Surface Temperature Variation Patterns and Prediction Method for Liquid Cooling Plate during Multi-Condition Cooling Processes

Li Chunxi; Lu Gaofeng; Zhai Xiaoqiang

doi:10.12465/issn.0253-4339.20250812001

您当前的位置：

首页 >

文章列表页 >

Surface Temperature Variation Patterns and Prediction Method for Liquid Cooling Plate during Multi-Condition Cooling Processes

更新时间：2026-01-21

- Surface Temperature Variation Patterns and Prediction Method for Liquid Cooling Plate during Multi-Condition Cooling Processes
- Journal of Refrigeration Pages: 1-10(2026)
- 作者机构：
  
  1.上海交通大学制冷与低温工程研究所上海 200240
  2. 苏州华旃航天电器有限公司苏州 215129
  3. 苏州工学院常熟 215500
- 作者简介：
- 基金信息：
  
  the Jiangsu Provincial Natural Science Foundation of China(BK20230711)
- DOI：10.12465/issn.0253-4339.20250812001
  CLC： TB61⁺1;TQ026.2;TB657.5
- CSTR：XXXXX.XX.XXX.20250812001
- Received：12 August 2025，
  
  Revised：2025-09-07，
  
  Accepted：13 October 2025，
  
  Published Online：19 January 2026，
- 稿件说明：
移动端阅览
李纯熙,陆高锋,翟晓强.液冷板多工况冷却过程中表面温度的变化规律及其预测方法[J].制冷学报,

Li Chunxi,Lu Gaofeng,Zhai Xiaoqiang.Surface Temperature Variation Patterns and Prediction Method for Liquid Cooling Plate during Multi-Condition Cooling Processes[J].Journal of Refrigeration,
李纯熙,陆高锋,翟晓强.液冷板多工况冷却过程中表面温度的变化规律及其预测方法[J].制冷学报, DOI：10.12465/issn.0253-4339.20250812001. CSTR： XXXXX.XX.XXX.20250812001.

Li Chunxi,Lu Gaofeng,Zhai Xiaoqiang.Surface Temperature Variation Patterns and Prediction Method for Liquid Cooling Plate during Multi-Condition Cooling Processes[J].Journal of Refrigeration, DOI：10.12465/issn.0253-4339.20250812001. CSTR： XXXXX.XX.XXX.20250812001.

摘要

近年来，模块化液冷板在船舶电子设备的散热系统中得到了广泛应用，在保证供冷能力的同时防止液冷板表面结露对于电子设备的安全运行至关重要。本文实验研究了不同冷却工况下液冷板表面温度的动态变化和结露现象，并建立了卷积神经网络（CNN）和长短期记忆网络（LSTM）的混合模型（CNN-LSTM）预测液冷板表面易结露区域温度。结果表明：液冷板易结露区域受边缘效应影响，且在温度降至露点后至实际结露的过程中，存在过冷和结露延迟现象。同时，CNN-LSTM模型温度预测值的平均绝对误差MAE相较CNN和LSTM分别降低41.7%和48.8%；均方根误差RMSE相较上述2个模型分别降低40.7%和49.1%；拟合优度R²也优于CNN和LSTM模型。

Abstract

In recent years， modular liquid cooling plates have been increasingly used for thermal management in marine electronic equipment. In addition to maintaining the cooling performance， preventing surface condensation is critical for device safety. This study experimentally investigated the surface-temperature dynamics and condensation phenomena under various cooling conditions. A hybrid model that combined a convolutional neural network （CNN） and long short-term memory network （LSTM） was developed to predict the surface temperatures in condensation-prone regions of a liquid cooling plate. The results indicated that such areas are affected by edge effects. Moreover， supercooling and delayed condensation were observed when the temperature fell below the dew point， as well as the actual occurrence of condensation. The proposed model reduced the mean absolute error （MAE） by 41.7% and 48.8% and the root mean squared error （RMSE） by 40.7% and 49.1%， respectively， compared to the standalone CNN and LSTM models， while also achieving a higher coefficient of determination （R2）.

关键词

Keywords

references

中国制冷学会数据中心冷却工作组组织 . 中国数据中心冷却技术年度发展研究报告2024 ［M］. 北京：中国建材工业出版社， 2025 .

Chinese Association of Refrigeration Data Center Cooling Working Group . Annual research report on data center cooling technology in China 2024 ［M］. Beijing ： China Building Material Industry Publishing House ， 2025 .

孙山林 . 舰用电子设备冷却方式及其特点［J］. 流体机械， 2008 ， 36 （ 4 ）： 47 - 49 .

Sun Shanlin . Cooling method and characteristics of electron equipment ［J］. Fluid Machinery ， 2008 ， 36 （ 4 ）： 47 - 49 .

王宁，付云鹏，李艇，等 . 基于FloMaster-Simulink联合仿真的大流量海水冷却系统控制方案优化［J］. 上海交通大学学报， 2022 ， 56 （ 3 ）： 379 - 385 .

Wang Ning ， Fu Yunpeng ， Li Ting ， et al . Optimization of control scheme for large flow seawater cooling system based on FloMaster-Simulink co-simulation ［J］. Journal of Shanghai Jiao Tong University ， 2022 ， 56 （ 3 ）： 379 - 385 .

