Investigation of solid-liquid thermal resistance based on molecular dynamics simulation and machine learning

YANG Die; FENG Yibo; LI Haiyang; WANG Jun; XIA Guodong

doi:10.11949/0438-1157.20260687

您当前的位置：

首页 >

文章列表页 >

Investigation of solid-liquid thermal resistance based on molecular dynamics simulation and machine learning

更新时间：2026-07-17

- Investigation of solid-liquid thermal resistance based on molecular dynamics simulation and machine learning
- CIESC Journal (2026)
- 作者机构：
  
  1.北京工业大学传热与能源利用北京市重点实验室，北京 100124
  2.河南理工大学机械与动力工程学院，河南焦作454003
- 作者简介：
- 基金信息：
- DOI：10.11949/0438-1157.20260687
  CLC： TK124
- Received：18 May 2026，
  
  Revised：2026-07-16，
  
  Accepted：17 July 2026，
- 稿件说明：
移动端阅览
YANG Die, FENG Yibo, LI Haiyang, et al. Investigation of solid-liquid thermal resistance based on molecular dynamics simulation and machine learning[J/OL]. CIESC Journal, 2026.
DOI：

YANG Die, FENG Yibo, LI Haiyang, et al. Investigation of solid-liquid thermal resistance based on molecular dynamics simulation and machine learning[J/OL]. CIESC Journal, 2026. DOI： 10.11949/0438-1157.20260687.

摘要

随着微纳电子器件等高新技术领域的快速发展，器件与系统正向微型化、集成化方向演进，单位面积热流密度和散热需求急剧升高。鉴于微纳通道液体冷却被认为是最有效的散热方式之一，热阻是阻碍热量高效传递的关键因素，因此微纳尺度下的固液界面热阻已成为制约相关领域技术突破的核心瓶颈。结合分子动力学模拟方法和机器学习方法，计算并分析了纳米尺度下固液界面热阻。基于分子动力学模拟方法，建立固-液-固纳米受限系统的界面模型，模拟计算得到热阻数据。考虑到模拟计算成本高昂，机器学习方法成本效益高且预测准确，因此引入机器学习方法分析研究热阻，构建反向传播神经网络模型和基于遗传算法优化的反向传播神经网络模型。模型选取界面结合强度、系统温度、两侧固体温度与系统温度的比值作为输入参数，界面热阻作为输出参数。评估结果表明：遗传算法优化后的反向传播神经网络具有较小的误差，预测精度相对较高，其中均方根误差、平均绝对相对误差和决定系数分别为1.204×10

-9

/W、2.2995和0.9989。

Abstract

The cooling technology for micro-electronic devices has attached much attention in recent decades because of the dramatic increase in heat dissipation demands. Considering that micro-nano channel liquid cooling is one of the most potential methods for thermal dissipation

it is necessary to study the solid–liquid interfacial thermal resistance

which plays an important role in micro-nano channel liquid cooling. In this work

molecular dynamic (MD) simulation and machine learning are used to calculate and analyze the solid-liquid interfacial thermal resistance at the nanoscale. A MD simulation model for solid-liquid-solid sandwiched structure is established

wherein the solid-liquid interfacial thermal resistance can be obtained. Because of the time-consuming MD simulations

machine learning methods are adopted for thermal resistance analysis. Accordingly

a back propagation neural network and a genetic algorithm-optimized back propagation neural network are established in this study. The interfacial coupling strength parameter

system temperature

and the ratio of solid temperatures on both sides to the system temperature are selected as input parameters

while the interfacial thermal resistance is the output parameter. The performance of the models are evaluated by comparing the errors and prediction results of the two models. In conclusion

the back propagation neural network optimized by genetic algorithms has smaller errors and relatively high prediction accuracy

with a root mean square error of 1.204×10

-9

an average absolute relative deviation of 2.2995

and a coefficient of determination of 0.9989.

