The influence of the efficiency of the initial thermoelectric materials on the dynamics of the functioning of the thermoelectric cooling device for various characteristic current modes of operation in the range of operating temperature drops and heat load at a given geometry of thermoelement legs is considered. The parameters of thermoelectric materials of thermoelements are conventionally divided into three groups: used for batch production, laboratory research and maximum values. The criterion for choosing the operating mode of the thermoelectric cooler takes into account the mutual influence and weight of each of the limiting factors. Since the design conditions can be very diverse, simultaneously varying several limiting factors (constructive, energy and reliability), you can choose the most rational mode of operation. The analysis was carried out for typical current modes of operation of thermoelectric coolers: maximum cooling capacity, maximum cooling capacity at a given current, maximum coefficient of performance, minimum failure rate. It is shown that with an increase in the efficiency of the initial thermoelectric materials, the time for reaching the stationary operating mode of the thermoelectric cooler, the required number of thermoelements, and the maximum temperature difference increase. A method is proposed for reducing the time constant of thermoelectric coolers due to the revealed relationship between the efficiency of thermoelectric materials and the dynamic characteristics of thermoelements. It is shown that an increase in the dynamic characteristics of thermoelectric coolers is achieved without changing the design documentation, manufacturing technology and additional climatic and mechanical testing of products.
{"title":"Method for increasing the dynamic characteristics of thermoelectric coolers","authors":"Y. Zhuravlov","doi":"10.15276/hait.04.2021.6","DOIUrl":"https://doi.org/10.15276/hait.04.2021.6","url":null,"abstract":"The influence of the efficiency of the initial thermoelectric materials on the dynamics of the functioning of the thermoelectric cooling device for various characteristic current modes of operation in the range of operating temperature drops and heat load at a given geometry of thermoelement legs is considered. The parameters of thermoelectric materials of thermoelements are conventionally divided into three groups: used for batch production, laboratory research and maximum values. The criterion for choosing the operating mode of the thermoelectric cooler takes into account the mutual influence and weight of each of the limiting factors. Since the design conditions can be very diverse, simultaneously varying several limiting factors (constructive, energy and reliability), you can choose the most rational mode of operation. The analysis was carried out for typical current modes of operation of thermoelectric coolers: maximum cooling capacity, maximum cooling capacity at a given current, maximum coefficient of performance, minimum failure rate. It is shown that with an increase in the efficiency of the initial thermoelectric materials, the time for reaching the stationary operating mode of the thermoelectric cooler, the required number of thermoelements, and the maximum temperature difference increase. A method is proposed for reducing the time constant of thermoelectric coolers due to the revealed relationship between the efficiency of thermoelectric materials and the dynamic characteristics of thermoelements. It is shown that an increase in the dynamic characteristics of thermoelectric coolers is achieved without changing the design documentation, manufacturing technology and additional climatic and mechanical testing of products.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131144954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Larshin, O. Babiychuk, Oleksandr V. Lysyi, Serhii M. Verpivskyi, Zhang Yunxuan
In accordance with the principles of hierarchical management, a comprehensive two-level management system is presented for the development and manufacturing of products for the stages of pre-production (the upper level of the management hierarchy) and for the actual production stage (the lower level of the management hierarchy). At the stage of pre-production, the gear grinding operation design on the “MAAG” type machines was carried out. For this purpose, a technique for optimizing the gear grinding parameters for a two dish-wheel rolling scheme has been developed, a mathematical optimization model containing an objective function with restrictions imposed on it has been created. The objective function is the gear grinding machine time, which depends on the operation parameters (gear grinding stock allowance, cutting modes, grinding wheel specification, part material) and the design features of the gears being ground (module, diameter, number of teeth, radius of curvature of the involutes). The article shows that at the stage of pre-production, the gear grinding optimization is a method of operation design. At the stage of actual production, a closed-loop automatic control system with feedback on the deviation of the adjustable value (gear grinding power) automatically supports the numerical power values that were found at the operation design stage, taking into account ensuring defect-free high-performance gear grinding (minimum number of working strokes and maximum longitudinal feeds). At this stage, i.e. when a robust longitudinal feed automatic control system is operating, the optimization carried out at the previous stage (pre-production) sets the functioning algorithm for the adaptive system with corresponding control algorithm. Thus, at the production stage (when the gear grinding machine is running), the operation optimization is a control method. Therefore, it is shown that with two-level control, the gear grinding operation optimization performs a dual function. On the one hand, it is a design method (at the pre-production stage), and on the other – a management method (at the actual production stage). With this approach, i.e. with the integration of production and its preparation based on a single two-level management, the efficiency of a single integrated design and production automation system is significantly higher due to general (unified) optimization, rather than partial one.
