Thermal conductivity estimation using Physics-Informed Neural Networks with limited data

被引：3

作者：

Jo, Junhyoung ^{[1
]}

Jeong, Yeonhwi ^{[2
]}

Kim, Jinsu ^{[2
]}

Yoo, Jihyung ^{[1
]}

机构：

[1] Hanyang Univ, Dept Automot Engn, Seoul, South Korea

[2] Hanyang Univ, Dept Automot Engn Automot Comp Convergence, Seoul, South Korea

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 2024年 / 137卷

基金：

新加坡国家研究基金会;

关键词：

Physics-informed neural network; Data-driven; Heat transfer; Conductivity; Lithium-ion battery; FREQUENCY-DOMAIN REFLECTOMETRY; OPTICAL-FIBER; COMPONENTS;

D O I：

10.1016/j.engappai.2024.109079

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A modified physics-informed neural network (PINN) tailored for solving inverse problems in data-driven engineering applications was demonstrated. The inherited PINN framework enabled the network to integrate ill-posed, noisy experimental data while enforcing a wide range of governing equations, initial and boundary conditions. The network was designed to predict system parameters in governing equations based on a limited number of data points down to three. The general network architecture was further refined to predict thermal conductivity and its performance was validated under various cases. Furthermore the prediction of 18650 Li-ion battery cell thermal conductivity values based on experimental temperature measurements was also conducted.

引用

页数：13

共 50 条

[41] fPINNs: FRACTIONAL PHYSICS-INFORMED NEURAL NETWORKS
Pang, Guofei
Lu, Lu
Karniadakis, George E. M.
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2019, 41 (04): : A2603 - A2626
[42] Physics-informed neural networks for diffraction tomography
Amirhossein Saba
Carlo Gigli
Ahmed B.Ayoub
Demetri Psaltis
Advanced Photonics, 2022, 4 (06) : 48 - 59
[43] PINNProv: Provenance for Physics-Informed Neural Networks
de Oliveira, Lyncoln S.
Kunstmann, Liliane
Pina, Debora
de Oliveira, Daniel
Mattoso, Marta
2023 INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING WORKSHOPS, SBAC-PADW, 2023, : 16 - 23
[44] Physics-Informed Neural Networks for Power Systems
Misyris, George S.
Venzke, Andreas
Chatzivasileiadis, Spyros
2020 IEEE POWER & ENERGY SOCIETY GENERAL MEETING (PESGM), 2020,
[45] Multi-scale modeling in thermal conductivity of Polyurethane incorporated with Phase Change Materials using Physics-Informed Neural Networks
Liu, Bokai
Wang, Yizheng
Rabczuk, Timon
Olofsson, Thomas
Lu, Weizhuo
RENEWABLE ENERGY, 2024, 220
[46] 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,
[47] Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
De Ryck, Tim
Mishra, Siddhartha
ACTA NUMERICA, 2024, 33 : 633 - 713
[48] Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks
Rohrhofer, Franz M. M.
Posch, Stefan
Gossnitzer, Clemens
Geiger, Bernhard C.
IEEE ACCESS, 2023, 11 : 86252 - 86261
[49] Certified machine learning: A posteriori error estimation for physics-informed neural networks
Hillebrecht, Birgit
Unger, Benjamin
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
[50] GaborPINN: Efficient Physics-Informed Neural Networks Using Multiplicative Filtered Networks
Huang X.
Alkhalifah T.
IEEE Geoscience and Remote Sensing Letters, 2023, 20

← 1 2 3 4 5 →