关键词

Keywords

references

Yin X Y , Li C Z , Kou Z H , et al . Effect of depositional nanoparticles on heat transfer at the solid–liquid interface using molecular dynamics simulations [J ] . Journal of Non-Equilibrium Thermodynamics , 2025 , 50 ( 3 ): 391 - 402 .

Ma D K , Xing Y H , Zhang L F . Reducing interfacial thermal resistance by interlayer [J ] . Journal of Physics: Condensed Matter , 2023 , 35 ( 5 ): 053001 .

宋善鹏 , 于志家 , 刘兴华 , 等 . 超疏水表面微通道内水的传热特性 [J ] . 化工学报 , 2008 , 59 ( 10 ): 2465 - 2469 .

Song S P , Yu Z J , Liu X H , et al . Heat transfer characteristics of water flowing in microchannels with super-hydrophobic inner surface [J ] . Journal of Chemical Industry and Engineering (China) , 2008 , 59 ( 10 ): 2465 - 2469 .

Klochko L , Mandrolko V , Castanet G , et al . Molecular dynamics simulation of thermal transport across a solid/liquid interface created by a meniscus [J ] . Physical Chemistry Chemical Physics , 2023 , 25 ( 4 ): 3298 - 3308 .

齐凯 , 朱星光 , 王军 , 等 . 外电场作用下纳米结构表面的固-液界面传热特性 [J ] . 物理学报 , 2024 , 73 ( 15 ): 118 - 125 .

Qi K , Zhu X G , Wang J , et al . Heat transfer characteristics of solid-liquid interface on nanostructure surface under external electric field [J ] . Acta Physica Sinica , 2024 , 73 ( 15 ): 118 - 125 .

马学虎 , 陈晓峰 . 固液界面接触角对膜状冷凝传热强化的初步分析 [J ] . 化工学报 , 2003 , 54 ( 6 ): 850 - 853 .

Ma X H , Chen X F . Analysis of effect of solid-liquid contact angle on heat transfer enhancement of filmwise condensation [J ] . CIESC Journal , 2003 , 54 ( 6 ): 850 - 853 .

Wang Z Y , Sun F Y , Liu Z H , et al . Regulated thermal boundary conductance between copper and diamond through nanoscale interfacial rough structures [J ] . ACS Applied Materials & Interfaces , 2023 , 15 ( 12 ): 16162 - 16176 .

李海洋 , 李凡 , 王军 , 等 . 固液界面中热整流效应及其翻转 [J ] . 工程热物理学报 , 2020 , 41 ( 11 ): 2813 - 2817 .

Li H Y , Li F , Wang J , et al . Reversed thermal R ectification effect in solid-liquid interface [J ] . Journal of Engineering Thermophysics , 2020 , 41 ( 11 ): 2813 - 2817 .

Giri A , Hopkins P E . A review of experimental and computational advances in thermal boundary conductance and nanoscale thermal transport across solid interfaces [J ] . Advanced Functional Materials , 2020 , 30 ( 8 ): 1903857 .

Li D C , Wang J H , Ding Y L , et al . Dynamic thermal management for industrial waste heat recovery based on phase change material thermal storage [J ] . Applied Energy , 2019 , 236 : 1168 - 1182 .

Pop E . Energy dissipation and transport in nanoscale devices [J ] . Nano Research , 2010 , 3 ( 3 ): 147 - 169 .

Roy A K , Farmer B L , Varshney V , et al . Importance of interfaces in governing thermal transport in composite materials: modeling and experimental perspectives [J ] . ACS Applied Materials & Interfaces , 2012 , 4 ( 2 ): 545 - 563 .

Kapitza P L . The study of heat transfer in helium Ⅱ [M ] // Helium 4 . Amsterdam : Elsevier , 1971 : 114 - 153 .

毕丽森 , 刘斌 , 胡恒祥 , 等 . 粗糙界面上纳米液滴蒸发模式的分子动力学研究 [J ] . 化工学报 , 2023 , 74 ( S1 ): 172 - 178 .

