Leonid Kulakovskyi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Leonid Kulakovskyi has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Alla Bosak
National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute, 37, Beresteiskyi Ave., Kyiv, 03056, Ukraine
4 shared publications - Dmytro Matushkin
General Energy Institute, National Academy of Science of Ukraine, Kyiv, Ukraine
2 shared publications - Nataliya Chornomaz
Тернопільський національний технічний університет імені Івана Пулюя
2 shared publications - Oleksandr Matviiuk
National University Of Water And Environmental Engineering
2 shared publications - Sviatoslav Homon
The National University of Water and Environmental Engineering
2 shared publications - Tetiana Dovbenko
Національний університет водного господарства та природокористування
2 shared publications
Latest Publications
- 28 March 2026
- Published by Vidnovluvana energetika in Vidnovluvana energetika
- No. 1(84)
STATE OF HEALTH (SOH) ESTIMATION FOR EMBEDDED BATTERY MANAGEMENT SYSTEMS: A COMPARATIVE ANALYSIS OF COMPUTATIONALLY EFFICIENT METHODS
Accurate State of Health (SOH) estimation is critically important for the safe and long-term operation of lithium-ion batteries. However, the implementation of estimation algorithms in embedded Battery Management Systems (BMS) is significantly limited by available computational resources. This paper presents a scientifically grounded comparative analysis of two computationally efficient machine learning methods – Support Vector Regression (SVR) and Random Forest – to determine the optimal algorithm for practical implementation, with a dual focus on prediction accuracy and computational efficiency. Based on an open dataset, systematic hyperparameter tuning with GridSearchCV and cross-validation was conducted for both models. The performance of the final, optimized models was evaluated by accuracy metrics (RMSE, MAE) and indicators of suitability for embedded systems (forecasting time, model size). The results showed that even after thorough optimization, the SVR model demonstrated higher prediction accuracy (RMSE 2.67% vs. 3.08% for Random Forest). An even more significant advantage was found in the efficiency analysis: SVR was found to be almost 170 times faster (forecast time of 0.119 ms vs 20.570 ms) and 200 times more compact (model size 8.6 kB vs 1718.6 kB). It is concluded that, for the problem of estimating SOH based on cyclic data, the SVR model is the optimal candidate for practical implementation in embedded BMS. It offers the best balance of high accuracy and minimal hardware resource requirements, outperforming Random Forest across all key criteria for engineering practice.
- 28 March 2026
- Published by Vidnovluvana energetika in Vidnovluvana energetika
- No. 1(84)
STATE OF HEALTH (SOH) ESTIMATION FOR EMBEDDED BATTERY MANAGEMENT SYSTEMS: A COMPARATIVE ANALYSIS OF COMPUTATIONALLY EFFICIENT METHODS
Accurate State of Health (SOH) estimation is critically important for the safe and long-term operation of lithium-ion batteries. However, the implementation of estimation algorithms in embedded Battery Management Systems (BMS) is significantly limited by available computational resources. This paper presents a scientifically grounded comparative analysis of two computationally efficient machine learning methods – Support Vector Regression (SVR) and Random Forest – to determine the optimal algorithm for practical implementation, with a dual focus on prediction accuracy and computational efficiency. Based on an open dataset, systematic hyperparameter tuning with GridSearchCV and cross-validation was conducted for both models. The performance of the final, optimized models was evaluated by accuracy metrics (RMSE, MAE) and indicators of suitability for embedded systems (forecasting time, model size). The results showed that even after thorough optimization, the SVR model demonstrated higher prediction accuracy (RMSE 2.67% vs. 3.08% for Random Forest). An even more significant advantage was found in the efficiency analysis: SVR was found to be almost 170 times faster (forecast time of 0.119 ms vs 20.570 ms) and 200 times more compact (model size 8.6 kB vs 1718.6 kB). It is concluded that, for the problem of estimating SOH based on cyclic data, the SVR model is the optimal candidate for practical implementation in embedded BMS. It offers the best balance of high accuracy and minimal hardware resource requirements, outperforming Random Forest across all key criteria for engineering practice.
