基于GA-BP神经网络的超临界CO2传热特性预测研究

doi:10.11949/0438-1157.20210156

摘要/Abstract

摘要：

超临界二氧化碳（S-CO₂）动力循环在能源利用领域中拥有广阔的应用前景，其中超临界CO₂的传热特性对其能量转换效率至关重要。开展了超临界CO₂在水平小圆管内对流传热实验研究，并通过建立遗传算法优化的BP神经网络模型（GA-BP），对其在不同工况下的传热特性进行预测分析。实验参数范围：系统压力7.5~9.5 MPa，质量流速1100~2100 kg/（m²?s），热通量120~560 kW/m²。实验结果表明，超临界CO₂传热系数随流体温度的升高先增大后减小，在拟临界温度附近达到最大值。GA-BP神经网络模型能有效地预测超临界CO₂的传热系数，预测数据的决定系数R²为0.99662，超过95%的数据误差位于±10%范围内，平均误差为3.55%，为超临界流体传热预测提供新的思路。

关键词: 超临界二氧化碳, 对流, 传热, GA-BP神经网络, 传热预测

Abstract:

Supercritical carbon dioxide (S-CO₂) power cycle has a broad application prospect in the field of energy utilization, in which the heat transfer of supercritical CO₂ plays a significant role in its energy conversion efficiency. Therefore, an experiment has been conducted to determine the convective heat transfer characteristics of supercritical CO₂ flowing in a mini horizontal circular tube, and a BP neural network optimized by genetic algorithm has been established to predict the heat transfer coefficient of supercritical CO₂under different conditions. The experimental parameters are as follows: system pressure 7.5—9.5 MPa, mass flux 1100—2100 kg/(m²?s), heat flux 120—560 kW/m². The experimental results show that the heat transfer coefficient of supercritical CO₂ increases first and then decreases with increasing fluid temperature, and reaches maximum near the pseudo-critical temperature. The model of the GA-BP neural network can effectively predict the heat transfer coefficient of supercritical CO₂, the determinate coefficient of predicted data R² is 0.99662, and more than 95% of the data are within the error range of ±10%, the average error is 3.55%. GA-BP neural network model provides a novel idea for heat transfer prediction for supercritical fluids.

Key words: supercritical carbon dioxide, convection, heat transfer, GA-BP neural network, prediction of heat transfer

中图分类号:

TK 124

颜建国, 郑书闽, 郭鹏程, 张博, 毛振凯. 基于GA-BP神经网络的超临界CO₂传热特性预测研究[J]. 化工学报, 2021, 72(9): 4649-4657.

Jianguo YAN, Shumin ZHENG, Pengcheng GUO, Bo ZHANG, Zhenkai MAO. Prediction of heat transfer characteristics for supercritical CO₂ based on GA-BP neural network[J]. CIESC Journal, 2021, 72(9): 4649-4657.

图/表 14

图1 超临界CO2流动传热实验系统

Fig.1 Schematic diagram of experimental test loop for supercritical CO2

图2 实验段示意图

Fig.2 Schematic diagram of test section

表1 实验工况

Table 1 Test conditions

实验参数	数值
系统压力p/ MPa	7.5，8.5，9.5
质量流速G/( kg/(m²?s))	1100，1600，2100
实验段热通量q/( kW/m²)	120，340，560
进口温度T_in/℃	20~60

表2 参数不确定度

Table 2 Parameter uncertainties

实验参数	不确定度/%
压力/ MPa	0.14
流体温度/℃	0.5
壁面温度/℃	0.4
质量流速/(kg/(m²?s))	0.75
热通量/(kW/m²)	4.63
传热系数/(W/(m²·K))	5.20

图3 BP神经网络示意图

Fig.3 Schematic diagram of BP neural network

图4 GA-BP神经网络程序流程

Fig.4 Flow chart of GA-BP neural network program

图5 神经网络预测值与实验值的对比

Fig.5 Comparison of prediction results and experimental results with neural networks

