BP Neural Network Based Optimization for China Railway Freight Transport Network

Abstract:

In order to optimize the railway freight transport network, integrate the limited transport resources and overcome the current problems existing in the traditional transport organization, in this study, we propose a three-layer railway freight transport network system, analyze its hierarchical structure and describe the respective function orientation of the railway freight stations in different layers. Then we design a BP neural network model with adaptive learning algorithm and momentum BP algorithm to classify the railway freight stations into three layers. Finally, an empirical case study is presented to test the feasibility of the BP neural network. The simulation result indicates that the BP neural network model can classify the railway freight stations into three layers under relatively high training accuracy.

• Periodical: Advanced Materials Research (Volume 1037)
• Pages: 404-410
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1037.404
• Online since: October 2014
• Authors: Yan Sun*, Mao Xiang Lang, Dan Zhu Wang
• Keywords: Bp Neural Network Model, Optimization, Railway Freight Transport, Three-Layer Railway Freight Transport Network System

References

[1] L.L. Wang, X.C. Zhang, T. Hai, Weighted cluster analysis on macroscopic distribution areas of railway dangerous goods stations, J. China Railw. Soc. 29 (2007) 101-105.

[2] Y. Zhao, Y. Pu, C.Z. Yi, Optimizing railway logistics structure by fuzzy mathematical theory and analytic hierarchy process, China Railw. Sci. 26 (2005) 119-123.

[3] M.X. Lang, M. Zhong, D.Z. Wang, Study on the closing of private railway sidings by using fuzzy comprehensive evaluation method, Chinese J. Manage. Sci. 10 (2002) 107-110.

[4] D.Z. Wang, X.F. Li, M.X. Lang, Application of fuzzy comprehensive evaluation on optimization and integration of railway special lines, Railw. Transport Econ. 33 (2010) 22-26.

[5] R. Wei, Study on the adjusting method for the layout of railway freight stations, Master Thesis, Beijing Jiaotong University, Beijing, (2007).

[6] H. Azami, M.R. Mosavi, S. Sanei, Classification of GPS satellites using improved back propagation training algorithms, Wireless Pers. Commun. 71 (2013) 789-803.

DOI: 10.1007/s11277-012-0844-7

[7] N. Lin, W.N. Yang, B. Wang, Hyperspectral image classification on KMNF and BP neural network, Comput. Eng. Des. 34 (2013) 2774-2777.

[8] G.S. Wang, An improved BP neural network algorithm and it's application in customer classification, Int. J. Appl. Math. Stat. 46 (2013) 111-118.

[9] Q. Li, Z. Pei, X. Zhou, The research of radio signal classification based on improved BP neural network, ICIC Express Lett. Part B Appl. 3 (2012) 1547-1555.

[10] C.R. Wu, H.X. Huang, Evaluation and research on sports psychology based on BP neural network model, Adv. Inf. Sci. Serv. Sci. 4 (2012) 355-363.

[11] I. Tsuda, Dynamic link of memory-chaotic memory map in nonequilibrium neural networks, Neural Networks 5 (1992) 313-326.

DOI: 10.1016/s0893-6080(05)80029-2

[12] W.W. Sun, Q.S. Liu, Joint-optimization algorithm of BP neural network, Comput. Eng. Appl. 45 (2009) 50-51, 54.

[13] Z. Wang, Y.H. Hui, L.M. Jia, P. Li, The application of improved BP neural network in the prediction of railway passenger volume time serial, China Railw. Sci. 26 (2005) 127-131.