Prediction of Outbound Transportation Volume of Xinjiang Coal Railway by Integrating Sparrow Search with Long Short-Term Memory

doi:10.16097/j.cnki.1009-6744.2024.05.002

Abstract

Abstract: To enhance the precision of predicting the Xinjiang's coal railway outbound volume transportation, a prediction model integrating the sparrow search algorithm and the long and short-term memory network (SSA-LSTM) is proposed. The model introduces the sparrow search algorithm to optimize the hyper-parameters of the LSTM model in order to improve the model prediction performance. Based on the data of Xinjiang coal rail outbound transportation volume from 2015 to 2022, the gray correlation analysis is employed to comprehensively evaluate the impact of factors, including economic and transportation aspects, ensuring that the selected factors exhibit a strong correlation with the prediction targets. Among the influencing factors, the GDP data is adjusted for Consumer Price Index (CPI) effects, and the refined data are then fed into the model for prediction. Finally, the model is applied to predict the Xinjiang's coal rail outbound transportation volume across short, medium, and long time horizons. The results demonstrate that the SSA-LSTM model outperforms both the BP neural network and the conventional LSTM model, achieving a Mean Absolute Percentage Error (MAPE) of 0.88% and a Root Mean Square Error (RMSE) of 49.9. Furthermore, incorporating CPI processing into the prediction process significantly reduces the prediction error, with MAPE and RMSE decreasing by 75.8% and 56.2%, respectively, compared to non-CPI-processed predictions. This study provides an effective approach for predicting Xinjiang's coal rail outbound transportation volume, offering important data insights that inform the strategic design of coal transportation routes out of Xinjiang.

Key words: railway transportation, outbound transportation volume of Xinjiang coal railway, SSA-LSTM model, grey correlation analysis, forecasting

摘要： 为准确预测新疆煤炭铁路外运量，本文提出一种融合麻雀搜索算法与长短时记忆网络的(SSA-LSTM)预测模型，模型引入麻雀搜索算法对长短时记忆网络(Long Short-Term Memory,LSTM)模型的超参数进行优化，以提高模型预测性能。以2015—2022年新疆煤炭铁路外运量数据为基础，综合考虑经济、运输等多种因素，对各影响因素的灰色关联度进行计算，验证所选因素与预测指标具有较强的关联度。对影响因素中的GDP数据进行消费者价格指数(Consumer PriceIndex, CPI)处理，并将处理后的数据输入模型进行预测，最后应用该模型对未来新疆煤炭初、近、远期铁路外运量进行预测。研究结果表明，SSA-LSTM 模型的预测效果显著优于 BP(BackPropagation)神经网络和传统 LSTM 模型，平均绝对百分比误差(MAPE)为 0.88%，均方根误差(RMSE)为 49.9。同时，与未经 CPI 处理的预测相比，经过 CPI 处理后预测误差更小，MAPE 和RMSE分别降低了75.8%和56.2%。本文为新疆煤炭铁路外运量预测提供了一种有效方法，为疆煤外运通道设计提供了重要数据支撑。

关键词: 铁路运输, 疆煤铁路外运量, SSA-LSTM模型, 灰色关联分析, 预测

CLC Number:

U294.1+3

LI Haijun, ZHANG Xiaoyang , GAO Ruhu , WEI Dehua, CHEN Xiaoming. Prediction of Outbound Transportation Volume of Xinjiang Coal Railway by Integrating Sparrow Search with Long Short-Term Memory[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(5): 14-23.

李海军, 张晓洋, 高如虎, 魏德华, 陈晓明. 融合麻雀搜索与长短时记忆的疆煤铁路外运量预测[J]. 交通运输系统工程与信息, 2024, 24(5): 14-23.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/10.16097/j.cnki.1009-6744.2024.05.002

http://www.tseit.org.cn/EN/Y2024/V24/I5/14

References

[1] YANG F, TANG X Y, GAN Y X, et al. Forecast of freight volume in Xi'an based on gray GM (1, 1) model and Markov forecasting model[J]. Journal of Mathematics, 2021, 2021(1): 1-6.