- Open Access
- 30 June 2025
- Published by Vidnovluvana energetika in Vidnovluvana energetika
- No. 2(81),p. 114-125
ГІБРИДНИЙ ПІДХІД ДО ВІДСТЕЖЕННЯ МАКСИМАЛЬНОЇ ТОЧКИ ПОТУЖНОСТІ У ФОТОЕЛЕКТРИЧНИХ СИСТЕМАХ
Стаття досліджує гібридний підхід до відстеження максимальної точки потужності (MPPT) у фотоелектричних системах, зосереджуючись на підвищенні ефективності та стабільності методів. Обговорюються різноманітні алгоритми MPPT, як-от Perturb and Observe (P&O), Incremental Conductance (INC) і Double Increment (DM), у поєднанні зі штучними нейронними мережами (ANN) та алгоритмом оптимізації рою частинок (PSO). Використання реальних даних сонячної електростанції дозволило провести комп’ютерне моделювання для оптимізації параметрів системи. Результати аналізу демонструють, що кожен метод має свої особливості, що дозволяє вибрати оптимальний підхід залежно від критеріїв, таких як продуктивність, стабільність та швидкість реакції. Отримані висновки можуть бути корисними для проєктування та налаштування PV-систем в умовах реальної експлуатації, особливо у змінних погодних умовах.
- 30 June 2025
- Published by Vidnovluvana energetika in Vidnovluvana energetika
- No. 2(81),p. 114-125
Open AccessГІБРИДНИЙ ПІДХІД ДО ВІДСТЕЖЕННЯ МАКСИМАЛЬНОЇ ТОЧКИ ПОТУЖНОСТІ У ФОТОЕЛЕКТРИЧНИХ СИСТЕМАХ
Стаття досліджує гібридний підхід до відстеження максимальної точки потужності (MPPT) у фотоелектричних системах, зосереджуючись на підвищенні ефективності та стабільності методів. Обговорюються різноманітні алгоритми MPPT, як-от Perturb and Observe (P&O), Incremental Conductance (INC) і Double Increment (DM), у поєднанні зі штучними нейронними мережами (ANN) та алгоритмом оптимізації рою частинок (PSO). Використання реальних даних сонячної електростанції дозволило провести комп’ютерне моделювання для оптимізації параметрів системи. Результати аналізу демонструють, що кожен метод має свої особливості, що дозволяє вибрати оптимальний підхід залежно від критеріїв, таких як продуктивність, стабільність та швидкість реакції. Отримані висновки можуть бути корисними для проєктування та налаштування PV-систем в умовах реальної експлуатації, особливо у змінних погодних умовах.
- 21 September 2024
- Published by Springer Nature
- p. 77-97
Optimization of Double Inverter-Feed Drive Work According to Minimum of Dynamic Error Criteria
- 21 September 2024
- Published by Springer Nature
- p. 77-97
Optimization of Double Inverter-Feed Drive Work According to Minimum of Dynamic Error Criteria
- 1 August 2022
- Published by National University of Water and Environmental Engineering in Ресурсоекономні матеріали, конструкції, будівлі та споруди
- No. 40,p. 10-17
ДОСЛІДЖЕННЯ МІЦНІСНИХ ПОКАЗНИКІВ ДЕРЕВИНИ ПІД ВПЛИВОМ АГРЕСИВНОГО СЕРЕДОВИЩА
Розроблено методику експериментальних досліджень деревини осьовимстиском уздовж волокон короткочасним навантаженням за роботи вагресивному середовищі за приростом переміщень. Наведено результатидосліджень граничної міцності з врахуванням фактора агресивностісередовища. Встановлено, що вплив кислот на деревину з різнимтерміном просочення значно зменшує її міцнісні показники.
