Nadezeya V. Hruntovich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nadezeya V. Hruntovich has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Aliaksey A. Kapanski
Department of Power Supply, Sukhoi State Technical University of Gomel, 246746 Gomel, Belarus
5 shared publications - Roman Vladimirovich Klyuev
Moscow Polytechnic University, Moscow, Russian Federation
4 shared publications - Aleksandr E. Boltrushevich
Department of Information Technology, Tomsk Polytechnic University, 634050 Tomsk, Russia
2 shared publications - Anton Y. Demin
Department of Information Technology, Tomsk Polytechnic University, 634050 Tomsk, Russia
2 shared publications - Nikita Vladimirovich Martyushev
Department of Information Technology, Tomsk Polytechnic University, 634050 Tomsk, Russia
2 shared publications - Svetlana N. Sorokova
Department of Mechanical Engineering, Tomsk Polytechnic University, 634050 Tomsk, Russia
2 shared publications
Latest Publications
- Open Access
Assessing the Potential for Intra-Day Load Redistribution in Water Intake Systems Under Different Electricity Tariff Models: A Comparative Case Study of Belarus and China
This article assesses the potential for intra-day redistribution of the electrical load of water intake systems under different electricity tariff models, using water supply systems in Belarus and China as case studies. It demonstrates how tariff policy influences the electrical load profile of a water intake system and quantitatively evaluates the economic effect of optimizing the operating modes of pumping equipment. The analysis is based on daily profiles of electric power and water supply. For the Belarusian water supply system, data for 2019 were considered, corresponding to the baseline operating mode without targeted load management, and data for 2023 were considered after the transition to dispatch-based control of well activation with account taken of tariff constraints (without automation tools). For the Chinese water intake system, hourly data for 2025 were used. The load redistribution potential was assessed on the basis of lagged correlation between power and water supply profiles. In addition, the F-index was applied as an aggregated diagnostic indicator intended for the comparative assessment of potential load transferability across technological stages, taking into account their share in total energy consumption. For the Chinese case, it was shown that the maximum correlation between water supply and electricity consumption across all technological stages is achieved near zero lag, which indicates a high adaptation of system operating modes to current demand; at the same time, the R values were 0.19 for reservoir intake, 0.86 for water treatment, and 0.51 for the pumping station. In the Belarusian case, for the first-lift stage, the maximum correlation is shifted by −6 h relative to zero lag, indicating a less rigid linkage of pump operation to current demand and a more inertial response of the system. A comparison of 2019 and 2023 for the Belarusian facility showed that targeted regulation of well activation and load redistribution across tariff zones reduced the total electricity cost by 1.58%, confirming the potential for further optimization of electricity consumption regimes.
Open AccessAssessing the Potential for Intra-Day Load Redistribution in Water Intake Systems Under Different Electricity Tariff Models: A Comparative Case Study of Belarus and China
This article assesses the potential for intra-day redistribution of the electrical load of water intake systems under different electricity tariff models, using water supply systems in Belarus and China as case studies. It demonstrates how tariff policy influences the electrical load profile of a water intake system and quantitatively evaluates the economic effect of optimizing the operating modes of pumping equipment. The analysis is based on daily profiles of electric power and water supply. For the Belarusian water supply system, data for 2019 were considered, corresponding to the baseline operating mode without targeted load management, and data for 2023 were considered after the transition to dispatch-based control of well activation with account taken of tariff constraints (without automation tools). For the Chinese water intake system, hourly data for 2025 were used. The load redistribution potential was assessed on the basis of lagged correlation between power and water supply profiles. In addition, the F-index was applied as an aggregated diagnostic indicator intended for the comparative assessment of potential load transferability across technological stages, taking into account their share in total energy consumption. For the Chinese case, it was shown that the maximum correlation between water supply and electricity consumption across all technological stages is achieved near zero lag, which indicates a high adaptation of system operating modes to current demand; at the same time, the R values were 0.19 for reservoir intake, 0.86 for water treatment, and 0.51 for the pumping station. In the Belarusian case, for the first-lift stage, the maximum correlation is shifted by −6 h relative to zero lag, indicating a less rigid linkage of pump operation to current demand and a more inertial response of the system. A comparison of 2019 and 2023 for the Belarusian facility showed that targeted regulation of well activation and load redistribution across tariff zones reduced the total electricity cost by 1.58%, confirming the potential for further optimization of electricity consumption regimes.