{"title":"Optimization of the precision gear grinding operation based on integrated information system","authors":"V. Larshin, O. Babiychuk, Oleksandr V. Lysyi, Serhii M. Verpivskyi, Zhang Yunxuan","doi":"10.15276/hait.04.2021.2","DOIUrl":"https://doi.org/10.15276/hait.04.2021.2","url":null,"abstract":"In accordance with the principles of hierarchical management, a comprehensive two-level management system is presented for the development and manufacturing of products for the stages of pre-production (the upper level of the management hierarchy) and for the actual production stage (the lower level of the management hierarchy). At the stage of pre-production, the gear grinding operation design on the “MAAG” type machines was carried out. For this purpose, a technique for optimizing the gear grinding parameters for a two dish-wheel rolling scheme has been developed, a mathematical optimization model containing an objective function with restrictions imposed on it has been created. The objective function is the gear grinding machine time, which depends on the operation parameters (gear grinding stock allowance, cutting modes, grinding wheel specification, part material) and the design features of the gears being ground (module, diameter, number of teeth, radius of curvature of the involutes). The article shows that at the stage of pre-production, the gear grinding optimization is a method of operation design. At the stage of actual production, a closed-loop automatic control system with feedback on the deviation of the adjustable value (gear grinding power) automatically supports the numerical power values that were found at the operation design stage, taking into account ensuring defect-free high-performance gear grinding (minimum number of working strokes and maximum longitudinal feeds). At this stage, i.e. when a robust longitudinal feed automatic control system is operating, the optimization carried out at the previous stage (pre-production) sets the functioning algorithm for the adaptive system with corresponding control algorithm. Thus, at the production stage (when the gear grinding machine is running), the operation optimization is a control method. Therefore, it is shown that with two-level control, the gear grinding operation optimization performs a dual function. On the one hand, it is a design method (at the pre-production stage), and on the other – a management method (at the actual production stage). With this approach, i.e. with the integration of production and its preparation based on a single two-level management, the efficiency of a single integrated design and production automation system is significantly higher due to general (unified) optimization, rather than partial one.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116495287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Denysova, V. Nikulshin, V. Wysochin, O. Zhaivoron, Yana V. Solomentseva
The paper considers modeling the efficiency of power system with integration large share of variable renewable sources of energy with the account of climate conditions of Ukraine. The proposed methodology with its position between system planning and dispatch simulation contributes to the field of hybrid energy system models. The idea behind the method allows high spatial and temporal resolution as well as the inclusion of the technical details of the power system and its dispatch. The novelty of this method is the usage of a parametric approach is chosen to analyze different variable renewable sources of energy scenarios, precisely every possible its share and mix. This provides insights on the systematic effects of different resource mixes and may serve as a new approach to the analysis of future power system development. The additional novelty aspect allows the optimization of the design of the technical details of the power system with large variable renewable sources shares to have continuous improvement of its energy efficiency. The energy balance model generator is well suited for the analysis of large share of variable renewable sources integration in the power system. The design of technical details of the power system with large variable renewable sources shares was optimized with the energy balance model. The results of numerical modelling demonstrated that at 80% variable renewable sources of energy share, the overproduction is reduced to 20%, down from over 100 % without grid extensions. With it, the necessary wind and solar capacity decreases. Consequently, the possible achievable variable renewable sources of energy share is increased, assuming the same technical potential. According to the results, a Ukrainian grid would allow to increase the possible variable renewable sources of energy share from 50% to 75%.
