[1]张济辞,秦新,杨珺舒,等.铁路旅客车站基于长短期记忆模型的暖通空调节能控制效能测算[J].高速铁路技术,2025,16(06):133-139.[doi:10.12098/j.issn.1674-8247.2025.06.019]
　ZHANG Jici,QIN Xin,YANG Junshu,et al.Energy-saving Control Efficacy Evaluation of HVAC in Railway Passenger Stations Based on the Long Short-Term Memory Model[J].HIGH SPEED RAILWAY TECHNOLOGY,2025,16(06):133-139.[doi:10.12098/j.issn.1674-8247.2025.06.019]
点击复制

铁路旅客车站基于长短期记忆模型的暖通空调节能控制效能测算()

《高速铁路技术》[ISSN:1674-8247/CN:51-1730/U]

卷:
16卷
期数:
2025年06期
页码:
133-139
栏目:
客运服务
出版日期:
2025-12-30

文章信息/Info

Title:
Energy-saving Control Efficacy Evaluation of HVAC in Railway Passenger Stations Based on the Long Short-Term Memory Model
文章编号:
1674-8247(2025)06-0133-07
作者:
张济辞1; 秦新2; 杨珺舒1; 邓维韬3; 梁栋3
(1.中铁二院工程集团有限责任公司, 成都 610031; 2. 中铁八局集团有限公司, 成都 610000; 3.四川旷谷信息工程有限公司, 成都 610000)
Author(s):
ZHANG Jici1;  QIN Xin2;  YANG Junshu1;  DENG Weitao3;  LIANG Dong3
(1.China Railway Eryuan Engineering Group Co., Ltd., Chengdu 610031, China; 2. China Railway No.8 Engineering Group Co., Ltd., Chengdu 610000, China; 3. Sichuan Crungoo Information Engineering Co., Ltd., Chengdu 610000, China)
关键词:
铁路旅客车站;  暖通设备;  节能策略;  人工智能;  神经网络
Keywords:
railway passenger station;  HVAC equipment;  energy-saving strategy;  artificial intelligence;  neural network
分类号:
U291.1+2
DOI:
10.12098/j.issn.1674-8247.2025.06.019
文献标志码:
A
摘要:
当前,铁路旅客车站的暖通空调系统仍然大量沿用传统“按季空调”“按季供暖”模式,运行模式简单,缺乏弹性调节,且能耗较大。因此,针对铁路旅客车站暖通空调系统控制粗放的问题,研究提出基于长短期记忆模型的暖通空调节能控制系统设计方法,采集铁路站房空调运行数据,并对节能系统的任务场景适应性和节能效果进行了评估测算。研究表明,结果证明长短期记忆模型在铁路旅客车站暖通空调节能控制任务场景中具备良好的适应性,且在空调季理论节能率可达16.4%,供暖季理论节能率可达17.4%。
Abstract:
Currently, the HVAC systems in railway stations still largely adopt traditional “seasonal cooling” and “seasonal heating” modes, which feature simplistic operation, lack flexible regulation, and consume substantial energy. To address the issue of inefficient control in such systems, this paper proposed an energy-saving control system design method based on a Long Short-Term Memory(LSTM)model. Operational data from station HVAC systems were collected, and the adaptability of the energy-saving system to task scenarios as well as its energy-saving effects were evaluated. The results demonstrate that the LSTM model exhibits strong adaptability in energy-saving control tasks for railway station HVAC systems, with a theoretical energy-saving rate of 16.4% during the cooling season and 17.4% during the heating season.

参考文献/References:

