EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Yaroslav Sokolovskyy iD, Kazimierz Drozd iD, Tetiana Samotii iD, Iryna Boretska iD

Materials · 27.09.2024 · 17 (19) · 4753

DOI: 10.3390/ma17194753 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 27.09.2024. Verfasst von Yaroslav Sokolovskyy und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer-Aided Design, Lviv Polytechnic National University, 12 S. Bandery Street, 79013 Lviv, Ukraine. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lublin University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

fractal neural methodfractal structurefractional-differential apparatusheat-and-mass exchangeself-organizationstep-by-step learning

Autor:innen und Institutionen

  • Department of Computer-Aided Design, Lviv Polytechnic National University, 12 S. Bandery Street, 79013 Lviv, Ukraine.
  • Department of Materials Engineering, Faculty of Mechanical Engineering, Lublin University of Technology, 36 Nadbystrzycka Street, 20-618 Lublin, Poland.
  • Department of Software Engineering, Ukrainian National Forestry University, 103 Gen. Chuprynky Street, 79057 Lviv, Ukraine.
  • Department of Computer Science, Ukrainian National Forestry University, 103 Gen. Chuprynky Street, 79057 Lviv, Ukraine.

ORCID-Profile: Yaroslav Sokolovskyy, Kazimierz Drozd, Tetiana Samotii, Iryna Boretska

Förderung

  • Lublin University of Technology

Zitieren

APA

Sokolovskyy, Y., Drozd, K., Samotii, T., & Boretska, I. (2024). Fractional-Order Modeling of Heat and Moisture Transfer in Anisotropic Materials Using a Physics-Informed Neural Network. Materials, 17(19), 4753. https://doi.org/10.3390/ma17194753

Vancouver

Sokolovskyy Y, Drozd K, Samotii T, Boretska I. Fractional-Order Modeling of Heat and Moisture Transfer in Anisotropic Materials Using a Physics-Informed Neural Network. Materials. 2024;17(19):4753. doi:10.3390/ma17194753

BibTeX
@article{Sokolovskyy2024,
  author = {Sokolovskyy, Yaroslav and Drozd, Kazimierz and Samotii, Tetiana and Boretska, Iryna},
  title = {Fractional-Order Modeling of Heat and Moisture Transfer in Anisotropic Materials Using a Physics-Informed Neural Network},
  journal = {Materials},
  year = {2024},
  volume = {17},
  number = {19},
  pages = {4753},
  doi = {10.3390/ma17194753}
}
Kostenlos starten →