K. A. Korennaya, Novokuznetsk Russian Federation Jsc “Kuznetsk Ferroalloys”, A. Hollay, O. V. Loginovsky
Today, the problem of increasing the efficiency of large Russian industrial enterprises is one of the most important national economic problems of the domestic economy. Purpose of the study. In this regard, the purpose of the study of this work is to improve the processes of prepa¬ring and mak-ing managerial decisions on the strategic and operational management of industrial enterprises of our country in the current conditions of global instability and increasing international competition. Materials and methods. The scientific provisions presented in the article are an integral set of measures that ensure the implementation of both strategic and operational management algorithms for industrial enterprises. At the same time, the methods of mathematical modeling and financial and economic analytics were used. Results. The results of the study are: a well-founded set of scien-tific provisions on the strategic management of industrial enterprises, as well as a predictive and adaptive approach to the operational management of production companies in the conditions of both stable development of the world economy and international financial and economic crises. On the basis of the developed sets of scientific provisions, sets of mathematical models for the stra-tegic management of industrial enterprises and their operational management are formed. Conclu-sion. The scientific provisions and materials presented in this article enable the heads of industrial enterprises to form holistic and comprehensively justified strategies for their long-term development, as well as algorithms for operational management of industrial divisions of enterprises during peri-ods of global instability.
{"title":"FUNDAMENTALS OF EFFECTIVE MANAGEMENT OF INDUSTRIAL ENTERPRISES IN MODERN CONDITIONS","authors":"K. A. Korennaya, Novokuznetsk Russian Federation Jsc “Kuznetsk Ferroalloys”, A. Hollay, O. V. Loginovsky","doi":"10.14529/ctcr210316","DOIUrl":"https://doi.org/10.14529/ctcr210316","url":null,"abstract":"Today, the problem of increasing the efficiency of large Russian industrial enterprises is one of the most important national economic problems of the domestic economy. Purpose of the study. In this regard, the purpose of the study of this work is to improve the processes of prepa¬ring and mak-ing managerial decisions on the strategic and operational management of industrial enterprises of our country in the current conditions of global instability and increasing international competition. Materials and methods. The scientific provisions presented in the article are an integral set of measures that ensure the implementation of both strategic and operational management algorithms for industrial enterprises. At the same time, the methods of mathematical modeling and financial and economic analytics were used. Results. The results of the study are: a well-founded set of scien-tific provisions on the strategic management of industrial enterprises, as well as a predictive and adaptive approach to the operational management of production companies in the conditions of both stable development of the world economy and international financial and economic crises. On the basis of the developed sets of scientific provisions, sets of mathematical models for the stra-tegic management of industrial enterprises and their operational management are formed. Conclu-sion. The scientific provisions and materials presented in this article enable the heads of industrial enterprises to form holistic and comprehensively justified strategies for their long-term development, as well as algorithms for operational management of industrial divisions of enterprises during peri-ods of global instability.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133725745","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 COVID-19 pandemic has really become a real shock for the whole world. The way of life has changed not only for people, but also for companies in various industries. Today, the real estate market, like many other industries, is in conditions of economic instability. The study highlights the problems faced by the construction sector in the current conditions of the coronavirus pandem-ic. One of these problems is the sustainable competitiveness of construction and its compliance with new consumer preferences. Aim. The study of the influence of engineering solutions and other fac-tors on the competitiveness of construction in modern economic conditions, the definition of key criteria. Development and description of the decision-making methodology for choosing the optimal construction enterprise from the point of view of competitiveness. Materials and methods. The methods of system analysis, optimization methods, hierarchy analysis and decision theory are ap-plied in the work. Within the framework of the proposed methodology, the author's method of identifying key competitiveness criteria has been developed. Since the problem of choosing the optimal solution from among the alternatives is based on a multi-criteria approach, the use of this method is quite appropriate. The template for the formation of the methodology was identified based on the analy-sis of existing research in this area. Results. The author summarizes and supplements the criteria and factors affecting the competitiveness of construction organizations in the study. The author's method of making a decision on determining the optimal construction enterprise from the point of view of competitiveness based on the criteria considered by the author is presented. This technique includes several stages: 1) forming a goal; 2) formation of criteria by which organizations will be evaluated; 3) calculation of criteria for each organization and bringing them to a homogeneous type of data; 4) building a tree of goals and a matrix of priorities; 5) Determining the values of priority vectors for each organization under study. Conclusion. The total influence of criteria and engineering solutions on the competitiveness of construction is determined. In this regard, the implementation of the con-struction project should be carried out taking into account the strategic goals of the organization and binding to the identified criteria. The proposed methodology is developed for Russian construc-tion companies operating in modern economic conditions.
