Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110786
I. Galiev, M. Garifullin, I. Alekseev, Ainaz R. Gizatullin, A. M. Makletsov
The paper proposes implementation of the concept of integrated expert diagnostic system (IESD) of distribution network equipment based on AI technology. Complexes and modules of IESD interact with subsystems of retrospective, supplemented and updated offline information (database) and online monitoring and diagnostics of main electrical equipment. The objects of study in this work are the operating main equipment of 110/6(10) kV substation and adjacent 0.4÷6(10) kV distribution network. IESD consists of the following computational complexes: executive, which provides the system with offline and online data input; intelligent, which consists of computing and analytical modules; knowledge base (KB) - Expert system that performs requests for additional data to correct calculations in the calculation modules. The aim of the work is to integrate existing and additional subsystems of online monitoring into a unified expert diagnostic system that allows for real objects: to adequately assess the condition of the main equipment and monitor its remaining life; to evaluate the distribution network state, optimize the current mode for reliability, voltage levels and power losses; to monitor the development of equipment defects and use predictive analysis models for planning of repairs and maintenance. The significance of the work lies in the development of mathematical models of operational and predictive assessment of the state of power transformers and network equipment, as well as in the formation of key components of information and analytical support for decision-making on its operation. Scientific novelty consists in the development of methods and algorithms using combined methods and learning models.
{"title":"Development of an Integrated Expert System for Distribution Network Diagnostics Based on Artificial Intelligence Technology","authors":"I. Galiev, M. Garifullin, I. Alekseev, Ainaz R. Gizatullin, A. M. Makletsov","doi":"10.1109/SmartIndustryCon57312.2023.10110786","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110786","url":null,"abstract":"The paper proposes implementation of the concept of integrated expert diagnostic system (IESD) of distribution network equipment based on AI technology. Complexes and modules of IESD interact with subsystems of retrospective, supplemented and updated offline information (database) and online monitoring and diagnostics of main electrical equipment. The objects of study in this work are the operating main equipment of 110/6(10) kV substation and adjacent 0.4÷6(10) kV distribution network. IESD consists of the following computational complexes: executive, which provides the system with offline and online data input; intelligent, which consists of computing and analytical modules; knowledge base (KB) - Expert system that performs requests for additional data to correct calculations in the calculation modules. The aim of the work is to integrate existing and additional subsystems of online monitoring into a unified expert diagnostic system that allows for real objects: to adequately assess the condition of the main equipment and monitor its remaining life; to evaluate the distribution network state, optimize the current mode for reliability, voltage levels and power losses; to monitor the development of equipment defects and use predictive analysis models for planning of repairs and maintenance. The significance of the work lies in the development of mathematical models of operational and predictive assessment of the state of power transformers and network equipment, as well as in the formation of key components of information and analytical support for decision-making on its operation. Scientific novelty consists in the development of methods and algorithms using combined methods and learning models.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114992637","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110761
E. S. Abramova, A. Orlov
Extreme Learning Machine is a single-hidden-layer feed-forward neural network that has the advantage of high learning speed and ease of implementation. The efficiency of an extreme learning machine in human activity recognition largely depends on three parameters, such as the weight matrix, the hidden layer neurons number, and the activation functions. This study is aimed at building an artificial neural network to solve the problem of human activity recognition to analyze the influence on the accuracy of parameters neural networks such as input weights, activation functions, and the neurons number in the hidden layer. For the experiment, an open dataset was used, which includes information about seven physical activity types. We compared the accuracy when training a neural network with an extreme learning machine and an extreme learning machine with the weight coefficient values calculated using the particle swarm optimization method. Also, the influence on the accuracy of such activation functions as a hyperbolic tangent, rectified linear unit, sigmoid, sinusoidal, and binary step function for different hidden layer neurons numbers was evaluated.