{"title":"Modelling the efficiency of power system with reserve capacity from variable renewable sources of energy","authors":"A. Denysova, V. Nikulshin, V. Wysochin, O. Zhaivoron, Yana V. Solomentseva","doi":"10.15276/hait.04.2021.3","DOIUrl":"https://doi.org/10.15276/hait.04.2021.3","url":null,"abstract":"The paper considers modeling the efficiency of power system with integration large share of variable renewable sources of energy with the account of climate conditions of Ukraine. The proposed methodology with its position between system planning and dispatch simulation contributes to the field of hybrid energy system models. The idea behind the method allows high spatial and temporal resolution as well as the inclusion of the technical details of the power system and its dispatch. The novelty of this method is the usage of a parametric approach is chosen to analyze different variable renewable sources of energy scenarios, precisely every possible its share and mix. This provides insights on the systematic effects of different resource mixes and may serve as a new approach to the analysis of future power system development. The additional novelty aspect allows the optimization of the design of the technical details of the power system with large variable renewable sources shares to have continuous improvement of its energy efficiency. The energy balance model generator is well suited for the analysis of large share of variable renewable sources integration in the power system. The design of technical details of the power system with large variable renewable sources shares was optimized with the energy balance model. The results of numerical modelling demonstrated that at 80% variable renewable sources of energy share, the overproduction is reduced to 20%, down from over 100 % without grid extensions. With it, the necessary wind and solar capacity decreases. Consequently, the possible achievable variable renewable sources of energy share is increased, assuming the same technical potential. According to the results, a Ukrainian grid would allow to increase the possible variable renewable sources of energy share from 50% to 75%.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127182054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The purpose of this study is to analyze and implement the acceleration of the neural network learning process by predicting the weight coefficients. The relevance of accelerating the learning of neural networks is touched upon, as well as the possibility of using prediction models in a wide range of tasks where it is necessary to build fast classifiers. When data is received from the array of sensors of a chemical unit in real time, it is necessary to be able to predict changes and change the operating parameters. After assessment, this should be done as quickly as possible in order to promptly change the current structure and state of the resulting substances.. Work on speeding up classifiers usually focuses on speeding up the applied classifier. The calculation of the predicted values of the weight coefficients is carried out using the calculation of the value using the known prediction models. The possibility of the combined use of prediction models and optimization models was tested to accelerate the learning process of a neural network. The scientific novelty of the study lies in the effectiveness analysis of prediction models use in training neural networks. For the experimental evaluation of the effectiveness of prediction models use, the classification problem was chosen. To solve the experimental problem, the type of neural network “multilayer perceptron” was chosen. The experiment is divided into several stages: initial training of the neural network without a model, and then using prediction models; initial training of a neural network without an optimization method, and then using optimization methods; initial training of the neural network using combinations of prediction models and optimization methods; measuring the relative error of using prediction models, optimization methods and combined use. Models such as “Seasonal Linear Regression”, “Simple Moving Average”, and “Jump” were used in the experiment. The “Jump” model was proposed and developed based on the results of observing the dependence of changes in the values of the weighting coefficient on the epoch. Methods such as “Adagrad”, “Adadelta”, “Adam” were chosen for training neural and subsequent verification of the combined use of prediction models with optimization methods. As a result of the study, the effectiveness of the use of prediction models in predicting the weight coefficients of a neural network has been revealed. The idea is proposed and models are used that can significantly reduce the training time of a neural network. The idea of using prediction models is that the model of the change in the weight coefficient from the epoch is a time series, which in turn tends to a certain value. As a result of the study, it was found that it is possible to combine prediction models and optimization models. Also, prediction models do not interfere with optimization models, since they do not affect the formula of the training itself, as a result of which it is possible to ac
