Bayesian Optimizasyonu ile Gauss Proses Regresyon Yöntemlerini Kullanarak Demiryolu Sinyalizasyon Sistemi için Ortalama Hız Tahmini

Year 2021, Issue: 14, 274 - 286, 31.07.2021

Mehmet Taciddin Akçay Abdurrahim Akgundogdu Hasan Tiryaki

https://doi.org/10.47072/demiryolu.942730

Cited By: 4

Abstract

Ulaşım sistemleri trafik planlaması içerisinde önemli bir yere sahiptir. Ulaşım sistemleri göz önünde bulundurulduğunda ise demiryolları tüm sistemde büyük pay kaplamaktadır. Demiryolları tasarlanırken erişim noktaları arası ulaşımın istenilen sürede gerçekleştirilmesi planlanmaktadır. Erişim noktaları arası ortalama hız; bekleme süresi, hareket direnci, eğim, kurp, cer kuvveti, maximum hız, aracın kütlesi ve iki istasyon arası mesafe gibi parametrelerden etkilenmektedir. Aracı hareketi bu parametreler ile hesaplanarak sistem tasarımı buna göre gerçekleştirilmektedir. Ortalama hız iki erişim noktası arası seyir süresini etkileyen en önemli unsurlardan biridir. Ortalama hıza bağlı olarak sefer sıklığı süresi değişebilmektedir. Bu çalışmada raylı sistemlerde istasyonlar arası hesaplanan ortalama hızların tahmini için farklı regresyon yöntemleri uygulanmış ve elde edilen başarılı sonuçlar karşılaştırılmalı olarak verilmiştir. Kullanılan yöntemler incelendiğinde Bayesian algoritması ile optimize edilen Gaussian Process Regression yönteminin en başarılı sonucu verdiği görülmüştür. Gauss proses (GP), herhangi bir sonlu sayıda Gauss dağılımına sahip rastgele değişkenlerin topluluğudur. Benzetimler sonrasında root mean square error ve mean absolute error değerleri sırasıyla 0.064 ve 0.047 olarak bulunmuş ve yöntemin başarı oranı hesaplandığında determinasyon katsayısı (R2) değeri 1 olarak elde edilmiştir.

Keywords

Bayesian Optimizasyon, Cer Gücü, Demiryolu, Gaussian Proses, Ortalama Hız, Regresyon

Estimation of the Average Speed for a Railway Signaling System by Using Gaussian Process Regression Methods with Bayesian Optimization

Abstract

Transportation systems take an essential place in traffic planning. While designing railways, transportation between access points is planned to be realized within the desired time. The average speed between access points is affected by parameters like waiting time, motion resistance, slope, curve, traction force, maximum speed, the mass of the vehicle, and distance between two stations. The motion of the vehicle is calculated with these parameters, and the system design is performed accordingly. The average speed is one of the most critical factors affecting travel time between two access points. The headway may vary depending on the average speed. In this study, different regression methods were applied to estimate the average speeds calculated between stations in rail systems, and the obtained successful results were presented comparatively. When the methods used were examined, the Gaussian process regression method, which was optimized with the Bayesian algorithm, was observed to yield the most successful result. A Gaussian process (GP) is a collection of random variables, any finite number of which have a Gaussian distribution. Following simulations, the root mean square error and mean absolute error were found to be 0.064 and 0.047, respectively, and the coefficient of determination (R2) value was obtained as 1 when the success rate of the method was calculated.

Keywords

Average Speed, Bayesian Optimization, Gaussian Process, Railway, Regression, Traction