{"title":"Optimal Parameters Determination for Extreme Learning Machine in the Human Activity Recognition","authors":"E. S. Abramova, A. Orlov","doi":"10.1109/SmartIndustryCon57312.2023.10110761","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110761","url":null,"abstract":"Extreme Learning Machine is a single-hidden-layer feed-forward neural network that has the advantage of high learning speed and ease of implementation. The efficiency of an extreme learning machine in human activity recognition largely depends on three parameters, such as the weight matrix, the hidden layer neurons number, and the activation functions. This study is aimed at building an artificial neural network to solve the problem of human activity recognition to analyze the influence on the accuracy of parameters neural networks such as input weights, activation functions, and the neurons number in the hidden layer. For the experiment, an open dataset was used, which includes information about seven physical activity types. We compared the accuracy when training a neural network with an extreme learning machine and an extreme learning machine with the weight coefficient values calculated using the particle swarm optimization method. Also, the influence on the accuracy of such activation functions as a hyperbolic tangent, rectified linear unit, sigmoid, sinusoidal, and binary step function for different hidden layer neurons numbers was evaluated.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115639654","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110784
A. Martyshkin, R. A. Biktashev, E. Bershadskaya
The article is devoted to the development of a means and algorithm for balancing the load of processors of a reconfigurable computing system. A theoretical overview of the subject area of the research is given. Architectural solutions of modern analogues often do not allow scaling the system, which provides increased productivity and responsiveness. Modern solutions do not contribute to improving performance due to the use of shared memory and bus topology for switching processors, which impose additional conditions on shared memory access and synchronization of processor caches. The proposed approach will partially avoid the existing disadvantages of known solutions by using a cluster architecture to build a reconfigurable computing system, for the efficient operation of which all processors must be balanced. The issue of balancing the system load is not fully resolved, therefore, relevant. Further, the choice of the architecture of the reconfigurable computing system is justified, for which the synthesized algorithm of planning and dispatching is suitable. A description of the task planning algorithm for reconfigurable computing systems is given. The principles of interaction of processors in a reconfigurable computing system are described, taking into account the chosen architecture. The efficiency of the synthesized algorithm is analyzed using the example of test data. Using the input data, the load balancing algorithm identified various options for the distribution of tasks, one of which was marked as optimal, which is characterized by a minimum load spread of all processors of the reconfigurable computing system. At the end of the article, the main conclusions on the work are formulated.
{"title":"Development of a Means and Algorithm for Balancing the Load of Processors in a Reconfigurable Computing System","authors":"A. Martyshkin, R. A. Biktashev, E. Bershadskaya","doi":"10.1109/SmartIndustryCon57312.2023.10110784","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110784","url":null,"abstract":"The article is devoted to the development of a means and algorithm for balancing the load of processors of a reconfigurable computing system. A theoretical overview of the subject area of the research is given. Architectural solutions of modern analogues often do not allow scaling the system, which provides increased productivity and responsiveness. Modern solutions do not contribute to improving performance due to the use of shared memory and bus topology for switching processors, which impose additional conditions on shared memory access and synchronization of processor caches. The proposed approach will partially avoid the existing disadvantages of known solutions by using a cluster architecture to build a reconfigurable computing system, for the efficient operation of which all processors must be balanced. The issue of balancing the system load is not fully resolved, therefore, relevant. Further, the choice of the architecture of the reconfigurable computing system is justified, for which the synthesized algorithm of planning and dispatching is suitable. A description of the task planning algorithm for reconfigurable computing systems is given. The principles of interaction of processors in a reconfigurable computing system are described, taking into account the chosen architecture. The efficiency of the synthesized algorithm is analyzed using the example of test data. Using the input data, the load balancing algorithm identified various options for the distribution of tasks, one of which was marked as optimal, which is characterized by a minimum load spread of all processors of the reconfigurable computing system. At the end of the article, the main conclusions on the work are formulated.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"650 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115748617","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110774
E. Koptjaev, A. M. Marques Cardoso
This article presents the main results of the study of a brushless monopolar generator at various proportions of the main dimensions, as well as the experimental data necessary for the calculations. The design of the non-salient pole monopolar generator was used as a model; however, the main results can be applied to all three variants of the generator – with salient poles, nonsalient poles and the generator with longitudinal excitation. In the course of the study, a 3D model of the generator was used using finite elements; for better quality of the results and their clarity, the results are presented in 3D graphs for 3 parameters. The results generally confirmed the methodology of calculations, and also made it possible to compare different ratios of the length and diameter of the generators. The choice based on the length of the generator can be successfully made according to the formula, depending on the requested proportion of its dimensions. The dependence of losses in steel on the dimensions of a monopolar generator was revealed, which has implications for the generator efficiency studies.
