中国物理B ›› 2024, Vol. 33 ›› Issue (8): 84401-084401.doi: 10.1088/1674-1056/ad4326

• • 上一篇    下一篇

A graph neural network approach to the inverse design for thermal transparency with periodic interparticle system

Bin Liu(刘斌)1,† and Yixi Wang(王译浠)2   

  1. 1 Department of Electronic Information and Artificial Intelligence, LeShan Normal University, LeShan 614099, China;
    2 Department of Physics, State Key Laboratory of Surface Physics, and Key Laboratory of Micro and Nano Photonic Structures (MOE), Fudan University, Shanghai 200438, China
  • 收稿日期:2024-02-23 修回日期:2024-04-08 出版日期:2024-08-15 发布日期:2024-07-15
  • 通讯作者: Bin Liu E-mail:liubin@fudan.edu.cn
  • 基金资助:
    We gratefully acknowledge funding from the National Natural Science Foundation of China (Grant Nos. 12035004 and 12320101004) and the Innovation Program of Shanghai Municipal Education Commission (Grant No. 2023ZKZD06).

A graph neural network approach to the inverse design for thermal transparency with periodic interparticle system

Bin Liu(刘斌)1,† and Yixi Wang(王译浠)2   

  1. 1 Department of Electronic Information and Artificial Intelligence, LeShan Normal University, LeShan 614099, China;
    2 Department of Physics, State Key Laboratory of Surface Physics, and Key Laboratory of Micro and Nano Photonic Structures (MOE), Fudan University, Shanghai 200438, China
  • Received:2024-02-23 Revised:2024-04-08 Online:2024-08-15 Published:2024-07-15
  • Contact: Bin Liu E-mail:liubin@fudan.edu.cn
  • Supported by:
    We gratefully acknowledge funding from the National Natural Science Foundation of China (Grant Nos. 12035004 and 12320101004) and the Innovation Program of Shanghai Municipal Education Commission (Grant No. 2023ZKZD06).

RichHTML

0

PDF (PC)

58

赞

摘要： Recent years have witnessed significant advances in utilizing machine learning-based techniques for thermal metamaterial-based structures and devices to attain favorable thermal transport behaviors. Among the various thermal transport behaviors, achieving thermal transparency stands out as particularly desirable and intriguing. Our earlier work demonstrated the use of a thermal metamaterial-based periodic interparticle system as the underlying structure for manipulating thermal transport behavior and achieving thermal transparency. In this paper, we introduce an approach based on graph neural network to address the complex inverse design problem of determining the design parameters for a thermal metamaterial-based periodic interparticle system with the desired thermal transport behavior. Our work demonstrates that combining graph neural network modeling and inference is an effective approach for solving inverse design problems associated with attaining desirable thermal transport behaviors using thermal metamaterials.

关键词: thermal metamaterial, thermal transparency, inverse design, machine learning, graph neural network

Abstract: Recent years have witnessed significant advances in utilizing machine learning-based techniques for thermal metamaterial-based structures and devices to attain favorable thermal transport behaviors. Among the various thermal transport behaviors, achieving thermal transparency stands out as particularly desirable and intriguing. Our earlier work demonstrated the use of a thermal metamaterial-based periodic interparticle system as the underlying structure for manipulating thermal transport behavior and achieving thermal transparency. In this paper, we introduce an approach based on graph neural network to address the complex inverse design problem of determining the design parameters for a thermal metamaterial-based periodic interparticle system with the desired thermal transport behavior. Our work demonstrates that combining graph neural network modeling and inference is an effective approach for solving inverse design problems associated with attaining desirable thermal transport behaviors using thermal metamaterials.

Key words: thermal metamaterial, thermal transparency, inverse design, machine learning, graph neural network

中图分类号:  (Analytical and numerical techniques)

  • 44.05.+e
44.90.+c (Other topics in heat transfer) 07.05.Mh (Neural networks, fuzzy logic, artificial intelligence) 65.90.+i (Other topics in thermal properties of condensed matter)