koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2026-3-282-295koz-2776Research ArticleИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИINFORMATION AND COMMUNICATION TECHNOLOGIESВНЕДРЕНИЕ СИСТЕМЫ ПРЕДИКТИВНОГО ОБСЛУЖИВАНИЯ НА АВТОМОБИЛЬНОМ ПРЕДПРИЯТИИ: ЭКОНОМИЧЕСКИЙ ЭФФЕКТ И ПРОИЗВОДСТВЕННЫЕ РЕЗУЛЬТАТЫIMPLEMENTATION OF A PREDICTIVE MAINTENANCE SYSTEM IN AN AUTOMOTIVE ENTERPRISE: ECONOMIC IMPACT AND PRODUCTION RESULTShttps://orcid.org/0009-0000-4990-4308АлдашеваД. Т.AldashevaD. T.

Костанай

Master of Pedagogical Sciences, senior teacher of the Department of Information Technology and Automation

Kostanay

aldasheva.dinara@mail.ruhttps://orcid.org/0000-0002-8681-4552СалыковаО. С.SalykovaO. S.

Костанай

Candidate of Technical Sciences, Head of the Software Department

Kostanay

solga0603@mail.ruhttps://orcid.org/0000-0003-4147-3843МауленовК. С.MaulenovK. S.

Костанай

PhD, Head of the Department of Digital Technologies and Artificial Intelligence

Kostanay

k.maulenov070693@gmail.comhttps://orcid.org/0009-0009-6191-458XБаеноваГ. М.BaenovaG. M.

Астана

corresponding author, PhD, senior teacher of the Department of computer and software engineering

Astana

baenova_gm@enu.kzКостанайский инженерно-экономический университет им. М. ДулатоваКазахстанKostanay Engineering and Economics University named after M. DulatovKazakhstanКостанайский региональный университет имени Ахмет БайтүрсынүлыКазахстанAkhmet Baitursynuly Kostanay Regional UniversityKazakhstanЕвразийский национальный университет им. Л.Н. ГумилеваКазахстанL.N. Gumilyov Eurasian National UniversityKazakhstan20263009202603 (71)282295Copyright © Алдашева Д.Т., Салыкова О.С., Мауленов К.С., Баенова Г.М., 20262026Алдашева Д.Т., Салыкова О.С., Мауленов К.С., Баенова Г.М.Aldasheva D.T., Salykova O.S., Maulenov K.S., Baenova G.M.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2776

В статье представлены результаты опытно-промышленного внедрения системы предиктивного обслуживания оборудования на предприятии автомобильной промышленности SaryarkaAvtoProm LLP. В основу системы положен ансамбль алгоритмов машинного обучения, обученных на многоканальных сенсорных данных (вибрация, температура, давление, расход технологических жидкостей) и журналах отказов. Прототип системы онлайн-мониторинга был интегрирован с двумя приоритетными сборочными линиями механосборочного цеха (двигательные и трансмиссионные узлы). В течение двух месяцев система в реальном времени анализировала потоки сенсорных данных и формировала предупреждения при превышении порога вероятности отказа 0,7. За указанный период сгенерировано 14 тревожных уведомлений, девять из которых соответствовали реально предотказным состояниям оборудования, а в пяти случаях были выявлены выраженные признаки износа, устраненные в рамках плановых ремонтов. Показано, что внедрение системы предиктивного обслуживания позволило снизить суммарные затраты на обслуживание с 1 000 000 до 720 000 условных единиц (экономия порядка 28 %) и сократить длительность незапланированных простоев с 340 до 200 часов (уменьшение на -41%). Анализируются факторы экономического эффекта: заблаговременное планирование ремонтов, снижение количества аварийных ситуаций, оптимизация складских запасов и уменьшение объема экстренных закупок.

В рамках пилота были реализованы сбор и предобработка сенсорных данных, ансамблевая оценка риска, интерфейс оповещений и представление вклада признаков. Цифровые двойники и федеративное обучение в экспериментальную систему не входили и рассматриваются только как направления дальнейшего масштабирования.