{"title":"Accelerating the learning process of a neural network by predicting the weight coefficient","authors":"V. Speranskyy, Mihail O. Domanciuc","doi":"10.15276/hait.04.2021.1","DOIUrl":"https://doi.org/10.15276/hait.04.2021.1","url":null,"abstract":"The purpose of this study is to analyze and implement the acceleration of the neural network learning process by predicting the weight coefficients. The relevance of accelerating the learning of neural networks is touched upon, as well as the possibility of using prediction models in a wide range of tasks where it is necessary to build fast classifiers. When data is received from the array of sensors of a chemical unit in real time, it is necessary to be able to predict changes and change the operating parameters. After assessment, this should be done as quickly as possible in order to promptly change the current structure and state of the resulting substances.. Work on speeding up classifiers usually focuses on speeding up the applied classifier. The calculation of the predicted values of the weight coefficients is carried out using the calculation of the value using the known prediction models. The possibility of the combined use of prediction models and optimization models was tested to accelerate the learning process of a neural network. The scientific novelty of the study lies in the effectiveness analysis of prediction models use in training neural networks. For the experimental evaluation of the effectiveness of prediction models use, the classification problem was chosen. To solve the experimental problem, the type of neural network “multilayer perceptron” was chosen. The experiment is divided into several stages: initial training of the neural network without a model, and then using prediction models; initial training of a neural network without an optimization method, and then using optimization methods; initial training of the neural network using combinations of prediction models and optimization methods; measuring the relative error of using prediction models, optimization methods and combined use. Models such as “Seasonal Linear Regression”, “Simple Moving Average”, and “Jump” were used in the experiment. The “Jump” model was proposed and developed based on the results of observing the dependence of changes in the values of the weighting coefficient on the epoch. Methods such as “Adagrad”, “Adadelta”, “Adam” were chosen for training neural and subsequent verification of the combined use of prediction models with optimization methods. As a result of the study, the effectiveness of the use of prediction models in predicting the weight coefficients of a neural network has been revealed. The idea is proposed and models are used that can significantly reduce the training time of a neural network. The idea of using prediction models is that the model of the change in the weight coefficient from the epoch is a time series, which in turn tends to a certain value. As a result of the study, it was found that it is possible to combine prediction models and optimization models. Also, prediction models do not interfere with optimization models, since they do not affect the formula of the training itself, as a result of which it is possible to ac","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The comparative analysis of means of control of a thermal mode at minimization of a complex of the basic parameters in various combinations with indicators of reliability and dynamics of functioning of one-stage thermoelectric cooler is resulted. The study was conducted for the operating range of temperature differences, standard heat load and different geometry of the branches of thermocouples. According to the results of research to minimize the sets of basic parameters in interaction with the indicators of reliability and dynamics of work, a number of current modes of operation have been developed. The developed mathematical models for the optimal operating current from the relative temperature difference and heat transfer of the radiator for the proposed operating modes are analyzed. The results of calculations of the main parameters, reliability indicators, and time of transition to stationary mode of operation for different current modes of operation in the range of temperature differences for different geometry of branches of thermoelements are given. The extremes of dependences of the cooling coefficient, heat dissipation capacity of the radiator, the amount of energy consumed on the relative operating current are determined, which is essential for the implementation of the control function. The possibility of choosing the current mode of operation for optimal control of the thermal regime of single-stage thermoelectric devices manufactured by the same technology, taking into account mass, size, energy, reliability and dynamic characteristics. The developed method of optimal regulation of the thermal regime of a single-stage thermoelectric cooler based on minimizing the set of basic parameters allows finding and choosing compromise solutions taking into account the importance of each of the limiting factors.