- Open Access
- 3 October 2025
- Published by MDPI AG in Technologies
- Vol. 13 (10) , 449
Temporal Segmentation of Urban Water Consumption Patterns Based on Non-Parametric Density Clustering
The management of modern water supply systems requires a detailed analysis of consumption patterns in order to optimize pump operation schedules, reduce energy costs, and support the development of intelligent management systems. Traditional clustering algorithms are applied for these tasks; however, their limitation lies in the need to predefine the number of clusters. The aim of this study was to develop and validate a non-parametric method for clustering daily water consumption profiles based on a modified DBSCAN algorithm. The proposed approach includes the automatic optimization of neighborhood radius and the minimum number of points required to form a cluster. The input data consisted of half-hourly water supply and electricity consumption values for the water supply system of Gomel (Republic of Belarus), supplemented with the time-of-day factor. As a result of the multidimensional clustering, two stable regimes were identified: a high-demand regime (6:30–22:30), covering about 46% of the data and accounting for more than half of the total water supply and electricity consumption, and a low-demand regime (0:30–6:00), representing about 21% of the data and forming around 15% of the resources. The remaining regimes reflect transitional states in morning and evening periods. The obtained results make it possible to define the temporal boundaries of the regimes and to use them for data labeling in the development of predictive water consumption models.
- 3 October 2025
- Published by MDPI AG in Technologies
- Vol. 13 (10) , 449
Open AccessTemporal Segmentation of Urban Water Consumption Patterns Based on Non-Parametric Density Clustering
The management of modern water supply systems requires a detailed analysis of consumption patterns in order to optimize pump operation schedules, reduce energy costs, and support the development of intelligent management systems. Traditional clustering algorithms are applied for these tasks; however, their limitation lies in the need to predefine the number of clusters. The aim of this study was to develop and validate a non-parametric method for clustering daily water consumption profiles based on a modified DBSCAN algorithm. The proposed approach includes the automatic optimization of neighborhood radius and the minimum number of points required to form a cluster. The input data consisted of half-hourly water supply and electricity consumption values for the water supply system of Gomel (Republic of Belarus), supplemented with the time-of-day factor. As a result of the multidimensional clustering, two stable regimes were identified: a high-demand regime (6:30–22:30), covering about 46% of the data and accounting for more than half of the total water supply and electricity consumption, and a low-demand regime (0:30–6:00), representing about 21% of the data and forming around 15% of the resources. The remaining regimes reflect transitional states in morning and evening periods. The obtained results make it possible to define the temporal boundaries of the regimes and to use them for data labeling in the development of predictive water consumption models.
- 2 May 2025
- Published by Springer Nature in Water Conservation Science and Engineering
- Vol. 10 (2) , 1-16
Identification of Easily Accessible Urban Water Consumption Factors for Energy-Efficient Management of Pumping Stations
- 2 May 2025
- Published by Springer Nature in Water Conservation Science and Engineering
- Vol. 10 (2) , 1-16
Identification of Easily Accessible Urban Water Consumption Factors for Energy-Efficient Management of Pumping Stations
- Open Access
- 2 April 2025
- Published by MDPI AG in Smart Cities
- Vol. 8 (2) , 59
Intelligent Methods of Operational Response to Accidents in Urban Water Supply Systems Based on LSTM Neural Network Models
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data pre-processing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt–Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.
- 2 April 2025
- Published by MDPI AG in Smart Cities
- Vol. 8 (2) , 59
Open AccessIntelligent Methods of Operational Response to Accidents in Urban Water Supply Systems Based on LSTM Neural Network Models
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data pre-processing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt–Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.
- Open Access
- 7 February 2025
- Published by MDPI AG in Preprints.org
Intelligent Methods of Operational Response to Accidents in Urban Water Supply Systems Based on LSTM Neural Network Models
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data preprocessing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt-Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.
- 7 February 2025
- Published by MDPI AG in Preprints.org
Open AccessIntelligent Methods of Operational Response to Accidents in Urban Water Supply Systems Based on LSTM Neural Network Models
This paper investigates the application of recurrent neural networks, specifically Long Short-Term Memory (LSTM) models, for pressure forecasting in urban water supply systems. The objective of this study was to evaluate the effectiveness of LSTM models for pressure prediction tasks. To acquire real-time pressure data, an information system based on Internet of Things (IoT) technology using the MQTT protocol was proposed. The paper presents a data preprocessing algorithm for model training, as well as an analysis of the influence of various architectural parameters, such as the number of LSTM layers, the utilization of Dropout layers for regularization, and the number of neurons in Dense (fully connected) layers. The impact of seasonal factors, including month, day of the week, and time of day, on the pressure forecast quality was also investigated. The results obtained demonstrate that the optimal model consists of two LSTM layers, one Dropout layer, and one Dense layer. The incorporation of seasonal parameters improved prediction accuracy. The model training time increased significantly with the number of layers and neurons, but this did not always result in improved forecast accuracy. The results showed that the optimally tuned LSTM model can achieve high accuracy and outperform traditional methods such as the Holt-Winters model. This study confirms the effectiveness of using LSTM for forecasting in the water supply field and highlights the importance of pre-optimizing the model parameters to achieve the best forecasting results.