谢坤 . 船舶电气设备高效冷却方案研究与应用［J］. 船电技术， 2017 ， 37 （ 2 ）： 33 - 37 .

Xie Kun . Research and application of efficient cooling system for shipboard electrical equipment ［J］. Marine Electric & Electronic Engineering ， 2017 ， 37 （ 2 ）： 33 - 37 .

Xing Daoming ， Li Nianping ， Zhang Chen ， et al . A critical review of passive condensation prevention for radiant cooling ［J］. Building and Environment ， 2021 ， 205 ： 108230 .

Wang Qian ， Liu Shuming ， Liu Shuqi ， et al . Super-hydrophobic silicone rubber for outdoor electrical insulation ［J］. Nano Today ， 2024 ， 58 ： 102406 .

Zhang Chen ， Wang Hongqiang ， Shen Jun ， et al . Dominant factors for moisture resistance of Sol-gel silica coatings： Surface chemical composition or inner microstructure？［J］. Applied Surface Science ， 2024 ， 642 ： 158616 .

袁博 . 电柜防凝露的神经网络预测控制方法研究［D］. 广州：华南理工大学， 2019 .

Yuan Bo . Research on neural network predictive control method for anti-condensation of electric cabinet ［D］. Guangzhou ： South China University of Technology ， 2019 .

Zhao Lei ， Wang Hu ， Li Meng ， et al . Performance analysis of a temperature adaptive anti-condensation device in open-plan control cabinets ［J］. Thermal Science and Engineering Progress ， 2023 ， 42 ： 101883 .

Li Jinbo ， Luo Xue ， Wang Man ， et al . Study of flow and heat transfer characteristics of tandem cold plates for data center cooling ［J］. Case Studies in Thermal Engineering ， 2025 ， 73 ： 106590 .

Lee H ， Lee Y J ， Kim S J . One-dimensional model of manifold microchannels for embedded cooling： Prediction of thermal performance and flow non-uniformity ［J］. International Communications in Heat and Mass Transfer ， 2024 ， 155 ： 107498 .

Wang Qian ， Wang Chunhua ， Zhang Jingzhou . Prediction of cooling performance of laminated structures based on machine learning ［J］. Thermal Science and Engineering Progress ， 2025 ， 64 ： 103790 .

Zhang Weiyi ， Zhou Haiyang ， Bao Xiaohua ， et al . Outlet water temperature prediction of energy pile based on spatial-temporal feature extraction through CNN-LSTM hybrid model ［J］. Energy ， 2023 ， 264 ： 126190 .

王得道，王森荣，林超，等 . 基于CNN-LSTM融合神经网络的CRTSⅡ型轨道板温度预测方法［J ］. 铁道学报， 2023 ， 45 （ 2 ）： 108 - 115 .

Wang Dedao ， Wang Senrong ， Lin Chao ， et al . CRTSⅡ track slab temperature forecasting method based on CNN-LSTM fusion neural network network ［J］. Journal of the China Railway Society ， 2023 ， 45 （ 2 ）： 108 - 115 .

Dupont V ， Nicolle T ， Billet C . Temperature swing issue， how a passive two-phase cooling loop can improve the power electronic lifetime ［C］// PCIM Europe 2017 International Exhibition and Conference for Power Electronics， Intelligent Motion， Renewable Energy and Energy Management ， 2017 .

温荣福 . 低压蒸汽滴状冷凝传热微观机理及强化［D］. 大连：大连理工大学， 2015 .

Wen Rongfu . Microscopic mechanism of steam dropwise condensation at low pressure and heat transfer enhancement ［D］. Dalian ： Dalian University of Technology ， 2015 .

金梧凤，赵宁，毕晨，等 . 辐射空调过冷度与结露延迟时间动态变化特性研究［J］. 流体机械， 2021 ， 49 （ 2 ）： 90 - 96 .

Jin Wufeng ， Zhao Ning ， Bi Chen ， et al . Study on dynamic variation characteristics of subcooling degree and dew delay time of radiant air conditioning system ［J］. Fluid Machinery ， 2021 ， 49 （ 2 ）： 90 - 96 .

Wang Xin ， Liu Xiang ， Bai Yun . Prediction of the temperature of diesel engine oil in railroad locomotives using compressed information-based data fusion method with attention-enhanced CNN-LSTM ［J］. Applied Energy ， 2024 ， 367 ： 123357 .

Liu Shuanglong ， Zhang Chao ， Ma Jinwen . CNN-LSTM neural network model for quantitative strategy analysis in stock markets ［C］// Neural Information Processing . Cham ： Springer International Publishing ， 2017 ： 198 - 206 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Experimental Research on an 8 kW Direct Cooling Unit for Power Battery Used in a Vehicle

Related Author

He Xian

Deng Dong

Su Jian

Sha Haijian

Hu Jing

Related Institution

Dun An Automotive Thermal Management Technology Co. Ltd.

DunAn Environmental Technology Co., Ltd.

Zhengjiang Dunan Electro-Mechanical Technology Co.,Ltd.

Address：10/F, Yindu Mansion, 67 Fucheng Road, Haidian Dist, Beijing, China Postal code：100142
Tel：010-68711412 Email：editor@car.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