Nikola Tesla Institute
Dr. Vladimir Polužanski
Monitoring of Wind Power Plant Generators / Predictive Maintenance of Hydro Units: A Data-Driven Approach
Abstract: Monitoring of Wind Power Plant Generators
This paper examines the key electrical equipment of wind power plants, with particular emphasis on the generator as one of the most critical and heavily loaded components of the electricity generation system. The generator represents the central element in the conversion of wind mechanical energy into electrical energy, and its reliability directly affects the efficiency, availability, and economic viability of wind farm operation. In this context, generator monitoring is presented as an integral part of the predictive maintenance concept, aimed at early fault detection, reduction of unplanned downtime, and optimization of maintenance costs throughout the entire lifecycle of the facility. The study analyzes advanced condition monitoring techniques that generate relevant data for further processing, statistical evaluation, and modeling. These include: (a) vibration measurement and analysis for detecting mechanical irregularities, rotor imbalance, and bearing damage; (b) oil residue measurement and analysis to monitor wear and identify the presence of metallic particles as indicators of internal faults; (c) temperature monitoring of windings, bearings, and cooling systems to assess overload conditions and insulation degradation; (d) stress measurement using strain gauges to evaluate mechanical loads on structural components; and (e) acoustic measurement and analysis for identifying operational anomalies and unusual sound patterns. Special emphasis is placed on the integration of these parameters into a unified system for continuous condition monitoring and decision support. The application of artificial intelligence in generator monitoring is also presented, including the use of machine learning algorithms, neural networks, and deep learning methods for pattern recognition, fault prediction, and automatic classification of equipment condition. Data-driven models based on large datasets improve diagnostic accuracy, reduce false alarms, and enhance condition-based maintenance strategies. Furthermore, the paper addresses cybersecurity aspects of wind power plant information and operational systems, including the protection of SCADA systems, communication protocols, and industrial control systems from potential cyber threats. The importance of implementing security standards, network segmentation, access control mechanisms, and continuous security monitoring is emphasized to ensure safe, reliable, and resilient operation as part of critical energy infrastructure. Finally, the economic justification for implementing advanced monitoring systems is analyzed through a cost–benefit perspective, highlighting reduced downtime and extended generator lifespan. The significance of data standardization, system interoperability, and integration within smart grid concepts is underscored in the context of sustainable development.
Keywords: wind farm, generator, monitoring, tracking techniques, artificial intelligence, cybersecurity
Abstract: Predictive Maintenance of Hydro Units: A Data-Driven Approach
In modern power systems, hydropower plants play a crucial role. Considering their irreplaceable functions in providing fast system response, balancing variable energy sources, and integrating an increasing share of renewable energy, their importance is expected to continue growing in the future. The central element of every hydropower plant is the hydro unit, a complex electromechanical system comprising the generator, turbine, and auxiliary equipment, whose unplanned failures can lead to significant economic losses, reduced system reliability, and disruptions in electricity supply. In addition to direct losses, such failures may also cause secondary effects, including increased balancing costs and additional stress on other generation capacities. The development of modern information and communication technologies and advanced analytical methods represents a key prerequisite for the modernization of hydropower plant operation and the transition toward intelligent control and maintenance systems. The integration of diverse data sources, their centralization, and advanced processing enable a deeper understanding of system behavior and support real-time decision-making. Improving maintenance strategies for hydro units and associated equipment requires a transition from traditional approaches, based on periodic inspections or reactive maintenance, to more advanced concepts such as Condition-Based Maintenance (CBM). This approach relies on the analysis of large volumes of data collected from various sources, including SCADA systems, monitoring systems, dedicated sensors, and results of periodic testing, to continuously assess the current condition of the equipment (data-driven approach). This enables the timely identification of deviations from normal operation, early detection of degradation indicators, and data-driven decision-making for planning and executing maintenance activities, thereby reducing the risk of unplanned failures. A specific subset of CBM strategies is Predictive Maintenance (PdM), which utilizes advanced algorithms based on machine learning and artificial intelligence to forecast degradation trends and estimate the remaining useful life of hydro units. These models enable not only anomaly detection but also the prediction of potential failures before they occur, significantly reducing the risk of unplanned outages, increasing system availability, and optimizing overall maintenance costs. Within the poster session, the conceptual design and key functionalities of a dedicated predictive maintenance solution for hydro units (Ægir), developed by the US-based company Elder Research, will be presented. The Ægir platform enables advanced analytics, early diagnostics, and decision support in real-world operational environments. Based on previous experience with the application of the Ægir platform, its implementation is expected to contribute to increased reliability and availability of hydro units, as well as to the overall efficiency improvement of the power system.
Keywords: hydrogenerator, diagnostics, predictive maintenance, AI
Biography of the presenter
Dr. Vladimir Polužanski is the Head of the Office for Digitalization and AI Implementation at the Nikola Tesla Institute of Electrical Engineering JSC Belgrade, one of the leading research and development institutes in the field of electrical engineering in the region. He obtained his PhD in Artificial Intelligence at the School of Electrical Engineering, University of Belgrade, within the Software Engineering program. His work focuses on the application of advanced analytical methods and artificial intelligence in the energy sector, with a particular emphasis on the digitalization of power systems, predictive maintenance, and the development of digital twins. He is currently leading an R&D pilot project aimed at introducing a new concept of hydropower unit maintenance for EPS AD, implemented in collaboration with partners from the United States of America. He is certified as an ISO/IEC 27001:2022 auditor and is actively engaged in information security topics in the context of critical infrastructure. He also actively participates in the SAIGE project of the Ministry of Science, Technological Development and Innovation, implemented with the support of the World Bank and the European Union, aimed at strengthening capacities for innovation and technology transfer.