiation techniques, the particle trajectory reconstruction model is optimized. This solves the problems of high computational resource consumption and limited accuracy of traditional methods in complex flow fields, and achieves efficient and high-precision particle trajectory reconstruction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-03
AI Technical Summary
Traditional particle trajectory reconstruction methods consume large amounts of computational resources and have limited accuracy in complex flow fields, especially when dealing with high-dimensional data and complex flow fields.
The particle trajectory reconstruction method based on fluid-sensing implicit neural representation constructs a spatiotemporal position embedding network using a multilayer perceptron and implicit neural representation model. It combines Taylor expansion and automatic differentiation techniques and optimizes the particle trajectory reconstruction model through a multi-scale residual learning module and target constraints.
It achieves high-precision particle trajectory reconstruction, effectively restores the particle motion law of complex flow fields, and improves reconstruction efficiency and accuracy.
Smart Images

Figure CN122088216B_ABST
Abstract
Citation Information
Patent Citations
Outdoor unbounded scene three-dimensional reconstruction method and system based on neural radiation field
CN116051740A
Incompressible turbulent flow field prediction method based on potential diffusion model
CN121145732A