An intelligent selection method of iteration strategy and preconditioner for CFD sparse linear system based on structure-aware graph embedding

By using residual-driven sampling and structure-aware graph embedding models, combined with a decoupled integrated decision recommendation system, the iteration strategy and preconditioner for CFD sparse linear systems are intelligently selected, solving the problems of physical consistency and long-tail distribution in CFD simulation and improving simulation efficiency and stability.

CN121920100BActive Publication Date: 2026-06-09CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
2 Cites 0 Cited by

Patent Information

Application Number
CN202610352856.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-03-23
Publication Date
2026-06-09
Estimated Expiration
2046-03-23

AI Technical Summary

Technical Problem

Existing CFD sparse linear system solvers suffer from physical consistency issues and decision failures under long-tailed distributions in real CFD simulation scenarios, resulting in low simulation efficiency and a high risk of crashing.

Method used

A physically consistent dataset is constructed using a residual-driven sampling mechanism. A structure-aware graph embedding model and a decoupled ensemble decision recommendation system are used to intelligently select the iterative strategy and preconditioner for the CFD sparse linear system. The selection is then combined with a machine learning classifier and an automated hyperparameter optimization component.

Benefits of technology

It improves the efficiency of CFD numerical simulation, significantly reduces the risk of crashes during large-scale simulations, and enhances the accuracy of identifying long-tailed samples and the accuracy of predicting key samples for simulation success or failure.

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

Abstract

The application discloses an intelligent selection method of CFD sparse linear system iteration strategy and preconditioner based on structure-aware graph embedding, and relates to the technical field of computers, comprising: in the process of executing a target simulation task based on a CFD simulation software, collecting data by using a residual-driven sampling mechanism to obtain a physically consistent data set, performing graph modeling based on the physically consistent data set, and determining a graph embedding vector by using a graph modeling result and a structure-aware graph embedding model; determining a combination selection result of the CFD sparse linear system iteration strategy and the preconditioner based on the graph embedding vector and a decoupled integrated decision recommendation system; and completing a CFD numerical simulation operation corresponding to the target simulation task based on the combination selection result and the CFD simulation software. The application effectively solves the problems in the prior art, thereby improving the efficiency of CFD numerical simulation and reducing the collapse risk in large-scale simulation.
Need to check novelty before this filing date? Find Prior Art