Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network

Abstract Heat dissipation performance is critical to the design of high-end equipment, such as integrated chips and high-precision machine tools. Owing to the advantages of artificial intelligence in solving complex tasks involving a large number of variables, researchers have exploited deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiyin Lin, Feiyu Gu, Chen Wang, Hao Guan, Tao Wang, Kaiyi Zhou, Lian Liu, Desheng Yao
Format: Article
Language:English
Published: SpringerOpen 2025-04-01
Series:Chinese Journal of Mechanical Engineering
Subjects:
Online Access:https://doi.org/10.1186/s10033-025-01222-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850187363830988800
author Qiyin Lin
Feiyu Gu
Chen Wang
Hao Guan
Tao Wang
Kaiyi Zhou
Lian Liu
Desheng Yao
author_facet Qiyin Lin
Feiyu Gu
Chen Wang
Hao Guan
Tao Wang
Kaiyi Zhou
Lian Liu
Desheng Yao
author_sort Qiyin Lin
collection DOAJ
description Abstract Heat dissipation performance is critical to the design of high-end equipment, such as integrated chips and high-precision machine tools. Owing to the advantages of artificial intelligence in solving complex tasks involving a large number of variables, researchers have exploited deep learning to expedite the optimization of material properties, such as the heat dissipation of solid isotropic materials with penalization (SIMP). However, because the approach is limited by discrete datasets and labeled training forms, ensuring the continuous adaptation of the condition domain and maintaining the stability of the design structure remain major challenges in the current intelligent design methodology for thermally conductive structures. In this study, we propose an innovative intelligent design framework integrating Conditional Deep Convolutional Generative Adversarial Networks (CDCGAN) with SIMP, capable of creating topology structures that meet prescribed thermal conduction performance. This proposed design strategy significantly reduces the computational time required to solve symmetric and random heat sink problems compared with existing design approaches and is approximately 98% faster than standard SIMP methods and 55.5% faster than conventional deep-learning-based methods. In addition, we benchmarked the design performance of the proposed framework against theoretical structural designs via experimental measurements. We observed a 50.1% reduction in the average temperature and a 28.2% reduction in the highest temperature in our designed topology compared with those theoretical structure designs.
format Article
id doaj-art-a2404da5dd7841bb874da356e9e36938
institution OA Journals
issn 2192-8258
language English
publishDate 2025-04-01
publisher SpringerOpen
record_format Article
series Chinese Journal of Mechanical Engineering
spelling doaj-art-a2404da5dd7841bb874da356e9e369382025-08-20T02:16:06ZengSpringerOpenChinese Journal of Mechanical Engineering2192-82582025-04-0138111610.1186/s10033-025-01222-wIntelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative NetworkQiyin Lin0Feiyu Gu1Chen Wang2Hao Guan3Tao Wang4Kaiyi Zhou5Lian Liu6Desheng Yao7Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityKey Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, School of Mechanical Engineering, Xi’an Jiaotong UniversityDepartment of Material Science and Engineering, University of California, BerkeleyAbstract Heat dissipation performance is critical to the design of high-end equipment, such as integrated chips and high-precision machine tools. Owing to the advantages of artificial intelligence in solving complex tasks involving a large number of variables, researchers have exploited deep learning to expedite the optimization of material properties, such as the heat dissipation of solid isotropic materials with penalization (SIMP). However, because the approach is limited by discrete datasets and labeled training forms, ensuring the continuous adaptation of the condition domain and maintaining the stability of the design structure remain major challenges in the current intelligent design methodology for thermally conductive structures. In this study, we propose an innovative intelligent design framework integrating Conditional Deep Convolutional Generative Adversarial Networks (CDCGAN) with SIMP, capable of creating topology structures that meet prescribed thermal conduction performance. This proposed design strategy significantly reduces the computational time required to solve symmetric and random heat sink problems compared with existing design approaches and is approximately 98% faster than standard SIMP methods and 55.5% faster than conventional deep-learning-based methods. In addition, we benchmarked the design performance of the proposed framework against theoretical structural designs via experimental measurements. We observed a 50.1% reduction in the average temperature and a 28.2% reduction in the highest temperature in our designed topology compared with those theoretical structure designs.https://doi.org/10.1186/s10033-025-01222-wTopology optimizationIntelligent predictionThermal conductivity structureGenerative adversarial networkInstantaneous prediction
spellingShingle Qiyin Lin
Feiyu Gu
Chen Wang
Hao Guan
Tao Wang
Kaiyi Zhou
Lian Liu
Desheng Yao
Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
Chinese Journal of Mechanical Engineering
Topology optimization
Intelligent prediction
Thermal conductivity structure
Generative adversarial network
Instantaneous prediction
title Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
title_full Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
title_fullStr Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
title_full_unstemmed Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
title_short Intelligent Design Method for Thermal Conductivity Topology Based on a Deep Generative Network
title_sort intelligent design method for thermal conductivity topology based on a deep generative network
topic Topology optimization
Intelligent prediction
Thermal conductivity structure
Generative adversarial network
Instantaneous prediction
url https://doi.org/10.1186/s10033-025-01222-w
work_keys_str_mv AT qiyinlin intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT feiyugu intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT chenwang intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT haoguan intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT taowang intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT kaiyizhou intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT lianliu intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork
AT deshengyao intelligentdesignmethodforthermalconductivitytopologybasedonadeepgenerativenetwork