{"title":"EFFICIENT ENGINEERING IN DEVELOPMENT OF CONSTRUCTION SECTOR COMPETITIVENESS","authors":"O. Bekirova, S. Barkalov, M. Trifonova","doi":"10.14529/ctcr210309","DOIUrl":"https://doi.org/10.14529/ctcr210309","url":null,"abstract":"The COVID-19 pandemic has really become a real shock for the whole world. The way of life has changed not only for people, but also for companies in various industries. Today, the real estate market, like many other industries, is in conditions of economic instability. The study highlights the problems faced by the construction sector in the current conditions of the coronavirus pandem-ic. One of these problems is the sustainable competitiveness of construction and its compliance with new consumer preferences. Aim. The study of the influence of engineering solutions and other fac-tors on the competitiveness of construction in modern economic conditions, the definition of key criteria. Development and description of the decision-making methodology for choosing the optimal construction enterprise from the point of view of competitiveness. Materials and methods. The methods of system analysis, optimization methods, hierarchy analysis and decision theory are ap-plied in the work. Within the framework of the proposed methodology, the author's method of identifying key competitiveness criteria has been developed. Since the problem of choosing the optimal solution from among the alternatives is based on a multi-criteria approach, the use of this method is quite appropriate. The template for the formation of the methodology was identified based on the analy-sis of existing research in this area. Results. The author summarizes and supplements the criteria and factors affecting the competitiveness of construction organizations in the study. The author's method of making a decision on determining the optimal construction enterprise from the point of view of competitiveness based on the criteria considered by the author is presented. This technique includes several stages: 1) forming a goal; 2) formation of criteria by which organizations will be evaluated; 3) calculation of criteria for each organization and bringing them to a homogeneous type of data; 4) building a tree of goals and a matrix of priorities; 5) Determining the values of priority vectors for each organization under study. Conclusion. The total influence of criteria and engineering solutions on the competitiveness of construction is determined. In this regard, the implementation of the con-struction project should be carried out taking into account the strategic goals of the organization and binding to the identified criteria. The proposed methodology is developed for Russian construc-tion companies operating in modern economic conditions.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126214254","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}
Mostafa Salaheldin Abdelsalam Abotaleb, T. Makarovskikh
Time series analysis became one of the most investigated fields of knowledge during spreading of the COVID-19 around the world. The problem of modeling and forecasting infection cases of COVID-19, deaths, recoveries and other parameters is still urgent. Purpose of the study. Our article is devoted to investigation of classical statistical and neural network models that can be used for forecasting COVID-19 cases. Materials and methods. We discuss neural network model NNAR, compare it with linear and nonlinear models (BATS, TBATS, Holt's linear trend, ARIMA, classical epidemiological SIR model). In our article we discuss the Epemedic.Network algorithm using the R programming language. This algorithm takes the time series as input data and chooses the best model from SIR, statistical models and neural network model. The model selection criterion is the MAPE error. We consider the implementation of our algorithm for analysis of time series for COVID -19 spreading in Chelyabinsk region, and predicting the possible peak of the third wave using three possible scenarios. We mention that the considered algorithm can work for any time se-ries, not only for epidemiological ones. Results. The developed algorithm helped to identify the pat-tern of COVID -19 infection for Chelyabinsk region using the models realized as parts of the consi-dered algorithm. It should be noted that the considered models make it possible to form short-term forecasts with sufficient accuracy. We show that the increase in the number of neurons led to in-creasing accuracy, as there are other cases where the error is reduced in case of reducing the number of neurons, and this depends on COVID -19 infection spreading pattern. Conclusion. Hence, to get a very accurate forecast, we recommend re-running the algorithm weekly. For medium-range fore-casting, only the NNAR model can be used from among those considered but it also allows to get good forecasts only with horizon 1–2 weeks.