- 1 August 2022
- Published by National University of Water and Environmental Engineering in Ресурсоекономні матеріали, конструкції, будівлі та споруди
- No. 40,p. 10-17
ДОСЛІДЖЕННЯ МІЦНІСНИХ ПОКАЗНИКІВ ДЕРЕВИНИ ПІД ВПЛИВОМ АГРЕСИВНОГО СЕРЕДОВИЩА
Розроблено методику експериментальних досліджень деревини осьовимстиском уздовж волокон короткочасним навантаженням за роботи вагресивному середовищі за приростом переміщень. Наведено результатидосліджень граничної міцності з врахуванням фактора агресивностісередовища. Встановлено, що вплив кислот на деревину з різнимтерміном просочення значно зменшує її міцнісні показники.
- Open Access
- 11 April 2022
- Published by Kyiv National University of Construction and Architecture in Urban development and spatial planning
- No. 79,p. 87-92
ANALYSIS OF TEST EQUIPMENT FOR INVESTIGATION OF MATERIALS UNDER A STRONG LOAD APPLICATION
An analysis of publications on this topic. It is established that in most literature sources the work of wood is shown only in the ascending branch of deformation, which is a false statement. The method of experimental studies of alder and spruce wood by axial compression along the fibers with a short-term load at standard humidity (by increasing displacements) is presented. The age of the wood was about 40 years. Experimental studies of such samples were performed on a modern STM- 100 test machine. 18 samples with a cross section of 30x30x120 mm were tested. Based on the experiment, complete deformation diagrams “stress σc - strain uc” were constructed and the main parameters were established: critical and residual strains, as well as their corresponding stresses. It is established that both diagrams have an ascending and descending branch, ie they work in both pre-critical and super-critical stages of work. The average critical deformations of alder wood uc,0,d = 0,00397, as well as the corresponding maximum stresses fc,0,d = 35,6 MPa, and spruce wood - uc,0,d = 0,00421 (fc,0,d = 38.1 MPa). Also, the average residual deformations for alder wood uc,fin = 0.277, and the corresponding stresses σc,fin = 3.9 MPa; for spruce wood uc,fin = 0.212, and stress - σc,fin = 3.6 MPa. It is confirmed that deciduous and coniferous wood at standard humidity has an ascending and descending branch, ie works in the subcritical and supercritical stages of work. In the future it is necessary to conduct such experimental studies for other deciduous and coniferous species. In the future, determined mechanical characteristics experimentally, it is necessary to propose methods for finding and theoretical, which will give a complete picture of such materials.
- 11 April 2022
- Published by Kyiv National University of Construction and Architecture in Urban development and spatial planning
- No. 79,p. 87-92
Open AccessANALYSIS OF TEST EQUIPMENT FOR INVESTIGATION OF MATERIALS UNDER A STRONG LOAD APPLICATION
An analysis of publications on this topic. It is established that in most literature sources the work of wood is shown only in the ascending branch of deformation, which is a false statement. The method of experimental studies of alder and spruce wood by axial compression along the fibers with a short-term load at standard humidity (by increasing displacements) is presented. The age of the wood was about 40 years. Experimental studies of such samples were performed on a modern STM- 100 test machine. 18 samples with a cross section of 30x30x120 mm were tested. Based on the experiment, complete deformation diagrams “stress σc - strain uc” were constructed and the main parameters were established: critical and residual strains, as well as their corresponding stresses. It is established that both diagrams have an ascending and descending branch, ie they work in both pre-critical and super-critical stages of work. The average critical deformations of alder wood uc,0,d = 0,00397, as well as the corresponding maximum stresses fc,0,d = 35,6 MPa, and spruce wood - uc,0,d = 0,00421 (fc,0,d = 38.1 MPa). Also, the average residual deformations for alder wood uc,fin = 0.277, and the corresponding stresses σc,fin = 3.9 MPa; for spruce wood uc,fin = 0.212, and stress - σc,fin = 3.6 MPa. It is confirmed that deciduous and coniferous wood at standard humidity has an ascending and descending branch, ie works in the subcritical and supercritical stages of work. In the future it is necessary to conduct such experimental studies for other deciduous and coniferous species. In the future, determined mechanical characteristics experimentally, it is necessary to propose methods for finding and theoretical, which will give a complete picture of such materials.
