This paper presents a model for intelligent management of vehicle fleets and service networks based on the integration of digital twins and predictive analytics. The proposed framework combines data obtained from optical diagnostics, telemetric systems, and operational records into a unified analytical platform linking vehicle-level and network-level monitoring.The study describes the architecture for constructing digital twins, mechanisms for multisensor data fusion, and methods for predicting technical degradation of key vehicle components and assemblies. The presented approach supports reliable management decision-making, reduces unplanned downtime, and improves the efficiency of maintenance and service processes.The results confirm the potential of adaptive digital twin technologies and predictive models for enhancing operational reliability and forming the foundation of intelligent service ecosystems in the automotive industry.
Evgeny Popov (Mon,) studied this question.