Nikola Miladinović
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nikola Miladinović has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Filip Kilibarda
Nikola Tesla Institute of Electrical Engineering, University of Belgrade, Koste Glavinica 8a, 11040 Belgrade, Serbia
2 shared publications - Uroš Radoman
Nikola Tesla Institute of Electrical Engineering, University of Belgrade, Belgrade, Serbia
2 shared publications - Vladimir Polužanski
School of Electrical Engineering, University of Belgrade, 73 Kralja Aleksandra Boulevard, 11120 Belgrade, Serbia
2 shared publications - Aleksandar Žigić
Univerzitet u Beogradu Elektrotehnički institut Nikola Tesla Koste Glavinića 8a 11000 Beograd Srbija
1 shared publication - Blagoje Babić1 shared publication
- Branko Pejović
Univerzitet u Beogradu Elektrotehnički institut Nikola Tesla Koste Glavinića 8a 11000 Beograd Srbija
1 shared publication
Latest Publications
- Open Access
- 29 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8607
Predictive Maintenance of Hydro Turbine-Generator Units: A Review
Reliable operation of hydro turbine-generator units (HTGUs) is central to safe, flexible, and efficient hydropower generation. State-of-the-art approaches to condition monitoring, fault diagnosis, and early fault detection increasingly rely on artificial intelligence (AI)-driven methods. However, labeled fault data remain scarce and industrial validation of these AI methods remains limited. This paper presents a systematic, algorithm-focused review of predictive maintenance (PdM) for HTGUs. Using a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-guided literature search, we map data-driven and AI-enabled methods from classical machine learning through deep Autoencoders and hybrids to Transformers and state-space models (SSMs), and we compare them with respect to their interpretability, data requirements, and industrial deployability. Relative to plant-wide sensing surveys and generator-centric AI reviews, the contribution is an HTGU-wide assessment of which method families are validated on operational plants versus rotating-machinery benchmarks. Across the reviewed studies, several general patterns emerge: hydropower-specific work is dominated by unsupervised anomaly detection, classical machine learning approaches remain a strong, plant-validated baseline, and high accuracies of recent Transformer/SSM architectures should be interpreted as architectural potential on related assets, not as demonstrated HTGU deployability. We translate the identified gaps into a short-/medium-/long-term roadmap toward transferable, explainable, and industrially validated PdM.
- 29 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8607
Open AccessPredictive Maintenance of Hydro Turbine-Generator Units: A Review
Reliable operation of hydro turbine-generator units (HTGUs) is central to safe, flexible, and efficient hydropower generation. State-of-the-art approaches to condition monitoring, fault diagnosis, and early fault detection increasingly rely on artificial intelligence (AI)-driven methods. However, labeled fault data remain scarce and industrial validation of these AI methods remains limited. This paper presents a systematic, algorithm-focused review of predictive maintenance (PdM) for HTGUs. Using a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-guided literature search, we map data-driven and AI-enabled methods from classical machine learning through deep Autoencoders and hybrids to Transformers and state-space models (SSMs), and we compare them with respect to their interpretability, data requirements, and industrial deployability. Relative to plant-wide sensing surveys and generator-centric AI reviews, the contribution is an HTGU-wide assessment of which method families are validated on operational plants versus rotating-machinery benchmarks. Across the reviewed studies, several general patterns emerge: hydropower-specific work is dominated by unsupervised anomaly detection, classical machine learning approaches remain a strong, plant-validated baseline, and high accuracies of recent Transformer/SSM architectures should be interpreted as architectural potential on related assets, not as demonstrated HTGU deployability. We translate the identified gaps into a short-/medium-/long-term roadmap toward transferable, explainable, and industrially validated PdM.
- Open Access
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
- No. 00,p. 2
Design and implementation of the software architecture for a rotor pole temperature monitoring system at the Đerdap 2 hydroelectric power plant
The paper presents the architecture of a software system for monitoring rotor pole temperature in the Đerdap 2 hydropower plant. The system is implemented using the .NET 10 platform and is based on a layered architecture with the application of the repository pattern, enabling clear separation of responsibilities between system components. Data collected from sensors are stored in an SQL database using ADO.NET technology. Special emphasis is placed on security, scalability, and the potential for further system development in real industrial environments. The contribution of this work lies in defining a customized layered architecture for an industrial monitoring system, which enables efficient processing of a large amount of measurement data in real time, along with the application of the MVVM pattern for organizing the user interface and improving the separation of the presentation layer.
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
- No. 00,p. 2
Open AccessDesign and implementation of the software architecture for a rotor pole temperature monitoring system at the Đerdap 2 hydroelectric power plant
The paper presents the architecture of a software system for monitoring rotor pole temperature in the Đerdap 2 hydropower plant. The system is implemented using the .NET 10 platform and is based on a layered architecture with the application of the repository pattern, enabling clear separation of responsibilities between system components. Data collected from sensors are stored in an SQL database using ADO.NET technology. Special emphasis is placed on security, scalability, and the potential for further system development in real industrial environments. The contribution of this work lies in defining a customized layered architecture for an industrial monitoring system, which enables efficient processing of a large amount of measurement data in real time, along with the application of the MVVM pattern for organizing the user interface and improving the separation of the presentation layer.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
- No. 34,p. 61-82
Concept and application of Digital Twins for oil-immersed power transformers
This paper provides a literature review and establishes the state-of-the-art in the concept and application of Digital Twin (DT) technology to power transformers. The introductory sections focus on the evolving definition and universal concepts of DT, independent of specific fields of application, as well as the goals of Industry 4.0 and the technologies that enable digital transformation in industry. Special attention is given to the particularities of the power industry, with an emphasis on the unique requirements posed by the nature and importance of oil-filled power transformers, which serve as the foundation for the development of systems based on DT technologies.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Zbornik Radova, Elektrotehnicki Institut Nikola Tesla
- No. 34,p. 61-82
Open AccessConcept and application of Digital Twins for oil-immersed power transformers
This paper provides a literature review and establishes the state-of-the-art in the concept and application of Digital Twin (DT) technology to power transformers. The introductory sections focus on the evolving definition and universal concepts of DT, independent of specific fields of application, as well as the goals of Industry 4.0 and the technologies that enable digital transformation in industry. Special attention is given to the particularities of the power industry, with an emphasis on the unique requirements posed by the nature and importance of oil-filled power transformers, which serve as the foundation for the development of systems based on DT technologies.