- Open Access
- 29 October 2021
- Published by Kyiv National University of Construction and Architecture in Urban development and spatial planning
- No. 78,p. 166-172
ANALYSIS OF TEST EQUIPMENT FOR INVESTIGATION OF MATERIALS UNDER A STRONG LOAD APPLICATION
An analysis of modern testing equipment to establish the mechanical properties of different in structure and origin of building materials. As a result, it was established, that the most effective for testing are foreign electromechanical and servo-hydraulic machines of different configurations. It is determined that this type of technical systems allows to study different types of materials, including high-strength, compressive, tensile, bending and other types of loads in accordance with current international regulations. The article analyzes the principles of operation of the universal test machine INSTRON and the universal servo test machine UIT STM 100S. The configuration of such modern technical systems involves the availability of electronic computers and software, which allows testing in automatic mode, program research factors, determine the current and maximum values of mechanical properties of building materials, perform mathematical calculation of characteristics, reproduce information on the device screen, build research diagrams in electronic and printed form. It has been found that the advantages of such test machines are a load of up to 60 tons. It was determined that the universal machine UIT STM 100S is characterized by a large traverse stroke and a wide range of test speeds, which allows to expand the solution of quality control problems in industry. It is also established that the UIT STM 100S has software that includes a standard library of test methods according to regulatory documentation. The advantages of such a machine are the possible expansion of the standard information base necessary for the operation of the standards or the installation of an additional software module that provides the ability into independently supplement the standard library. Given the wide range of measurements of the universal testing machine UIT STM 100S, we envisage its use for the study of deciduous and coniferous wood in modern rigid test mode.
- 29 October 2021
- Published by Kyiv National University of Construction and Architecture in Urban development and spatial planning
- No. 78,p. 166-172
Open AccessANALYSIS OF TEST EQUIPMENT FOR INVESTIGATION OF MATERIALS UNDER A STRONG LOAD APPLICATION
An analysis of modern testing equipment to establish the mechanical properties of different in structure and origin of building materials. As a result, it was established, that the most effective for testing are foreign electromechanical and servo-hydraulic machines of different configurations. It is determined that this type of technical systems allows to study different types of materials, including high-strength, compressive, tensile, bending and other types of loads in accordance with current international regulations. The article analyzes the principles of operation of the universal test machine INSTRON and the universal servo test machine UIT STM 100S. The configuration of such modern technical systems involves the availability of electronic computers and software, which allows testing in automatic mode, program research factors, determine the current and maximum values of mechanical properties of building materials, perform mathematical calculation of characteristics, reproduce information on the device screen, build research diagrams in electronic and printed form. It has been found that the advantages of such test machines are a load of up to 60 tons. It was determined that the universal machine UIT STM 100S is characterized by a large traverse stroke and a wide range of test speeds, which allows to expand the solution of quality control problems in industry. It is also established that the UIT STM 100S has software that includes a standard library of test methods according to regulatory documentation. The advantages of such a machine are the possible expansion of the standard information base necessary for the operation of the standards or the installation of an additional software module that provides the ability into independently supplement the standard library. Given the wide range of measurements of the universal testing machine UIT STM 100S, we envisage its use for the study of deciduous and coniferous wood in modern rigid test mode.