{"title":"Development of Algorithms for Choosing the Best Time Series Models and Neural Networks to Predict COVID-19 Cases","authors":"Mostafa Salaheldin Abdelsalam Abotaleb, T. Makarovskikh","doi":"10.14529/ctcr210303","DOIUrl":"https://doi.org/10.14529/ctcr210303","url":null,"abstract":"Time series analysis became one of the most investigated fields of knowledge during spreading of the COVID-19 around the world. The problem of modeling and forecasting infection cases of COVID-19, deaths, recoveries and other parameters is still urgent. Purpose of the study. Our article is devoted to investigation of classical statistical and neural network models that can be used for forecasting COVID-19 cases. Materials and methods. We discuss neural network model NNAR, compare it with linear and nonlinear models (BATS, TBATS, Holt's linear trend, ARIMA, classical epidemiological SIR model). In our article we discuss the Epemedic.Network algorithm using the R programming language. This algorithm takes the time series as input data and chooses the best model from SIR, statistical models and neural network model. The model selection criterion is the MAPE error. We consider the implementation of our algorithm for analysis of time series for COVID -19 spreading in Chelyabinsk region, and predicting the possible peak of the third wave using three possible scenarios. We mention that the considered algorithm can work for any time se-ries, not only for epidemiological ones. Results. The developed algorithm helped to identify the pat-tern of COVID -19 infection for Chelyabinsk region using the models realized as parts of the consi-dered algorithm. It should be noted that the considered models make it possible to form short-term forecasts with sufficient accuracy. We show that the increase in the number of neurons led to in-creasing accuracy, as there are other cases where the error is reduced in case of reducing the number of neurons, and this depends on COVID -19 infection spreading pattern. Conclusion. Hence, to get a very accurate forecast, we recommend re-running the algorithm weekly. For medium-range fore-casting, only the NNAR model can be used from among those considered but it also allows to get good forecasts only with horizon 1–2 weeks.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124206457","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 collective agent coordination problem in organizational behavior systems is consider. In particular, the problem of coordinating of the agents’ interests to assess the degree of achieve-ment of the corporate strategic targets. The relevance of the problem is due to the need to increase the speed of decision-making, the speed of reaction to changes in the external environment, which can be achieved using appropriate control mechanisms. Aim. Improving methods of collective deci-sion making under circumstances where agents have different ranks of significance. Materials and methods. Methods comprise the integrated rating mechanisms and the generalized median voter schemes. The mathematical apparatus was chosen is contingent on the group decision making in organizational systems. Active agents strives to maximize his target function in the process of inter-action, which leads to a conflict of interests and a desire to distort information. The chosen methods allow these problems to be solved. The first ones are used to aggregate indicators that reflect the de-gree of achievement of the private goals of the organization at the strategic level. The second ones are used to identification the true agents’ opinions about the type of target index convolution matri-ces. Results. The matrix non-anonymous generalized median mechanism is proposed. The non-anonymous statement allows taking into account the interests of agents with different ranks. It is shown how to reduce non-anonymous procedure to an anonymous one. Decisions making process about all elements of the convolution matrices in integrated rating mechanisms with using anony-mous median voter scheme is strategy proofnees. However, the results of aggregation are not stabil-ity to the agent strategic behavior in cases of application anonymous or non-anonymous coordina-tion procedures. The new integrated mechanism based on the synthesis of known control mecha-nisms is proposed to overcome the discovered problem. Conclusion. The statement of the problem corresponds to the real procedures of decision making by governance board, when the opinion of one agent turns out to be more significant than the opinion of another agent. The developed mech-anism makes it possible to agree on the opinions of experts on the degree of achievement of the strategic goals of the organization; it can also be adapted to solve other applied problems, for ex-ample, making a decision on the choice of a project, assessing risks, assessing suppliers, etc.
{"title":"APPLICATION OF INTEGRATED RATING MECHANISMS AND MATRIX NON-ANONYMOUS GENERALIZED MEDIAN VOTER SCHEMES TO COORDINATION OF THE AGENTS’ INTERESTS","authors":"A. Alekseev, T. Kataeva","doi":"10.14529/ctcr210308","DOIUrl":"https://doi.org/10.14529/ctcr210308","url":null,"abstract":"The collective agent coordination problem in organizational behavior systems is consider. In particular, the problem of coordinating of the agents’ interests to assess the degree of achieve-ment of the corporate strategic targets. The relevance of the problem is due to the need to increase the speed of decision-making, the speed of reaction to changes in the external environment, which can be achieved using appropriate control mechanisms. Aim. Improving methods of collective deci-sion making under circumstances where agents have different ranks of significance. Materials and methods. Methods comprise the integrated rating mechanisms and the generalized median voter schemes. The mathematical apparatus was chosen is contingent on the group decision making in organizational systems. Active agents strives to maximize his target function in the process of inter-action, which leads to a conflict of interests and a desire to distort information. The chosen methods allow these problems to be solved. The first ones are used to aggregate indicators that reflect the de-gree of achievement of the private goals of the organization at the strategic level. The second ones are used to identification the true agents’ opinions about the type of target index convolution matri-ces. Results. The matrix non-anonymous generalized median mechanism is proposed. The non-anonymous statement allows taking into account the interests of agents with different ranks. It is shown how to reduce non-anonymous procedure to an anonymous one. Decisions making process about all elements of the convolution matrices in integrated rating mechanisms with using anony-mous median voter scheme is strategy proofnees. However, the results of aggregation are not stabil-ity to the agent strategic behavior in cases of application anonymous or non-anonymous coordina-tion procedures. The new integrated mechanism based on the synthesis of known control mecha-nisms is proposed to overcome the discovered problem. Conclusion. The statement of the problem corresponds to the real procedures of decision making by governance board, when the opinion of one agent turns out to be more significant than the opinion of another agent. The developed mech-anism makes it possible to agree on the opinions of experts on the degree of achievement of the strategic goals of the organization; it can also be adapted to solve other applied problems, for ex-ample, making a decision on the choice of a project, assessing risks, assessing suppliers, etc.