岩性油气藏 ›› 2024, Vol. 36 ›› Issue (2): 15–22.doi: 10.12108/yxyqc.20240202

• 新能源与伴生资源 • 上一篇    

基于BP算法的中深层同轴套管换热量预测

熊波, 朱冬雪, 方朝合, 王社教, 杜广林, 薛亚斐, 莫邵元, 辛福东   

  1. 中石油深圳新能源研究院有限公司, 广东 深圳 518000
  • 收稿日期:2023-08-24 修回日期:2023-10-09 发布日期:2024-03-06
  • 通讯作者: 朱冬雪（1990—），男，硕士，副研究员，研究方向为地热能开发利用。Email：335758788@qq.com。 E-mail:335758788@qq.com。
  • 作者简介:熊波（1979—），男，博士，教授，主要从事地热能开发利用及智慧能源研究方面的工作。地址：（518000）广东省深圳市南山区南山大道1110号中国石油大厦。Email：xiongb69@petrochina.com.cn。
  • 基金资助:
    中石油重大科技攻关项目“干热岩资源勘探开发关键技术研究”（编号：2022DJ5503）资助。

Heat transfer prediction of medium and deep coaxial casing based on BP algorithm

XIONG Bo, ZHU Dongxue, FANG Chaohe, WANG Shejiao, DU Guanglin, XUE Yafei, MO Shaoyuan, XIN Fudong   

  1. PetroChina Shenzhen New Energy Research Institute Company, Shenzhen 518000, Guangdong, China
  • Received:2023-08-24 Revised:2023-10-09 Published:2024-03-06

PDF (PC)

127

摘要： 通过搭建热泵测试试验台，进行多工况试验获取试验数据来建立BP神经网络同轴套管换热量预测模型，并进行仿真模拟，对同轴套管换热量进行预测。结果表明：①热泵系统在水流量28 m3/h、回水温度10℃的工况下稳定运行能效最高，同轴套管有效换热量为563kW。②隐含层节点数为12时，BP神经网络预测模型最优，训练最大均方误差MSE为0.023%，最优模型基本结构为9-12-1。③对比同轴套管换热量预测值与检验值仿真结果，BP神经网络同轴套管换热量预测平均百分比误差MAPE为0.235%，预测准确率为99.765%。该预测模型具有较高的精度和可靠性，能够准确预测同轴套管换热量的变化趋势，对于提高热泵系统的能效和性能具有广泛的应用价值。

关键词: BP神经网络, 中深层同轴套管, 热泵, 仿真模拟, 换热量预测

Abstract: By building a heat pump test bench and obtaining test data under multiple working conditions，a BP neural network coaxial casing heat transfer prediction model was established，and the simulation was carried out to predict the heat transfer of the coaxial casing. The results show that：（1）The heat pump system has the highest energy efficiency during stable operation at a water flow rate of 28 m3/h and a return water temperature of 10 °C， and the effective heat transfer of coaxial casing is 563 kW.（2）When the number of hidden layer nodes is 12，the BP neural network prediction model is optimal，with a maximum training mean square error（MSE）is 0.023%， and the basic structure of the optimal model is 9-12-1.（3）Comparing the simulation results of the predicted value and the test value of the coaxial casing，the average percentage error of the prediction of heat transfer of the coaxial casing of the BP neural network is 0.235%，and the prediction accuracy is 99.765%. The prediction model has high accuracy and reliability，and can accurately predict the change trend of heat transfer of coaxial casing，which has a wide range of application value for improving the energy efficiency and performance of heat pump systems.

Key words: BP neural network, medium and deep coaxial casing, heat pumps, simulation, heat transfer prediction

中图分类号: 

