基于BP神经网络和遗传算法的翅片管结构优化

doi:10.6040/j.issn.1672-3961.0.2024.333

摘要/Abstract

摘要： 为提升热管换热器的综合性能,通过反向传播(back propagation, BP)神经网络预测模型与带精英策略的非支配排序遗传算法(non-dominated sorting genetic algorithm Ⅱ, NSGA-Ⅱ)相结合,对核电站主控室非能动冷却系统中重力热管蒸发段的翅片管结构进行多目标优化设计。以翅片厚度、间距、高度、横向管间距、纵向管间距、长径比等6个结构参数为自变量,建立努塞尔数、压降和最小截面处风速的预测模型,通过NSGA-Ⅱ算法以传热因子最大化和阻力因子最小化为目标进行全局寻优。优化后的翅片结构参数组合(翅片厚度为1 mm、间距为6 mm、高度为5 mm、横向管间距为70 mm、纵向管间距为75 mm、长径比为1.4)使传热因子提升25.86%,阻力因子降低17.96%,综合性能系数提升35.24%。本研究验证了BP神经网络与遗传算法联合优化方法在热管结构设计中的有效性,为核电站主控室非能动冷却系统的工程优化提供关键参数和理论指导。

关键词: BP神经网络, 非支配排序遗传算法, 非能动冷却系统, 重力热管, 多目标优化

Abstract: To enhance the comprehensive performance of the heat pipe heat exchanger, the finned tube structure in a thermosyphon evaporator for nuclear power plant passive cooling systems was optimized using the hybrid back propagation(BP)neural network prediction model and non-dominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ). Six structural parameters, such as fin thickness, spacing, height, transverse tube pitch, longitudinal tube pitch, and aspect ratio, were selected as design variables. Predictive models for the Nusselt number, pressure drop, and minimum cross-sectional airflow velocity were developed, enabling multi-objective optimization targeting maximum heat transfer and minimum flow resistance. The optimal configuration(1 mm fin thickness, 6 mm spacing, 5 mm height, 70 mm transverse tube pitch, 75 mm longitudinal tube pitch, 1.4 aspect ratio)resulted in a 25.86% increase in the heat factor, a 17.96% reduction in the flow resistance, and a 35.24% improvement in the overall performance coefficient. These results validated the effectiveness of the combined BP neural network and genetic algorithm for heat pipe design, providing both critical parameters and theoretical guidance for engineering optimization of nuclear power plant passive cooling systems.

Key words: BP neural network, non-dominated sorting genetic algorithm, passive cooling system, thermosyphon, multi-objective optimization

中图分类号:

TK172

邵孟伟,袁世飞,周宏志,王乃华. 基于BP神经网络和遗传算法的翅片管结构优化[J]. 山东大学学报 (工学版), 2025, 55(6): 76-82.

SHAO Mengwei, YUAN Shifei, ZHOU Hongzhi, WANG Naihua. Optimisation of finned tube structure based on BP neural network and genetic algorithm[J]. Journal of Shandong University(Engineering Science), 2025, 55(6): 76-82.