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115845798","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 importance of production planning for improving the performance indicators of a mining enterprise is indicated. The possibility of simulation modeling using for this aim is shown. It is shown that the created model has a large number of stochastic parameters. It is investigated that there is a problem of research lack about the choice influence of the mining modeling results with different statistical distributions. It is known that with an increase in stochastic deviations from the initial parameters, the productivity of queuing systems decreases. Purpose of work is to study this influence with four statistical distributions of a random quantity (uniform, normal, negative bi-nomial and Poisson distribution) for individual operations and their combinations. In addition, it is necessary to determine how much a change in one particular parameter will affect the overall result of the modeling. Materials and methods. In the previously created simulation model, a stochastic delay is added to the time of individual operations. The addition of such a delay with different sta-tistical distributions and with the same mathematical expectation is investigated. The simulation re-sults are compared with each other, for each individual operation the absolute and relative devia-tion of the results is shown. Further, a similar simulation is performed when all the simultaneously selected parameters changing. Result. It is shown that the magnitude of the deviation significantly differs among all deviations. It is shown that for various single changes in operations, the largest and smal-lest deviations can be given by different statistical distributions. To study the joint change with all parameters, 3 modeling scenarios are implemented: all uniform distributions (this case is used now), the scenario with the smallest deviation and the scenario with the largest deviation. It is shown that switching to another scenario leads to a significant change in the simulation. Conclusion. It is con-cluded that the used significant influence of statistical distributions choice to the accuracy of model-ing the operation of the mining machine is shown, especially when they are taken into account to-gether. The results can be used to clarify the influence of individual factors in the simulation model and improve the planning of potash mining operations, for individual mining machines too.
{"title":"INVESTIGATION OF THE RANDOM VALUE STATISTICAL DISTRIBUTIONS MODELS CHOICE INFLUENCE ON THE MINING OPERATIONS MODELING RESULTS","authors":"A. Zatonskiy, P. A. Yazev","doi":"10.14529/ctcr210313","DOIUrl":"https://doi.org/10.14529/ctcr210313","url":null,"abstract":"The importance of production planning for improving the performance indicators of a mining enterprise is indicated. The possibility of simulation modeling using for this aim is shown. It is shown that the created model has a large number of stochastic parameters. It is investigated that there is a problem of research lack about the choice influence of the mining modeling results with different statistical distributions. It is known that with an increase in stochastic deviations from the initial parameters, the productivity of queuing systems decreases. Purpose of work is to study this influence with four statistical distributions of a random quantity (uniform, normal, negative bi-nomial and Poisson distribution) for individual operations and their combinations. In addition, it is necessary to determine how much a change in one particular parameter will affect the overall result of the modeling. Materials and methods. In the previously created simulation model, a stochastic delay is added to the time of individual operations. The addition of such a delay with different sta-tistical distributions and with the same mathematical expectation is investigated. The simulation re-sults are compared with each other, for each individual operation the absolute and relative devia-tion of the results is shown. Further, a similar simulation is performed when all the simultaneously selected parameters changing. Result. It is shown that the magnitude of the deviation significantly differs among all deviations. It is shown that for various single changes in operations, the largest and smal-lest deviations can be given by different statistical distributions. To study the joint change with all parameters, 3 modeling scenarios are implemented: all uniform distributions (this case is used now), the scenario with the smallest deviation and the scenario with the largest deviation. It is shown that switching to another scenario leads to a significant change in the simulation. Conclusion. It is con-cluded that the used significant influence of statistical distributions choice to the accuracy of model-ing the operation of the mining machine is shown, especially when they are taken into account to-gether. The results can be used to clarify the influence of individual factors in the simulation model and improve the planning of potash mining operations, for individual mining machines too.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125148342","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}
In the Russian Federation, the agro-industrial complex is one of the leading sectors of the eco-nomy with a volume of domestic product of 4.5%. Russia owns 10 % of all arable land in the world. According to the data on the sown areas by crops in 2020, most of the agricultural area of Russia is occupied by wheat. The Russian Federation ranks third in the ranking of leading countries in the production of this type of grain crops, as well as leading positions in its export. Brown (leaf) and linear (stem) rust is the most harmful disease of grain crops. It is the reason for the sparseness of wheat crops and leads to a sharp decrease in yield. Therefore, one of the main tasks of farmers is to preserve the crop from diseases. The application of such areas of artificial intelligence as computer vision, machine learning and deep learning is able to cope with this task. These artificial intelligence technologies allow us to successfully solve applied problems of the agro-industrial complex using automated analysis of photographic materials. Aim. To consider the application of computer vision methods for the problem of classification of lesions of cultivated plants on the example of wheat. Materials and methods. The CGIAR Computer Vision for Crop Disease dataset for the crop disease recognition task is taken from the open source Kaggle. It is proposed to use an approach to the re-cognition of lesions of cultivated plants using the well-known neural network models ResNet50, DenseNet169, VGG16 and EfficientNet-B0. Neural network models receive images of wheat as in-put. The output of neural networks is the class of plant damage. To overcome the effect of overfit-ting neural networks, various regularization techniques are investigated. Results. The results of the classification quality, estimated by the software using the F1-score metric, which is the average harmonic between the Precision and Recall measures, are presented. Conclusion. As a result of the conducted research, it was found that the DenseNet model showed the best recognition accuracy us-ing a combination of transfer learning technology and DropOut and L2 regulation technologies to overcome the effect of retraining. The use of this approach allowed us to achieve a recognition ac-curacy of 91%.
