A data-driven method for reconstructing the flow field in a coupled water and fish scene

By constructing a coupled water and fish flow field dataset, and utilizing convolutional neural networks and the Eulerian-Lagrange method, rapid sharing and interaction of flow field information were achieved, solving the problems of high cost and low efficiency in traditional flow field simulation methods and improving simulation accuracy.

CN117236222BActive Publication Date: 2026-05-26CHINA INST OF WATER RESOURCES & HYDROPOWER RES
2 Cites 0 Cited by

Patent Information

Application Number
CN202311234813.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-22
Publication Date
2026-05-26
Estimated Expiration
2043-09-22

AI Technical Summary

Technical Problem

Traditional numerical simulation methods for flow fields are costly, inefficient, and have low accuracy. They are not suitable for widespread application and cannot fully consider the impact of fish on the flow field and the feedback effect of the flow field on fish swimming.

Method used

A data-driven flow field reconstruction method for water and fish coupled scenarios is adopted. A water and fish coupled flow field dataset is constructed through a CFD model, and a dynamic mesh of fish body and background is constructed using a convolutional neural network prediction method. The flow field is then rapidly reconstructed by combining the Eulerian-Lagrange method, so as to realize the sharing and interaction of flow field information.

Benefits of technology

It achieves speed and effectiveness in flow field reconstruction, improves the accuracy of flow field simulation, reduces computational costs, and is suitable for a wide range of applications.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention discloses a data-driven method for reconstructing the flow field in a water-fish coupled scenario, relating to the intersection of fluid mechanics and artificial intelligence. The method includes the following steps: using a CFD model to simulate the water-fish coupled flow field under various scenarios, constructing a water-fish coupled flow field dataset; based on the water-fish coupled flow field dataset, constructing dynamic meshes for the fish body and background using a convolutional neural network prediction method via a Lagrangian module; constructing convolutional neural network models for both the fish body and background dynamic meshes; and constructing a rapid flow field reconstruction model based on the convolutional neural network model and the Eulerian-Lagrangian method to accurately predict the water-fish coupled flow field. This invention solves the problems of high cost, low efficiency, low accuracy, and unsuitability for widespread application of traditional flow field numerical simulation methods.
Need to check novelty before this filing date? Find Prior Art