References

• [1] R., Riccardo, G., Massimiliano, “An empirical analysis of vehicle time headways on rural two-lane two-way roads,” Procedia - Social and Behavioral Sciences, no. 54, pp. 865 – 874, 2012.
• [2] I., W., Suweda, “Time headway analysis to determine the road capacity”, Jurnal Spektran, vol. 4, no. 2, pp. 71-75, 2016.
• [3] H., Nakamura, “Analysis of minimum train headway on a moving block system by genetic algorithm,” Transactions on the Built Environment, 34, 1014-1022, 1998.
• [4] J., Jang, C., Park, B., Kim, N., Choi, “Modeling of time headway distribution on suburban arterial:Case study from South Korea”, Procedia - Social and Behavioral Sciences, no. 16, pp. 240 – 247, 2011.
• [5] A., K., Maurya, S., Das, S., Dey, S., Nama, “Study on speed and time-headway distributions on two-lane B-bidirectional road in heterogeneous traffic condition,” Transportation Research Procedia, no. 17, pp. 428 – 437, 2016.
• [6] A., K., Maurya, S., Dey, S., Das, “Speed and time headway distribution under mixed traffic condition,” Journal of the Eastern Asia Society for Transportation Studies, no. 11, pp. 1774-1792, 2015.
• [7] C., C., Minh, K., Sano, S., Matsumoto, “The speed, flow and headway analyses of motorcycle traffic,” Journal of the Eastern Asia Society for Transportation Studies, no. 6, pp. 1496 – 1508, 2005.
• [8] D., Kong, X., Guo, “Analysis of vehicle headway distribution on multi-lane freeway considering car–truck interaction,” Advances in Mechanical Engineering, vol. 8, no. 4, pp. 1–12, 2016.
• [9] Y., Moriyama, M., Mistsuhashi, S., Hirai, T., Oguchi, “The effect on lane utilization and traffic capacity of adding an auxiliary lane,” Procedia - Social and Behavioral Sciences, no. 16, pp. 37 – 47, 2011.
• [10] H., Faheem, I., H., Hashim, “Analysis of traffic characteristics at multi-lane divided highways, case study from cairo-aswan agriculture highway,” International Refereed Journal of Engineering and Science (IRJES), vol. 3 no. 1, pp. 58-65, 2014.
• [11] Z., Lv, J., Xu, K., Zheng, H., Yin, P., Zhao, X., Zhou, “LC-RNN: A deep learning model for traffic speed prediction,” Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden, 2018, pp. 3470-3476.
• [12] A., Dhamaniya, S., Chandra. “Speed prediction models for urban arterials under mixed traffic conditions,” Procedia - Social and Behavioral Sciences, no. 104, pp. 342 – 351, 2013.
• [13] M., Gmira, M., Gendreau, A., Lodi, J., Potvin, “Travel speed prediction based on learning methods for home delivery,” Interuniversity Research Center On Business Networks, logistics and transport, CIRRELT, no.1, pp. 1-34, 2018.
• [14] M., Bysveen, “Vehicle speed prediction models for consideration of energy demand within road design,” Master’s Thesis, Civil and Environmental Engineering, Norwegian University of Science and Technology, 2017.
• [15] B., Mirbaha, M., Saffarzadeh, S., A., Beheshty, , M., Aniran, M., Yazdani, B., Shirini, “Predicting average vehicle speed in two lane highways considering weather condition and traffic characteristics”, IOP Conference Series: Materials Science and Engineering, no.1, pp. 1-7, 2017
• [16] M., Gmira, M., Gendreau, A., Lodi, J., Potvin, “Travel speed prediction using machine learning techniques”, ITS World Congress, Montreal, 2017, pp.1-10.
• [17] M., T., Akçay, “Estimation of constant speed time for railway vehicles by stochastic gradient descent algorithm”, Sakarya University Journal of Computer and Information Sciences, 3 (3) , 355-365, 2020.
• [18] W., Xinyue, S., Xianfeng, W., Jialiang, Y., Xun, H., Baoguo, “Train speed estimation from track structure vibration measurements,” Applied Sciences, no. 10, pp. 4742, 2020.
• [19] Z., Yuliang, W., Li, “Continuous monitoring of train parameters using ıot sensor and edge computing,” IEEE Sensors Journal, no. 1, pp. 1-10, 2020.
• [20] C., E., Rasmussen, C., K., I., Williams, “Gaussian processes for machine learning”, MIT Press. Cambridge, Massachusetts, 2006.
• [21] The Mathworks, Statistics and machine learning toolbox user’s guide, 2019.