{"title":"A Comparative Study of Brushless Non-salient Pole Monopolar Generators","authors":"E. Koptjaev, A. M. Marques Cardoso","doi":"10.1109/SmartIndustryCon57312.2023.10110774","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110774","url":null,"abstract":"This article presents the main results of the study of a brushless monopolar generator at various proportions of the main dimensions, as well as the experimental data necessary for the calculations. The design of the non-salient pole monopolar generator was used as a model; however, the main results can be applied to all three variants of the generator – with salient poles, nonsalient poles and the generator with longitudinal excitation. In the course of the study, a 3D model of the generator was used using finite elements; for better quality of the results and their clarity, the results are presented in 3D graphs for 3 parameters. The results generally confirmed the methodology of calculations, and also made it possible to compare different ratios of the length and diameter of the generators. The choice based on the length of the generator can be successfully made according to the formula, depending on the requested proportion of its dimensions. The dependence of losses in steel on the dimensions of a monopolar generator was revealed, which has implications for the generator efficiency studies.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"39 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120993158","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110762
I. Zaitceva, N. Kuznetsov, B. Andrievsky
In the human-machine system, the human operator, acting as a regulator, controls various devices through servomechanisms. The system parameters and the parameters of the human operator model, to one degree or another, can change due to numerous factors. It can lead to a deviation of the output signal from the specified one or loss of stability, which manifests as oscillatory processes. Usually, drive nonlinearities exert a vast load on the system's stable operation, which requires a thorough analysis of the system and taking this fact into account when designing the control system. In this work, conditions are found under which system performance deteriorates. It manifests itself as a significant increase in performance error or the appearance of unwanted oscillation. A simple method was proposed to prevent them by introducing a nonlinear corrective device into the drive control loop. Also, an analysis of the system on the parameter plane of the forcing signal was proposed by calculating the generalized sensitivity functions.
{"title":"Approach to Identifying Areas of Uncontrolled Oscillations in Human-Machine Systems","authors":"I. Zaitceva, N. Kuznetsov, B. Andrievsky","doi":"10.1109/SmartIndustryCon57312.2023.10110762","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110762","url":null,"abstract":"In the human-machine system, the human operator, acting as a regulator, controls various devices through servomechanisms. The system parameters and the parameters of the human operator model, to one degree or another, can change due to numerous factors. It can lead to a deviation of the output signal from the specified one or loss of stability, which manifests as oscillatory processes. Usually, drive nonlinearities exert a vast load on the system's stable operation, which requires a thorough analysis of the system and taking this fact into account when designing the control system. In this work, conditions are found under which system performance deteriorates. It manifests itself as a significant increase in performance error or the appearance of unwanted oscillation. A simple method was proposed to prevent them by introducing a nonlinear corrective device into the drive control loop. Also, an analysis of the system on the parameter plane of the forcing signal was proposed by calculating the generalized sensitivity functions.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127108815","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110740
E. Koptjaev, A. M. Marques Cardoso
In some experimental setups, it is required to obtain ultrahigh direct current voltages, including pulses of a given polarity and energy. Getting direct current for their testing and operation is accompanied by the process of rectifying the alternating current at the output of the power supply, which always requires diodes with a voltage rating higher than the nominal one. At the same time, the allowable voltage limit of the diodes is limited, not more than 10 kV. This article proposes a new design of a power supply with an output capacitance, which makes it possible to charge this capacitor without using diodes on the high voltage side, which significantly increases the reliability of operation and reduces the cost of the design as a whole. Also, the advantages include lower dimensions, and the possibility of obtaining high currents in installations with superconductivity.