图6 GA-BP神经网络预测误差

Fig.6 Predictive error of GA-BP neural network

图7 典型工况下的传热特性及其预测结果

Fig.7 Heat transfer characteristics under typical condition and the prediction results

图8 不同压力下的传热特性

Fig.8 Heat transfer characteristics under different pressures

图9 不同质量流速下的传热特性

Fig.9 Heat transfer characteristics at different mass fluxes

图10 不同热通量下传热特性

Fig.10 Heat transfer characteristics under different heat fluxes

图11 预测数据与独立工况实验数据对比

Fig.11 Comparisons of the prediction data with experimental data from extra testing

图12 预测数据与文献中的实验数据对比

Fig.12 Comparisons of the prediction data with experimental data from literature

参考文献 32

1	Liang Y C, Bian X Y, Qian W W, et al. Theoretical analysis of a regenerative supercritical carbon dioxide Brayton cycle/organic Rankine cycle dual loop for waste heat recovery of a diesel/natural gas dual-fuel engine[J]. Energy Conversion and Management, 2019, 197: 111845.
2	Wu P, Ma Y D, Gao C T, et al. A review of research and development of supercritical carbon dioxide Brayton cycle technology in nuclear engineering applications[J]. Nuclear Engineering and Design, 2020, 368: 110767.
3	徐进良, 刘超, 孙恩慧, 等. 超临界二氧化碳动力循环研究进展及展望[J]. 热力发电, 2020, 49(10): 1-10.
	Xu J L, Liu C, Sun E H, et al. Review and perspective of supercritical carbon dioxide power cycles[J]. Thermal Power Generation, 2020, 49(10): 1-10.
4	Novales D, Erkoreka A, de la Peña V, et al. Sensitivity analysis of supercritical CO₂ power cycle energy and exergy efficiencies regarding cycle component efficiencies for concentrating solar power[J]. Energy Conversion and Management, 2019, 182: 430-450.
5	Teng L, Xuan Y M. A novel solar receiver for supercritical CO₂ Brayton cycle[J]. Energy Procedia, 2019, 158: 339-344.
6	Kim S G, Yu H, Moon J, et al. A concept design of supercritical CO₂ cooled SMR operating at isolated microgrid region[J]. International Journal of Energy Research, 2017, 41(4): 512-525.
7	Oh B S, Ahn Y H, Yu H, et al. Safety evaluation of supercritical CO₂ cooled micro modular reactor[J]. Annals of Nuclear Energy, 2017, 110: 1202-1216.
8	Chen Y, Ma G W, Wang H D, et al. Application of carbon dioxide as working fluid in geothermal development considering a complex fractured system[J]. Energy Conversion and Management, 2019, 180: 1055-1067.
9	Ruiz-Casanova E, Rubio-Maya C, Pacheco-Ibarra J J, et al. Thermodynamic analysis and optimization of supercritical carbon dioxide Brayton cycles for use with low-grade geothermal heat sources[J]. Energy Conversion and Management, 2020, 216: 112978.
10	Chu W X, Bennett K, Cheng J, et al. A review of supercritical CO₂ Brayton cycle using in renewable energy applications[J]. Renewable Energy and Sustainable Development, 2018, 4(1): 14.
11	Cabeza L F, de Gracia A, Fernández A I, et al. Supercritical CO₂ as heat transfer fluid: a review[J]. Applied Thermal Engineering, 2017, 125: 799-810.
12	Ehsan M M, Guan Z Q, Klimenko A Y. A comprehensive review on heat transfer and pressure drop characteristics and correlations with supercritical CO₂ under heating and cooling applications[J]. Renewable and Sustainable Energy Reviews, 2018, 92: 658-675.
13	吴新明, 朱兵国, 张良, 等. 圆管内超临界CO₂的阻力特性[J]. 化工学报, 2018, 69(12): 5024-5033.
	Wu X M, Zhu B G, Zhang L, et al. Resistance characteristics of supercritical CO₂ in circular tube[J]. CIESC Journal, 2018, 69(12): 5024-5033.
14	王乃心, 杨大章, 谢晶, 等. 超临界CO₂对流换热特性试验研究进展[J]. 流体机械, 2020, 48(11): 73-79.
	Wang N X, Yang D Z, Xie J, et al. A review on experimental studies of convection heat transfer characteristic of supercritical CO₂[J]. Fluid Machinery, 2020, 48(11): 73-79.