{"title":"Control of thermal regime of thermoelectric coolers in uniform temperature field","authors":"Vladimir P. Zaykov, V. Mescheryakov, Y. Zhuravlov","doi":"10.15276/hait.04.2021.4","DOIUrl":"https://doi.org/10.15276/hait.04.2021.4","url":null,"abstract":"The comparative analysis of means of control of a thermal mode at minimization of a complex of the basic parameters in various combinations with indicators of reliability and dynamics of functioning of one-stage thermoelectric cooler is resulted. The study was conducted for the operating range of temperature differences, standard heat load and different geometry of the branches of thermocouples. According to the results of research to minimize the sets of basic parameters in interaction with the indicators of reliability and dynamics of work, a number of current modes of operation have been developed. The developed mathematical models for the optimal operating current from the relative temperature difference and heat transfer of the radiator for the proposed operating modes are analyzed. The results of calculations of the main parameters, reliability indicators, and time of transition to stationary mode of operation for different current modes of operation in the range of temperature differences for different geometry of branches of thermoelements are given. The extremes of dependences of the cooling coefficient, heat dissipation capacity of the radiator, the amount of energy consumed on the relative operating current are determined, which is essential for the implementation of the control function. The possibility of choosing the current mode of operation for optimal control of the thermal regime of single-stage thermoelectric devices manufactured by the same technology, taking into account mass, size, energy, reliability and dynamic characteristics. The developed method of optimal regulation of the thermal regime of a single-stage thermoelectric cooler based on minimizing the set of basic parameters allows finding and choosing compromise solutions taking into account the importance of each of the limiting factors.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121414328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
I. Shpinareva, A. Yakushina, Lyudmila A. Voloshchuk, N. Rudnichenko
This article shows the relevance of developing a cascade of deep neural networks for detecting and classifying network attacks based on an analysis of the practical use of network intrusion detection systems to protect local computer networks. A cascade of deep neural networks consists of two elements. The first network is a hybrid deep neural network that contains convolutional neural network layers and long short-term memory layers to detect attacks. The second network is a CNN convolutional neural network for classifying the most popular classes of network attacks such as Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnais-sance, Shellcode, and Worms. At the stage of tuning and training the cascade of deep neural networks, the selection of hyperparame-ters was carried out, which made it possible to improve the quality of the model. Among the available public datasets, one ofthe current UNSW-NB15 datasets was selected, taking into account modern traffic. For the data set under consideration, a data prepro-cessing technology has been developed. The cascade of deep neural networks was trained, tested, and validated on the UNSW-NB15 dataset. The cascade of deep neural networks was tested on real network traffic, which showed its ability to detect and classify at-tacks in a computer network. The use of a cascade of deep neural networks, consisting of a hybrid neural network CNN + LSTM and a neural network CNNhas improved the accuracy of detecting and classifying attacks in computer networks and reduced the fre-quency of false alarms in detecting network attacks
{"title":"Detection and classification of network attacks using the deep neural network cascade","authors":"I. Shpinareva, A. Yakushina, Lyudmila A. Voloshchuk, N. Rudnichenko","doi":"10.15276/hait.03.2021.4","DOIUrl":"https://doi.org/10.15276/hait.03.2021.4","url":null,"abstract":"This article shows the relevance of developing a cascade of deep neural networks for detecting and classifying network attacks based on an analysis of the practical use of network intrusion detection systems to protect local computer networks. A cascade of deep neural networks consists of two elements. The first network is a hybrid deep neural network that contains convolutional neural network layers and long short-term memory layers to detect attacks. The second network is a CNN convolutional neural network for classifying the most popular classes of network attacks such as Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnais-sance, Shellcode, and Worms. At the stage of tuning and training the cascade of deep neural networks, the selection of hyperparame-ters was carried out, which made it possible to improve the quality of the model. Among the available public datasets, one ofthe current UNSW-NB15 datasets was selected, taking into account modern traffic. For the data set under consideration, a data prepro-cessing technology has been developed. The cascade of deep neural networks was trained, tested, and validated on the UNSW-NB15 dataset. The cascade of deep neural networks was tested on real network traffic, which showed its ability to detect and classify at-tacks in a computer network. The use of a cascade of deep neural networks, consisting of a hybrid neural network CNN + LSTM and a neural network CNNhas improved the accuracy of detecting and classifying attacks in computer networks and reduced the fre-quency of false alarms in detecting network attacks","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117354123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Ostroverkhov, V. Chumack, Yevhen Monakhov, B. Pryymak
