Darko Babunski

Darko Babunski

Auto-generated profile, based on publicly available information

Darko Babunski

Department of Hydraulic Engineering and Automation, Macedonia, Faculty of Mechanical Engineering in Skopje, Macedonia, Ss. Cyril and Methodius University in Skopje, 1000 Skopje, North Macedonia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Energija Ekonomija Ekologija
Verified
Journal Article
Closed access
Radmila KolevaRadmila Koleva
Radmila Koleva
DBDarko Babunski
Darko Babunski
EZEmil Zaev
Emil Zaev
ATAtanasko Tuneski
Atanasko Tuneski
LTLaze Trajkovski
Laze Trajkovski
A new approach to efficient, faster, and intelligent hydropower plant (HPP) control, where constituent equipment is described with highly non-linear mathematical models based on the recommendation from the working group of IEEE on prime movers, is represented in this paper. HPP stability and high efficiency are important factors dependent on the dynamic changes in the energy system demands and the starting time of the plant because the obtained energy is very flexible to those changes in the energy system. This paper is shown and analysed the implementation of the artificial neural network-based controller with PID as an auxiliary controller which helped achieve better behaviour, faster plant stabilization, and operation. The benefits of new technologies and possibilities led to improvements in HPP control and faster system operation. This is achieved by using MATLAB® – Deep Learning Toolbox whereas the simulations are prepared in Simulink. Artificial Neural Networks (ANN) as a technique used in the HPP control systems have advantages in getting a stable and faster response but the complexity of the structure behind the neural networks (NN), meaning algorithms, number of hidden layers, training function, activation function can complicate and destabilize the process. In this paper, the focus is put on the mechanical power responses improvement and the advantages of implementing new technologies contrary to the problems that can occur by using them such as plant destabilization by implementing minor changes, fitting parameters, learning, and training processes, number of hidden layers/neurons, number of epochs, etc.

20 January 2026 in Water
Verified
Journal Article
Open access
PDF file
MLMarija Lazarevikj
Marija Lazarevikj
Radmila KolevaRadmila Koleva
Radmila Koleva
EZEmil Zaev
Emil Zaev
DBDarko Babunski
Darko Babunski
Zoran MarkovZoran Markov
Zoran Markov
Besides the purification process in the wastewater treatment plant that includes mechanical, biological, and chemical approaches, analysis of hydraulic behavior is also fundamental. This means developing a digital replica of the physical process by simulating the hydraulic parameters. Studying fluid behavior in the plant enables process optimization, improves plant behavior, prevents equipment malfunctions, and more. This paper focuses on defining the concept of a wastewater treatment plant prototype, simulating it, and identifying the available and most suitable software that enables efficient process simulation and validation. The hydraulic parameters, as per the literature review and the proposed concept, that will be simulated are pressure, flow, pressure drop, and water level. MATLAB/Simulink and Python programming languages are considered the most suitable software/programming languages for hydraulic parameters simulation.

31 March 2025 in Precision Mechanics & Digital Fabrication
Verified
Journal Article
Open access
PDF file
Radmila KolevaRadmila Koleva
Radmila Koleva
DBDarko Babunski
Darko Babunski
EZEmil Zaev
Emil Zaev
The accurate determination of the conduit water starting time constant ($T_w$) is critical for optimizing hydro turbine performance and dynamic control in hydropower plants. Instead of relying on conventional calculation methods, machine learning (ML) techniques, specifically long short-term memory (LSTM) networks and multilayer perceptron (MLP) models, have been employed to identify $T_w$. The dataset used for model training and validation comprises real operational data collected from two hydropower plants. The effectiveness of both algorithms in $T_w$ identification has been evaluated through simulation, with Python serving as the primary programming environment. The findings indicate that, despite its more complex architecture, LSTM does not necessarily yield superior results. In contrast, MLP, as a relatively simpler model, demonstrates greater accuracy in estimating $T_w$, suggesting that intricate network structures are not always required for precise identification. Additionally, an optimization function ($F_\text{opt}$) has been utilized to assess the reliability of the identified $T_w$ values by comparing them with actual hydro turbine responses. The results underscore the practicality of MLP in hydropower system modeling, providing a computationally efficient alternative for conduit water starting time constant identification. These insights contribute to improving real-time turbine control and enhancing the efficiency of hydropower generation.

13 November 2026 in Water
Verified
Journal Article
Open access
PDF file
Radmila KolevaRadmila Koleva
Radmila Koleva
MLMarija Lazarevikj
Marija Lazarevikj
EZEmil Zaev
Emil Zaev
DBDarko Babunski
Darko Babunski
Zoran MarkovZoran Markov
Zoran Markov
Water management is essential for ensuring the reliable and efficient use of available water resources, while water supply systems depend on the coordinated operation of pipelines, pumps, reservoirs, and storage tanks. Accurate modeling of these systems is important for predicting their hydraulic behavior under different operating conditions. This study investigates the filling process of a frustum-shaped tank in a laboratory water supply system through experimental measurements and one-dimensional numerical modeling in both MATLAB/Simulink Version 2021a and AFT Impulse 4. The laboratory setup includes a lower storage tank, an elevated conical tank, a centrifugal pump, and the pipeline network. The variation of the water level in the upper tank was recorded during the experiment and used for model validation. In the numerical models, the upper tank was represented with a variable cross-section corresponding to its physical dimensions. Experimental repeatability was assessed using three accepted filling runs, which showed good agreement over the complete filling interval, with a mean coefficient of variation of approximately 1.36%. The representative experimental response was obtained by averaging the filtered runs and was used for numerical model validation. Among the evaluated approaches, the MATLAB first-order decay model provided the closest agreement with the experimental response, with MAE = 0.0276 L, RMSE = 0.0317 L, and MAPE = 4.87%. The results indicate that the developed model can closely reproduce the main filling behavior of a frustum tank and can be applied to the analysis of similar laboratory-scale water supply and storage systems.