Automation of the Process of Diagnostics of Electric Locomotive Current Collectors

The paper presents an automated system for diagnosing electric locomotive current collectors based on machine vision, which allows for the replacement of time-consuming and subjective manual inspections with non-contact, high-precision measurements. The Python program, using the OpenCV, NumPy, and SciPy libraries, analyzes photos and video streams. It measures the minimum thickness and width of the carbon insert using photos, and tracks the geometric parameters of the current collector in real-time using video with reflective markers, calculating the distances and angles between control points. A 3D model of the current collector has been created for testing purposes. The implementation of the system reduces the influence of the human factor, allows for the detection of defects at an early stage, the prediction of the residual resource of equipment, the reduction of operating costs, and the minimization of the risk of emergencies, thereby increasing the reliability of the power supply for electric rolling stock.

1. Dmitrenko, A. V. Assessment of the Influence of the Average Weight of Freight Trains on the Size of Their Movement on Mainline Railway Lines / A. V. Dmitrenko, S. M. Nauruzbaev // Bulletin of the Rostov State University of Railway Engineering. – 2025. – No. 4. – Pp. 81–89.

2. Kolosov D. V., Zharkov Yu. I., Semenov Yu. G., Otypka J. The principals of operation of the automated current collection diagnostic system for electrified railways // 2015 16th International Scientific Conference on Electric Power Engineering (EPE). — Kouty nad Desnou, Czech Republic, 2015. — P. 1–6.

3. Shepilova, E. G. Problems and Prospects of Artificial Intelligence Development in the Russian Railway Transport / E. G. Shepilova, V. R. Khusainov // Innovative Development of the Transport and Construction Complexes: Proceedings of the International Scientific and Practical Conference Dedicated to the 70th Anniversary of BelIIZhTa - BelGUTa. In 2 parts, Gomel, November 16–17, 2023. – Gomel: Belarusian State University of Transport, 2023. – Pp. 193-195. – EDN LUJHBG.

4. Khusainov, V. R. Application of Artificial Intelligence in the Development of Modern Applications / V. R. Khusainov, P. D. Shramkova // Digital Infocommunication Technologies: Collection of Scientific Papers of the V International Scientific and Practical Conference Dedicated to the 50th Anniversary of the Department of Communications in Railway Transport. In 2 volumes, Rostov-onDon, October 23, 2025. – Rostov-on-Don: Rostov State Transport University, 2025. – Pp. 212-217. – EDN HVFVJF.

5. Butakova, M. A. Artificial Intelligence Technologies and Applications: A Study Guide / M. A. Butakova, M. I. Myalova. – Rostov-on-Don: Southern Federal University, 2021. – 48 p. – EDN KHOJPY.

6. Myalova, M. I. Development of a Pythonbased user interface for automatically selecting a data clustering algorithm / M. I. Myalova, M. A. Pazin // Digital Infocommunication Technologies : Collection of Scientific Papers, Rostov-on-Don, September 7, 2021. – Rostovon-Don: Rostov State Transport University, 2021. – Pp. 77-81. – EDN JBFZAJ.