Physics-informed deep learning for solving phonon Boltzmann transport equation with large temperature non-equilibrium

作     者：Ruiyang Li Jian-Xun Wang Eungkyu Lee Tengfei Luo 

作者机构：Department of Aerospace and Mechanical EngineeringUniversity of Notre DameNotre DameIN46556USA Department of Electronic EngineeringKyung Hee UniversityYongin-siGyeonggi-do17104South Korea Department of Chemical and Biomolecular EngineeringUniversity of Notre DameNotre DameIN46556USA Center for Sustainable Energy of Notre Dame(ND Energy)University of Notre DameNotre DameIN46556USA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2022年第8卷第1期

页      面：245-254页

核心收录：

学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学] 

基　　金：The authors would like to thank ONR MURI(N00014-18-1-2429)for the financial support.The simulations are supported by the Notre Dame Center for Research Computing NSF through the eXtreme Science and Engineering Discovery Environment(XSEDE)computing resources provided by Texas Advanced Computing Center(TACC)Stampede II under grant number TG-CTS100078 This work is also supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1C1C1006251) 

主　　题：phonon equilibrium equation 

摘      要：Phonon Boltzmann transport equation(BTE)is a key tool for modeling multiscale phonon transport,which is critical to the thermal management of miniaturized integrated circuits,but assumptions about the system temperatures(i.e.,small temperature gradients)are usually made to ensure that it is computationally *** include the effects of large temperature non-equilibrium,we demonstrate a data-free deep learning scheme,physics-informed neural network(PINN),for solving stationary,mode-resolved phonon BTE with arbitrary temperature *** scheme uses the temperature-dependent phonon relaxation times and learns the solutions in parameterized spaces with both length scale and temperature gradient treated as input *** experiments suggest that the proposed PINN can accurately predict phonon transport(from 1D to 3D)under arbitrary temperature ***,the proposed scheme shows great promise in simulating device-level phonon heat conduction efficiently and can be potentially used for thermal design.