参考文献

[1] WOUTERS P, DUCARME D, DEMEESTER J, et al. Ventilation requirements in non-domestic buildings and energy efficiency[J]. Energy and Buildings, 1998, 27(3): 257-261.
[2] SUTHARSHAN B, MUTYALA M, VIJUK R P, et al. The AP1000TM reactor: passive safety and modular design[J]. Energy Procedia, 2011, 7: 293-302.
[3] LEED S, LIU M L, HUNG T C, et al. Optimal structural analysis with associated passive heat removal for AP1000 shield building[J]. Applied Thermal Engineering, 2013, 50(1): 207-216.
[4] WU X Y, HUANG Y X, YE W, et al. Optimization analysis of passive fin-concrete heat sinks for thermal environment control in main control room[J]. Case Studies in Thermal Engineering, 2022, 35: 102108.
[5] HUANG Y X, WU X Y, YE W, et al. Dynamic performance and multi-objective optimization of fin-concrete heat sinks[J]. Applied Thermal Engineering, 2021, 195: 117146.
[6] HUANG Y X, SU X, WU X Y, et al. Dynamic thermal performance analysis for fin-concrete ceiling in main control rooms of passive nuclear power plants[J]. Case Studies in Thermal Engineering, 2021, 28: 101402.
[7] CHANG L, ZHANG X, CAI Y Y. Cold concrete envelopes with fins regulating control rooms temperature under accident conditions[J]. Procedia Engineering, 2017, 205: 3493-3496.
[8] 赵剑刚. 非能动冰蓄冷技术在核电站主控室可居留性应用分析[J]. 广东化工, 2014, 41(15): 58-59. ZHAO Jiangang. Application analysis of passive ice-storage technology in main control room habitability[J]. Guangdong Chemical Industry, 2014, 41(15): 58-59.
[9] 赵丹, 林宇清, 吕胡人. 基于相变蓄冷的核电厂主控室非能动冷却系统[J]. 暖通空调, 2024, 54(1): 1-4. ZHAO Dan, LIN Yuqing, LÜ Huren. Passive cooling system of main control room in nuclear power plants based on phase change cold storage[J]. Heating Ventilating & Air Conditioning, 2024, 54(1): 1-4.
[10] 李进. 核电站主控室在断电事故中利用高压空气非能动制冷研究[D]. 重庆: 重庆大学, 2015: 88-96. LI Jin. Study on the passive refrigeration with high-pressure air for main control room of nuclear power plant in blackout accident[D]. Chongqing: Chongqing Univer-sity, 2015: 88-96.
[11] LI H, LI K N, LIU B, et al. Study on the passive refrigeration for main control room of nuclear power plant in power outage accident[J]. Nuclear Engineering and Design, 2018, 326: 183-189.
[12] WANG S L, CHEN G M, FANG M, et al. A new compressed air energy storage refrigeration system[J]. Energy Conversion and Management, 2006, 47(18/19): 3408-3416.
[13] PARKS K, AHN J H, KIM T S. Off-design operating characteristics of an open-cycle air refrigeration system[J]. International Journal of Refrigeration, 2012, 35(8): 2311-2320.
[14] 周照春. 核电站主控室热管换热非能动通风系统研究[D]. 北京: 北京化工大学, 2022: 33-42. ZHOU Zhaochun. Research on passive ventilation a system using heat pipe for thermal exchange in main control room of nuclear power plant[D]. Beijing: Beijing University of Chemical Technology, 2022: 33-42.
[15] WU X P, JOHNSON P, AKBARZADEH A. Application of heat pipe heat exchangers to humidity control in air-conditioning systems[J]. Applied Thermal Engineering, 1997, 17(6): 561-568.
[16] CHERNYSHEVA M A, YUSHAKOVA S I, MAYDANIK Y F. Copper-water loop heat pipes for energy-efficient cooling systems of supercomputers[J]. Energy, 2014, 69: 534-542.
[17] ZHANG G H, WANG B L, LI X T, et al. Review of experimentation and modeling of heat and mass transfer performance of fin-and-tube heat exchangers with dehumidification[J]. Applied Thermal Engineering, 2019, 146: 701-717.
[18] 王玲, 李俐, 朱翔鸥, 等. 基于粒子群算法的强迫风冷散热器多目标优化[J]. 电气技术, 2022, 23(2): 20-25. WANG Ling, LI Li, ZHU Xiang'ou, et al. Multi-objective optimization of forced air-cooled radiators based on particle swarm algorithm[J]. Electrical Technology, 2022, 23(2): 20-25.
[19] 龙浪. 螺旋翅片管式换热器散热仿真分析及结构优化设计[D]. 成都: 电子科技大学, 2023. LONG Lang. Thermal simulation analysis and structural optimization design of spiral finned tube heat exchangers[D]. Chengdu: University of Electronic Science and Technology, 2023.
[20] WANG S M, XIAO J, WANG J R, et al. Application of response surface method and multi-objective genetic algorithm to configuration optimization of shell-and-tube heat exchanger with fold helical baffles[J]. Applied Thermal Engineering, 2018, 129: 512-520.
[21] ZHANG T Y, CHEN L, WANG J. Multi-objective optimization of elliptical tube fin heat exchangers based on neural networks and genetic algorithm[J]. Energy, 2023, 269: 126729.
[22] KAYS W M, LONDON A L, ECKERT E R G. Compact heat exchangers[J]. Journal of Applied Mechanics, 1960, 27(2): 377.

