After analyzing the influencing factors of railway freight volume, the WD-WNN forecast method of railway freight volume based on grey correlation analysis is proposed, in order to improve the prediction accuracy of regional railway freight volume. The gray correlation analysis method is used to analyze the correlation between the freight volume and its influencing factors, and WNN input variables are selected by the gray correlation. Then the influencing factors original sequence are denoised by WD technology to improve the smoothness of the input variables. Finally, the freight volumes are trained and predicted by the WNN prediction model. The analysis of the freight volume of Qinghai Province in China from 1990 to 2017 shows that the GRA-WD-WNN method has a faster convergence speed and higher prediction accuracy, and the average relative error of the prediction results is only 4.30%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Railway Freight Volume Forecast Based on GRA-WD-WNN


    Contributors:
    Tian, Wan qi (author) / Zhao, Peng (author) / Qiao, Ke (author)


    Publication date :

    2019-09-01


    Size :

    3142451 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Railway freight volume forecast based on Hybird Algorithms

    Tang, Shijie / Zhang, Donglei | IEEE | 2022



    The Application of Combined Forecast Method in Predicting Freight Volume of Railway

    Huang, F. / Shen, Y. / Tao, S. et al. | British Library Conference Proceedings | 2007



    Railway Freight Turnover Forecast Based on the BP Neural Network

    Sun, Jiang ;Wei, Chong | Trans Tech Publications | 2014