高铁动态牵引负荷预测研究  

A Research on Dynamic Traction Load Forecasting for High-speed Railways

作　　者：李宁[1] 蒋玲[1] 潘东旭[1] 李帅 任瑞 LI Ning;JIANG Ling;PAN Dong-xu;LI Shuai;REN Rui(School of Electrical and Automation,Wuhu Institute of Technology,Wuhu,Anhui 241000,China;LCFC(Hefei)Electronics Technology Co.,Ltd,Hefei,Anhui 230000,China)

机构地区：[1]芜湖职业技术学院电气与自动化学院,安徽芜湖241000 [2]合肥联宝信息技术有限公司,安徽合肥230000

出　　处：《河北北方学院学报（自然科学版）》2024年第7期34-41,共8页Journal of Hebei North University:Natural Science Edition

基　　金：2021年安徽省高校科学研究项目(KJ2021A1330);安徽省教育厅高校自然科学重大项目(KJ2021ZD0152);芜湖职业技术学院自然科学研究一般项目(wzyzr202220);芜湖职业技术学院教育教学改革研究项目(2022jyyb05);芜湖职业技术学院技术技能型大师工作室(2022dsgzs02)。

摘　　要：目的探讨提高高铁电力供应系统能效并减少能源浪费的方法。方法根据高铁牵引变电站检测到的负荷数据构建负荷数据库,并结合列车运行信息表对负荷数据进行分类识别,使用BP神经网络技术对负荷数据进行拟合,建立相应类型的负荷预测模型,并进行仿真验证。结果建立的负荷预测模型优度均高于0.95。结论该预测方法能够有效预测高铁在典型日的电力负荷,为合理规划运行方案和提高经济效益提供了理论依据。Objective To explore methods to improve energy efficiency and reduce energy waste in high-speed rail power supply systems.Methods The study first constructs a load database based on load data detected by high-speed rail traction substations,and combines it with train operation information tables for classification and identification of load data.Subsequently,BP neural network technology was used to fit the load data,establish corresponding types of load prediction models,and perform simulation verification.Results The goodness of the established load forecasting models was higher than 0.95.Conclusion This prediction method can effectively predict the electrical load of high-speed rail on typical days,providing a theoretical basis for reasonable planning of operation schemes and improving economic benefits.

关 键 词：高铁牵引负荷 负荷预测 BP神经网络 能效优化 能源管理 

分 类 号：TM714[电气工程—电力系统及自动化]