The article presents the results of the pilot implementation of the predictive equipment maintenance system at the SaryarkaAvtoProm LLP automotive industry enterprise. The system is based on an ensemble of machine learning algorithms trained on multichannel sensor data (vibration, temperature, pressure, flow rate of process fluids) and failure logs. The prototype of the online monitoring system was integrated with two priority assembly lines of the machine assembly shop (engine and transmission units).

For two months, the system analyzed sensor data streams in real time and generated warnings when the failure probability threshold of 0.7 was exceeded. During this period, 14 alarm notifications were generated, nine of which corresponded to the actual pre-failure conditions of the equipment, and in five cases pronounced signs of wear were detected, eliminated as part of scheduled repairs. It is shown that the introduction of a predictive maintenance system has reduced total maintenance costs from 1,000,000 to 720,000 conventional units (savings of about 28%) and reduced the duration of unplanned downtime from 340 to 200 hours (a decrease of ≈41%). The economic impact factors are analyzed: advance planning of repairs, reduction of the number of emergency situations, optimization of stocks and reduction of the volume of emergency purchases.

The pilot implemented sensor-data acquisition and preprocessing, ensemble-based risk estimation, an alert interface, and feature-contribution explanations. Digital twins and federated learning were not part of the experimental system and are considered only as directions for future scaling.

