计算机与现代化 ›› 2022, Vol. 0 ›› Issue (10): 24-28.

• 人工智能 • 上一篇    下一篇

基于GS-LSTM模型的铁路货运量预测

  

  1. (上海工程技术大学航空运输学院,上海201620)
  • 出版日期:2022-10-20 发布日期:2022-10-21
  • 作者简介:周昌野(1991—),男,黑龙江双鸭山人,硕士研究生,研究方向:机器学习,E-mail: sunday6669@163.com; 通信作者:李程(1980—),男,上海人,副教授,博士,研究方向:企业运营与决策,E-mail: Lcheng8066@126.com。
  • 基金资助:
    国家社会科学基金资助项目(15BJL104)

Prediction of Railway Freight Volume Based on GS-LSTM Model

  1. (School of Air Transportation, Shanghai University of Engineering Science, Shanghai 201620, China)
  • Online:2022-10-20 Published:2022-10-21

摘要: 铁路货运量预测的准确性对铁路运输企业制定营销计划和营销决策来说是必要的,尤其是短期铁路货运量的影响至关重要。为了提高铁路货运量的预测精度,提出一种优化长短期记忆网络(Long-Short Term Memory, LSTM)参数的预测模型——GS-LSTM模型,通过利用网格搜索算法(Grid Search)对LSTM模型训练网络中最主要的参数(批量大小、隐含层神经单元个数和学习率)进行优化。基于2005年1月—2021年7月的铁路货运量月度数据,首先建立BP和LSTM模型对预测结果进行比较,LSTM模型比BP模型的MAPE降低1.55个百分点,然后分别对BP和LSTM模型的网络参数进行优化后再进行比较,优化后的2种模型比基础模型的预测效果均有提高,而且优化后的LSTM模型比BP模型的MAPE又进一步降低0.18个百分点。实验结果显示,优化后的LSTM模型预测效果更佳,泛化能力更好,具有很好的研究和使用价值。

关键词: LSTM模型, 网格搜索算法, BP模型, 铁路货运量, 时间序列预测

Abstract: The accuracy of railway freight volume forecasting is necessary for railway transportation companies to make marketing plans and marketing decisions, especially the impact of short-term railway freight volume is crucial. In order to improve the prediction accuracy of railway freight volume, this paper establishes a predictive model by optimizing the parameters of the long-short term memory network (GS-LSTM) and by using the grid search algorithm to optimize the most important parameters (batch size, number of hidden layer neural units and learning rate) in the LSTM model training network. Based on the monthly railway freight volume data from January 2005 to July 2021, firstly, BP and LSTM models are established to compare the prediction results. The MAPE of the LSTM model is 1.55 percentage points lower than that of the BP model. Then the network parameters of the BP and LSTM models are optimized and compared, the two optimized models have improved prediction effects than the basic model and the optimized LSTM model is further reduced by 0.18 percentage points than the BP model. The experimental results show that the optimized LSTM model has better prediction effect and better generalization ability, and has good research and utilization value. 

Key words: long short-term memory model, grid search algorithm, BP neural network, railway freight volume, time series prediction