Current state and prospects of development of energy-optimal control systems for 2ES6 electric locomotives

Introduction. The research focuses on the current state and prospects of development of the systems of energyoptimal train driven by freight main line DC electric locomotives 2ES6. An analysis of current trends in energy saving and increasing the efficiency of traction energy resources in railway transport and their impact on haulage of trains shows that train guidance based on machine learning and artificial intelligence remains poorly researched. The study is primarily intended to determine the actual use of automation of goods train driving in the sections of the Ural-Siberian railway proving ground and its impact on the energy-optimal schedule of completed train operations.

Materials and methods. The problem solving involved the basic provisions of the theory of haulage of trains, concepts of the theory of automated control and diagnostics of electric rolling stock, as well as statistical methods of data processing.

Results. The authors hypothesise that a smart adaptive rolling stock control support system with machine learning and AI would reduce the specific power consumption of locomotives. The researchers show that the most feasible way to build real-time dynamic models of energy-optimal locomotive motion for such smart system is to use data from the automated workstation of a freight locomotives motion recorder and auto-drive, as this is the data that contains accurate geographic coordinates to synchronise measurements on trips in a particular section.

Discussion and conclusion. A tunable artificial recurrent neural network on long short-term memory in new or existing improved methods for energy-efficient train rolling stock control would improve the motion recorders used on locomotives. The developed algorithm may form the basis of a fundamentally new smart adaptive rolling stock control support system with machine learning and AI. Further research would be focused on the development of technology for building dynamic models of energy-optimal real-time locomotive movement with train.

1. Khudorozhko M. V., Eliseev I. A., Stelmashenko A. V. Single-crew locomotive driving system for coupled trains. Railway Equipment. 2024;(1):28-31. (In Russ.). EDN: https://elibrary.ru/kuikgx.

2. Khudorozhko M. V., Eliseev I. A., Stelmashenko A. V. Implementation of technical solutions for driving a coupled train by one locomotive crew (SAU-OP). In: Science 1520 VNIIZhT: Look beyond the horizon: Collection of proceedings of II International conf., Moscow, 24–25 August 2023. Moscow: Railway Research Institute; 2023. p. 304–310. (In Russ.). EDN: https://elibrary.ru/aodtgv.

3. Khudorozhko M. V., Eliseev I. A., Murov S. A., Stelmashenko A. V., Lantsov A. P. AV-RT system: heading towards unmanned technologies. Lokomotiv. 2020;(2):11-13. (In Russ.). EDN: https://elibrary.ru/ywxtad.

4. Eliseev I. A., Hazov M. S., Hudorozhko M. V. In-process determination of actual coefficient of traction of locomotive wheels with rails. In: Major issues of rail transport development: sourcebook of the All-Russian scientific and practical conf. for the 75th Anniversary of the postgraduate programme of the Railway Research Institute, Moscow, 5 June 2019. Moscow: RAS Publ.; 2019. p. 151–159. (In Russ.). EDN: https://elibrary.ru/pvzysp.

5. Eliseev I. A. Increase of energy efficiency of the electric locomotive control by in-process specification of traction forces and electric braking: Cand. Sci. (Eng.) thesis synopsis: 05.22.07. Moscow; 2013. 26 p. (In Russ.). EDN: https://elibrary.ru/sioirj.

6. Zhebrak L. M., Eliseev I. A. Methods of real-time adjustment of tractive effort acting from locomotive to train. Russian Railway Science Journal. 2012;(4):38-42. (In Russ.). EDN: https://elibrary.ru/pbeumr.

7. Eliseev I. A. Trends in the development of auto-driving systems. In: Kuchumov V. A., Nikiforova N. B. (eds) Improvement of tractive rolling stock electrical equipment: Collection of scientific works of the Railway Research Institute. Moscow: Intext Publ.; 2011. p. 38–45. (In Russ.). EDN: https:// elibrary.ru/spiqit.

8. Zhebrak L. M., Eliseev I. A. Setting of the problem of in-process specification of the traction force acting on the train in motion. In: Prospects of railway transport development: Collection of articles of young scientists and postgraduates of the Railway Research Institute. Moscow: Intext Publ.; 2010. p. 35–39. (In Russ.). EDN: https://elibrary.ru/tajeur.

9. Eliseev I. A. Stochastic model of locomotive's tractive effort. Russian Railway Science Journal. 2010;(4):30-33. (In Russ.). EDN: https://elibrary.ru/mvcrxt.

10. Eliseev I. A., Hudorozhko M. V., Zhebrak L. M. Method of variable estimation with minimum dispersion. World of Transport and Transportation. 2009;7(1):28-32. (In Russ.). EDN: https://elibrary.ru/jybizh.

11. Muginshteyn L. A., Vinogradov S. A., Kiryakin V. Yu., Lyashko O. V., Anfinogenov A. Yu., Yabko I. A. Elbrus Innovations Project. Zheleznodorozhnyy transport. 2013;(12):18-25. (In Russ.). EDN: https://www. elibrary.ru/rmtbfp.

12. Muginshteyn L. A., Vinogradov S. A., Kiryakin V. Yu., Lyashko O. V., Anfinogenov A. Yu., Novgorodtseva A. V. Polygon technologies of scheduled train traffic based on the Elbrus Automated System. Zheleznodorozhnyy transport. 2015;(3):13-19. (In Russ.). EDN: https://elibrary.ru/tkirfp.

13. Muginshteyn L. A., Vinogradov S. A., Yabko I. A. Energy-optimal traction calculation of train traffic. Zheleznodorozhnyy transport. 2010;(2):24-29. (In Russ.). EDN: https://elibrary.ru/oyseib.

14. Muginshteyn L. A., Ilyutovich A. E., Yabko I. A. Energy-optimal methods of train traffic control: Collection of scientific works of the Railway Research Institute. Moscow; 2012. p. 79. (In Russ.). EDN: https://elibrary.ru/qnxwzz.

15. Muginshteyn L. A., Ilyutovich A. E., Yabko I. A. Mimimum energy consumption based train performance calculation. Russian Railway Science Journal. 2013;(6):3-13. (In Russ.). EDN: https://elibrary.ru/ tolgrr.

16. Muginshteyn L. A., Molchanov A. I., Vinogradov S. A., Popov K. M., Shkol'nikov E. N. Modern methodology of technical rationing of fuel and energy consumption by locomotives for train traction. Moscow: VMG-Print Publ.; 2014. 144 p. (In Russ.). EDN: https://elibrary.ru/vtzsnn.

17. Yurenko K. I. Study of methods for optimising train driving modes using a smart simulation model. In: Smart control systems on railway transport. Computer and mathematical modelling (ISUZhT – 2018): Proceedings of the Seventh Scientific and Technical Conf., Moscow, 14 November 2018. Moscow: Research and Design Institute of Informatisation, Automation and Communication on Railway Transport; 2018. p. 236–240. (In Russ.). EDN: https://elibrary.ru/sqsndv.

18. Cuéllar M., Delgado M., Pegalajar M. An application of nonlinear programming to train recurrent neural networks in time series prediction problems. In: Chen C.-S., Filipe J., Seruca I., Cordeiro J. (eds) Enterprise Information Systems VII. Dordrecht: Springer; 2007. р. 95–102. https://doi.org/10.1007/978-1-4020-5347-4_11.

19. Zhuang N., Qi G.-J., Kieu T. D., Hua K. A. Rethinking the Combined and Individual Orders of Derivative of States for Differential Recurrent Neural Networks. ACM Transactions on Multimedia Computing, Communications, and Applications. 2019;15(3):1-21. https://doi. org/10.1145/3337928.