{"title":"APPLICATION OF COMPUTER VISION TECHNOLOGIES FOR THE DEVELOPMENT OF A MODEL FOR THE RECOGNITION OF LESIONS OF CULTIVATED PLANTS","authors":"N. Yanishevskaya, I. Bolodurina","doi":"10.14529/ctcr210301","DOIUrl":"https://doi.org/10.14529/ctcr210301","url":null,"abstract":"In the Russian Federation, the agro-industrial complex is one of the leading sectors of the eco-nomy with a volume of domestic product of 4.5%. Russia owns 10 % of all arable land in the world. According to the data on the sown areas by crops in 2020, most of the agricultural area of Russia is occupied by wheat. The Russian Federation ranks third in the ranking of leading countries in the production of this type of grain crops, as well as leading positions in its export. Brown (leaf) and linear (stem) rust is the most harmful disease of grain crops. It is the reason for the sparseness of wheat crops and leads to a sharp decrease in yield. Therefore, one of the main tasks of farmers is to preserve the crop from diseases. The application of such areas of artificial intelligence as computer vision, machine learning and deep learning is able to cope with this task. These artificial intelligence technologies allow us to successfully solve applied problems of the agro-industrial complex using automated analysis of photographic materials. Aim. To consider the application of computer vision methods for the problem of classification of lesions of cultivated plants on the example of wheat. Materials and methods. The CGIAR Computer Vision for Crop Disease dataset for the crop disease recognition task is taken from the open source Kaggle. It is proposed to use an approach to the re-cognition of lesions of cultivated plants using the well-known neural network models ResNet50, DenseNet169, VGG16 and EfficientNet-B0. Neural network models receive images of wheat as in-put. The output of neural networks is the class of plant damage. To overcome the effect of overfit-ting neural networks, various regularization techniques are investigated. Results. The results of the classification quality, estimated by the software using the F1-score metric, which is the average harmonic between the Precision and Recall measures, are presented. Conclusion. As a result of the conducted research, it was found that the DenseNet model showed the best recognition accuracy us-ing a combination of transfer learning technology and DropOut and L2 regulation technologies to overcome the effect of retraining. The use of this approach allowed us to achieve a recognition ac-curacy of 91%.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114145869","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}
This article discusses the problem of controlling the process of electromagnetic oscillations in a long-distance transmission line. A long line is understood as an electrical line formed, in the sim-plest case, by two parallel current conductors, the length of which exceeds the wavelength of the transmitted electromagnetic waves, and the distance between the conductors is much less than the wavelength. Such a line is characterized by four distributed parameters, namely the ohmic re-sistance of the conductor, inductance, electrical capacity and leakage coefficient. A signal generator is connected to the left end of the line, and the right is grounded, but not of high quality. When transmitting a signal, the current and voltage make small oscillation. The control is the voltage at the left end of the long line, and the disturbance voltage at the right end, the values of which are li-mited. The boundaries of their permissible values are set. The magnitude of the aggregate of exter-nal disturbances acting on the conductor is not known exactly, but only its variation limits are given. Aim. The purpose of the control process is that at a given moment in time, the average value of the voltage value is in a given interval. This average is calculated using the specified function. Materials and methods. To solve the problem, the method of optimizing the guaranteed result was applied. Results. A transition was made to a new one-dimensional variable, with the help of which the considered problem was reduced to a control problem of the same type in the presence of inter-ference. This made it possible to find the necessary and sufficient conditions under which it is pos-sible to achieve the set goals with any admissible set of external forces and interference at the right end. A corresponding algorithm for constructing the law of voltage change at the left end of the conductor is proposed. An example is analyzed that clearly shows how management is built that guarantees the achievement of the set goal. Conclusion. If the found necessary and sufficient con-ditions are fulfilled, then it is always possible to construct such a law of voltage variation at the left end, which will lead to the achievement of the goal for any admissible interference.
