Surrogate modeling for physical fields of heat transfer processes based on physics-informed neural network

被引：0

作者：

Lu Z. ^{[1
]}

Qu J. ^{[2
]}

Liu H. ^{[2
]}

He C. ^{[2
,3
]}

Zhang B. ^{[2
,3
]}

Chen Q. ^{[2
,3
]}

机构：

[1] School of Materials Science and Engineering, Sun Yat-sen University, Guangzhou

[2] School of Chemical Engineering and Technology, Sun Yat-sen University, Zhuhai

[3] Guangdong Engineering Center for Petrochemical Energy Conservation, Sun Yat-sen University, Guangzhou

来源：

Huagong Xuebao/CIESC Journal | 2021年 / 72卷 / 03期

关键词：

Boundary setting; Heat transfer; Laws of physics; Neural networks; Nonlinear partial differential equations; Prediction; Surrogate model;

D O I：

10.11949/0438-1157.20201879

中图分类号：

学科分类号：

摘要：

By constructing structured deep neural network architecture, physics-informed neural networks (PINN) can be trained to solve supervised learning tasks with limited amount of boundary data while effectively integrating any given laws of physics described by general nonlinear partial differential equations (i.e., Navier-Stokes equation). However, the effect of PINN training is closely related to how the boundary conditions are set. In this work, two 2-D steady-state heat transfer problems, namely heat conduction model with internal heat source and convection heat transfer equation between plates are taken as examples. Two surrogate models are trained based on PINN by using two setting methods of soft boundary and hard boundary. The trained surrogate models are used to predict the output of temperature fields, which are verified and compared with the simulated data. The comparison results show that the prediction ability of PINN based on hard boundary is superior to the rival. © 2021, Editorial Board of CIESC Journal. All right reserved.

引用

页码：1496 / 1503

页数：7