This paper deals with information supply of automatic maximum power control system of synchronous hybrid excited genera-tor for the autonomous wind unit. The power supply system based on an autonomous wind turbine consists of an electric generator, a battery charging controller, a battery pack and an inverter, which provides the required frequency and valueof the consumer's supply voltage.Three phase permanent magnet synchronous generator that have high technical and economic indicators are most widely used as electric generator of autonomous wind turbines.The main disadvantage of these generators is the lack of effectivemethods of magnetic flux control, limiting the optimization of the energy balance of the wind turbine.The paper discusses the application of synchronous generator with hybrid excitation system that consists of permanent magnets and additional field excitation winding lo-cated on the stator. Mathematical model of a hybrid excited synchronous generator is presented. Also,an output maximum power control system in a case of wind speed change by varying field excitation current is developed. Control system is developed based on concept of reverse task of dynamics in combination with minimization of local functionals of instantaneous values of energies.In the basics of the control method is put an idea of the reversibility of the Lyapunov direct method for the stability analysis.Obtained con-trol law provides thesystem stability inwhole, which allows solving control tasks of interrelated objects via mathematical models of local loops. Control law also provides low sensitiveness to parametric disturbances and gives dynamic decomposition of interrelated non linear system that ensures its practical implementation. The study of the proposed power control system based on parameters of hybrid excited synchronous generator experimental sample has been carried out. The graphs of transient process of armature power, voltage and current in a case of wind speed change from 3 to 8 m/s were obtained, as well as in a case of active resistance load change. The results of study showed high efficiency of power control of a wind turbine with hybrid excited synchronous generator
{"title":"Information supply of the power control system of the synchronous generator of the autonomous wind unit","authors":"M. Ostroverkhov, V. Chumack, Yevhen Monakhov, B. Pryymak","doi":"10.15276/hait.03.2021.5","DOIUrl":"https://doi.org/10.15276/hait.03.2021.5","url":null,"abstract":"This paper deals with information supply of automatic maximum power control system of synchronous hybrid excited genera-tor for the autonomous wind unit. The power supply system based on an autonomous wind turbine consists of an electric generator, a battery charging controller, a battery pack and an inverter, which provides the required frequency and valueof the consumer's supply voltage.Three phase permanent magnet synchronous generator that have high technical and economic indicators are most widely used as electric generator of autonomous wind turbines.The main disadvantage of these generators is the lack of effectivemethods of magnetic flux control, limiting the optimization of the energy balance of the wind turbine.The paper discusses the application of synchronous generator with hybrid excitation system that consists of permanent magnets and additional field excitation winding lo-cated on the stator. Mathematical model of a hybrid excited synchronous generator is presented. Also,an output maximum power control system in a case of wind speed change by varying field excitation current is developed. Control system is developed based on concept of reverse task of dynamics in combination with minimization of local functionals of instantaneous values of energies.In the basics of the control method is put an idea of the reversibility of the Lyapunov direct method for the stability analysis.Obtained con-trol law provides thesystem stability inwhole, which allows solving control tasks of interrelated objects via mathematical models of local loops. Control law also provides low sensitiveness to parametric disturbances and gives dynamic decomposition of interrelated non linear system that ensures its practical implementation. The study of the proposed power control system based on parameters of hybrid excited synchronous generator experimental sample has been carried out. The graphs of transient process of armature power, voltage and current in a case of wind speed change from 3 to 8 m/s were obtained, as well as in a case of active resistance load change. The results of study showed high efficiency of power control of a wind turbine with hybrid excited synchronous generator","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129828034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergency situations have a huge impact on various important areas of human life. Every year there are many situations, the elimination of which requires a lot of financial and human resources. Therefore, the ability to reduce the impact of the consequences and increase the speed of their elimination is extremely important. In this article, a multi-level model of a system was proposed that provides support for performing operational tasks in emergency situations in open areas. The most important elements, areas of their responsibility, and interconnection were identified and described in architectural style. The idea of the work is to design asystem that should use Swarm intelligence under the hood to provide continuous support in emergency situations. The system consists of 4 main parts: Cloud, Swarm, Swarm operator, and Swarm Node. The Cloud (Swarm Wamb) is the main decision-maker that provides ETL data pipelines and operates under strategicallytasks. In accordance with the idea, Swarm womb should be a cloud service-like system with the ability to scale over the world. The Swarm is a combined set of multiple Swarm Nodes and only one Swarm Operator. The main task of the Swarm is to provide support in local operational tasks where SN is responsible for the execution and SOis for control. Rescue and search operation after any natural disaster is a target to show the system’s purpose. In practice, the cloud system (Swarm Wamb) receives requests to perform an operation, calculates resources effort first, anddelegates a task to the Swarm. When the swarm reaches the location, it starts executing. Operator with nodes tries to find survivors and collect as much important information as they can. Video, images, recognized objects are continuously sending to the Cloud for additional analysis in real-time. Any information in an emergency situation can help save more humans lives and reduce risks. In this article, the multilayer distributed intelligence system architecture for emergency area scanning was designed and described. The set of terminology was proposed as well. This architecture covers different levels of tactical and operational tasks