15	Rao N T, Oumer A N, Jamaludin U K. State-of-the-art on flow and heat transfer characteristics of supercritical CO₂ in various channels[J]. The Journal of Supercritical Fluids, 2016, 116: 132-147.
16	颜建国, 朱凤岭, 郭鹏程, 等. 高热流低流速条件下超临界CO₂在小圆管内的对流传热特性[J]. 化工学报, 2019, 70(5): 1779-1787.
	Yan J G, Zhu F L, Guo P C, et al. Convective heat transfer of supercritical CO₂ flowing a mini circular tube under high heat flux and low mass flux conditions[J]. CIESC Journal, 2019, 70(5): 1779-1787.
17	Zhang S J, Xu X X, Liu C, et al. Experimental and numerical comparison of the heat transfer behaviors and buoyancy effects of supercritical CO₂ in various heating tubes[J]. International Journal of Heat and Mass Transfer, 2020, 149: 119074.
18	朱兵国, 吴新明, 张良, 等. 垂直上升管内超临界CO₂流动传热特性研究[J]. 化工学报, 2019, 70(4): 1282-1290, 1661.
	Zhu B G, Wu X M, Zhang L, et al. Flow and heat transfer characteristics of supercritical CO₂ in vertical tube[J]. CIESC Journal, 2019, 70(4): 1282-1290, 1661.
19	Guo P C, Liu S C, Yan J G, et al. Experimental study on heat transfer of supercritical CO₂ flowing in a mini tube under heating conditions[J]. International Journal of Heat and Mass Transfer, 2020, 153: 119623.
20	Wang J Y, Guan Z Q, Gurgenci H, et al. A computationally derived heat transfer correlation for in-tube cooling turbulent supercritical CO₂[J]. International Journal of Thermal Sciences, 2019, 138: 190-205.
21	Ma T, Chu W X, Xu X Y, et al. An experimental study on heat transfer between supercritical carbon dioxide and water near the pseudo-critical temperature in a double pipe heat exchanger[J]. International Journal of Heat and Mass Transfer, 2016, 93: 379-387.
22	Wang L, Pan Y C, Lee J D, et al. Convective heat transfer characteristics of supercritical carbon dioxide in vertical miniature tubes of a uniform heating experimental system[J]. International Journal of Heat and Mass Transfer, 2021, 167: 120833.
23	Dhanuskodi R, Kaliappan R, Suresh S, et al. Artificial neural networks model for predicting wall temperature of supercritical boilers[J]. Applied Thermal Engineering, 2015, 90: 749-753.
24	Mohanraj M, Jayaraj S, Muraleedharan C. Applications of artificial neural networks for thermal analysis of heat exchangers - a review[J]. International Journal of Thermal Sciences, 2015, 90: 150-172.
25	Yang F B, Cho H, Zhang H G, et al. Artificial neural network (ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery[J]. Energy Conversion and Management, 2018, 164: 15-26.
26	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.
27	Azizi S, Ahmadloo E. Prediction of heat transfer coefficient during condensation of R134a in inclined tubes using artificial neural network[J]. Applied Thermal Engineering, 2016, 106: 203-210.
28	Pesteei S M, Mehrabi M. Modeling of convection heat transfer of supercritical carbon dioxide in a vertical tube at low Reynolds numbers using artificial neural network[J]. International Communications in Heat and Mass Transfer, 2010, 37(7): 901-906.
29	Lei X L, Zhang J, Gou L T, et al. Experimental study on convection heat transfer of supercritical CO₂ in small upward channels[J]. Energy, 2019, 176: 119-130.
30	章聪, 江锦波, 彭旭东, 等. 近临界区CO₂物性预测模型对比与修正[J]. 化工学报, 2019, 70(8): 3058-3070.
	Zhang C, Jiang J B, Peng X D, et al. Comparison and correction of CO₂ properties model in critical region[J]. CIESC Journal, 2019, 70(8): 3058-3070.
31	Coleman H W, Steele W G. Engineering application of experimental uncertainty analysis[J]. AIAA Journal, 1995, 33(10): 1888-1896.
32	Zahlan H, Groeneveld D, Tavoularis S. Measurements of convective heat transfer to vertical upward flows of CO₂ in circular tubes at near-critical and supercritical pressures[J]. Nuclear Engineering and Design, 2015, 289: 92-107.

