It is crucial to accurately predict railway monthly freight volume to make railway transportation plans and improve railway freight competitiveness. This paper puts forward a screening model of monthly freight volume influencing factors based on grey incidence analysis. From the 23 secondary indicators under the three primary indicators of macro-economy, infrastructure construction, and other modes of transportation, 13 indicators are selected as the key indicators affecting the monthly freight volume. After that, the pa-per puts forward the monthly freight volume prediction model based on LSTM and GRU. The model is validated using the monthly data of railway freight volume from 2008 to 2019 obtained from the China National Bureau of statistics. The results state clearly that the mean absolute percentage error of the two neural networks can reach the level of less than 5%. Compared with GRU, LSTM has a better prediction effect on RMSE, MAE, and MAPE. The model proposed in this paper provides a basis for the relevant railway departments to make transportation plans and puts forward new ideas.
Prediction of Railway Monthly Freight Volume Based on Grey Incidence Analysis and RNN
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Chapter : 36 ; 326-334
2022-02-19
9 pages
Article/Chapter (Book)
Electronic Resource
English
Prediction of Railway Monthly Freight Volume Based on Grey Incidence Analysis and RNN
British Library Conference Proceedings | 2022
|Railway Container Key Station Freight Volumes Prediction Based on Grey-Markov Chain Method
British Library Conference Proceedings | 2009
|