相关文章 15

[1]	韦修喜,陶道,黄华娟. 改进果蝇算法优化BP神经网络预测汽油辛烷值[J]. 山东大学学报 (工学版), 2023, 53(5): 20-28.
[2]	李浩源,于景明,张桂林,张斌. 基于智能算法的光纤预制棒芯层制备工艺参数优化[J]. 山东大学学报 (工学版), 2023, 53(4): 149-156.
[3]	赵康,田浩,马欢,杨冬. 基于复杂网络理论的多直流馈入受端电网优化分区方法[J]. 山东大学学报 (工学版), 2022, 52(1): 128-134.
[4]	丁飞,江铭炎. 基于改进狮群算法和BP神经网络模型的房价预测[J]. 山东大学学报 (工学版), 2021, 51(4): 8-16.
[5]	武慧虹,钱淑渠,刘衍民,徐国峰,郭本华. 精英克隆局部搜索的多目标动态环境经济调度差分进化算法[J]. 山东大学学报 (工学版), 2021, 51(1): 11-23.
[6]	孙东磊,王艳,于一潇,韩学山,杨明,闫芳晴. 基于BP神经网络的短期光伏集群功率区间预测[J]. 山东大学学报 (工学版), 2020, 50(5): 70-76.
[7]	金保明,卢光毅,王伟,杜伦阅. 基于弹性梯度下降算法的BP神经网络降雨径流预报模型[J]. 山东大学学报 (工学版), 2020, 50(3): 117-124.
[8]	孙润稼,朱海南,刘玉田. 基于偏好多目标优化和遗传算法的输电网架重构[J]. 山东大学学报 (工学版), 2019, 49(5): 17-23.
[9]	杨冬,王世文,王勇,陈博,郑天茹,周宁,肖天,赵雅文. 并网型风电场扩展光伏互补发电容量优化配置[J]. 山东大学学报 (工学版), 2019, 49(5): 44-51.
[10]	郑店坤,许同乐,尹召杰,孟庆民. 改进PSO-BP神经网络对尾矿坝地下水位的预测方法[J]. 山东大学学报 (工学版), 2019, 49(3): 108-113.
[11]	杨亚楠,夏斌,谢楠,袁文浩. 基于BP神经网络和多元Taylor级数的混合定位算法[J]. 山东大学学报 (工学版), 2019, 49(1): 36-40.
[12]	钱淑渠,武慧虹,徐国峰,金晶亮. 计及排放的动态经济调度免疫克隆演化算法[J]. 山东大学学报(工学版), 2018, 48(4): 1-9.
[13]	王飞,徐健,李伟,汪新浩,施啸寒. 基于分布式储能系统的风储滚动优化调度方法[J]. 山东大学学报(工学版), 2017, 47(6): 89-94.
[14]	裴小兵,陈慧芬,张百栈,陈孟辉. 改善式BVEDA求解多目标调度问题[J]. 山东大学学报(工学版), 2017, 47(4): 25-30.
[15]	邓冠龙,杨洪勇,张淑宁,顾幸生. 零等待flow shop多目标调度的混合差分进化算法[J]. 山东大学学报(工学版), 2016, 46(5): 21-28.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed