Method and system for simulating slow-release pollutant transport based on data-driven turbulence modeling

By introducing a loss function with physical constraints into the turbulence model and jointly training a deep learning model, the problem of scenario adaptability and reliability of the turbulence model in the simulation of slow-release pollutants from microscale solid powders is solved, achieving high-fidelity simulation of the slow-release gas propagation process and supporting urban environmental planning.

CN122334100APending Publication Date: 2026-07-03XI'AN PETROLEUM UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610719982.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-25
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing turbulence models suffer from insufficient scenario adaptability and simulation reliability when simulating the pollution distribution and dynamic behavior of gas released from microscale solid powders. Traditional models cannot accurately describe the complete process of solid powder propagation-gas release-gas diffusion, while deep learning-based turbulence viscosity models lack physical interpretability.

Method used

By integrating deep learning models with a numerical simulation framework for slow-release pollutants, a loss function containing physical constraints is introduced for joint training and optimization to construct a large-scale model for predicting turbulent viscosity. This model is then coupled with the transport and diffusion equations of slow-release pollutants to form a high-fidelity simulation method.

Benefits of technology

It achieves high-precision simulation of microscale solid powder slow-release pollutants in complex urban environments, ensuring the reliability and stability of model output results, comprehensively describing the solid powder propagation-gas slow release-gas diffusion process, and providing a scientific basis for urban environmental planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122334100A_ABST
    Figure CN122334100A_ABST
Patent Text Reader

Abstract

This application discloses a data-driven turbulence modeling-based method and system for simulating the transport of slow-release pollutants, relating to the field of artificial intelligence technology. The method includes: simulating the flow field of a three-dimensional ideal urban street valley physical model to obtain a flow field dataset; using this dataset to train and improve a deep learning model to obtain a large-scale turbulence viscosity prediction model; establishing a numerical simulation method for the transport and diffusion of slow-release pollutants, coupling it with the large-scale turbulence viscosity prediction model to obtain a numerical model for predicting the transport of slow-release pollutants; constructing a physical model of the target urban street, and using the numerical model for predicting the transport of slow-release pollutants to perform simulations and obtain simulation results. This method fills the gap in the lack of numerical models for predicting the dynamic behavior of slow-release pollutants from microscale solid powders, and solves the problem of weak physical interpretability in existing deep learning-based turbulence viscosity models. It achieves high-fidelity simulation of the gas release and migration process of slow-release solid particles in complex urban wind fields.
Need to check novelty before this filing date? Find Prior Art