PDF To download article.

DOI: 10.15507/2658-4123.032.202203.437-459


Automated Train Coordinate Determination System with Self-Tuning of the Decision Function


Evgeny M. Tarasov
Head of the Chair of Automatics, Telemechanics and Communication on Railway Transport, Samara State Transport University (2V Svoboda St., Samara 443066, Russian Federation), Dr.Sci. (Engr.), Professor, ORCID https://orcid.org/0000-0003-2717-7343, Researcher ID: C-2505-2018, Scopus ID: 57076210800, This email address is being protected from spambots. You need JavaScript enabled to view it.

Anna E. Tarasova
Postgraduate Student of the Chair of Automatics, Telemechanics and Communication on Railway Transport, Samara State Transport University (2V Svoboda St., Samara 443066, Russian Federation), ORCID: https://orcid.org/0000-0001-6907-6036, Researcher ID: C-2497-2018, This email address is being protected from spambots. You need JavaScript enabled to view it.

Introduction. The problem of determining the train coordinates on the approach section to the crossing is associated with the impact of destabilizing factors on the information primary detector ? the rail line with distributed parameters. This leads to an error in calculating train coordinates. The aim of the study is to develop and scientifically substantiate the principle of building a system for calculating train coordinates with self-tuning of the decision function under the influence of significant destabilizing factors on the information primary sensor.
Materials and Methods. To solve the problem of reliable determination of train coordinates, we propose a two-phase principle for forming the decision function. At the first stage, by means of a training sample of images and using the learning principle, the decision function (model) of the system for calculating train coordinates is determined. When the train enters a fixed-length approach section, the mismatch is determined by comparing the calculated coordinate with the fixed one. The second stage is the self-tuning of the coefficients of the decision function until the required accuracy is achieved.
Results. The article shows the stages of forming the decision function by two-dimensional images; there was developed and tested an algorithm for self-turning of the decision function under the influence of various destabilizing factors. Through using 6 attributes of components of current and voltage vectors at the rail line input, 6 solving functions were obtained. Various combinations of two-dimensional images were used as polynomial arguments.
Discussion and Conclusion. The study results confirm the feasibility of forming decision function and its self-tuning. The maximum error in calculating coordinates for various combinations ranges from 9.97% (199.34 m) to 4.57% (91.49 m). The error of determination of 5% for two decisive functions satisfies the safety requirements, since in a 45-second time interval to activate an automatic crossing signal, a distance of 100 m is covered in 3 seconds, i.e. the elapsed time is only 3 seconds in a 45 second interval.

Keywords: rail line, decisive function, self-tuning, fine tuning, informative features, invariance, calculation error

Funding: The article was prepared as part of the research work on the state assignment of budgetary organizations of higher education subordinate to the Federal Agency for Railway Transport (Roszheldor), registration number 122022200432-8 “Development of an intelligent system for managing traffic flows at railway crossings based on machine learning and continuous determining train coordinates with an adaptive self-tuning algorithm for correcting the equation for calculating train coordinates”.

Conflict of interest: The authors declare no conflict of interest.

For citation: Tarasov Е.М., Tarasova А.Е. Automated Train Coordinate Determination System with Self-Tuning of the Decision Function. Engineering Technologies and Systems. 2022;32(3):437–459. doi: https://doi.org/10.15507/2658-4123.032.202203.437-459

Contribution of the authors:
E. M. Tarasov – problem statement, theoretical consulting, analysis of research results, development of mathematical models.
A. E. Tarasova – processing the research results, conducting the research using Matlab software, analyzing literary sources.

All authors have read and approved the final manuscript.

Submitted 24.05.2022; approved after reviewing 20.06.2022;
accepted for publication 04.07.2022



1. Zhou W., Lu Y., Liu M., Zhang K. Machine Learning Methods Based on Probabilistic Decision Tree under the Multi-Valued Preference Environment. Economic Research-Ekonomska Istraživanja. 2022;35(1):38–59. Available at: https://www.tandfonline.com/doi/citedby/10.1080/1331677X.2021.1875866?scroll=top&needAccess=true (accessed 20.05.2022).

2. Sarker I.H. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science. 2021;2(160). doi: https://doi.org/10.1007/s42979-021-00592-x

3. Boukerche A., Wang J. Machine Learning-Based Traffic Prediction Models for Intelligent Transportation Systems. Computer Networks. 2020;181(3). doi: https://doi.org/10.1016/j.comnet.2020.107530

4. Singh G., Kumar P., Mishra R.K., et al. Security System for Railway Crossings Using Machine Learning. In: 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) (18–19 December 2020). Noida: IEEE; 2020. p. 135–139. doi: https://doi.org/10.1109/ICACCCN51052.2020.9362976

5. Falahati A., Shafiee E. Improve Safety and Security of Intelligent Railway Transportation System Based on Balise Using Machine Learning Algorithm and Fuzzy System. International Journal of Intelligent Transportation Systems Research. 2022;20:117–131. doi: https://doi.org/10.1007/s13177-021-00274-1

6. Tarasov Ye.M., Tarasova A.Ye. [Development of a Device for Calculating the Speed of a Mobile Unit on the Rail Track]. Vestnik SamGUPS. 2019;(1):123–130. Available at: https://www.elibrary.ru/item.asp?id=38098897 (accessed 20.05.2022). (In Russ.)

