Abstract
This work considers the indicators that affect the state of the traction electric motor of electric rolling stock and are used for predictive diagnostics as part of an intelligent system for managing the production resources of urban rail transport systems in solving the following tasks: assessing the condition of a vehicle’s equipment, predicting its operability, and deciding on the need for unscheduled inspection and repairs; improving the process of scheduling the turnover of rolling stock and its adaptation under dynamically variable conditions; and improving the efficiency of electric rolling stock control, namely, increasing the level of efficiency and reducing the likelihood of unscheduled repairs and the amount of repair costs. A variant of using the parameters of armature current as an indicator, affecting the condition of the traction motor of electric rolling stock, is proposed. The condition of the traction motor is assessed by comparing sections on which unscheduled repairs are performed and those that do not undergo any such repairs. A review of predictive diagnostics systems used in railroad transport for locomotives is carried out.
Similar content being viewed by others
REFERENCES
Khromov, I.Yu., Justification for the operating mode violation impact on the deterioration of the technical condition of locomotives, Sovrem. Tekhnol. Sist. Anal. Model., 2020, no. 2, pp. 62–68. https://doi.org/10.26731/1813-9108.2020.2(66).62-68
Baranov, L.A. and Balakina, E.P., The random processes prediction based on orthogonal polynomials on the set of equally spaced points, Elektrotekhnika, 2020, no. 9, pp. 39–46.
Zhogolev, E.N., Investigation of the causes of failures of traction motors on DC 2ES6 freight locomotives, Fundamental’nye i prikladnye nauchnye issledovaniya. Aktual’nye voprosy, dostizheniya i innovatsii (Fundamental and Applied Scientific Research: Topical Issues, Achiements, and Innovations), Penza: Nauka i Prosveshchenie, 2020, pp. 76–79.
Domanov, K.I., Estimation of the technical condition of traction electric motors of electric locomotives of series 2ES6, Innovatsionnye proekty i tekhnologii v obrazovanii, promyshlennosti i na transporte (Innovation Projects and Technologies in Education, Industry, and Transport), Omsk: Omskii Gos. Univ. Putei Soobshch., 2018, pp. 338–343.
Sidorenko, V.G. and Kulagin, M.A., Predicting the failure of traction electric motors of electric rolling stock of railways using deep neural networks, Russ. Electr. Eng., 2021, vol. 92, no. 9, pp. 515–519. https://doi.org/10.3103/S1068371221090121
Fedotov, M.V., Grachev, V.V., and Kim, S.I., The usage of neural network models for modern locomotives onboard equipment diagnostic, Vestn. Inst. Probl. Estestvennykh Monopolii: Tekh. Zheleznykh Dorog, 2018, no. 3, pp. 22–31.
Fedotov, M.V. and Grachev, V.V., Predictive technical diagnostic system for locomotives utilising data mining technologies, Transp. Ross. Fed., 2020, no. 6, pp. 28–34.
Chilikin, M.G. and Sandler, A.S., Obshchii kurs elektroprivoda (General Course of Electric Drive), Moscow: Energoizdat, 1981.
Armenskii, E.V. and Falk, G.B., Elektricheskie mikromashiny (Electric Micromachines), Moscow: Vysshaya Shkola, 1985.
Funding
This work was supported by the Russian Foundation for Basic Research, Sirius University, OAO RZD, and Talent and Success Education Fund, project no. 20-37-51001
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by S. Kuznetsov
About this article
Cite this article
Sidorenko, V.G., Kulagin, M.A. & Mikhailov, S.V. Approach to Predicting Failures of Traction Electric Motors. Russ. Electr. Engin. 93, 592–595 (2022). https://doi.org/10.3103/S1068371222090139
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068371222090139