[1] 徐亦锦. 基于模型预测的铁路客站空气调节控制策略研究[D]. 武汉: 华中科技大学, 2022.
XU Yijin. Research on Air Conditioning Control Strategy of Railway Passenger Station Based on Model Prediction[D]. Wuhan: Huazhong University of Science and Technology, 2022.
[2] 刘孝先. 大型铁路客运站能耗控制管理的实践与思考[J]. 铁路节能环保与安全卫生, 2018, 8(6): 290-294.
LIU Xiaoxian. Practice and Thinking of Energy Consumption Control Management in Large Railway Passenger Stations[J]. Railway Energy Saving & Environmental Protection & Occupational Safety and Health, 2018, 8(6): 290-294.
[3] 王文强, 赵跟党, 刘正宁, 等. 基于边缘计算的车站空调控制系统应用研究[J/OL]. 铁道科学与工程学报, 2025: 1-11.(2025-04-27). http://kns.cnki.net/KCMS/detail/detail.aspx?filename=CSTD20250425001&dbname=CJFD&dbcode=CJFQ.
WANG Wenqiang, ZHAO Gendang, LIU Zhengning, et al. Research on Application of Station Air Conditioning Control System Based on Edge Computing[J/OL]. Journal of Railway Science and Engineering, 2025: 1-11.(2025-04-27).http://kns.cnki.net/KCMS/detail/detail.aspx?filename=CSTD20250425001&dbname=CJFD&dbcode=CJFQ.
[4] 吴俊霖. 基于解耦模型的铁路客站空气调节前馈反馈复合控制策略研究[D]. 武汉: 华中科技大学, 2022.
WU Junlin. Research on Feedforward Feedback Compound Control Strategy of Railway Passenger Station Air Conditioning Based on Decoupling Model[D]. Wuhan: Huazhong University of Science and Technology, 2022.
[5] 黄子建, 刘媛华. 长短期记忆模型在股票价格趋势预测应用研究[J]. 生产力研究, 2020(1): 36-39.
HUANG Zijian, LIU Yuanhua. Application of Long-short-term Memory Model in Stock Price Trend Prediction[J]. Productivity Research, 2020(1): 36-39.
[6] 李荣宗, 张超群, 杨邵渊. 基于长短期记忆模型的船舶横摇运动预测[J]. 上海船舶运输科学研究所学报, 2025, 48(1): 1-7, 24.
LI Rongzong, ZHANG Chaoqun, YANG Shaoyuan. Ship Roll Motion Prediction Based on Long Short-term Memory Model[J]. Journal of Shanghai Ship and Shipping Research Institute, 2025, 48(1): 1-7, 24.
[7] 李赛, 雷欣怡, 丁芝侠, 等. 基于Adam的分数阶GRU神经网络的轴承故障诊断[J]. 自动化与仪表, 2025, 40(4): 56-60, 66.
LI Sai, LEI Xinyi, DING Zhixia, et al. Bearing Fault Diagnosis Based on Adam Fractional Order GRU Neural Network[J]. Automation & Instrumentation, 2025, 40(4): 56-60, 66.
[8] 张妙妙, 吕佳, 吴剑, 等. 基于正交参数优化LSTM神经网络的SOFC性能预测[J/OL]. 电源学报, 2024: 1-12.(2024-10-14). http://kns.cnki.net/KCMS/detail/detail.aspx?filename=DYXB20241012003&dbname=CJFD&dbcode=CJFQ.
ZHANG Miaomiao, LV Jia, WU Jian, et al. Performance Prediction of SOFC Based on LSTM Neural Network Optimized by Orthogonal Parameters[J/OL]. Journal of Power Supply, 2024: 1-12.(2024-10-14). http://kns.cnki.net/KCMS/detail/detail.aspx?filename=DYXB20241012003&dbname=CJFD&dbcode=CJFQ.
[9] 张俊月, 方豪, 郭士超, 等. 公共建筑供热节能及热源配置分析[J]. 区域供热, 2025(2): 107-113.
ZHANG Junyue, FANG Hao, GUO Shichao, et al. Analysis of Heating Energy Saving and Heat Source Configuration in Public Buildings[J]. District Heating, 2025(2): 107-113.
[10] 王新颖, 刘岚, 陈海群, 等. 基于K均值聚类算法和LSTM神经网络的管道腐蚀阶段预测方法[J]. 腐蚀与防护, 2024, 45(8): 84-89.
WANG Xinying, LIU Lan, CHEN Haiqun, et al. A Pipeline Stage Corrosion Prediction Method Based on K-Means Clustering Algorithm and LSTM Neural Network[J]. Corrosion & Protection, 2024, 45(8): 84-89.
[11] 任伟皓. 校园节能平台监管控制系统的设计[D]. 石家庄: 石家庄铁道大学, 2016.
REN Weihao. Design of a Supervision and Control System for Campus Energy-saving Platforms[D]. Shijiazhuang: Shijiazhuang Tiedao University, 2016.

备注/Memo

备注/Memo:
收稿日期:2025-07-30
作者简介:张济辞(1994-),男,工程师。
基金项目:中国中铁股份有限公司科技研究开发计划课题(2023-重大-07)
更新日期/Last Update: 2025-12-30