- Open Access
- 25 October 2019
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 124, 02008
Vibration diagnostic of electric motor roller bearings
The low quality of the new rolling bearings leads to additional costs for electric motor repair, and additional expenses connected with the technological process, value of which can reach from several thousand to tens of thousand dollars. To increase detection, the reliability of rolling bearing defects of asynchronous motors, complex vibration diagnostics was used at informative frequencies in the vibration frequency and amplitude in the range of 5-5000 Hz. Based on the diagnostic model of rolling bearings the software program “Tayamnitsa” is developed, which allows to calculate the diagnostic frequency corresponding to certain defects, determine the defect level and form a diagnostic table for defects. Vibration diagnostics of new and used rolling bearings have been conducted for various regional enterprises and power plants. It has been determined that 40-50% of used bearings are removed in good technical condition. When new bearings were diagnosed in the 500-5000 Hz range, only 48.4% of the bearings are considered serviceable due to the low accuracy class of metal processing and unacceptably high vibration level.
- 25 October 2019
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 124, 02008
Open AccessVibration diagnostic of electric motor roller bearings
The low quality of the new rolling bearings leads to additional costs for electric motor repair, and additional expenses connected with the technological process, value of which can reach from several thousand to tens of thousand dollars. To increase detection, the reliability of rolling bearing defects of asynchronous motors, complex vibration diagnostics was used at informative frequencies in the vibration frequency and amplitude in the range of 5-5000 Hz. Based on the diagnostic model of rolling bearings the software program “Tayamnitsa” is developed, which allows to calculate the diagnostic frequency corresponding to certain defects, determine the defect level and form a diagnostic table for defects. Vibration diagnostics of new and used rolling bearings have been conducted for various regional enterprises and power plants. It has been determined that 40-50% of used bearings are removed in good technical condition. When new bearings were diagnosed in the 500-5000 Hz range, only 48.4% of the bearings are considered serviceable due to the low accuracy class of metal processing and unacceptably high vibration level.
- Open Access
- 1 January 2019
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 124, 05060
Optimization of a variable frequency drive pump working on a water tower
The development of the existing water supply system in towns and villages involves the use of frequency converters and specialized control algorithms that can maintain the pressure level established in the supply grid within certain limits. The implementation of the standard scheme includes the elimination of the water tower, which, on the one hand, reduces the cost of its maintenance. On the other hand, in emergency situations, the water tower can still supply water to the consumer, which increases the time of uninterrupted water supply during repairs. The article reveals a method of increasing the energy efficiency of transporting drinking water with the help of a water tower by eliminating the excessive pressure of the water rise when using frequency converters. Our research that involved more than 300 pumping stations, allowed to establish the average value of the excessive pressure of water rise, which reached 0.36 MPa. For the wells under study, optimization of the pump operation modes revealed the energy-saving potential of up to 52% due to excessive pressure reduction and up to 2.0% due to a decrease in starting power at the time of engine acceleration.
- 1 January 2019
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 124, 05060
Open AccessOptimization of a variable frequency drive pump working on a water tower
The development of the existing water supply system in towns and villages involves the use of frequency converters and specialized control algorithms that can maintain the pressure level established in the supply grid within certain limits. The implementation of the standard scheme includes the elimination of the water tower, which, on the one hand, reduces the cost of its maintenance. On the other hand, in emergency situations, the water tower can still supply water to the consumer, which increases the time of uninterrupted water supply during repairs. The article reveals a method of increasing the energy efficiency of transporting drinking water with the help of a water tower by eliminating the excessive pressure of the water rise when using frequency converters. Our research that involved more than 300 pumping stations, allowed to establish the average value of the excessive pressure of water rise, which reached 0.36 MPa. For the wells under study, optimization of the pump operation modes revealed the energy-saving potential of up to 52% due to excessive pressure reduction and up to 2.0% due to a decrease in starting power at the time of engine acceleration.