{"title":"A New DC Source for Experimental Use","authors":"E. Koptjaev, A. M. Marques Cardoso","doi":"10.1109/SmartIndustryCon57312.2023.10110740","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110740","url":null,"abstract":"In some experimental setups, it is required to obtain ultrahigh direct current voltages, including pulses of a given polarity and energy. Getting direct current for their testing and operation is accompanied by the process of rectifying the alternating current at the output of the power supply, which always requires diodes with a voltage rating higher than the nominal one. At the same time, the allowable voltage limit of the diodes is limited, not more than 10 kV. This article proposes a new design of a power supply with an output capacitance, which makes it possible to charge this capacitor without using diodes on the high voltage side, which significantly increases the reliability of operation and reduces the cost of the design as a whole. Also, the advantages include lower dimensions, and the possibility of obtaining high currents in installations with superconductivity.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125953570","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110809
E. Koptjaev, A. M. Marques Cardoso
The article describes the design of a rectifier with 12 output voltage ripples with improved dimensions and weight of a three-phase transformer, and hence the entire rectifier as a whole. The greatest effect from its use will be achieved in powerful industrial systems and DC power lines. In addition, the absence of a delta winding reduces losses when operating on an unbalanced load, or when voltage fluctuates in the phases of the supply network. A comprehensive comparison of the advantages of this rectifier in comparison with the classic 12-pulse rectifier with two bridges and star-delta windings has been carried out. Theoretical results are confirmed using a 3D model for a transformer operating as part of a rectifier. Dependences of the advantages in size for different powers in the range from 1-63 MVA, as well as graphs for the currents consumed from the supply network at different thyristor control angles, were obtained. The presented materials make it possible to evaluate the quality of this rectifier in comparison with the classical one. The connection diagram of the windings of a three-phase transformer is not known, and is proposed by the authors of the article for the first time; in some cases, it can be used to power a 6-phase load, subject to certain conditions.
{"title":"A New Rectifier for Industrial Use","authors":"E. Koptjaev, A. M. Marques Cardoso","doi":"10.1109/SmartIndustryCon57312.2023.10110809","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110809","url":null,"abstract":"The article describes the design of a rectifier with 12 output voltage ripples with improved dimensions and weight of a three-phase transformer, and hence the entire rectifier as a whole. The greatest effect from its use will be achieved in powerful industrial systems and DC power lines. In addition, the absence of a delta winding reduces losses when operating on an unbalanced load, or when voltage fluctuates in the phases of the supply network. A comprehensive comparison of the advantages of this rectifier in comparison with the classic 12-pulse rectifier with two bridges and star-delta windings has been carried out. Theoretical results are confirmed using a 3D model for a transformer operating as part of a rectifier. Dependences of the advantages in size for different powers in the range from 1-63 MVA, as well as graphs for the currents consumed from the supply network at different thyristor control angles, were obtained. The presented materials make it possible to evaluate the quality of this rectifier in comparison with the classical one. The connection diagram of the windings of a three-phase transformer is not known, and is proposed by the authors of the article for the first time; in some cases, it can be used to power a 6-phase load, subject to certain conditions.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126772012","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110838
R. Tashbulatov, R. Karimov, A. Valeev
The paper studies the feasibility and determines optimal ways to increase the throughput capacity of limited oil main pipelines sections by developing the decision support system based on calculation automation algorithms and optimization problems aimed at finding the best technical and economical performances of an investment project in terms of payback period and expected profit. The goal of the present research is to reduce the time required for option design solutions based on the minimum initial data on the economics of retrospective already applied projects, as well as technical conditions and existing technological limitations of the oil pipeline operation. This goal is achieved by both analyzing existing approaches to solving similar optimization tasks, retrospective data analysis of real finished pipelines projects, developing automated calculation tools and optimization algorithms based on theoretical and practical methods to solve hydraulic amd economic problems. The paper proposes a methodology to quickly select the optimal method to increase the throughput capacity of main oil pipelines, including a hydraulic calculations module and an optimization algorithm.
{"title":"Decision Support System for Feasibility Study and Determination the Optimal Way to Increase the Throughput Capacity of Main Oil Pipelines","authors":"R. Tashbulatov, R. Karimov, A. Valeev","doi":"10.1109/SmartIndustryCon57312.2023.10110838","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110838","url":null,"abstract":"The paper studies the feasibility and determines optimal ways to increase the throughput capacity of limited oil main pipelines sections by developing the decision support system based on calculation automation algorithms and optimization problems aimed at finding the best technical and economical performances of an investment project in terms of payback period and expected profit. The goal of the present research is to reduce the time required for option design solutions based on the minimum initial data on the economics of retrospective already applied projects, as well as technical conditions and existing technological limitations of the oil pipeline operation. This goal is achieved by both analyzing existing approaches to solving similar optimization tasks, retrospective data analysis of real finished pipelines projects, developing automated calculation tools and optimization algorithms based on theoretical and practical methods to solve hydraulic amd economic problems. The paper proposes a methodology to quickly select the optimal method to increase the throughput capacity of main oil pipelines, including a hydraulic calculations module and an optimization algorithm.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122517981","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110744
E. Abdulova
The paper is devoted to the problems of the information task of the upper level control system of the NPP I&C system "Calculation and analysis of technical and economic indicators" and the construction of instantaneous predictive models for this task based on the critical parameters of the power unit. The article considers a modified algorithm for assessing the risk potential of a technological process based on data mining, analysis of approximating and detailing coefficients of the wavelet decomposition of the input and output parameters of the instantaneous predictive model, and stability conditions of the predictive model based on a multiple-scale transformation. Using the example of an instantaneous predictive model for the feed water temperature at the inlet of a high-pressure heater, Hurst indicators for the measured parameters of the model are given, and a conclusion is made about the persistence of the ongoing process with the effect of long-term memory, a sample of close states from the object database is shown on the example of one of the points. Also, for this model, a comparison of real data and the predictive model is given, which shows the adequacy of the developed instant predictive model. In this connection, it is concluded that this model can be used to monitor the state of the NPP power unit, which allows identifying changes of various nature in the processes occurring in the system to assess the risk potential of processes, despite the presence of unreliable or substituted signals.
