МЕТОД ПРОГНОЗУВАННЯ ТЕХНІЧНОГО СТАНУ ТРАНСПОРТНИХ ЗАСОБІВ ІЗ ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ ВЕЛИКИХ ДАНИХ
Системи управління, навігації та зв’язку. Збірник наукових праць · 04.05.2026 · 2 (84) · 20-27
DOI: 10.26906/sunz.2026.2.020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Системи управління, навігації та зв’язку. Збірник наукових праць, online erschienen am 04.05.2026. Verfasst von Illia Skliarov und 1 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Relevance. The relevance of the study is determined by the need to improve the efficiency of service technologies in the automotive industry under conditions of growing volumes of telematics, diagnostic, and operational data accompanying the functioning of modern vehicles. Modern automobiles are characterized by a complex structure of technical systems, the presence of a large number of interconnected components, the heterogeneity of operating modes, and an increased risk of failures, which complicates the timely assessment of their technical condition. Existing approaches to forecasting the technical condition of automobiles mostly do not ensure the comprehensive consideration of streaming sensor data, maintenance history, and operational parameters, which complicates the substantiated decision-making process regarding service actions. Therefore, the development of a method for forecasting the technical condition of automobiles based on Big Data is relevant for supporting the timely detection of risky conditions and optimizing maintenance. Purpose of the article is to develop a method for forecasting the technical condition of automobiles based on Big Data technologies through the integration of streaming sensor data, maintenance history, and operational parameters for the timely detection of probable failures, improvement of the accuracy of assessing the technical condition of vehicles, and optimization of service decisions. Object of research is the process of forecasting the technical condition of automobiles in service maintenance systems based on the analysis of large volumes of heterogeneous data. Subject of research is methods, models, and tools for forecasting the technical condition of automobiles based on Big Data through the integration of sensor, operational, and service data. Research results. The study addresses the problem of forecasting the technical condition of automobiles based on Big Data in order to improve the efficiency of service technologies in the automotive industry. A method is proposed that involves the integration of operational, sensor, and service data within a unified analytical framework for assessing the risk of failures. The method was implemented in Python in the Google Colab environment using the open SCANIA Component X dataset. In the course of the study, data preparation, elimination of target variable leakage, construction of a predictive model, adjustment of the classification threshold, and formation of service decisions were carried out. The obtained results confirmed the high quality of forecasting and the suitability of the proposed approach for use in tasks supporting vehicle maintenance.
Zitieren
APA
Skliarov, I., & Herevych, M. (2026). МЕТОД ПРОГНОЗУВАННЯ ТЕХНІЧНОГО СТАНУ ТРАНСПОРТНИХ ЗАСОБІВ ІЗ ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ ВЕЛИКИХ ДАНИХ. Системи управління, навігації та зв’язку. Збірник наукових праць, 2(84), 20-27. https://doi.org/10.26906/sunz.2026.2.020
Vancouver
Skliarov I, Herevych M. МЕТОД ПРОГНОЗУВАННЯ ТЕХНІЧНОГО СТАНУ ТРАНСПОРТНИХ ЗАСОБІВ ІЗ ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ ВЕЛИКИХ ДАНИХ. Системи управління, навігації та зв’язку. Збірник наукових праць. 2026;2(84):20-27. doi:10.26906/sunz.2026.2.020
BibTeX
@article{Skliarov2026,
author = {Skliarov, Illia and Herevych, Mykhailo},
title = {МЕТОД ПРОГНОЗУВАННЯ ТЕХНІЧНОГО СТАНУ ТРАНСПОРТНИХ ЗАСОБІВ ІЗ ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ ВЕЛИКИХ ДАНИХ},
journal = {Системи управління, навігації та зв’язку. Збірник наукових праць},
year = {2026},
volume = {2},
number = {84},
pages = {20--27},
doi = {10.26906/sunz.2026.2.020}
}
EUVIMED