航空学报 > 2026, Vol. 47 Issue (13): 133030-133030   doi: 10.7527/S1000-6893.2026.33030

流动控制与热管理专刊

|

机载电子设备复合微通道液冷板智能优化设计

张同勇1,2, 曾萌祥1,2, 陈强1,2, 费庆国1,2, 张大海1,2()   

  1. 1.东南大学 高速飞行器结构与热防护教育部重点实验室,南京 211189
    2.东南大学 机械工程学院,南京 211189
  • 收稿日期:2025-11-03 修回日期:2025-11-28 接受日期:2026-02-02 出版日期:2026-02-10 发布日期:2026-02-09
  • 通讯作者: 张大海 E-mail:dzhang@seu.edu.cn
  • 基金资助:
    国家自然科学基金(52125209);国家自然科学基金(52532012);国家自然科学基金(52302514);国家自然科学基金(52472377);国家自然科学基金(52502441);国家自然科学基金(52572404);江苏省自然科学基金(BK20231542);中国科协青年人才托举工程(YESS20230551)

Intelligent optimization design of composite microchannel liquid cold plate for airborne electronic devices

Tongyong ZHANG1,2, Mengxiang ZENG1,2, Qiang CHEN1,2, Qingguo FEI1,2, Dahai ZHANG1,2()   

  1. 1.Key Laboratory of Structure and Thermal Protection of High Speed Aircraft,Ministry of Education,Southeast University,Nanjing 211189,China
    2.School of Mechanical Engineering,Southeast University,Nanjing 211189,China
  • Received:2025-11-03 Revised:2025-11-28 Accepted:2026-02-02 Online:2026-02-10 Published:2026-02-09
  • Contact: Dahai ZHANG E-mail:dzhang@seu.edu.cn
  • Supported by:
    National Natural Science Foundation of China(52125209);Jiangsu Natural Science Foundation(BK20231542);Young Elite Scientists Sponsorship Program by CAST(YESS20230551)

摘要:

随着机载电子器件在性能与集成度上的进步,传统微通道散热器已难以满足其日益增长的散热需求。为此,围绕新型复合扰流结构微通道冷板,建立了基于神经网络的性能预示代理模型,并将其与NSGA-Ⅱ算法相结合开展多目标优化研究,以进一步提升冷板综合性能。通过SHAP法揭示了影响冷板性能的主要因素,并基于熵权TOPSIS决策法获得了冷板最优无量纲设计参数。实验结果表明:神经网络能够充分学习和掌握冷板特征与性能间的复杂映射关系,具备较好的拟合精度和预测能力,最大平均绝对误差仅为0.383;代理模型大幅加速了优化进程,并保证了优化结果的可靠性,最大误差仅为6.34%;相较于原设计,所得最优冷板的平均努塞尔数和综合换热因子分别达70.755和2.223,换热性能提升了36.7%,综合性能提升了9.2%。

关键词: 微通道换热器, 强化换热, 多目标优化, 神经网络, NSGA-Ⅱ算法

Abstract:

With the improvements in performance and integration of onboard electronics, traditional microchannel heat sinks (MCHs) are inadequate for the escalating thermal management requirements. A surrogate model for MCH with turbulence-promoting structures is established based on neural network. Combined with the NSGA-Ⅱ algorithm, the surrogate is employed to conduct multi-objective optimization. The primary factors governing thermal-hydraulic performance are identified by SHAP analysis. Additionally, the optimal nondimensional design parameters are obtained based on entropy-weighted TOPSIS. The results indicate that the neural network fully learns the complex mapping between features and performance, achieving good fitting and predictive ability, with a maximum mean absolute error of 0.383. The surrogate accelerates optimization process, with a maximum error of 6.34%. Compared with the original design, the optimized MCH achieves an average Nusselt number of 70.755 and an overall performance factor (PEC) of 2.223, yielding enhancements of 36.7% in heat transfer and 9.2% in comprehensive performance.

Key words: microchannel heat sinks, heat transfer enhancement, multi-objective optimization, neural network, NSGA-Ⅱ algorithm

中图分类号: