INTELLIGENT SYSTEMS FOR DIAGNOSTICS AND MONITORING OF POWER EQUIPMENT
This article provides a review of methods for collecting and analyzing data characterizing the operating modes of key equipment in electric power systems. Using this information to model virtual replicas of power equipment (digital twins) provides a comprehensive assessment of the condition of electrical machines and devices in real time. This approach will ultimately enable a transition to predictive maintenance, reducing the likelihood of failures and increasing the reliability of power complexes. Examples of using multifunctional sensor systems to monitor the condition of turbogenerators, transformers, and high-voltage equipment are provided. It is shown that optimizing transformer and generator repairs through the transition to predictive maintenance reduces operating costs by 20–25 %. The limitations and prospects for integrating digital technologies into the energy sector are discussed to ensure sustainable energy consumption, minimize accidents, and digitalize the Russian energy sector.