基于SSA-BP的铁路沿线风速预测方法  

A Method for Predicting Wind Speed Along Railway Lines Based on SSA-BP

作　　者：张俱珲 孟建军[1,2,3] 李德仓 陈晓强 ZHANG Ju-hui;MENG Jian-jun;LI De-cang;CHEN Xiao-qiang(Mechatronics T&R Institute,Lanzhou Jiaotong University,Lanzhou Gansu 730070,China;Gansu Provincial Engineering Technology Center for Informatization of Logistics&Transport Equipment,Lanzhou Gansu 730070,China;Gansu Provincial Industry Technology Center of Logistics&Transport Equipment,Lanzhou Gansu 730070,China)

机构地区：[1]兰州交通大学机电技术研究所,甘肃兰州730070 [2]甘肃省物流及运输装备信息化工程技术研究中心,甘肃兰州730070 [3]甘肃省物流与运输装备行业技术中心,甘肃兰州730070

出　　处：《计算机仿真》2023年第12期209-212,260,共5页Computer Simulation

基　　金：国家自然科学基金(72061021,62063013);兰州交通大学青年基金(2021018);甘肃省科技计划项目(20JR10RA251,21JR7RA284)。

摘　　要：精确的铁路沿线风速预测对提升列车运行控制和调度智能化水平起着关键作用。提出在BP神经网络的基础上采用麻雀搜索算法(SSA)对其进行优化,构建SSA-BPNN模型,新的模型优化了BP神经网络的阈值和权值,将SSA-BPNN模型与GA-BPNN模型的预测值进行对比。结果表明,两种模型均可对铁路沿线时间序列的风速进行预测,但SSA-BP算法的预测精度更高,预测性能更加良好,RMSE从1.3743减小到0.7803,R2则从0.8901增大到0.9363。Accurate wind speed prediction along railway lines is of significant importance in improving train oper⁃ation control and level of intelligent dispatching.In the paper,a Sparrow Search Algorithm(SSA)was used to optimize the BP neural net-work and a SSA-BPNN model was constructed.The new model optimized the thresholds and weights of the BP neural network.The predicted values of the SSA-BPNN model were compared with ones of the GA-BPNN model.The results show that both GA-BPNN and SSA-BPNN can predict wind speed along railway in time series,but the prediction accuracy of SSA-BP algorithm is higher and the predictive performance is better,RMSE decreases from 1.3743 to 0.7803,R2 increases from 0.8901 to 0.9363.

关 键 词：铁路 风速预测 神经网络 麻雀搜索算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]