MACHINE LEARNING TECHNOLOGIES IN PREDICTING VEHICLE ENGINE MAINTENANCE IN MILITARY LOGISTICS
Keywords:
artificial intelligence, machine learning, military logisticsAbstract
This study examines the prospects for the introduction of artificial intelligence (AI) technologies in the field of maintenance of logistics vehicles used by the armed forces. Modern challenges of military logistics require high reliability, responsiveness, and maximum readiness of equipment to perform tasks in various conditions. In this regard, predictive maintenance approaches are of particular importance, as they allow for the detection of potential malfunctions before they occur. Unlike traditional methods that are based on a routine approach or response to existing breakdowns, predictive maintenance uses machine learning capabilities to analyze large amounts of sensor data in real time. This creates the conditions for flexible, dynamic, and more efficient strategies for the operation of equipment. Logistics transport, which is a key component of logistics support – transportation of ammunition, fuel, food, equipment, and personnel – must be not only functional but also as accessible as possible for use at any time. In this context, the use of AI minimizes the risk of sudden failures and reduces the workload of repair units. In addition, automated systems for analyzing technical condition provide an increase in the accuracy of forecasts, which, in turn, improves mission planning and logistics operations.This includes the need for standardized sensor systems, secure data transmission channels, and cyber resilience, as data leakage or manipulation in a military environment can have critical consequences. Despite these challenges, the potential of AI in logistics transport services opens new horizons for improving efficiency, cost-effectiveness, and readiness of equipment for combat and logistics missions. This approach forms the basis for the transition to a new model of technical management based on intelligent analytics, flexibility, and proactive decision-making.
References
Mobley R. K. An introduction to predictive maintenance. Amsterdam : Elsevier, 2002.
Narayanan T. S. A., Padhy S. C. Artificial Intelligence for Predictive Maintenance of Armoured Fighting Vehicles Engine. Indian Journal of Artificial Intelligence and Neural Networking (IJAINN). 2023. Vol. 3, No. 5.
Sengupta P., Mehta A., Rana P. S. Predictive Maintenance of Armoured Vehicles using Machine Learning Approaches [Електронний ресурс]. DOI: https://doi.org/10.48550/arXiv.2307.14453
Samatas G.G., Moumgiakmas S.S., Papakostas G.A. Predictive Maintenance – Bridging Artificial Intelligence and IoT // Proceedings of the 2021 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA, 10–13 May 2021. Piscataway, NJ : IEEE, 2021. P. 413–419.
Xu G., Liu M., Wang J. та ін. Data-driven fault diagnostics and prognostics for predictive maintenance: A brief overview // Proceedings of the 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), Vancouver, Canada, 22–26 August 2019. Piscataway, NJ : IEEE, 2019. P. 103–108.
Longo N., Serpi V., Jacazio G., Sorli M. Model-based predictive maintenance techniques applied to the automotive industry // PHM Society European Conference. 2018. Vol. 4. Utrecht, The Netherlands, 3–6 July 2018.
Xiao Z., Cheng Z., Li Y. A review of fault diagnosis methods based on machine learning patterns // 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing). 2021. P. 1–4.
Theissler A., Perez-Velázquez J., Kettelgerdes M., Elger G. Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry // Reliability Engineering & System Safety. 2021. Vol. 215. P. 107864.
Torcianti A., Matzka S. Explainable artificial intelligence for predictive maintenance applications using a local surrogate model // 4th International Conference on Artificial Intelligence for Industries (AI4I). 2021. P. 86–88.
Zhang W., Yang D., Wang H. Data-driven methods for predictive maintenance of industrial equipment: A survey // IEEE Systems Journal. 2019. Vol. 13, No. 3. P. 2213–2227.
Souza R. M., Nascimento E. G. S., Miranda U. A. та ін. Deep learning for diagnosis and classification of faults in industrial rotating machinery // Computers & Industrial Engineering. 2021. Vol. 153. P. 107060.
Longo N., Serpi V., Jacazio G., Sorli M. Model-based predictive maintenance techniques applied to the automotive industry // PHM Society European Conference. 2018. Vol. 4. Utrecht, The Netherlands, 3–6 July 2018.
Tessaro I., Mariani V. C., Coelho L. S. Machine learning models applied to predictive maintenance in automotive engine components // Proceedings. 2020. Vol. 64. P. 26.
Furch J., Turo T., Krobot Z., Stastny J. Using telemetry for maintenance of special military vehicles // Intelligent Systems in Production Engineering and Maintenance. 2018. P. 267–275. DOI: 10.1007/978-3-319-76072-8_28
Virca I., Badea D. Study on the Predictive Maintenance of Vehicles and its Management Using the Specific “Keep the Machine Running” Application // International conference KNOWLEDGE-BASED ORGANIZATION. 2019. Vol. 25. P. 291–297. DOI: 10.2478/kbo-2019-0048