  • TE09
[1] FANG L,DIAO N R,SHAO Z K,et al. A computationally efficient numerical model for heat transfer simulation of deep borehole heat exchangers[J]. Energy and Buildings,2018,167:79-88.
[2] SPITTLER N,SHAFIEI E,DAVIDSDOTTIR B,et al. Modelling geothermal resource utilization by incorporating resource dynamics,capacity expansion,and development costs[J]. Energy, 2019,190:116407.
[3] GAO Yuefen,GAO Tingting,LIU Zhao. Study on the heat transfer performance of boiling in vertical buried tube of direct expansion ground source heat pump[J]. Energy Procedia,2019, 158:5494-5503.
[4] DEBASREE R,CHAKRABORTY T,BASU D,et al. Feasibility and performance of ground source heat pump systems for commercial applications in tropical and subtropical climates[J]. Renewable Energy,2020,152:467-483.
[5] LE LOUS M,LARROQUE F,DUPUY A,et al. Thermal performance of a deep borehole heat exchanger:Insights from a synthetic coupled heat and flow model[J]. Geothermics,2015, 57:157-172.
[6] KERME E D,FUNG A S. Transient heat transfer simulation, analysis and thermal performance study of double U-tube borehole heat exchanger based on numerical heat transfer model[J]. Applied Thermal Engineering,2020,173:115189.
[7] KUMAR S,MURUGESAN K. Optimization of geothermal interaction of a double U-tube borehole heat exchanger for space heating and cooling applications using Taguchi method and utility concept[J]. Geothermics,2020,83:101723.
[8] 王科荀,姚海清,赵树旺,等.地埋管换热器传热模拟与优化研究进展[J].区域供热,2022(5):92-105. WANG Kexun,YAO Haiqing,ZHAO Shuwang,et al. Advance in heat transfer simulation and optimization of ground heat exchanger[J]. District Heating,2022(5):92-105.
[9] MORCHIO S,FOSSA M. Thermal modeling of deep borehole heat exchangers for geothermal applications in densely populated urban areas[J]. Thermal Science and Engineering Progress,2019, 13:100363.
[10] LUO Yongqiang,GUO Hongshan,MEGGERS F,et al. Deep coaxial borehole heat exchanger:Analytical modeling and thermal analysis[J]. Energy,2019,185:1298-1313.
[11] CAI Wanlong,WANG Fenghao,LIU Jun,et al. Experimental and numerical investigation of heat transfer performance and sustainability of deep borehole heat exchangers coupled with ground source heat pump systems[J]. Applied Thermal Engineering,2019,149:975-986.
[12] HUANG Yibin,ZHANG Yanjun,XIE Yangyang,et al. Thermal performance analysis on the composition attributes of deep coaxial borehole heat exchanger for building heating[J]. Energy and Buildings,2020,221:110019.
[13] SONG Xianzhi,WANG Gaosheng,SHI Yu,et al. Numerical analysis of heat extraction performance of a deep coaxial borehole heat exchanger geothermal system[J]. Energy,2018,164:1298-1310.
[14] WANG Z H,WANG F H,LIU J,et al. Field test and numerical investigation on the heat transfer characteristics and optimal design of the heat exchangers of a deep borehole ground source heat pump system[J]. Energy,2019,155:578-289.
[15] LI Ji,XU Wei,LI Jianfeng,et al. Heat extraction model and characteristics of coaxial deep borehole heat exchanger[J]. Renewable Energy,2021,169:738-751.
[16] 马娟,董娟,刘勇,等.紧邻的双井中深层套管式地埋管换热器换热特性研究[J].可再生能源,2022,40(12):1604-1612. MA Juan,DONG Juan,LIU Yong,et al. Study on heat transfer characteristics of deep casing buried pipe heat exchanger in adjacent double wells[J]. Renewable Energy Resources,2022,40(12):1604-1612.
[17] 徐中波,汪利兵,申春生,等.渤海蓬莱19-3油田新近系明下段曲流河储层构型表征[J].岩性油气藏,2023,35(5):100-107. XU Zhongbo,WANG Libing,SHEN Chunsheng,et al. Architecture characterization of meandering river reservoirs of lower Minghuazhen Formation of Neogene in Penglai 19-3 oilfield, Bohai Sea[J]. Lithologic Reservoirs,2023,35(5):100-107.
[18] 董江涛,杜震宇.基于GA-BP神经网络的土壤-空气换热器换热量预测分析[J].可再生能源,2021,39(3):307-314. DONG Jiangtao,DU Zhenyu. Heat exchange quantity prediction of earth-air heat exchanger based on GA-BP neural network[J]. Renewable Energy Resources,2021,39(3):307-314.