- Open Access
- 27 April 2020
- Published by Igor Sikorsky Kyiv Polytechnic Institute in POWER ENGINEERING: economics, technique, ecology
- No. 4
ANALYSIS OF FACTORS FOR FORECASTING ELECTRIC POWER GENERATION BY SOLAR POWER PLANTS
The new model of the wholesale electricity market in Ukraine causes appearance the market for the day ahead. In this market, the generating company undertakes to supply a certain amount of electricity. So, it is necessary to carry on the most accurate forecast of possible electricity generation by solar power plant (SPP). Generation value depends on certain factors. A brief summary of different influence of parameters on the PV cell performance has been provided. The article analyzes and identifies the factors that should be included in the forecast mathematical model of electricity generation by a solar power plant for a certain short-term period. According to analyzed data from SPP located in the Kyiv region, such parameters are the intensity of solar radiation, temperature and humidity, wind speed, and atmospheric pressure. The degree of influence of these factors on the initial function of electric energy generation were estimated by analyzing the scatter plot diagrams of relationship between parameters and correlation coefficients. Thus, the analysis of the influence of factors on the magnitude of electricity generation allowed to determine the priority of including each of the parameters in the mathematical model of the SPP power forecast. It was established that the influence of certain climate parameters for target function is different in each season. Therefore, in the mathematical model for forecasting electric power generation, it is necessary to take into account seasonality. In addition, the dynamic value change of factors also affects the current magnitude of electricity generation. Moreover, at different times of the year and with different combination of the corresponding values of climatic parameters, this effect may have different magnitudes. Therefore, the data obtained from the last periods before the forecasting should have a greater impact on obtaining the predicted value than the data from previous periods.
- 27 April 2020
- Published by Igor Sikorsky Kyiv Polytechnic Institute in POWER ENGINEERING: economics, technique, ecology
- No. 4
Open AccessANALYSIS OF FACTORS FOR FORECASTING ELECTRIC POWER GENERATION BY SOLAR POWER PLANTS
The new model of the wholesale electricity market in Ukraine causes appearance the market for the day ahead. In this market, the generating company undertakes to supply a certain amount of electricity. So, it is necessary to carry on the most accurate forecast of possible electricity generation by solar power plant (SPP). Generation value depends on certain factors. A brief summary of different influence of parameters on the PV cell performance has been provided. The article analyzes and identifies the factors that should be included in the forecast mathematical model of electricity generation by a solar power plant for a certain short-term period. According to analyzed data from SPP located in the Kyiv region, such parameters are the intensity of solar radiation, temperature and humidity, wind speed, and atmospheric pressure. The degree of influence of these factors on the initial function of electric energy generation were estimated by analyzing the scatter plot diagrams of relationship between parameters and correlation coefficients. Thus, the analysis of the influence of factors on the magnitude of electricity generation allowed to determine the priority of including each of the parameters in the mathematical model of the SPP power forecast. It was established that the influence of certain climate parameters for target function is different in each season. Therefore, in the mathematical model for forecasting electric power generation, it is necessary to take into account seasonality. In addition, the dynamic value change of factors also affects the current magnitude of electricity generation. Moreover, at different times of the year and with different combination of the corresponding values of climatic parameters, this effect may have different magnitudes. Therefore, the data obtained from the last periods before the forecasting should have a greater impact on obtaining the predicted value than the data from previous periods.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 329-333
Impact of EV Chargers on Total Harmonic Distortion in the Distribution System Network
Battery electric cars are mostly charged by on-board chargers, which are connected to the distribution grid. Charging of Electric Vehicles (EVs) increases additional energy demand to the grid. The main goals of each charging strategy are to charge EV in distribution grids with the lowest price electricity, provide stability during charging and prevent over-demand of energy. The main purpose of the research is to show the effect of harmonics of voltage and current on the low voltage network during charging of an EV.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 329-333
Impact of EV Chargers on Total Harmonic Distortion in the Distribution System Network
Battery electric cars are mostly charged by on-board chargers, which are connected to the distribution grid. Charging of Electric Vehicles (EVs) increases additional energy demand to the grid. The main goals of each charging strategy are to charge EV in distribution grids with the lowest price electricity, provide stability during charging and prevent over-demand of energy. The main purpose of the research is to show the effect of harmonics of voltage and current on the low voltage network during charging of an EV.
- 25 November 2015
- Published by Linkoping University Electronic Press
- Vol. 119, 31-41
Optimal Operation of the Peat Drying Process in Steam Tube Dryers
- 25 November 2015
- Published by Linkoping University Electronic Press
- Vol. 119, 31-41
Optimal Operation of the Peat Drying Process in Steam Tube Dryers