{"title":"ON ONE PROBLEM OF CONTROL OF VOLTAGE DURING SIGNAL TRANSMISSION IN A LONG LINE","authors":"N.D. Livanov, V. Ukhobotov","doi":"10.14529/ctcr210306","DOIUrl":"https://doi.org/10.14529/ctcr210306","url":null,"abstract":"This article discusses the problem of controlling the process of electromagnetic oscillations in a long-distance transmission line. A long line is understood as an electrical line formed, in the sim-plest case, by two parallel current conductors, the length of which exceeds the wavelength of the transmitted electromagnetic waves, and the distance between the conductors is much less than the wavelength. Such a line is characterized by four distributed parameters, namely the ohmic re-sistance of the conductor, inductance, electrical capacity and leakage coefficient. A signal generator is connected to the left end of the line, and the right is grounded, but not of high quality. When transmitting a signal, the current and voltage make small oscillation. The control is the voltage at the left end of the long line, and the disturbance voltage at the right end, the values of which are li-mited. The boundaries of their permissible values are set. The magnitude of the aggregate of exter-nal disturbances acting on the conductor is not known exactly, but only its variation limits are given. Aim. The purpose of the control process is that at a given moment in time, the average value of the voltage value is in a given interval. This average is calculated using the specified function. Materials and methods. To solve the problem, the method of optimizing the guaranteed result was applied. Results. A transition was made to a new one-dimensional variable, with the help of which the considered problem was reduced to a control problem of the same type in the presence of inter-ference. This made it possible to find the necessary and sufficient conditions under which it is pos-sible to achieve the set goals with any admissible set of external forces and interference at the right end. A corresponding algorithm for constructing the law of voltage change at the left end of the conductor is proposed. An example is analyzed that clearly shows how management is built that guarantees the achievement of the set goal. Conclusion. If the found necessary and sufficient con-ditions are fulfilled, then it is always possible to construct such a law of voltage variation at the left end, which will lead to the achievement of the goal for any admissible interference.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121310848","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 importance of the problem of ore averaging at potash enterprises and the search for the optimal set of measures to eliminate the problem are shown. The problem of a large spread of insol-uble residues in the potash enterprises of the Verkhnekamsky District is identified. At the moment, it is solved by bunker averaging, but this does not always work effectively. It was suggested to use the previously described method of meaningful distribution in the warehouse and targeted sampling depending on the composition. A mathematical model of loading and unloading of the warehouse was constructed; algorithms and calculation of the coordinates of the point of discharge and extrac-tion of ore were proposed, depending on the content of insoluble residue and potassium chloride in the ore. This method excludes the possibility of manufacturing defects and carries out the averaging of raw materials in an optimal way. According to the indicators in the simulation model, targeted sampling in the warehouse reduces the percentage spread of insoluble residues in the ore. It was de-cided to investigate the sampling process in the warehouse for identification. Purpose of work is to test the possibility of controlling the sample as a conventional technological object using a propor-tional-integral-differentiating controller. To do this, the control object was identified, namely: a sin-gle impact jump was applied to the system input. Materials and methods. The standard impact was modeled on a previously developed warehouse simulation model, where the geometric parameters of the warehouse, the physical parameters of the ore elements, as well as the parameters of the noz-zle and scraper movement are set. With its help, potassium chloride from ore is conducted. The re-sults of the ore sampling are recorded for the initial installations, and then after a five percent jump. The simulation results are presented as a normalized graph for comparing the results and determin-ing the behavior of the system. Result. The resulting array of values was moved to the previously developed transfer function calculator. Based on the values found, a smoothed normalized graph was constructed, which had to be identified. As a result of this work, the transfer function of the first-order aperiodic link with a delay was obtained. Conclusion. When analyzing the graphs, a con-clusion about the validity of the obtained function was made. Based on the obtained arrays of val-ues, an error of 6,5% was calculated. The transfer function has been identified, so the sample in the warehouse can be controlled using a proportional-integral-differentiating controller.
