TY  - JOUR
A1  - Guo, Hongwei
A1  - Alajlan, Naif
A1  - Zhuang, Xiaoying
A1  - Rabczuk, Timon
T1  - Physics-informed deep learning for three-dimensional transient heat transfer analysis of functionally graded materials
JF  - Computational Mechanics
N2  - We present a physics-informed deep learning model for the transient heat transfer analysis of three-dimensional functionally graded materials (FGMs) employing a Runge–Kutta discrete time scheme. Firstly, the governing equation, associated boundary conditions and the initial condition for transient heat transfer analysis of FGMs with exponential material variations are presented. Then, the deep collocation method with the Runge–Kutta integration scheme for transient analysis is introduced. The prior physics that helps to generalize the physics-informed deep learning model is introduced by constraining the temperature variable with discrete time schemes and initial/boundary conditions. Further the fitted activation functions suitable for dynamic analysis are presented. Finally, we validate our approach through several numerical examples on FGMs with irregular shapes and a variety of boundary conditions. From numerical experiments, the predicted results with PIDL demonstrate well agreement with analytical solutions and other numerical methods in predicting of both temperature and flux distributions and can be adaptive to transient analysis of FGMs with different shapes, which can be the promising surrogate model in transient dynamic analysis.
KW  - Wärmeübergang
KW  - Deep Learning
KW  - Modellierung
KW  - physics-informed activation function
KW  - heat transfer
KW  - functionally graded materials
Y1  - 2023
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20230517-63666
UR  - https://link.springer.com/article/10.1007/s00466-023-02287-x
VL  - 2023
SP  - 1
EP  - 12
PB  - Springer
CY  - Berlin
ER  - 
TY  - JOUR
A1  - Zhuang, Xiaoying
A1  - Huang, Runqiu
A1  - Liang, Chao
A1  - Rabczuk, Timon
T1  - A coupled thermo-hydro-mechanical model of jointed hard rock for compressed air energy storage
JF  - Mathematical Problems in Engineering
N2  - Renewable energy resources such as wind and solar are intermittent, which causes instability when being connected to utility grid of electricity. Compressed air energy storage (CAES) provides an economic and technical viable solution to this problem by utilizing subsurface rock cavern to store the electricity generated by renewable energy in the form of compressed air. Though CAES has been used for over three decades, it is only restricted to salt rock or aquifers for air tightness reason. In this paper, the technical feasibility of utilizing hard rock for CAES is investigated by using a coupled thermo-hydro-mechanical (THM) modelling of nonisothermal gas flow. Governing equations are derived from the rules of energy balance, mass balance, and static equilibrium. Cyclic volumetric mass source and heat source models are applied to simulate the gas injection and production. Evaluation is carried out for intact rock and rock with discrete crack, respectively. In both cases, the heat and pressure losses using air mass control and supplementary air injection are compared.
KW  - Energiespeicherung
KW  - Druckluft
KW  - Kaverne
KW  - Modellierung
Y1  - 2014
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20170428-31726
ER  -