Bi L S , Liu B , Hu H X , et al . Molecular dynamics study on evaporation modes of nanodroplets at rough interfaces [J ] . CIESC Journal , 2023 , 74 ( S1 ): 172 - 178 .

Jabbari F , Rajabpour A , Saedodin S , et al . Effect of water/carbon interaction strength on interfacial thermal resistance and the surrounding molecular nanolayer of CNT and graphene flake [J ] . Journal of Molecular Liquids , 2019 , 282 : 197 - 204 .

Li F , Wang J , Xia G D , et al . Negative differential thermal resistance through nanoscale solid–fluid–solid sandwiched structures [J ] . Nanoscale , 2019 , 11 ( 27 ): 13051 - 13057 .

王军 , 李海洋 , 夏国栋 . 固液界面热阻的温度依赖特性模拟研究 [J ] . 北京工业大学学报 , 2024 , 50 ( 7 ): 864 - 871 .

Wang J , Li H Y , Xia G D . Numerical study of the effects of system temperature on heat transfer at the solid-liquid interface [J ] . Journal of Beijing University of Technology , 2024 , 50 ( 7 ): 864 - 871 .

Vo T Q , Kim B . Interface thermal resistance between liquid water and various metallic surfaces [J ] . International Journal of Precision Engineering and Manufacturing , 2015 , 16 ( 7 ): 1341 - 1346 .

He Q X , Qin M M , Zhang H , et al . Encapsulated solid-liquid dual continuous pathways with low modulus and high thermal conductivity for dynamic target autonomous thermal management [J ] . Nano Today , 2024 , 59 : 102549 .

Zeng Z Y , Zeng L , Wang R Z , et al . Molecular understanding of heat transfer in ionic-liquid-based electric double layers [J ] . Journal of Thermal Science , 2023 , 32 ( 1 ): 192 - 205 .

Li H Y , Wang J , Xia G D . Thermal rectification induced by Wenzel–Cassie wetting state transition on nano-structured solid–liquid interfaces [J ] . Chinese Physics B , 2023 , 32 ( 5 ): 054401 .

张程宾 , 许兆林 , 陈永平 . 粗糙纳通道内流体流动与传热的分子动力学模拟研究 [J ] . 物理学报 , 2014 , 63 ( 21 ): 263 - 270 .

Zhang C B , Xu Z L , Chen Y P . Molecular dynamics simulation on fluid flow and heat transfer in rough nano channels [J ] . Acta Physica Sinica , 2014 , 63 ( 21 ): 263 - 270 .

Li H Y , Wang J , Xia G D . Negative differential thermal resistance effect in a nanoscale sandwiched system with nanostructured surfaces [J ] . International Communications in Heat and Mass Transfer , 2023 , 142 : 106605 .

Dong M , Xu J L , Wang Y , et al . Effect of pressure and surface wettability on thermal resistance across solid–liquid interface in supercritical regime [J ] . The Journal of Physical Chemistry C , 2024 , 128 ( 9 ): 4024 - 4037 .

Li Z G . Surface effects on friction-induced fluid heating in nanochannel flows [J ] . Physical Review E , 2009 , 79 ( 2 ): 026312 .

Liu C , Fan H B , Zhang K , et al . Flow dependence of interfacial thermal resistance in nanochannels [J ] . The Journal of Chemical Physics , 2010 , 132 ( 9 ): 094703 .

Rumelhart D E , Hinton G E , Williams R J . Learning representations by back-propagating errors [J ] . Nature , 1986 , 323 ( 6088 ): 533 - 536 .

Deng C C , Qiu T , Liu P , et al . BP neural network regularized by wall temperature characteristics to reduce the ill-posedness of two-dimensional inverse heat transfer problems in rotating disk cavities [J ] . International Journal of Thermal Sciences , 2024 , 203 : 109145 .