{"title":"STUDY OF THE POSSIBILITY OF CONTROLLING ORE AVERAGING BY METHODS OF CLASSICAL CONTROL THEORY","authors":"N. Bilfeld, D.V. Peyas, A.K. Shnabskaya","doi":"10.14529/ctcr210312","DOIUrl":"https://doi.org/10.14529/ctcr210312","url":null,"abstract":"The importance of the problem of ore averaging at potash enterprises and the search for the optimal set of measures to eliminate the problem are shown. The problem of a large spread of insol-uble residues in the potash enterprises of the Verkhnekamsky District is identified. At the moment, it is solved by bunker averaging, but this does not always work effectively. It was suggested to use the previously described method of meaningful distribution in the warehouse and targeted sampling depending on the composition. A mathematical model of loading and unloading of the warehouse was constructed; algorithms and calculation of the coordinates of the point of discharge and extrac-tion of ore were proposed, depending on the content of insoluble residue and potassium chloride in the ore. This method excludes the possibility of manufacturing defects and carries out the averaging of raw materials in an optimal way. According to the indicators in the simulation model, targeted sampling in the warehouse reduces the percentage spread of insoluble residues in the ore. It was de-cided to investigate the sampling process in the warehouse for identification. Purpose of work is to test the possibility of controlling the sample as a conventional technological object using a propor-tional-integral-differentiating controller. To do this, the control object was identified, namely: a sin-gle impact jump was applied to the system input. Materials and methods. The standard impact was modeled on a previously developed warehouse simulation model, where the geometric parameters of the warehouse, the physical parameters of the ore elements, as well as the parameters of the noz-zle and scraper movement are set. With its help, potassium chloride from ore is conducted. The re-sults of the ore sampling are recorded for the initial installations, and then after a five percent jump. The simulation results are presented as a normalized graph for comparing the results and determin-ing the behavior of the system. Result. The resulting array of values was moved to the previously developed transfer function calculator. Based on the values found, a smoothed normalized graph was constructed, which had to be identified. As a result of this work, the transfer function of the first-order aperiodic link with a delay was obtained. Conclusion. When analyzing the graphs, a con-clusion about the validity of the obtained function was made. Based on the obtained arrays of val-ues, an error of 6,5% was calculated. The transfer function has been identified, so the sample in the warehouse can be controlled using a proportional-integral-differentiating controller.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127983552","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}
Currently, the problems of distortion of measurement data by noise and the appearance of un-certainties in quality criteria have caused increased interest in research in the field of spline approx-imation. At the same time, existing methods of minimizing empirical risk, assuming that the noise is a uniform distribution with heavier tails than Gaussian, limit the scope of application of these studies. The problem of estimating noise-distorted data is usually based on solving an optimi-zation problem with a function containing uncertainty arising from the problem of finding optimal parameters. In this regard, the estimation of distorted noise cannot be solved by classical methods. Aim. This study is aimed at solving and analyzing the problem of spline approximation of data under uncertainty conditions based on the parametrization of control and the gradient projec-tion algorithm. Methods. The study of the problem of spline approximation of noisy data is carried out by the method of approximation of the piecewise constant control function. In this case, para-metrization of the control is possible only for a finite number of break points of the first kind. In the framework of the experimental study, the gradient projection algorithm is used for the numerical solution of the spline approximation problem. The proposed methods are used to study the parameters of the problem of spline approximation of data under conditions of uncertain-ty. Results. The numerical study of the control parametrization approach and the gradient projec-tion algorithm is based on the developed software and algorithmic tool for solving the problem of the spline approximation model under uncertainty. To evaluate the noise-distorted data, numerical experiments were conducted to study the model parameters and it was found that increasing the value of the parameter α leads to an increase in accuracy, but a loss of smoothness. In addition, the analysis showed that the considered distribution laws did not change the accuracy and convergence rate of the algorithm. Conclusion. The proposed approach for solving the problem of spline approx-imation under uncertainty conditions allows us to determine the problems of distortion of measure-ment data by noise and the appearance of uncertainties in the quality criteria. The study of the model parameters showed that the constructed system is stable to the error of the initial approxima-tion, and the distribution laws do not significantly affect the accuracy and convergence of the gra-dient projection method.
