[1]杨 飞,王洋.基于改进自然选择粒子群算法的铁路客运量组合预测研究[J].高速铁路技术,2022,13(06):63-68,73.[doi:10.12098/j.issn.1674-8247.2022.06.012 ]
 YANG Fei,WANG Yang.Study on Combination Forecast of Railway Passenger Volume by Improved Particle Swarm Optimization Algorithm Based on Natural Selection[J].HIGH SPEED RAILWAY TECHNOLOGY,2022,13(06):63-68,73.[doi:10.12098/j.issn.1674-8247.2022.06.012 ]
点击复制

基于改进自然选择粒子群算法的铁路客运量组合预测研究()
分享到:

《高速铁路技术》[ISSN:1674-8247/CN:51-1730/U]

卷:
13卷
期数:
2022年06期
页码:
63-68,73
栏目:
研究创新
出版日期:
2022-12-20

文章信息/Info

Title:
Study on Combination Forecast of Railway Passenger Volume by Improved Particle Swarm Optimization Algorithm Based on Natural Selection
文章编号:
1674—8247 (2022) 06—0063—06
作者:
杨 飞王洋
中铁工程设计咨询集团有限公司, 北京100055
Author(s):
YANG FeiWANG Yang
China Railway Engineering Design Consulting Group Co. ,Ltd. ,Beijing 100055 ,China
关键词:
自然选择理论 粒子群算法 铁路客运量 组合预测 权重
Keywords:
natural selection theoryparticle swarm optimization algorithmrailway passenger volumecombination forecastweight
分类号:
U293.13
DOI:
10.12098/j.issn.1674-8247.2022.06.012
文献标志码:
A
摘要:
为提高铁路客运量的预测精度,引入基于自然选择的粒子群算法以解决铁路客运量组合预测模型权重分配问题,借助对数函数和正弦函数非线性变化的特点对基于自然选择粒子群算法的权重和学习因子进行改进,并结合BP神经网络和ARIMA模型对北京市铁路客运量进行组合预测。研究结果表明:(1)改进基于自然选择的粒子群算法在权重分配过程中展现出更好的寻优能力和收敛速度;(2)相比于BP神经网络和ARIMA模型和等分权重法赋值的组合预测模型,改进基于自然选择的粒子群算法求解权重的组合预测精度更高,预测年度平均预测相对误差分别提高了1.934%、5.009%和1.118%。
Abstract:
In order to improve the forecast accuracy of railway passenger volume,the particle swarm optimization (PSO)algorithm based on natural selection is introduced to solve the weight allocation problem of combination forecast model for railway passenger volume. The author carried out the combination forecast of railway passenger volume in Beijing by improving the weight and learning factors of PSO algorithm based on natural selection according to the characteristics of nonlinear variation of logarithmic function and sinusoidal function,and in combination with the BP Neural Network and ARIMA model. The results show that:(1)The improved PSO algorithm based on natural selection shows better optimization ability and convergence speed in the process of weight allocation.(2)Compared with the "BP Neural Network + ARIMA model + value assignment by equal weight method" combination forecast model,the combination forecast by solving the weight by the improved PSO algorithm based on natural selection has a higher accuracy. The average relative forecast errors in three forecast years are increased by 1.934%,5.009% and 1.118%respectively.

参考文献/References:

[1] 游文倩,庄科俊. 基于组合预测模型对安徽省GDP的预测研究[J]. 黑龙江工业学院学报(综合版),2020,20(4): 103 - 107. YOU Wenqian,ZHUANG Kejun. Prediction of GDP in Anhui Province Based on Combination Forecasting Model[J]. Journal of Heilongjiang University of Technology (Comprehensive Edition), 2020,20(4): 103 - 107.
[2] 刘春红,杨亮,邓河,等. 基于ARIMA和BP神经网络的猪舍氨气浓度预测[J]. 中国环境科学,2019,39(6): 2320 - 2327. LIU Chunhong,YANG Liang,DENG He,et al. Prediction of Ammonia Concentration in Piggery Based on ARIMA and BP Neural Network[J]. China Environmental Science,2019,39(6): 2320 -2327.
[3] 王秀梅. 基于权重分配组合法的农产品冷链物流需求趋势预测[J]. 统计与决策,2018,34(9): 55 - 58. WANG Xiumei. Demand Trend Forecast of Agricultural Cold Chain Logistics Based on Weight Distribution Combination Method[J]. Statistics & Decision,2018,34(9): 55 - 58.
[4] 褚鹏宇,刘澜. 基于变权重组合模型的铁路客运量短期预测[J].计算机工程与应用,2017,53(4): 228 - 232. CHU Pengyu,LIU Lan. Short-Term Forecast of Railway Passenger Traffic Volume Based on Variable Weight Combination Model[J]. Computer Engineering and Applications,2017,53(4): 228 - 232.
[5] 苏丽敏,宋艳红,何慧爽. 考虑权重不确定性的变权重组合预测方法[J]. 统计与决策,2019,35(11): 60 - 63. SU Limin,SONG Yanhong,HE Huishuang. Variable Weight Combination Forecasting Method Considering Weight Uncertainty[J]. Statistics & Decision,2019,35(11): 60 - 63.
[6] 李佩,彭斯俊. 一种新的组合权重在组合预测模型中的应用[J].河南科技大学学报(自然科学版),2018,39(2): 87 - 93. LI Pei,PENG Sijun. Application of New Combination Weight to Combination Forecasting Model[J]. Journal of Henan University of
[7] 周宏,刘钊. 基于时间序列的高速公路短时交通流最优组合预测[J]. 工程与建设,2018,32(6): 812 - 814. ZHOU Hong,LIU Zhao. Optimal Combination Prediction of Short-Time Traffic Flow in Highways Based on Time Series Approaches[J]. Engineering and Construction,2018,32(6): 812 - 814.
[8] 李万,冯芬玲,蒋琦玮. 改进粒子群算法优化LSTM神经网络的铁路客运量预测[J]. 铁道科学与工程学报,2018,15(12):3274 - 3280. LI Wan,FENG Fenling,JIANG Qiwei. Prediction for Railway Passenger Volume Based on Modified PSO Optimized LSTM Neural Network[J]. Journal of Railway Science and Engineering,2018, 15(12): 3274 - 3280.
[9] 吕柏行,郭志光,赵韦皓,等. 标准粒子群算法的优化方式综述[J]. 科学技术创新,2021(28): 33 - 37. LV Bai|xing,GUO Zhiguang,ZHAO Weihao,et al. A Review on Optimization Methods of Standard Particle Swarm Optimization[J]. Scientific and Technological Innovation,2021(28): 33 - 37.
[10]?南敬林. 铁路客运量预测影响因素分析[J]. 综合运输,2016, 38(2): 35 - 40. NAN Jinglin. The Analysis of Influencing Factor about Railway Passenger Forecast[J]. China Transportation Review,2016,38(2):35 - 40.
[11]?徐森. 改进的神经网络及其时序组合模型在铁路客运量上的预测[D]. 兰州: 兰州交通大学,2020. XU Sen. Forecast of Railway Passenger Volume Based on Improved Neural Network and Its Time Series Combination Model[D]. Lanzhou: Lanzhou Jiatong University,2020.
[12]?陶海龙,李小平,张胜召,等. 基于IPSO-BP神经网络的铁路客运量预测[J]. 铁道运输与经济,2011,33(9): 78 - 82. TAO Hailong,LI Xiaoping,ZHANG Shengzhao,et al. Forecast of Railway Passenger Traffic Volume Based on IPSO-BP Neural Network [J]. Railway Transport and Economy,2011,33(9): 78 - 82.
[13]?温正,孙华克. MATLAB智能算法[M]. 北京: 清华大学出版社, 2017. WEN Zheng,SUN Huake. MATLAB Intelligent Algorithm[M]. Beijing: Tsinghua University Press,2017. [LinkOut]
[14]?姜永杰,张书豪,吴光,等. 基于灰色系统及BP神经网络算法的边坡变形预测精确度影响分析[J]. 高速铁路技术,2020,11(5):13 - 19. JIANG Yongjie,ZHANG Shuhao,WU Guang,et al. Influence Analysis of Slope Deformation Prediction Accuracy Based on Grey System and BP Neural Network Algorithm[J]. High Speed Railway Technology,2020,11(5): 13 - 19.

备注/Memo

备注/Memo:
收稿日期:2021-10-12
作者简介:杨飞(1995-),男,助理工程师。
更新日期/Last Update: 2022-12-20