A MODEL FOR ASSESSING THE ENERGY EFFICIENCY OF ELECTRIC ROLLING STOCK BASED ON ARTIFICIAL INTELLIGENCE
Keywords:
electric rolling stock, energy efficiency, traction calculation, artificial intelligence, machine learning, on-board data, driver advisory system.Abstract
The article proposes a hybrid model for assessing the energy efficiency of electric rolling stock that combines a physical traction energy balance with machine learning. The physical part calculates the reference energy for a given train, track profile and speed from the standard running resistance formulas. The machine-learning part learns from on-board data how actual consumption deviates from this reference. An energy efficiency index is defined as the ratio of reference to actual energy. An illustrative calculation for a 3,192 t train on a 50 km section shows that raising the cruising speed from 50 to 80 km/h cuts running time by 37.5% but increases net energy by 46%. The model is intended for UzEL electric locomotives operated by Uzbekistan Railways and forms the basis of a driver advisory system.
References
Oʻzbekiston Respublikasi Prezidentining 2023-yil 10-oktyabrdagi PQ-329-son qarori.
Howlett P., Pudney P. Energy-Efficient Train Control. – London: Springer, 1995.
Scheepmaker G.M., Goverde R.M.P., Kroon L.G. Review of energy-efficient train control and timetabling // European Journal of Operational Research. – 2017. – Vol. 257, No. 2. – P. 355–376.
Yang X., Li X., Ning B., Tang T. A survey on energy-efficient train operation for urban rail transit // IEEE Transactions on Intelligent Transportation Systems. – 2016. – Vol. 17, No. 1. – P. 2–13.
Ghofrani F., He Q., Goverde R.M.P., Liu X. Recent applications of big data analytics in railway transportation systems: A survey // Transportation Research Part C. – 2018. – Vol. 90. – P. 226–246.
Fayzibaev S., Muxammedova Z., Raxmiddinov I. Optimization models of repair periods of electrical equipment of self-propelled rolling stock, according to its technical condition // E3S Web of Conferences. – 2023. – Vol. 458. – 01015. https://doi.org/10.1051/e3sconf/202345801015
Rakhmiddinov I., Fayzibaev S., Kasimov O., Kosimov K., Panchenko V. Improving the structural reliability of self-propelled railcar frames through modernization techniques // AIP Conference Proceedings. – 2026. – Vol. 3447. – 060011. https://doi.org/10.1063/12.0044293
Правила тяговых расчетов для поездной работы. – М.: Транспорт, 1985. – 287 с.
Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2016. – P. 785–794.
Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45. – P. 5–32.