предиктивное обслуживаниемашинное обучениеонлайн-мониторингэкономическая эффективностьпростоиавтомобильная промышленностьсенсорный мониторингPredictive maintenancemachine learningonline monitoringeconomic efficiencydowntimeautomotive industrysensor monitoringReferencesEr-Ratby, M., et al. (2025). The impact of predictive maintenance on the performance of industrial enterprises. SN Computer Science, 6(1). https://doi.org/10.1007/s42979-024-03599-2Er-Ratby, M., et al. (2025). The impact of predictive maintenance on the performance of industrial enterprises. SN Computer Science, 6(1). https://doi.org/10.1007/s42979-024-03599-2Bucay-Valdiviezo, J., et al. (2023). Leveraging classical statistical methods for sustainable maintenance in automotive assembly equipment. Sustainability, 15(21), 15604. https://doi.org/10.3390/su152115604Bucay-Valdiviezo, J., et al. (2023). Leveraging classical statistical methods for sustainable maintenance in automotive assembly equipment. Sustainability, 15(21), 15604. https://doi.org/10.3390/su152115604Patrício, L., Varela, L., & Silveira, Z. (2025). Proposal for a sustainable model for integrating robotic process automation and machine learning in failure prediction and operational efficiency in predictive maintenance. Applied Sciences, 15(2), 854. https://doi.org/10.3390/app15020854Patrício, L., Varela, L., & Silveira, Z. (2025). Proposal for a sustainable model for integrating robotic process automation and machine learning in failure prediction and operational efficiency in predictive maintenance. Applied Sciences, 15(2), 854. https://doi.org/10.3390/app15020854Giacotto, A., Marques, H. C., & Martinetti, A. (2025). Prescriptive maintenance: A comprehensive review of current research and future directions. Journal of Quality in Maintenance Engineering, 31(1), 129-173. https://doi.org/10.1108/JQME-07-2023-0064Giacotto, A., Marques, H. C., & Martinetti, A. (2025). Prescriptive maintenance: A comprehensive review of current research and future directions. Journal of Quality in Maintenance Engineering, 31(1), 129-173. https://doi.org/10.1108/JQME-07-2023-0064Meddaoui, A., Hachmoud, A., & Hain, M. (2024). Advanced ML for predictive maintenance: A case study on remaining useful life prediction and reliability enhancement. The International Journal of Advanced Manufacturing Technology, 132(1-2), 323-335. https://doi.org/10.1007/s00170-024-13351-yMeddaoui, A., Hachmoud, A., & Hain, M. (2024). Advanced ML for predictive maintenance: A case study on remaining useful life prediction and reliability enhancement. The International Journal of Advanced Manufacturing Technology, 132(1-2), 323-335.Crespo del Castillo, A., & Parlikad, A. K. (2024). Dynamic fleet management: Integrating predictive and preventive maintenance with operation workload balance to minimise cost. Reliability Engineering & System Safety, 249, 110243. https://doi.org/10.1016/j.ress.2024.110243https://doi.org/10.1007/s00170-024-13351-yKliestik, T., et al. (2023). Artificial intelligence-based predictive maintenance, time-sensitive networking, and big data-driven algorithmic decision-making in the economics of Industrial Internet of Things. Oeconomia Copernicana, 14(4), 1097-1138. https://doi.org/10.24136/oc.2023.033Crespo del Castillo, A., & Parlikad, A. K. (2024). Dynamic fleet management: Integrating predictive and preventive maintenance with operation workload balance to minimise cost. Reliability Engineering & System Safety, 249, 110243. https://doi.org/10.1016/j.ress.2024.110243Singh, S. (2024). Enhancing road-based supply-chain efficiency in the US: Integrating AI/ML-based C3I systems with IoT-enabled trucks. International Journal of Supply Chain Management, 13(4), 1-10. https://doi.org/10.59160/ijscm.v13i4.6253Kliestik, T., et al. (2023). Artificial intelligence-based predictive maintenance, time-sensitive networking, and big data-driven algorithmic decision-making in the economics of Industrial Internet of Things. Oeconomia Copernicana, 14(4), 1097-1138. https://doi.org/10.24136/oc.2023.033Polverino, L., Abbate, R., Manco, P., Perfetto, D., Caputo, F., Macchiaroli, R., & Caterino, M. (2023). Machine learning for prognostics and health management of industrial mechanical systems and equipment: A systematic literature review. International Journal of Engineering Business Management, 15. https://doi.org/10.1177/18479790231186848Singh, S. (2024). Enhancing road-based supply-chain efficiency in the US: Integrating AI/ML-based C3I systems with IoT-enabled trucks. International Journal of Supply Chain Management, 13(4), 1-10. https://doi.org/10.59160/ijscm.v13i4.6253Nainggolan, N., Nima, E. M., Nainggolan, N., & Alwadi, B. M. (2024). Advancements in optimization for automotive manufacturing: Hybrid approaches and machine learning. International Journal of Industrial Engineering and Management, 15(3), 254-263. https://doi.org/10.24867/IJIEM-2024-3-361Polverino, L., Abbate, R., Manco, P., Perfetto, D., Caputo, F., Macchiaroli, R., & Caterino, M. (2023). Machine learning for prognostics and health management of industrial mechanical systems and equipment: A systematic literature review. International Journal of Engineering Business Management, 15. https://doi.org/10.1177/18479790231186848Bajic, B., Suzic, N., Simeunovic, N., Morača, S., & Rikalović, A. (2020). Real-time data analytics edge computing application for Industry 4.0: The