{"title":"The multilayer distributed intelligence system model for emergency area scanning","authors":"Andrey O. Tsariuk, E. Malakhov","doi":"10.15276/hait.03.2021.6","DOIUrl":"https://doi.org/10.15276/hait.03.2021.6","url":null,"abstract":"Emergency situations have a huge impact on various important areas of human life. Every year there are many situations, the elimination of which requires a lot of financial and human resources. Therefore, the ability to reduce the impact of the consequences and increase the speed of their elimination is extremely important. In this article, a multi-level model of a system was proposed that provides support for performing operational tasks in emergency situations in open areas. The most important elements, areas of their responsibility, and interconnection were identified and described in architectural style. The idea of the work is to design asystem that should use Swarm intelligence under the hood to provide continuous support in emergency situations. The system consists of 4 main parts: Cloud, Swarm, Swarm operator, and Swarm Node. The Cloud (Swarm Wamb) is the main decision-maker that provides ETL data pipelines and operates under strategicallytasks. In accordance with the idea, Swarm womb should be a cloud service-like system with the ability to scale over the world. The Swarm is a combined set of multiple Swarm Nodes and only one Swarm Operator. The main task of the Swarm is to provide support in local operational tasks where SN is responsible for the execution and SOis for control. Rescue and search operation after any natural disaster is a target to show the system’s purpose. In practice, the cloud system (Swarm Wamb) receives requests to perform an operation, calculates resources effort first, anddelegates a task to the Swarm. When the swarm reaches the location, it starts executing. Operator with nodes tries to find survivors and collect as much important information as they can. Video, images, recognized objects are continuously sending to the Cloud for additional analysis in real-time. Any information in an emergency situation can help save more humans lives and reduce risks. In this article, the multilayer distributed intelligence system architecture for emergency area scanning was designed and described. The set of terminology was proposed as well. This architecture covers different levels of tactical and operational tasks","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130730203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The article analyzes the existing approaches to the description of large dynamic information objects in the construction of Automated control systems. Introduced and defined the concept of a ComplexDynamical Information Object. A comparative analysis of the temporal complexities of tree-like structures is carried out and the optimal one for working with ComplexDynamical Information Objectis selected. Most modern automated control systems use various approaches to describe automation objects for their operation. Under the automation object, we mean functional objects that are described in the form of structural models that reflect the properties of physical objects. Thus, for optimal work with complex dynamic information objects, we have developed our own model and method for describing the LMS-tree (Log-structured merge-tree), with the ability to split and store down to elementary levels. One of the features of our approach to describing objects is the presence of tree-like levels -the so-called “leaves”, by which we mean special tree elements that expand the description of the tree structure of a particular tree level. The minimal elements of the leaves of the tree –“veins”-are details, that is, elementary information elements. A leaf is a combination of “veins”(details) according to certain characteristics, which provide extended information about the level of the tree object. An atomic-level descriptor is a multiple NoSQL database field (array) where the tree level number is the index of the database array. This approach allows you to retrieve and group objects according to the element level of the tree definition
{"title":"Model and method for representing complex dynamic information objects based on LMS-trees in NoSQL databases","authors":"O. Maksymov, E. Malakhov, V. Mezhuyev","doi":"10.15276/hait.03.2021.1","DOIUrl":"https://doi.org/10.15276/hait.03.2021.1","url":null,"abstract":"The article analyzes the existing approaches to the description of large dynamic information objects in the construction of Automated control systems. Introduced and defined the concept of a ComplexDynamical Information Object. A comparative analysis of the temporal complexities of tree-like structures is carried out and the optimal one for working with ComplexDynamical Information Objectis selected. Most modern automated control systems use various approaches to describe automation objects for their operation. Under the automation object, we mean functional objects that are described in the form of structural models that reflect the properties of physical objects. Thus, for optimal work with complex dynamic information objects, we have developed our own model and method for describing the LMS-tree (Log-structured merge-tree), with the ability to split and store down to elementary levels. One of the features of our approach to describing objects is the presence of tree-like levels -the so-called “leaves”, by which we mean special tree elements that expand the description of the tree structure of a particular tree level. The minimal elements of the leaves of the tree –“veins”-are details, that is, elementary information elements. A leaf is a combination of “veins”(details) according to certain characteristics, which provide extended information about the level of the tree object. An atomic-level descriptor is a multiple NoSQL database field (array) where the tree level number is the index of the database array. This approach allows you to retrieve and group objects according to the element level of the tree definition","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116715581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ivan Lobachev, S. Antoshchuk, Mykola A. Hodovychenko
