Siberian Researchers Develop a Formula for Train Movement
Rail operators could gain a tool that calculates a train’s movement with an almost human-like sensitivity to track conditions, weather and the characteristics of the train consist.
Scientists at Omsk State Transport University (OmGUPS) have developed a mathematical model that calculates train movements using not only equations but also real-world operating data. Its key advantage is its ability to account more accurately for factors such as track condition, weather and how trains are assembled. The algorithm draws on data from more than 1,500 actual freight train journeys hauled by electric locomotives on the West Siberian Railway. Onboard recorders captured speed, motor performance, braking loads and other operating parameters.
This approach allows the algorithm to reproduce train movements under conditions that are difficult to describe using equations alone. The results are promising: calculation accuracy improved by 10–15% compared with traditional methods, while the difference between calculated and actual running times was no more than one minute. This could help operators fine-tune acceleration, cruising speed and braking strategies, saving energy and reducing wear on rolling stock.
Optimising Load Parameters
The model’s main prospects lie in deployment on Russian railways, followed potentially by expansion into international markets. One key direction is integration with Russian Railways’ train automation systems. For example, the technology could enhance the capabilities of the AV-RT system (automated operation of heavy freight trains with locomotives distributed along the train), which already uses adaptive algorithms to optimise traction and braking.
If the technology proves effective in operational use, it could become another tool for improving energy efficiency.
Rail operators in the Commonwealth of Independent States (CIS) and Asia could also be interested in the technology, particularly where long-distance freight routes are important. Russian engineers already have experience supplying IT solutions to international markets. For example, the Railway Research Institute (VNIIZhT) has supplied software for controlling coupled trains to Uzbekistan’s railways.
Smart Rails
In recent years, automation and the adoption of intelligent technologies across Russia’s rail transport sector have accelerated considerably.
In 2021, trials were completed for machine vision and remote-control systems for the Lastochka (Swallow) electric multiple unit. In 2022, engineers at the Eastern Polygon railway network advanced virtual coupling technology, with algorithms that reduced the interval between trains to eight minutes and improved timetable accuracy. In 2023, VNIIZhT introduced AI models for predictive locomotive fault analysis. Using telemetry, these systems detected anomalies and forecast the remaining service life of equipment. In 2024, a Lastochka train operating at Grade of Automation 3 began carrying passengers, marking an important step from testing to practical use. In 2025, VNIIZhT continued to improve the AV-RT freight train automation system. By July 2026, Russian Railways was implementing 35 projects incorporating AI, ranging from automated railcar inspections to timetable planning.
The new model from OmGUPS fits naturally into this trend, adding a deeper understanding of the physical dynamics of locomotive-and-wagon movements to existing intelligent systems.
Precision, Savings and Headway
The OmGUPS development is more than another algorithm: it seeks to combine mathematical modelling with machine learning based on real-world data. This approach could significantly improve the accuracy of automated train operation systems, particularly on long-distance freight routes, where even modest gains can translate into substantial savings. The main hurdle, however, is still ahead: operational testing. Working with AVP Technology and Russian Railways’ Traction Directorate, the developers will need to verify not only the claimed accuracy but also actual electricity savings, reliable performance under different conditions and compatibility with existing infrastructure.
If testing is successful, the technology could become part of the national rail operator’s broader energy-efficiency programme and help strengthen Russia’s export offering in intelligent railway systems.