[2] 梁宁, 耿立艳, 张占福, 等. 基于GRA与SVM-mixed的货运量预测方法[J]. 交通运输系统工程与信息, 2016, 16(6): 94-99. [LIANG N, GENG L Y, ZHANG Z F, et al. A prediction method of railway freight volumes using GRA and SVM-mixed[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(6): 94-99.]

[3] 耿立艳, 张天伟, 赵鹏. 基于灰色关联分析的LS-SVM铁路货运量预测 [J]. 铁道学报, 2012, 34(3): 1- 6. [GENG L Y, ZHANG T W, ZHAO P. Forecast of railway freight volumes based on LS-SVM with Grey correlation analysis[J]. Journal of the China Railway Society, 2012, 34(3): 1-6.]

[4] 耿立艳, 梁毅刚. 基于灰色自适应粒子群LSSVM的铁路货运量预测[J]. 西南交通大学学报, 2012, 47(1): 144-150. [GENG L Y, LIANG Y G. Prediction of railway freight volumes based on Grey adaptive particle swarm least squares support vector machine model[J]. Journal of Southwest Jiaotong University, 2012, 47(1): 144-150.]

[5] HUANG L J, XIE G J, ZHAO W D, et al. Regional logistics demand forecasting: A BP neural network approach[J]. Complex & Intelligent Systems, 2023, 9(3): 2297-2312.

[6] LIU C G, ZHANG J Q, LUO X X, et al. Railway freight demand forecasting based on multiple factors: Grey relational analysis and deep autoencoder neural networks [J]. Sustainability, 2023, 15(12): 9652.

[7] 程肇兰, 张小强, 梁越. 基于LSTM网络的铁路货运量预测[J]. 铁道学报, 2020, 42(11): 15-21. [CHENG Z L, ZHANG X Q, LIANG Y. Railway freight volume prediction based on LSTM network[J]. Journal of the China Railway Society, 2020, 42(11): 15-21.]

[8] 谭雪, 张小强. 基于GRU深度网络的铁路短期货运量预测 [J]. 铁道学报, 2020, 42(12): 28- 35. [TAN X, ZHANG X Q. GRU deep neural network based shortterm railway freight demand forecasting[J]. Journal of the China Railway Society, 2020, 42(12): 28-35.]

[9] YU N, XU W, YU K L. Research on regional logistics demand forecast based on improved support vector machine: A case study of Qingdao city under the New Free Trade Zone Strategy[J]. IEEE Access, 2020, 8: 9551-9564.

[10] 张英贵, 杨蕙瑜, 雷定猷. 基于组合输入ES-GA-BP的中欧班列货运量预测[J]. 深圳大学学报(理工版), 2022, 39(2): 168-176. [ZHANG Y G, YANG H Y, LEI DY. Freight volume forecast of China railway express based on ES-GA-BP with combined input[J]. Journal of Shenzhen University Science and Engineering, 2022, 39 (2): 168-176.]

[11] ZHOU C, TAO J C. Adaptive combination forecasting model for China's logistics freight volume based on an improved PSO-BP neural network[J]. Kybernetes, 2015, 44(4): 646-666.

[12] 贺政纲, 黄娟. 基于FPSO灰色Verhulst模型的铁路货运量预测[J]. 铁道学报, 2018, 40(8): 1- 8. [HE Z G, HUANG J. Prediction of railway freight volumes based on FPSO grey Verhulst model[J]. Journal of the China Railway Society, 2018, 40(8): 1-8.]

[13] XUE J K, SHEN B. A novel swarm intelligence optimization approach: Sparrow search algorithm[J].Systems Science & Control Engineering, 2020, 8(1): 22-34.

[14] 钟红, 李宏瑾, 苏乃芳. 通货紧缩的定义、度量及对当前经济形势的判断[J]. 国际金融研究, 2015(7): 33-43. [ZHONG H, LI H J, SU N F. Definition and measurement of deflation and the status Quo in China[J]. Studies of International Finance, 2015(7): 33-43.]

[15] 周程, 李松. 基于多重“分解—集成”策略的物流货运量预测[J]. 交通运输系统工程与信息, 2015, 15 (1): 150-158. [ZHOU C, LI S. Logistics freight volume forecasting based on multilevel decompose-ensemble method[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(1): 150-158.]