| 注册

一种风向监督双流神经网络

耿浩冉 田浩 王成龙 宋宁 魏志强 冯毅雄 郭景任 聂婕

中国海洋大学学报(自然科学版)2024,Vol.54Issue(2):134-141,8.
中国海洋大学学报(自然科学版)2024,Vol.54Issue(2):134-141,8.DOI:10.16441/j.cnki.hdxb.20220485

一种风向监督双流神经网络

A Dual-Stream Neural Network Supervised by Wind Direction for One-Dimensional Burgers Equation

耿浩冉 1田浩 2王成龙 1宋宁 1魏志强 1冯毅雄 3郭景任 4聂婕1

作者信息

  • 1. 中国海洋大学信息科学与工程学部,山东 青岛 266100
  • 2. 中国海洋大学数学科学学院,山东 青岛 266100
  • 3. 浙江大学机械工程学院,浙江 杭州 310058
  • 4. 深圳中广核工程设计有限公司,广东 深圳 519000
  • 折叠

摘要

Abstract

Aiming at the problem that the single modeling method under the one-dimensional Burgers equation is difficult to fully consider the influence of wind direction on the coefficient at different stages,and cannot effectively obtain the relevant information between nodes.A wind direction supervised two-stream neural network is proposed to predict the finite difference coefficients of up and down wind direc-tions separately.At the same time,a wind direction judgment module is designed to realize the weight fusion of the predicted finite difference coefficients.The two-stream neural network is supervised by the wind direction,combined with the prior knowledge to assign a certain weight to the learned coefficients,so as to highlight the different influences of the upper and lower wind directions on the prediction re-sults,and can effectively realize the prediction of points in different wind directions,making the spatial structure characteristics Information mining is more sufficient,thereby improving the accuracy of differ-ential coefficient prediction.While the grid resolution is 4 to 8 times thicker than the traditional numeri-cal solution method,it improves the accuracy of the work of the Google team,thereby increasing the calculation speed.

关键词

风向监督双流神经网络/Burgers方程/机器学习/迎风格式/数据驱动离散化

Key words

wind direction supervised two-stream neural network/burgers equation/machine learn-ing/wind direction/data-driven discretization

分类

数理科学

引用本文复制引用

耿浩冉,田浩,王成龙,宋宁,魏志强,冯毅雄,郭景任,聂婕..一种风向监督双流神经网络[J].中国海洋大学学报(自然科学版),2024,54(2):134-141,8.

基金项目

国家重点研究发展计划项目(2020YFB1711700) (2020YFB1711700)

中央高校基本科研业务费专项资金项目(202042008) (202042008)

国家自然科学基金项目(62172376,62072418) (62172376,62072418)

山东省重大科技创新工程项目(2019JZZY020705)资助Supported by the National Key Research and Development Program of China(2020YFB1711700) (2019JZZY020705)

the Fundamental Research Funds for the Central Universities(202042008) (202042008)

the National Natural Science Foundation of China(62172376,62072418) (62172376,62072418)

the Major Scientific and Technological Innovation Project of Shandong(2019JZZY020705) (2019JZZY020705)

中国海洋大学学报(自然科学版)

OA北大核心CSTPCD

1672-5174

访问量0
|
下载量0
段落导航相关论文