Maximum Gradient Decision-Making for Railways Based on Convolutional Neural Network
This article has a reply.
VIEW THE REPLYPublication: Journal of Transportation Engineering, Part A: Systems
Volume 145, Issue 11
Abstract
Maximum gradient (MG) decision-making is among the most important in railway alignment design because it greatly affects railway transport capacity, construction costs, and operation costs. However, existing studies mainly focus on optimizing railway alignment for cases with predetermined MG values. Studies on MG decision-making are rare. In this study, a data-driven method is proposed for MG decision-making based on a convolutional neural network (CNN). A total of 246 existing established railway cases are compiled whose total length is nearly 30,000 km. Factors that influence MG decision-making are characterized as a multichannel image. The 246 railway cases are characterized as 246 multichannel images and cropped into 20,170 images. Using the cropped images as the input data, a CNN model is designed to explore the relations among the factors and the MG value in order to make MG decisions. The method’s performance is tested on 36 existing railway cases. The test accuracy is 94.44%, which demonstrates that the proposed method can match experienced human experts in determining MG values for railway cases.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This work was supported by the National Science Foundation China (NSFC) (Grant Nos. 51608543 and 51778640), the Natural Science Foundation of Hunan Province of China (Award No. 2017JJ3382), the Fundamental Research Funds for the Central Universities of Central South University (Grant No. 2017zzts201), the China Railway Eryuan Engineering Group CO. LTD (Award No. 2015-41), the State Key Laboratory of Rail Transit Engineering Informatization (FSDI) (Award No. SKLK18-04), and the China Railway Siyuan Survey and Design Group Co., Ltd. (Award No. 2016D02-1). The authors are very grateful to the China Railway First Survey and Design Institute Group Co., China Railway Eryuan Engineering Group Co., and China Railway Siyuan Survey and Design Group Co. for supporting the authors with many real cases.
References
Bababeik, M., and M. S. Monajjem. 2012. “Optimizing longitudinal alignment in railway with regard to construction and operating costs.” J. Transp. Eng. 138 (11): 1388–1395. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000448.
Cha, Y. J., W. Choi, and O. Büyüköztürk. 2017. “Deep learning-based crack damage detection using convolutional neural networks.” Comput.-Aided Civ. Inf. Eng. 32 (5): 361–378. https://doi.org/10.1111/mice.12263.
Chen, L. 2008. “Scheme alternative of maximum route gradient on Guiyang–Guangzhou railway.” [In Chinese.] J. Railw. Eng. Soc. 25 (8): 18–22.
Chen, X. 2016. “Study on maximum gradient of the railway in the difficult and dangerous mountain based on the integrated optimization method.” [In Chinese.] M.S. dissertation, Dept. of Civil Engineering, Southwest Jiaotong Univ.
Ciresan, D. C., U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber. 2011. “Flexible, high performance convolutional neural networks for image classification.” In Proc., 22nd Int. Joint Conf. on Artificial Intelligence, 1237–1242. Palo Alto, CA: AAAI Press.
Computer Network Information Center, Chinese Academy of Sciences. 2018. “Geospatial data cloud.” Accessed January 19, 2018. https://www.gscloud.cn.
Costa, A. L., M. C. Cunha, P. A. L. F. Coelho, and H. H. Einstein. 2013. “Solving high-speed rail planning with the simulated annealing algorithm.” J. Transp. Eng. 139 (6): 635–642. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000542.
Costa, A. L., M. C. Cunha, P. A. L. F. Coelho, and H. H. Einstein. 2016. “Decision support systems for real-world high-speed rail planning.” J. Transp. Eng. 142 (5): 04016015. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000837.
De Smith, M. 2006. “Determination of gradient and curvature constrained optimal paths.” Comput.-Aided Civ. Inf. Eng. 21 (1): 24–38. https://doi.org/10.1111/j.1467-8667.2005.00414.x.
Dorj, U. O., K. K. Lee, J. Y. Choi, and M. Lee. 2018. “The skin cancer classification using deep convolutional neural network.” Multimedia Tools Appl. 77 (8): 9909–9924. https://doi.org/10.1007/s11042-018-5714-1.
Espíndola, R. P., and N. F. F. Ebecken. 2005. “On extending f-measure and g-mean metrics to multi-class problems.” WIT Trans. Inf. Commun. Technol. 35: 25–34. https://doi.org/10.2495/DATA050031.
Goodfellow, I., Y. Bengio, and A. Courville. 2016. Deep learning. Cambridge, MA: MIT Press.
Kim, E., M. K. Jha, P. Schonfeld, and H. S. Kim. 2007. “Highway alignment optimization incorporating bridges and tunnels.” J. Transp. Eng. 133(2): 71–81. https://doi.org/10.1061/(ASCE)0733-947X(2007)133:2(71).
Kim, M., P. Schonfeld, and E. Kim. 2013. “Comparison of vertical alignments for rail transit.” J. Transp. Eng. 139 (2): 230–238. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000476.
Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2012. “Imagenet classification with deep convolutional neural networks.” In Proc., 25th Int. Conf. on Neural Information Processing Systems, 1097–1105. San Diego: Neural Information Processing Systems Foundation.
Li, W., H. Pu, P. Schonfeld, J. Yang, H. Zhang, L. Wang, and J. Xiong. 2017. “Mountain railway alignment optimization with bidirectional distance transform and genetic algorithm.” Comput.-Aided Civ. Infrastruct. Eng. 32 (8): 691–709. https://doi.org/10.1111/mice.12280.
Li, W., H. Pu, P. Schonfeld, H. Zhang, and X. Zheng. 2016. “Methodology for optimizing constrained 3-dimensional railway alignments in mountainous terrain.” Transp. Res. Part C. 68 (Jul): 549–565. https://doi.org/10.1016/j.trc.2016.05.010.
Ma, W., and L. Mi. 1998. “The formulation of railway maximum gradient standard.” [In Chinese.] Railw. Stand Des. 4: 22–23.
Mao, W., W. Wang, Z. Dou, and Y. Li. 2018. “Fire recognition based on multi-channel convolutional neural network.” Fire Technol. 54 (2): 531–554. https://doi.org/10.1007/s10694-017-0695-6.
Miao, M. 2011. “Research of selection of maximum gradient for Datong–Xi’an passenger dedicated railway.” [In Chinese.] J. Railw. Eng. Soc. 28 (2): 56–60.
Miki, Y., C. Muramatsu, T. Hayashi, X. R. Zhou, T. Hara, A. Katsumata, and H. Fujita. 2017. “Classification of teeth in cone-beam CT using deep convolutional neural network.” Comput. Biol. Med. 80 (Jan): 24–29. https://doi.org/10.1016/j.compbiomed.2016.11.003.
Nair, V., and G. E. Hinton. 2010. “Rectified linear units improve restricted boltzmann machines.” In Proc., 27th Int. Conf. on Machine Learning (ICML-10), 807–814. Princeton, NJ: International Machine Learning Society.
National Railway Administration of the People’s Republic of China. 2017. Code for design of railway line. [In Chinese.] Beijing: China Railway Publishing House.
Praticò, F. G., and M. Giunta. 2018. “Proposal of a key performance indicator for railway track based on LCC and RAMS analyses.” J. Constr. Eng. Manage. 144 (2): 04017104. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001422.
Pu, H., H. Zhang, W. Li, J. Xiong, J. Hu, and J. Wang. 2018. “Concurrent optimization of mountain railway alignment and station locations using a distance transform algorithm.” Comput. Ind. Eng. 127 (Jan): 1297–1314. https://doi.org/10.1007/s11042-018-5714-1.
Rumelhart, D. E., G. E. Hinton, and R. J. Williams. 1986. “Learning representations by back-propagating errors.” Nature 323 (6088): 533–536. https://doi.org/10.1038/323533a0.
Sadeghi, J. 2010. “Development of railway track geometry indexes based on statistical distribution of geometry data.” J. Transp. Eng. 136 (8): 693–700. https://doi.org/10.1061/(ASCE)0733-947X(2010)136:8(693).
Sadeghi, J., and H. Askarinejad. 2009. “An investigation into the effects of track structural conditions on railway track geometry deviations.” Proc. Inst. Mech. Eng. Part F: J. Rail Rapid Transit. 223 (4); 415–425. https://doi.org/10.1243/09544097JRRT266.
Sadeghi, J., and H. Askarinejad. 2012. “Application of neural networks in evaluation of railway track quality condition.” J. Mech. Sci. Technol. 26 (1): 113–122. https://doi.org/10.1007/s12206-011-1016-5.
Sadeghi, J., H. Heydari, and E. A. Doloei. 2017. “Improvement of railway maintenance approach by developing a new railway condition index.” J. Transp. Eng. Part A: Systems 143 (8): 04017037. https://doi.org/10.1061/JTEPBS.0000063.
Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. “Dropout: A simple way to prevent neural networks from overfitting.” J. Mach. Learn. Res. 15 (1): 1929–1958.
Wang, D. 1984. “Railway engineering design principle and synthetic optimization.” [In Chinese.] J. Southwest Jiaotong Univ. 3: 1–8.
Yan, L. C., B. Yoshua, and H. Geoffrey. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Yoon, B., and H. Chang. 2014. “Potentialities of data-driven nonparametric regression in urban signalized traffic flow forecasting.” J. Transp. Eng. 140 (7): 04014027. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000662.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 145 • Issue 11 • November 2019
Copyright
©2019 American Society of Civil Engineers.
History
Received: Oct 21, 2018
Accepted: Mar 21, 2019
Published online: Sep 10, 2019
Published in print: Nov 1, 2019
Discussion open until: Feb 10, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.