Multi-domain physics-informed neural network for solving heat conduction and conjugate natural convection with discontinuity of temperature gradient on interface

被引:0
|
作者
WANG TongSheng
WANG ZhiHeng
HUANG Zhu
XI Guang
机构
[1] SchoolofEnergyandPowerEngineering,Xi'anJiaotongUniversity
关键词
D O I
暂无
中图分类号
TP183 [人工神经网络与计算]; O551.3 [物质的热性质];
学科分类号
摘要
Deep learning has been increasingly recognized as a promising tool in solving kinds of physical problems beyond powerful approximations. A multi-domain physics-informed neural network(mPINN) is proposed to solve the non-uniform heat conduction and conjugate natural convection with the discontinuity of temperature gradient on the interface. Local radial basis function method(LRBF) is applied to compute the case without the analytical solution and is regarded as the benchmark solver.Each physical domain matches a private neural network and all neural networks are connected by the shared information of temperature and heat flux on the interface. Joint training and separate training are utilized to minimize the loss function, which usually consists of the residual of boundary conditions, interface conditions and governing equations. Joint training minimizes the sum of all losses from neural networks with one shared optimizer, while separate training owns its private optimizer. Local adaptive activation function(LAAF) is used to accelerate the convergence and acquire a lower loss value when compared with its fixed counterpart. The numerical experiments on three types of residual points, uniform, Gauss-Lobatto and random, are conducted and it can be concluded that the uniform residual points can obtain the most accurate solution than the random and Gauss-Lobatto. Joint training is more accurate than the separate training when the number of residual points is relatively small,while the separate training performs better than the joint training for the large number of residual points. Numerous test cases on multi-domain heat transfer and fluid flow show the accuracy of the proposed m PINN. Local and global heat transfer rates show good agreements with the results from LRBF. Excepting the forward problems, the thermal conductivity ratio, the constant source and the characteristic parameters of natural convection are accurately learned from sparsely distributed data points.
引用
收藏
页码:2442 / 2461
页数:20
相关论文
共 30 条
  • [1] Multi-domain physics-informed neural network for solving heat conduction and conjugate natural convection with discontinuity of temperature gradient on interface
    TongSheng Wang
    ZhiHeng Wang
    Zhu Huang
    Guang Xi
    Science China Technological Sciences, 2022, 65 : 2442 - 2461
  • [2] Multi-domain physics-informed neural network for solving heat conduction and conjugate natural convection with discontinuity of temperature gradient on interface
    WANG TongSheng
    WANG ZhiHeng
    HUANG Zhu
    XI Guang
    Science China(Technological Sciences), 2022, (10) : 2442 - 2461
  • [3] Multi-domain physics-informed neural network for solving heat conduction and conjugate natural convection with discontinuity of temperature gradient on interface
    Wang TongSheng
    Wang ZhiHeng
    Huang Zhu
    Xi Guang
    SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2022, 65 (10) : 2442 - 2461
  • [4] Multi-domain physics-informed neural networks for solving transient heat conduction problems in multilayer materials
    Zhang, Benrong
    Wang, Fajie
    Qiu, Lin
    JOURNAL OF APPLIED PHYSICS, 2023, 133 (24)
  • [5] Multi-domain physics-informed neural network for solving forward and inverse problems of steady-state heat conduction in multilayer media
    Zhang, Benrong
    Wu, Guozheng
    Gu, Yan
    Wang, Xiao
    Wang, Fajie
    PHYSICS OF FLUIDS, 2022, 34 (11)
  • [6] PHYSICS-INFORMED NEURAL NETWORK FOR INVERSE HEAT CONDUCTION PROBLEM
    Qian, Weijia
    Hui, Xin
    Wang, Bosen
    Zhang, Zongwei
    Lin, Yuzhen
    Yang, Siheng
    HEAT TRANSFER RESEARCH, 2023, 54 (04) : 65 - 76
  • [7] Solving elastodynamics via physics-informed neural network frequency domain method
    Liang, Ruihua
    Liu, Weifeng
    Xu, Lihui
    Qu, Xiangyu
    Kaewunruen, Sakdirat
    INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES, 2023, 258
  • [8] Physics-informed graph convolutional neural network for modeling fluid flow and heat convection
    Peng, Jiang-Zhou
    Hua, Yue
    Li, Yu-Bai
    Chen, Zhi-Hua
    Wu, Wei-Tao
    Aubry, Nadine
    PHYSICS OF FLUIDS, 2023, 35 (08)
  • [9] Enhanced surrogate modelling of heat conduction problems using physics-informed neural network framework
    Manavi, Seyedalborz
    Becker, Thomas
    Fattahi, Ehsan
    INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2023, 142
  • [10] HCP-PIGN: Efficient heat conduction prediction by physics-informed graph convolutional neural network
    Peng, Jiang-Zhou
    Aubry, Nadine
    Li, Yu-Bai
    Chen, Zhi-Hua
    Mei, Mei
    Hua, Yue
    INTERNATIONAL JOURNAL OF HEAT AND FLUID FLOW, 2024, 109