7. Zheng Z., Dai S., Xie X. Research on Fault Detection for ZPW-2000A Jointless Track Circuit Based on Deep Belief Network Optimized by Improved Particle Swarm Optimization Algorithm. IEEE Access. 2020;8:175981–175997. doi: https://doi.org/10.1109/ACCESS.2020.3025628

8. Tarasov E.M., Andronchev I.K., Bulatov A.A., Teplyakov V.B. Parametric Synthesis of a Track Condition Classifier. Russian Electrical Engineering. 2020;91(3):183–185. doi: https://doi.org/10.3103/S1068371220030189

9. Alawad H., Kaewunruen S., An M. Learning from Accidents: Machine Learning for Safety at Railway Stations. IEEE Access. 2020;8:633–648. doi: https://doi.org/10.1109/ACCESS.2019.2962072

10. Somogyi Z. Machine Learning Algorithms. In: Somogyi Z. (ed.) The Application of Artificial Intelligence. Cham: Springer; 2021. p. 17–86. doi: https://doi.org/10.1007/978-3-030-60032-7_2

11. Tou J.T., Gonzalez R.C. Pattern Recognition Principles. London-Amsterdam-Dom Mills, Ontario-Sydney-Tokyo. Addison-Wesley Publishing Company; 1974. 378 p. doi: https://doi.org/10.1002/zamm.19770570626

12. Zheleznov D.V., Tarasov Ye.M., Isaycheva A.G., Mikheeva T.I. Development of the Learning Classifier of Rail Lines States with Multivariate Informative Features. SPIIRAS Proceedings. 2017;(1):32–54. Available at: http://proceedings.spiiras.nw.ru/index.php/sp/article/view/3436 (accessed 20.05.2022). (In Russ., abstract in Eng.)

13. Kocbek S., Gabrys B. Automated Machine Learning Techniques in Prognostics of Railway Track Defects. In: International Conference on Data Mining Workshops (ICDMW) (08–11 November 2019). Beijing: IEEE; 2019. p. 777–784. doi: https://doi.org/10.1109/ICDMW.2019.00115

14. Prisukhina I.V., Borisenko D.V. [Machine Classification of Electric Rail Circuit Operating Mode Based on Logistic Regression]. Omsk Scientific Bulletin. 2018;(6):126–130. (In Russ.) doi: https://doi.org/10.25206/1813-8225-2018-162-126-130

15. Borisenko D.V., Prisukhina I.V., Lunev S.A. [Machine Classification of Electric Rail Circuit Operating Mode Based on Logistic Regression]. Omsk Scientific Bulletin. 2018;(4):67–72. (In Russ.) doi: https://doi.org/10.25206/1813-8225-2018-160-67-72

16. Tan H. Machine Learning Algorithm for Classification. In: Journal of Physics: Conference Series. 2021 International Conference on Big Data and Intelligent Algorithms (BDIA 2021) (9–11 July 2021). Vol. 1994. Chongqing; 2022. doi: https://doi.org/10.1088/1742-6596/1994/1/012016

17. Shetty Sh.H., Shetty S., Singh Ch., et al. Supervised Machine Learning: Algorithms and Applications. In: Singh P. (ed.) Fundamentals and Methods of Machine and Deep Learning. New York: Wiley; 2022. doi: https://doi.org/10.1002/9781119821908.ch1

18. Golden R. Formal Machine Learning Algorithms. Golden R. (ed.) Statistical Machine Learning: A Unified Framework. 1st ed. New York: Chapman and Hall/CRC; 2020. 524 p. doi: https://doi.org/10.1201/9781351051507-3

19. Ray S. A Quick Review of Machine Learning Algorithms. In: International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon) (14–16 February 2019). Faridabad: IEEE; 2019. p. 35–39. doi: https://doi.org/10.1109/COMITCon.2019.8862451

20. Rakcheeva T. Focal Model in the Pattern Recognition Problem. In: Hu Z., Petoukhov S., He M. (eds.) Advances in Artificial Systems for Medicine and Education II. AIMEE2018 2018. Advances in Intelligent Systems and Computing. Vol. 902. Cham: Springer; 2020. p. 127–138. doi: https://doi.org/10.1007/978-3-030-12082-5_12

21. Leurent E., Efimov D., Maillard O.-A. Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs. ArXiv. 2020. doi: https://doi.org/10.48550/arXiv.2002.10816

22. Zile M. Intelligent and Adaptive Control. In: Tabatabaei M.N., Kabalci E., Bizon N. (eds.) Microgrid Architectures, Control and Protection Methods. New York: Springer; 2020. p. 423–446. doi: https://doi.org/10.1007/978-3-030-23723-3_17

23. Girish J., Vasvir V., Girish Ch. Asynchronous Deep Model Reference Adaptive Control. ArXiv. 2020. doi: https://doi.org/10.48550/arXiv.2011.02920

24. Lopez B.T., Slotine J.-J.E. Universal Adaptive Control of Nonlinear Systems. IEEE Control Systems Letters. 2022;6:1826–1830. doi: https://doi.org/10.1109/LCSYS.2021.3133359

25. Yuzhen Zh., Qing L., Weicun Zh., Yuhang Y. Theory and Application of Multi-Model Adaptive Control. Journal of Engineering Science. 2020;42(2):135–143. doi: https://doi.org/10.13374/j.issn2095-9389.2019.02.25.006

26. Tarasov Е.М., Andronchev I.K., Bulatov A.A., et al. Development of a Trainable Classifier of State of Rail Lines with Multiple Patterns of Image Recognition. Engineering Technologies and Systems. 2020;30(4):659–682. (In Russ., abstract in Eng.) doi: https://doi.org/10.15507/2658-4123.030.202004.659-682

27. Tarasov Е.М., Gerus V.L., Tarasova А.Е. Study of Informative Value of Features in Rail Condition Monitoring. Mordovia University Bulletin. 2018;28(2):191–206. (In Russ., abstract in Eng.) doi: https://doi.org/10.15507/0236-2910.028.201802.191-206


Лицензия Creative Commons
This work is licensed under a Creative Commons Attribution 4.0 License.

Joomla templates by a4joomla