基于神经网络方法的布雷顿循环定量分析及多目标优化

顾新壮; 李青芯; 石明; 杨瑞睿; 殷岳; 杨航; 马文明; 魏务卿; 周朔晨; 陈昊芃

doi:10.19666/j.rlfd.202501012

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于神经网络方法的布雷顿循环定量分析及多目标优化

先进动力循环技术 | 更新时间：2025-11-21

- 基于神经网络方法的布雷顿循环定量分析及多目标优化
- Quantitative analysis and multi-objective optimization of Brayton cycle based on artificial neural network method
- 热力发电 2025年第11期页码：42-48
- 作者机构：
- 作者简介：
- 基金信息：
  
  上海市科委项目课题三（23DZ1201003,2024QT(83)-010,2024QT(81)-011）;中国长江三峡集团有限公司2024年首批非定向指南项目（2025QT(82)-001）~~
- DOI：10.19666/j.rlfd.202501012
  中图分类号：
- 纸质出版：2025
- 稿件说明：
移动端阅览
顾新壮, 李青芯, 石明, 等. 基于神经网络方法的布雷顿循环定量分析及多目标优化[J]. 热力发电, 2025,(11):42-48.

顾新壮, 李青芯, 石明, et al. Quantitative analysis and multi-objective optimization of Brayton cycle based on artificial neural network method[J]. Thermal Power Generation, 2025, (11): 42-48.
顾新壮, 李青芯, 石明, 等. 基于神经网络方法的布雷顿循环定量分析及多目标优化[J]. 热力发电, 2025,(11):42-48. DOI： 10.19666/j.rlfd.202501012.

顾新壮, 李青芯, 石明, et al. Quantitative analysis and multi-objective optimization of Brayton cycle based on artificial neural network method[J]. Thermal Power Generation, 2025, (11): 42-48. DOI： 10.19666/j.rlfd.202501012.

摘要

布雷顿循环被公认为第三代太阳能热发电技术的动力循环，得益于神经网络方法具有重要度评估和定量分析等优势。首先，采用控制变量法从多个运行参数中筛选出透平机进口温度和压缩比等重要参数，控制变量法中重要度随着R~2值的降低而增加，当不含上述重要参数时，其对应的R~2值分别降低到0.57和0.64，均低于其余运行参数；然后，采用布雷顿循环中的输出功定量分析结果，其R~2值大于0.999，其中热效率和输入热量的R~2值分别为0.992和0.988；最后，通过多目标优化结果所推荐的透平机进口温度和压缩比值分别为500℃和2.19，相对应的热效率、输出功和输入热量分别为46.58%、100.97 k J/kg和–176.5 kJ/kg。该研究可作为光热电站布雷顿循环的实际运行和性能研究的参考。

Abstract

关键词

Keywords

references

Carbon Capture Journal Group. IEA report:an energy sector roadmap to carbon neutrality in China[J]. Carbon Capture Journal, 2021(84):7-8.

MEHOS M, TURCHI C, VIDAL J, et al. Concentrating solar power Gen3 demonstration roadmap[R]. National Renewable Energy Lab, Golden, Colorado(United States), 2017:1.

王慧芳,孙恩慧,赵乘新,等. S-CO2部分膨胀循环余热利用系统热力学特性研究[J].热力发电, 2024,53(6):79-86.WANG Huifang, SUN Enhui, ZHAO Chengxin, et al.Thermodynamic characteristics of waste heat utilization system applying S-CO2 partial expansion cycle[J].Thermal Power Generation, 2024, 53(6):79-86.

韩冰川,陈永东,于改革,等.全回热超临界二氧化碳布雷顿联合循环特性及?经济性分析[J].热力发电,2023, 51(11):76-84.HAN Bingchuan, CHEN Yongdong, YU Gaige, et al.Study on characteristics and exergo-economic analysis of completely recuperative supercritical carbon dioxide Brayton combined cycle[J]. Thermal Power Generation,2023, 51(11):76-84.

JIN Q, XIA S, LI P, et al. Multi-objective performance optimization of regenerative S-CO2 Brayton cycle based on neural network prediction[J]. Energy Conversion and Management, 2022, 14:100203.

SUN F, XIE G, SONG J, et al. Thermal characteristics of in-tube upward supercritical CO2 flows and a new heat transfer prediction model based on artificial neural networks(ANN)[J]. Applied Thermal Engineering, 2021,194:117067.

KIM Y, LEE Y, AHN K, et al. Parametric study of a supercritical CO2 power cycle for waste heat recovery with variation in cold temperature and heat source temperature[J]. Energies, 2021, 14(20):6648.

KIM Y, SHIN D, KIM C, et al. Single-loop organic Rankine cycles for engine waste heat recovery using both low-and high-temperature heat sources[J]. Energy, 2016,96:482-494.

WANG X, LI B, YAN Y, et al. Predicting of thermal resistances of closed vertical meandering pulsating heat pipe using artificial neural network model[J]. Applied Thermal Engineering, 2019, 149:1134-1141.

TEE J, SELVARAJOO A, ARUMUGASAMY S.Prediction of carbon sequestration of biochar produced from biomass pyrolysis by artificial neural network[J].Journal of Environmental Chemical Engineering, 2022,10(3):107640.

AFRAND M, NAZARI N, AKBARI M. Effects of temperature and solid volume fraction on viscosity of SiO2-MWCNTs/SAE40 hybrid nanofluid as a coolant and lubricant in heat engines[J]. Applied Thermal Engineering, 2016, 102:45-54.

AHMADI M, MOHAMMADI A, DEHGHANI S, et al.Multi-objective thermodynamic-based optimization of output power of Solar Dish-Stirling engine by implementing an evolutionary algorithm[J]. Energy Conversion and Management, 2013, 75:438-445.

KULHANEK M, DOSTAL V. Supercritical carbon dioxide cycles thermodynamic analysis and comparison;proceedings of the Supercritical CO2 power cycle symposium[C]. Supercritical CO2 Power Cycle Symposium, 2011:24-25.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

超燃冲压发动机冷却与发电一体化系统性能优化

两级压缩超临界二氧化碳布雷顿循环系统性能分析

单罐储热系统充放热循环过程动态热特性及力学性能模拟

采用压缩储能的新型超临界二氧化碳布雷顿循环塔式太阳能热发电系统性能分析

超临界600 MW循环流化床锅炉燃用不同煤种燃烧特性及排放特性试验