[19] 杨建,杨程博,张岩,等.基于改进神经网络的渗透率预测方法[J].岩性油气藏,2011,23(1):98-102. YANG Jian,YANG Chengbo,ZHANG Yan,et al. Permeability prediction method based on improved BP neural network[J]. Lithologic Reservoirs,2011,23(1):98-102.
[20] 陈尚沅,茅靳丰,韩旭.基于神经网络的垂直地埋管换热量预测[J].太阳能学报,2017,38(11):3077-3084. CHEN Shangyuan,MAO Jinfeng,HAN Xu. Thermal prediction of a vertical ground heat exchanger using artificial neural networks[J]. Acta Energiae Solaris Sinica,2017,38(11):3077-3084.
[21] 王晓光.自适应BP神经网络在横波速度预测中的应用[J].岩性油气藏,2013,25(5):86-88. WANG Xiaoguang. Application of self-adaptive BP neural network to the prediction of shear wave velocity[J]. Lithologic Reservoirs,2013,25(5):86-88
[22] 朱冬雪,鹿世化,张帆,等. BP算法预测控制在供热系统中的节能应用[J].建筑热能通风空调,2020,39(4):50-52. ZHU Dongxue,LU Shihua,ZHANG Fan,et al. Energy-saving application of BP algorithm predictive control in heating system[J]. Building Energy & Environment,2020,39(4):50-52.
[23] 韩长城,林承焰,马存飞.地震多属性优选技术在碳酸盐岩缝洞型储层预测中的应用[J].岩性油气藏,2013,25(6):67-70. HAN Changcheng,LIN Chengyan,MA Cunfei. Application of seismic multi-attribute optimization technique to the prediction of carbonate fractured-vuggy reservoir[J]. Lithologic Reservoirs, 2013,25(6):67-70.
[24] 朱冬雪.基于BP神经网络的集中供热系统二次管网节能控制研究[D].南京:南京师范大学,2020. ZHU Dongxue. District heating system based on BP neural network is the secondary pipe network energy saving control research[D]. Nanjing:Nanjing Normal University,2020.
[25] 何婧涵. 基于优化BP神经网络的短期热负荷预测研究[D]. 天津:天津大学,2022. HE Jinghan. Based on optimized BP neural networkshort-term thermal load forecasting[D]. Tianjin:Tianjin University,2022.
[26] 蒋德鑫,姜正龙,张贺,等.烃源岩总有机碳含量测井预测模型探讨:以陆丰凹陷文昌组为例[J]. 岩性油气藏,2019,31(6):109-117. JIANG Dexin,JIANG Zhenglong,ZHANG He,et al. Well logging prediction models of TOC content in source rocks:A case of Wenchang Formation in Lufeng Sag[J]. Lithologic Reservoirs,2019,31(6):109-117.
[27] GU Jihao,WANG Jin,QI Chengying,et al. Medium-term heat load prediction for an existing residential building based on a wireless on-off control system[J]. Energy,2018,152:709-718.
[28] 熊镭,张超谟,张冲,等. A地区页岩气储层总有机碳含量测井评价方法研究[J].岩性油气藏,2014,26(3):74-78. XIONG Lei,ZHANG Chaomo,ZHANG Chong,et al. Research on logging evaluation method of TOC content of shale gas reservoir in A area[J]. Lithologic Reservoirs,2014,26(3):74-78.
[29] XUE Puning,JIANG Yi,ZHOU Zhigang,et al. Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms[J]. Energy,2019,188:1-15.
[30] 杨占伟,姜振学,梁志凯,等.基于2种机器学习方法的页岩TOC含量评价:以川南五峰组-龙马溪组为例[J].岩性油气藏,2022,34(1):130-138. YANG Zhanwei,JIANG Zhenxue,LIANG Zhikai,et al. Evaluation of shale TOC content based on two machine learning methods:A case study of Wufeng-Longmaxi Formation in southern Sichuan Basin[J]. Lithologic Reservoirs,2002,34(1):130-138.
[31] 石惠娴,孟祥真,游煜成,等.植物工厂地源热泵系统热负荷BP神经网络预测及验证[J]. 农业工程学报,2019,35(2):196-202. SHI Huixian,MENG Xiangzhen,YOU Yucheng,et al. Prediction and verification of heating load of ground source heat pump heating system based on BP neural network for plant factory[J]. Transactions of the Chinese Society of Agricultural Engineering,2019,35(2):196-202.
[32] 刘跃杰,刘书强,马强,等. BP神经网络法在三塘湖盆地芦草沟组页岩岩相识别中的应用[J]. 岩性油气藏,2019,31(4):101-111. LIU Yuejie,LIU Shuqiang,MA Qiang,et al. Application of BP neutral network method to identification of shale lithofacies of Lucaogou Formation in Santanghu Basin[J]. Lithologic Reservoirs,2019,31(4):101-111.
[1] 杨占伟, 姜振学, 梁志凯, 吴伟, 王军霞, 宫厚健, 李维邦, 苏展飞, 郝绵柱. 基于2种机器学习方法的页岩TOC含量评价——以川南五峰组—龙马溪组为例[J]. 岩性油气藏, 2022, 34(1): 130-138.
[2] 李紫晗, 何玉发, 张滨海, 钟海全. 深水气井测试温压场耦合模型求解及实现[J]. 岩性油气藏, 2020, 32(4): 163-171.
[3] 蒋德鑫, 姜正龙, 张贺, 杨舒越. 烃源岩总有机碳含量测井预测模型探讨——以陆丰凹陷文昌组为例[J]. 岩性油气藏, 2019, 31(6): 109-117.
[4] 刘跃杰, 刘书强, 马强, 姚宗森, 佘家朝. BP神经网络法在三塘湖盆地芦草沟组页岩岩相识别中的应用[J]. 岩性油气藏, 2019, 31(4): 101-111.
[5] 陈可洋. 高精度地震纯波震源数值模拟[J]. 岩性油气藏, 2012, 24(1): 84-91.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!

陇ICP备17006252号
版权所有© 2018 中国石油集团西北地质研究所有限公司《岩性油气藏》编辑部

地址：甘肃省兰州市城关区雁儿湾路535号(陇ICP备17006252号)    电话：0931-8686158;8686058;8686288    邮箱：yxyqc@petrochina.com.cn

甘公网安备 62010202002827号

本系统由北京玛格泰克科技发展有限公司设计开发