Mahalanobis-Taguchi approach. International Journal of Industrial Engineering and Management, 11(3), 146-156. https://doi.org/10.24867/IJIEM-2020-3-260Nainggolan, N., Nima, E. M., Nainggolan, N., & Alwadi, B. M. (2024). Advancements in optimization for automotive manufacturing: Hybrid approaches and machine learning. International Journal of Industrial Engineering and Management, 15(3), 254-263. https://doi.org/10.24867/IJIEM-2024-3-361Gültekin, Ö., Cinar, E., Ozkan, K., & Yazici, A. (2022). Real-time fault detection and condition monitoring for industrial autonomous transfer vehicles utilizing edge artificial intelligence. Sensors, 22(9), 3208. https://doi.org/10.3390/s22093208Bajic, B., Suzic, N., Simeunovic, N., Morača, S., & Rikalović, A. (2020). Real-time data analytics edge computing application for Industry 4.0: The Mahalanobis-Taguchi approach. International Journal of Industrial Engineering and Management, 11(3), 146-156. https://doi.org/10.24867/IJIEM-2020-3-260Erdoğan, F. A., Kucukmanisa, A., & Kilimci, Z. H. (2023). Detection of fault from acoustic signals in automobile engines using deep learning techniques. Kocaeli Journal of Science and Engineering, 6(2), 148-154. https://doi.org/10.34088/kojose.1225591Gültekin, Ö., Cinar, E., Ozkan, K., & Yazici, A. (2022). Real-time fault detection and condition monitoring for industrial autonomous transfer vehicles utilizing edge artificial intelligence. Sensors, 22(9), 3208. https://doi.org/10.3390/s22093208Uaisova, M., Zharlykassov, B., Aldasheva, D., Artykbayeva, A., & Radchenko, P. (2024). The use of ANN and machine learning algorithms to predict road surface deterioration. GEOMATE Journal, 27(121), 136-143. https://doi.org/10.21660/2024.121.m2422Erdoğan, F. A., Kucukmanisa, A., & Kilimci, Z. H. (2023). Detection of fault from acoustic signals in automobile engines using deep learning techniques. Kocaeli Journal of Science and Engineering, 6(2), 148-154. https://doi.org/10.34088/kojose.1225591Chellapandi, V. P., Yuan, L., Brinton, C. G., Zak, S. H., & Wang, Z. (2024). Federated learning for connected and automated vehicles: A survey of existing approaches and challenges. IEEE Transactions on Intelligent Vehicles, 9(1), 119-137. https://doi.org/10.1109/TIV.2023.3332675Uaisova, M., Zharlykassov, B., Aldasheva, D., Artykbayeva, A., & Radchenko, P. (2024). The use of ANN and machine learning algorithms to predict road surface deterioration. GEOMATE Journal, 27(121), 136-143. https://doi.org/10.21660/2024.121.m2422Matzka, S. (2020). Explainable artificial intelligence for predictive maintenance applications. In Third International Conference on Artificial Intelligence for Industries (AI4I) (pp. 69-74). IEEE. https://doi.org/10.1109/AI4I49448.2020.00023Chellapandi, V. P., Yuan, L., Brinton, C. G., Zak, S. H., & Wang, Z. (2024). Federated learning for connected and automated vehicles: A survey of existing approaches and challenges. IEEE Transactions on Intelligent Vehicles, 9(1), 119-137. https://doi.org/10.1109/TIV.2023.3332675Chen, C., Fu, H., Zheng, Y., Tao, F., Liu, Y. (2023). The advance of digital twin for predictive maintenance: The role and function of machine learning. Journal of Manufacturing Systems, 71, 581-594. https://doi.org/10.1016/j.jmsy.2023.10.010Matzka, S. (2020). Explainable artificial intelligence for predictive maintenance applications. In Third International Conference on Artificial Intelligence for Industries (AI4I) (pp. 69-74). IEEE. https://doi.org/10.1109/AI4I49448.2020.00023Skowron, M. (2024). Transfer learning-based fault detection system of permanent magnet synchronous motors. IEEE Access, 12, 135372-135389. https://doi.org/10.1109/ACCESS.2024.3463970Chen, C., Fu, H., Zheng, Y., Tao, F., Liu, Y. (2023). The advance of digital twin for predictive maintenance: The role and function of machine learning. Journal of Manufacturing Systems, 71, 581-594. https://doi.org/10.1016/j.jmsy.2023.10.010Radionov, A. A., Liubimov, I. V., Yachikov, I. M., Abdulveleev, I. R., Khramshina, E. A., & Karandaev, A. S. (2023). Method for forecasting the remaining useful life of a furnace transformer based on online monitoring data. Energies, 16(12), 4630. https://doi.org/10.3390/en16124630Skowron, M. (2024). Transfer learning-based fault detection system of permanent magnet synchronous motors. IEEE Access, 12, 135372-135389. https://doi.org/10.1109/ACCESS.2024.3463970Theissler, A., Pérez-Velázquez, J., Kettelgerdes, M., & Elger, G. (2021). Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry. Reliability Engineering & System Safety, 215, 107864. https://doi.org/10.1016/j.ress.2021.107864Radionov, A. A., Liubimov, I. V., Yachikov, I. M., Abdulveleev, I. R., Khramshina, E. A., & Karandaev, A. S. (2023). Method for forecasting the remaining useful life of a furnace transformer based on online monitoring data. Energies, 16(12), 4630. https://doi.org/10.3390/en16124630Theissler, A., Pérez-Velázquez, J., Kettelgerdes, M., & Elger, G. (2021). Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry. Reliability Engineering & System Safety, 215, 107864. https://doi.org/10.1016/j.ress.2021.107864Theissler, A., Pérez-Velázquez, J., Kettelgerdes, M., & Elger, G. (2021). Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry. Reliability Engineering & System Safety, 215, 107864. https://doi.org/10.1016/j.ress.2021.107864

The authors declare that there are no conflicts of interest present.