This paper focuses on the development of a methodology to compress neural networks thatis based on the mechanism of prun-ingthe hidden layer neurons. The aforementioned neural networks are created in order to process the data generated by numerous sensors present in a transducer network that would be employed in a smart building. The proposed methodology implements a single approach for the compression of both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) that are used for the tasks of classification and regression. The main principle behind this method is based on the dropout mechanism, which is employed as a regulation mechanism for the neural networks. The idea behind the method proposed consists of selecting optimal exclusion probability of a hidden layer neuron, based on the redundancy of the said neuron. The novelty of this method is theusage of a custom compression network thatis based on an RNN, which allows us to determine the redundancy parameter not just in a sin-gle hidden layer, but across severallayers. The additional novelty aspect consists of an iterative optimization of the network-optimizer, to have continuous improvement of the redundancy parameter calculator of the input network. For the experimental evalu-ation of the proposed methodology, the task of image recognition with a low-resolution camera was chosen, the CIFAR10 dataset was used to emulate the scenario. The VGGNet Convolutional Neural Network, that contains convolutional and fully connected lay-ers, was used as the network under test for the purposes of this experiment. The following two methods were taken as the analogous state of the art, the MagBase method, which is based on the sparcification principle as well as the method which is based on rarefied representation by employing the approach of rarefied encoding SFAC. The results of the experiment demonstrated that the amount of parameters in the compressed model is only 2.56% of the original input model. This has allowed us to reduce the logical output time by 93.7% and energy consumption by 94.8%. The proposed method allows to effectively usingdeep neural networks in transducer networks that utilize the architecture of edge computing. This in turn allows the system to process the data in real time, reduce the energy consumption and logical output time as well as lower the memory and storage requirements of real-world applications.
{"title":"Methodology of neural network compression for multi-sensor transducer network models based on edge computing principles","authors":"Ivan Lobachev, S. Antoshchuk, Mykola A. Hodovychenko","doi":"10.15276/hait.03.2021.3","DOIUrl":"https://doi.org/10.15276/hait.03.2021.3","url":null,"abstract":"This paper focuses on the development of a methodology to compress neural networks thatis based on the mechanism of prun-ingthe hidden layer neurons. The aforementioned neural networks are created in order to process the data generated by numerous sensors present in a transducer network that would be employed in a smart building. The proposed methodology implements a single approach for the compression of both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) that are used for the tasks of classification and regression. The main principle behind this method is based on the dropout mechanism, which is employed as a regulation mechanism for the neural networks. The idea behind the method proposed consists of selecting optimal exclusion probability of a hidden layer neuron, based on the redundancy of the said neuron. The novelty of this method is theusage of a custom compression network thatis based on an RNN, which allows us to determine the redundancy parameter not just in a sin-gle hidden layer, but across severallayers. The additional novelty aspect consists of an iterative optimization of the network-optimizer, to have continuous improvement of the redundancy parameter calculator of the input network. For the experimental evalu-ation of the proposed methodology, the task of image recognition with a low-resolution camera was chosen, the CIFAR10 dataset was used to emulate the scenario. The VGGNet Convolutional Neural Network, that contains convolutional and fully connected lay-ers, was used as the network under test for the purposes of this experiment. The following two methods were taken as the analogous state of the art, the MagBase method, which is based on the sparcification principle as well as the method which is based on rarefied representation by employing the approach of rarefied encoding SFAC. The results of the experiment demonstrated that the amount of parameters in the compressed model is only 2.56% of the original input model. This has allowed us to reduce the logical output time by 93.7% and energy consumption by 94.8%. The proposed method allows to effectively usingdeep neural networks in transducer networks that utilize the architecture of edge computing. This in turn allows the system to process the data in real time, reduce the energy consumption and logical output time as well as lower the memory and storage requirements of real-world applications.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117346384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：