A convolutional neural network-based model for reconstructing free surface flow fields

被引:0
|
作者
Wang, Jiahui [1 ]
Xiao, Hong [1 ]
机构
[1] Sichuan Univ, State Key Lab Hydraul & Mt River Engn, Chengdu 610065, Sichuan, Peoples R China
基金
中国国家自然科学基金;
关键词
DEEP; OPTIMIZATION; RECOGNITION;
D O I
10.1063/5.0248883
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
This paper introduces hydrological computational fluid dynamics model (HydroCFD), a deep learning model based on the convolutional neural network U-Net framework designed for reconstructing free surface flow fields. With well-posed boundary and initial conditions, the model rapidly generates a result that approximates the two-dimensional (2D) shallow water equations, significantly improving the efficiency of obtaining free surface flow fields compared to traditional computational fluid dynamics methods. The framework features an input layer that integrates water depth and terrain (hydrological element variables), and incorporates a new loss function, coefficient of variation loss function (CVLoss), based on the variation coefficient to improve accuracy and stability. HydroCFD is trained and validated on two different datasets, open channel flows with a groin, and with an abrupt expansion. Error analysis demonstrated that HydroCFD achieves high precision in reconstructing 2D free surface flow fields. Furthermore, a comparison of six different loss functions reveals that CVLoss contributes to improved accuracy and computational stability.
引用
收藏
页数:21
相关论文
共 50 条
  • [31] Deep Convolutional Neural Network-Based Detector for Index Modulation
    Wang, Tengjiao
    Yang, Fang
    Song, Jian
    Han, Zhu
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (10) : 1705 - 1709
  • [32] Deep Convolutional Neural Network-Based Approaches for Face Recognition
    Almabdy, Soad
    Elrefaei, Lamiaa
    APPLIED SCIENCES-BASEL, 2019, 9 (20):
  • [33] Convolutional Neural Network-Based Signal Classification in Real Time
    Cetin, Ramazan
    Gecgel, Selen
    Kurt, Gunes Karabulut
    Baskaya, Faik
    IEEE EMBEDDED SYSTEMS LETTERS, 2021, 13 (04) : 186 - 189
  • [34] A New Convolutional Neural Network-Based System for NILM Applications
    Ciancetta, Fabrizio
    Bucci, Giovanni
    Fiorucci, Edoardo
    Mari, Simone
    Fioravanti, Andrea
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70 (70)
  • [35] Convolutional neural network-based reconstruction for positronium annihilation localization
    Jegal, Jin
    Jeong, Dongwoo
    Seo, Eun-Suk
    Park, HyeoungWoo
    Kim, Hongjoo
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [36] Convolutional neural network-based registration for mosaicing of microscopic images
    Zhang, Junhua
    Huang, Yihua
    Song, Yingchao
    Jiang, Yi
    Zhang, Lun
    Zhang, Yufeng
    JOURNAL OF ELECTRONIC IMAGING, 2019, 28 (04)
  • [37] Convolutional Neural Network-Based Tire Pressure Monitoring System
    Marton, Zoltan
    Szalay, Istvan
    Fodor, Denes
    IEEE ACCESS, 2023, 11 : 70317 - 70332
  • [38] Convolutional Neural Network-Based Approach for Citrus Diseases Recognition
    Dong, Caixia
    Xu, Zheling
    Dai, Luanyuan
    Liu, Weinan
    Chen, Quan
    Liu, Yizhang
    Yang, Changcai
    Zou, Tengyue
    2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 1495 - 1499
  • [39] Convolutional neural network-based models for diagnosis of breast cancer
    Masud, Mehedi
    Rashed, Amr E. Eldin
    Hossain, M. Shamim
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (14): : 11383 - 11394
  • [40] Residual Convolutional Neural Network-Based Dysarthric Speech Recognition
    Kumar, Raj
    Tripathy, Manoj
    Anand, R. S.
    Kumar, Niraj
    ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2024, 49 (12) : 16241 - 16251