Zheng C M , Zhao C Y , Xiao W , et al . Falling film heat transfer from sensible convection to boiling on horizontal tubes: Database construction and machine learning-based heat transfer prediction [J ] . International Journal of Heat and Mass Transfer , 2025 , 245 : 127020 .

Ma D L , Zhou T , Chen J , et al . Supercritical water heat transfer coefficient prediction analysis based on BP neural network [J ] . Nuclear Engineering and Design , 2017 , 320 : 400 - 408 .

Yang Y T , Chen L H , Xiong Y , et al . Global sensitivity analysis based on BP neural network for thermal design parameters [J ] . Journal of Thermophysics and Heat Transfer , 2021 , 35 ( 1 ): 187 - 199 .

Gu J H , Wang J , Qi C Y , et al . Medium-term heat load prediction for an existing residential building based on a wireless on-off control system [J ] . Energy , 2018 , 152 : 709 - 718 .

Lee H W , Azid I H A . Neuro-genetic optimization of the diffuser elements for applications in a valveless diaphragm micropumps system [J ] . Sensors , 2009 , 9 ( 9 ): 7481 - 7497 .

Zhang Q L , Ma H R , Yu Z Y , et al . Study on heat transfer characteristics of supercritical R134a in square microchannel based on GA-BP neural network [J ] . Thermal Science and Engineering Progress , 2024 , 51 : 102654 .

Qin D , Su F H , Li Y C , et al . Radiator performance prediction based on multi-scale method and GA-BP neural network [J ] . International Journal of Heat and Mass Transfer , 2026 , 256 : 127922 .

颜建国 , 郑书闽 , 郭鹏程 , 等 . 基于GA-BP神经网络的超临界CO 2 传热特性预测研究 [J ] . 化工学报 , 2021 , 72 ( 9 ): 4649 - 4657 .

Yan J G , Zheng S M , Guo P C , et al . Prediction of heat transfer characteristics for supercritical CO2 based on GA-BP neural network [J ] . CIESC Journal , 2021 , 72 ( 9 ): 4649 - 4657 .

Ma W W , Feng T , Su C Q , et al . Performance optimization of phase change energy storage combined cooling, heating and power system based on GA + BP neural network algorithm [J ] . Journal of Energy Storage , 2024 , 88 : 111653 .

Xi L , Gao J M , Xu L , et al . Study on heat transfer performance of steam-cooled ribbed channel using neural networks and genetic algorithms [J ] . International Journal of Heat and Mass Transfer , 2018 , 127 : 1110 - 1123 .

Liu D W , Liu C , Tang Y , et al . A GA-BP neural network regression model for predicting soil moisture in slope ecological protection [J ] . Sustainability , 2022 , 14 ( 3 ): 1386 .

Li F , Sun P , Wu J L , et al . GA−BP prediction model for automobile exhaust waste heat recovery using thermoelectric generator [J ] . Processes , 2023 , 11 ( 5 ): 1498 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of biomass pyrolysis product yield based on machine learning algorithms

SINDy for discovering the governing equations of noisy rough granular flow in the homogeneous cooling state

Machine learning-assisted high-throughput screening of high-performance zeolites for CO2 adsorption

Machine learning-driven performance prediction and reverse design of lignin-based carbon quantum dots

Machine learning-driven design and optimization of molecular sieve-based efficient CO adsorbents

Related Author

LIU Xiaoyu

LI Qichen

HUO Lili

ZHAO Lixin

YAO Zonglu

SUN Peihao

JIA Jixiu

ZHU Benhai

Related Institution

Institute of Agricultural Environment and Sustainable Development, Chinese Academy of Agricultural Sciences

Key Laboratory of Green and Low-carbon Agriculture in North China Plain, Ministry of Agriculture and Rural Affairs

College of Mechanical and Transportation Engineering, China University of Petroleum

State Key Laboratory of Heavy Oil Processing, China University of Petroleum

State Key Laboratory of Deep Geothermal Resources, China University of Petroleum

⁰