[1]	张双星, 刘舫辰, 张义飞, 杜文静. R-134a脉动热管相变蓄放热实验研究[J]. 化工学报, 2023, 74(S1): 165-171.
[2]	张义飞, 刘舫辰, 张双星, 杜文静. 超临界二氧化碳用印刷电路板式换热器性能分析[J]. 化工学报, 2023, 74(S1): 183-190.
[3]	陈爱强, 代艳奇, 刘悦, 刘斌, 吴翰铭. 基板温度对HFE7100液滴蒸发过程的影响研究[J]. 化工学报, 2023, 74(S1): 191-197.
[4]	刘明栖, 吴延鹏. 导光管直径和长度对传热影响的模拟分析[J]. 化工学报, 2023, 74(S1): 206-212.
[5]	王志国, 薛孟, 董芋双, 张田震, 秦晓凯, 韩强. 基于裂隙粗糙性表征方法的地热岩体热流耦合数值模拟与分析[J]. 化工学报, 2023, 74(S1): 223-234.
[6]	晁京伟, 许嘉兴, 李廷贤. 基于无管束蒸发换热强化策略的吸附热池的供热性能研究[J]. 化工学报, 2023, 74(S1): 302-310.
[7]	程成, 段钟弟, 孙浩然, 胡海涛, 薛鸿祥. 表面微结构对析晶沉积特性影响的格子Boltzmann模拟[J]. 化工学报, 2023, 74(S1): 74-86.
[8]	李艺彤, 郭航, 陈浩, 叶芳. 催化剂非均匀分布的质子交换膜燃料电池操作条件研究[J]. 化工学报, 2023, 74(9): 3831-3840.
[9]	王玉兵, 李杰, 詹宏波, 朱光亚, 张大林. R134a在菱形离散肋微小通道内的流动沸腾换热实验研究[J]. 化工学报, 2023, 74(9): 3797-3806.
[10]	李科, 文键, 忻碧平. 耦合蒸气冷却屏的真空多层绝热结构对液氢储罐自增压过程的影响机制研究[J]. 化工学报, 2023, 74(9): 3786-3796.
[11]	齐聪, 丁子, 余杰, 汤茂清, 梁林. 基于选择吸收纳米薄膜的太阳能温差发电特性研究[J]. 化工学报, 2023, 74(9): 3921-3930.
[12]	杨越, 张丹, 郑巨淦, 涂茂萍, 杨庆忠. NaCl水溶液喷射闪蒸-掺混蒸发的实验研究[J]. 化工学报, 2023, 74(8): 3279-3291.
[13]	陈天华, 刘兆轩, 韩群, 张程宾, 李文明. 喷雾冷却换热强化研究进展及影响因素[J]. 化工学报, 2023, 74(8): 3149-3170.
[14]	洪瑞, 袁宝强, 杜文静. 垂直上升管内超临界二氧化碳传热恶化机理分析[J]. 化工学报, 2023, 74(8): 3309-3319.
[15]	张贲, 王松柏, 魏子亚, 郝婷婷, 马学虎, 温荣福. 超亲水多孔金属结构驱动的毛细液膜冷凝及传热强化[J]. 化工学报, 2023, 74(7): 2824-2835.

基于GA-BP神经网络的超临界CO₂传热特性预测研究

Prediction of heat transfer characteristics for supercritical CO₂ based on GA-BP neural network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价