{"title":"Modification of the Risk Potential Predicting Algorithm for Monitoring the State of the NPP Power Unit","authors":"E. Abdulova","doi":"10.1109/SmartIndustryCon57312.2023.10110744","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110744","url":null,"abstract":"The paper is devoted to the problems of the information task of the upper level control system of the NPP I&C system \"Calculation and analysis of technical and economic indicators\" and the construction of instantaneous predictive models for this task based on the critical parameters of the power unit. The article considers a modified algorithm for assessing the risk potential of a technological process based on data mining, analysis of approximating and detailing coefficients of the wavelet decomposition of the input and output parameters of the instantaneous predictive model, and stability conditions of the predictive model based on a multiple-scale transformation. Using the example of an instantaneous predictive model for the feed water temperature at the inlet of a high-pressure heater, Hurst indicators for the measured parameters of the model are given, and a conclusion is made about the persistence of the ongoing process with the effect of long-term memory, a sample of close states from the object database is shown on the example of one of the points. Also, for this model, a comparison of real data and the predictive model is given, which shows the adequacy of the developed instant predictive model. In this connection, it is concluded that this model can be used to monitor the state of the NPP power unit, which allows identifying changes of various nature in the processes occurring in the system to assess the risk potential of processes, despite the presence of unreliable or substituted signals.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114505983","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110830
E. Karmanova, Irina V. Gavrilova, Olga E. Maslennikova
The article deals with the current issues of knowledge management automation. The authors describe the possibilities of deep learning methods for checking homework and control tasks in such school subjects as Russian language, literature, social studies, history. As a rule, the main form of presenting answers to tasks is text. In this regard, it is proposed to automate the process of recognizing handwritten students texts and checking for compliance of the student’s response with the template document proposed by the teacher for this task. The main process of the service is handwritten text recognition technology, which is implemented on the basis of convolutional and recurrent neural network architecture using a decoding algorithm based on connective time classification. The article also provides a description of the online service, which implements the ability to download the answer to the task by students, recognition of the answer, determination and output of the answer similarity percentage with the attached answer from the teacher. According to the authors, this service will automate the teachers routine operations to check homework. It will be especially useful during the implementation of distance learning during pandemics, quarantines, etc.
{"title":"Deep Learning in Automation of Checking Homework Assignments","authors":"E. Karmanova, Irina V. Gavrilova, Olga E. Maslennikova","doi":"10.1109/SmartIndustryCon57312.2023.10110830","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110830","url":null,"abstract":"The article deals with the current issues of knowledge management automation. The authors describe the possibilities of deep learning methods for checking homework and control tasks in such school subjects as Russian language, literature, social studies, history. As a rule, the main form of presenting answers to tasks is text. In this regard, it is proposed to automate the process of recognizing handwritten students texts and checking for compliance of the student’s response with the template document proposed by the teacher for this task. The main process of the service is handwritten text recognition technology, which is implemented on the basis of convolutional and recurrent neural network architecture using a decoding algorithm based on connective time classification. The article also provides a description of the online service, which implements the ability to download the answer to the task by students, recognition of the answer, determination and output of the answer similarity percentage with the attached answer from the teacher. According to the authors, this service will automate the teachers routine operations to check homework. It will be especially useful during the implementation of distance learning during pandemics, quarantines, etc.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128394416","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：