基于动态客流量模型的地铁车站空调负荷预测
CSTR:
作者:
作者单位:

1.同济大学 机械与能源工程学院,上海 201804;2.同济大学 工程结构性能演化与控制教育部重点实验室,上海 200092;3.广州地铁设计研究院股份有限公司 节能和环保技术中心,广东 广州 510010

作者简介:

苏醒(1982—),男,副教授,博士生导师,工学博士,主要研究方向为低能耗除湿技术.E-mail: suxing@tongji.edu.cn

中图分类号:

TU96

基金项目:

“十三五”国家重点研发计划专项资助(2016YFC0700100)


Cooling Load Prediction for Metro Station Based on Dynamic Passenger Flow Model
Author:
Affiliation:

1.School of Mechanical Engineering, Tongji University, Shanghai 201804, China;2.Key Laboratory of Performance Evolution and Control for Engineering Structures of the Ministry of Education, Tongji University, Shanghai 200092, China;3.Energy Conservation and Environmental Protection Technology Center, Guangzhou Metro Design and Research Institute Co., Ltd., Guangzhou 510010, Guangdong, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为了准确预测地铁车站的空调负荷,首先通过地铁车站能耗监测平台的历史数据分析,识别得到客流量和室外气象参数是主要影响因素。其次利用车站CO2体积浓度逐时监测数据建立客流量神经网络预测模型,并与闸机数据对比,预测模型的复相关系数R2可达0.87。以客流量预测为基础,建立了车站空调负荷预测模型,并比较了不同时间尺度训练数据下误差反向传播神经网络算法和支持向量机算法的预测效果,两种算法的R2达到了0.95以上,均方根误差在70~90 kW之间,预测精度较高,但支持向量机算法的运算时间是误差反向传播神经网络算法的3~4倍左右,推荐数据量较大时优先选择神经网络算法。

    Abstract:

    In order to accurately predict the cooling load of metro stations, firstly, by analyzing the historical data from the metro station monitoring platform, the passenger flow and meteorological parameters are identified as the main influential factors. Then, a dynamic passenger flow neural network prediction model is established, by utilizing the hourly monitored carbon dioxide volume concentration data in the metro station, A comparion of the carbon dioxide data with the automatic fare collection data indicates that the correlation coefficient R2 of the prediction model can reach 0.87. After that, based on passenger flow prediction, the cooling load predicting model of the metro station is built. A comparsion of the predicting performance of back propagation neural network and support vector machine algorithm under different time scale training data suggests that the R2 of both models can reached 0.95 or higher, and the root mean square error is between 70 kW and 90 kW, which is of a high prediction accuracy. However, the calculation time of the support vector machine algorithm is about 3 to 4 times that of the back propagation neural network algorithm. The neural network model is recommended when the amount of data is large.

    参考文献
    [1] GUAN B, ZHANG T, LIU X. Performance investigation of outdoor air supply and indoor environment related to energy consumption in two subway stations [J]. Sustainable Cities and Society, 2018, 41: 513.
    [2] SU Z, LI X. Sub-system energy model based on actual operation data for subway stations [J]. Sustainable Cities and Society, 2020, 52: 101835.
    [3] GUAN B, LIU X, ZHANG T, et al. Energy consumption of subway stations in China: Data and influencing factors [J]. Sustainable Cities and Society, 2018, 43: 451.
    [4] CASALS M, GANGOLELLS M, FORCADA N, et al. A breakdown of energy consumption in an underground station[J]. Energy and Buildings, 2014, 78: 89.
    [5] WANG L, LEE W.M. E, YUEN K.K. R. Novel dynamic forecasting model for building cooling loads combining an artificial neural network and an ensemble approach [J]. Applied Energy, 2018, 228: 1740.
    [6] CHEN Z, SUN Y, YANG G, et al. Air conditioning load prediction based on DE-SVM algorithm [C]// Proceedings of the 2010 Third International Symposium on Intelligent Information Technology and Security Informatics. Jinggangshan: IEEE, 2010: 276-279.
    [7] LI Q, MENG Q, CAI J, et al. Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks [J]. Energy Conversion and Management, 2009, 50 (1): 90.
    [8] 樊佳慧. 基于乘客在站停留时间估计的地铁环控系统负荷计算研究[D]. 北京:北京交通大学交通运输学院,2018.
    [9] 李婷婷,毕海权,王宏林,等. 基于BP神经网络的地铁站厅空调负荷预测[J]. 计算机科学,2019, 46 (11): 590.
    [10] 付亮. 地铁车站中央空调系统负荷预测与节能优化[D]. 西安:西安建筑科技大学, 2019.
    [11] 梁园. 地铁换乘站公共区空调计算人员的研究[J]. 制冷与空调, 2013, 27 (2) : 158.
    [12] 何磊. 辐射末端复合空调系统监督控制方法研究[D]. 成都:西南交通大学,2016.
    [13] VAPNIK V N. The nature of statistical learning theory[M]. New York: Springer, 1995.
    [14] NANYE L, DANIEL G, GUILHERME J, et al. Application of support vector regression to genome-assisted prediction of quantitative traits[J]. Theoretical and Applied Genetics, 2011, 123 (7): 1065.
    [15] 周璇,刘庆典,闫军威. 基于小波分解和支持向量机的办公建筑空调负荷预测[J]. 暖通空调, 2016, 46 (5): 114.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

苏醒,王磊,田少宸,秦旭.基于动态客流量模型的地铁车站空调负荷预测[J].同济大学学报(自然科学版),2022,50(1):114~120

复制
分享
文章指标
  • 点击次数:292
  • 下载次数: 940
  • HTML阅读次数: 146
  • 引用次数: 0
历史
  • 收稿日期:2021-02-23
  • 在线发布日期: 2022-02-17
文章二维码