Fractional-Order Modeling of Heat and Moisture Transfer in Anisotropic Materials Using a Physics-Informed Neural Network

被引:1
|
作者
Sokolovskyy, Yaroslav [1 ]
Drozd, Kazimierz [2 ]
Samotii, Tetiana [3 ]
Boretska, Iryna [4 ]
机构
[1] Lviv Polytech Natl Univ, Dept Comp Aided Design, 12 S Bandery St, UA-79013 Lvov, Ukraine
[2] Lublin Univ Technol, Fac Mech Engn, Dept Mat Engn, 36 Nadbystrzycka St, PL-20618 Lublin, Poland
[3] Ukrainian Natl Forestry Univ, Dept Software Engn, 103 Gen Chuprynky St, UA-79057 Lvov, Ukraine
[4] Ukrainian Natl Forestry Univ, Dept Comp Sci, 103 Gen Chuprynky St, UA-79057 Lvov, Ukraine
关键词
fractal structure; self-organization; heat-and-mass exchange; fractional-differential apparatus; step-by-step learning; fractal neural method;
D O I
10.3390/ma17194753
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Mathematical models of heat and moisture transfer for anisotropic materials, based on the use of the fractional calculus of integro-differentiation, are considered because such two-factor fractal models have not been proposed in the literature so far. The numerical implementation of mathematical models for determining changes in heat exchange and moisture exchange is based on the adaptation of the fractal neural network method, grounded in the physics of processes. A fractal physics-informed neural network architecture with a decoupled structure is proposed, based on loss functions informed by the physical process under study. Fractional differential formulas are applied to the expressions of non-integer operators, and finite difference schemes are developed for all components of the loss functions. A step-by-step method for network training is proposed. An algorithm for the implementation of the fractal physics-informed neural network is developed. The efficiency of the new method is substantiated by comparing the obtained numerical results with numerical approximation by finite differences and experimental data for particular cases.
引用
收藏
页数:23
相关论文
共 50 条
  • [41] HEAT TRANSFER PREDICTION WITH UNKNOWN THERMAL BOUNDARY CONDITIONS USING PHYSICS-INFORMED NEURAL NETWORKS
    Cai, Shengze
    Wang, Zhicheng
    Chryssostomidis, Chryssostomos
    Karniadakis, George Em
    PROCEEDINGS OF THE ASME 2020 FLUIDS ENGINEERING DIVISION SUMMER MEETING (FEDSM2020), VOL 3, 2020,
  • [42] Simulation of multi-species flow and heat transfer using physics-informed neural networks
    Laubscher, R.
    PHYSICS OF FLUIDS, 2021, 33 (08)
  • [43] Modeling finite-strain plasticity using physics-informed neural network and assessment of the network performance
    Niu, Sijun
    Zhang, Enrui
    Bazilevs, Yuri
    Srivastava, Vikas
    JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS, 2023, 172
  • [44] 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
  • [45] A Physics-Informed Neural Network for Higher-Order Soliton Compression in Fibers
    Wu, Jinhong
    Wang, Zimiao
    Li, Qian
    2022 ASIA COMMUNICATIONS AND PHOTONICS CONFERENCE, ACP, 2022, : 71 - 73
  • [46] Hybrid Modeling of Fed-Batch Cell Culture Using Physics-Informed Neural Network
    Yang, Shu
    Fahey, William
    Truccollo, Brendha
    Browning, Jill
    Kamyar, Reza
    Cao, Huiyi
    INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2024, 63 (39) : 16833 - 16846
  • [47] MODELING THE BURNING OF POLYMER MATRIX: TRAINING COLLOCATION PHYSICS-INFORMED NEURAL NETWORK
    Ghaderi, Aref
    Dargazany, Roozbeh
    PROCEEDINGS OF ASME 2022 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, IMECE2022, VOL 9, 2022,
  • [48] A physics-informed neural network framework for modeling obstacle-related equations
    El Bahja, Hamid
    Hauffen, Jan C.
    Jung, Peter
    Bah, Bubacarr
    Karambal, Issa
    NONLINEAR DYNAMICS, 2025, 113 (11) : 12533 - 12544
  • [49] Modeling of the Forward Wave Propagation Using Physics-Informed Neural Networks
    Alkhadhr, Shaikhah
    Liu, Xilun
    Almekkawy, Mohamed
    INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS 2021), 2021,
  • [50] Reconstruction of downburst wind fields using physics-informed neural network
    Yao, Binbin
    Wang, Zhisong
    Fang, Zhiyuan
    Li, Zhengliang
    JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS, 2024, 254