{"title":"INVESTIGATION OF PARAMETERS OF THE PROBLEM OF SPLINE APPROXIMATION OF NOISY DATA BY NUMERICAL METHODS OF OPTIMAL CONTROL","authors":"I. Bolodurina, L. Grishina, L. M. Antsiferova","doi":"10.14529/ctcr210314","DOIUrl":"https://doi.org/10.14529/ctcr210314","url":null,"abstract":"Currently, the problems of distortion of measurement data by noise and the appearance of un-certainties in quality criteria have caused increased interest in research in the field of spline approx-imation. At the same time, existing methods of minimizing empirical risk, assuming that the noise is a uniform distribution with heavier tails than Gaussian, limit the scope of application of these studies. The problem of estimating noise-distorted data is usually based on solving an optimi-zation problem with a function containing uncertainty arising from the problem of finding optimal parameters. In this regard, the estimation of distorted noise cannot be solved by classical methods. Aim. This study is aimed at solving and analyzing the problem of spline approximation of data under uncertainty conditions based on the parametrization of control and the gradient projec-tion algorithm. Methods. The study of the problem of spline approximation of noisy data is carried out by the method of approximation of the piecewise constant control function. In this case, para-metrization of the control is possible only for a finite number of break points of the first kind. In the framework of the experimental study, the gradient projection algorithm is used for the numerical solution of the spline approximation problem. The proposed methods are used to study the parameters of the problem of spline approximation of data under conditions of uncertain-ty. Results. The numerical study of the control parametrization approach and the gradient projec-tion algorithm is based on the developed software and algorithmic tool for solving the problem of the spline approximation model under uncertainty. To evaluate the noise-distorted data, numerical experiments were conducted to study the model parameters and it was found that increasing the value of the parameter α leads to an increase in accuracy, but a loss of smoothness. In addition, the analysis showed that the considered distribution laws did not change the accuracy and convergence rate of the algorithm. Conclusion. The proposed approach for solving the problem of spline approx-imation under uncertainty conditions allows us to determine the problems of distortion of measure-ment data by noise and the appearance of uncertainties in the quality criteria. The study of the model parameters showed that the constructed system is stable to the error of the initial approxima-tion, and the distribution laws do not significantly affect the accuracy and convergence of the gra-dient projection method.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127309984","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 problem of bulkiness of mathematical models of manipulative systems of industrial robots is solved. Here we consider formulas for calculating static reactions in joints and formulas for active forces that balance the forces of gravity acting on the manipulator's bodies in its stationary state. The manipulator can be in such a state when it is before capturing the object of manipulation and releasing it, or when it is performing some assembly operations, or it is during spot welding and in slow (quasi-static) arc-welding and painting processes. Aim. The aim is to derive general recur-rence and finite formulas for calculating the reaction forces in joints and their projections to the ax-es of the coordinate system rigidly connected with the selected body. Express the formulas of force projections in terms of guiding cosines and justify their optimality in terms of the minimum of arithmetic operations. Derive general inverse recurrence formulas for writing out the guide cosines of the axes associated with the moving bodies of the coordinate system with respect to the stationary coordinate system. Research methods. The methods of research relate to vector mechanics and sys-tems analysis, and the algorithmization of calculations by reducing them to the use of recurrent formulas. Results. A systematic analysis of general formulas, in which all possible regular expres-sions are highlighted which are corresponding unambiguously to the kinematic parameters of ma-nipulators, is performed. These regular expressions are used in software for analytical modeling of manipulator, in particular, for the analytical solution of problems of statics of a manipulator. The method of analytical verification of the prescribed formulas is described. The tasks of writing out optimal formulas for calculating the projections of static reaction forces in joints have been solved. And the tasks of writing out optimal formulas for calculating active forces in progressive joints of universal manipulators with six degrees of freedom, operating in Cartesian, cylindrical, spherical and angular coordinate systems, have been solved also. Analytical verification of the derived equations of stat-ics is performed. Examples of the reuse of the derived formulas for manipulators with the same kin-ematic schemes of their subsystems. Conclusion. Expressions of the equations of statics of manipu-lators through the guide cosines of the axes of the associated coordinate systems of their bodies al-low us to write these equations through the known parameters of body orientation. The recurrent formulas for calculating directional cosines allows to use recursive functions in their software im-plementation, i.e. to increase the computational efficiency of the software.
{"title":"WRITING OUT OF FORMULAS FOR CALCULATING FORCES IN THE JOINTS OF MANIPULATORS IN STATICS","authors":"S. G. Pudovkina, A. I. Telegin","doi":"10.14529/ctcr210305","DOIUrl":"https://doi.org/10.14529/ctcr210305","url":null,"abstract":"The problem of bulkiness of mathematical models of manipulative systems of industrial robots is solved. Here we consider formulas for calculating static reactions in joints and formulas for active forces that balance the forces of gravity acting on the manipulator's bodies in its stationary state. The manipulator can be in such a state when it is before capturing the object of manipulation and releasing it, or when it is performing some assembly operations, or it is during spot welding and in slow (quasi-static) arc-welding and painting processes. Aim. The aim is to derive general recur-rence and finite formulas for calculating the reaction forces in joints and their projections to the ax-es of the coordinate system rigidly connected with the selected body. Express the formulas of force projections in terms of guiding cosines and justify their optimality in terms of the minimum of arithmetic operations. Derive general inverse recurrence formulas for writing out the guide cosines of the axes associated with the moving bodies of the coordinate system with respect to the stationary coordinate system. Research methods. The methods of research relate to vector mechanics and sys-tems analysis, and the algorithmization of calculations by reducing them to the use of recurrent formulas. Results. A systematic analysis of general formulas, in which all possible regular expres-sions are highlighted which are corresponding unambiguously to the kinematic parameters of ma-nipulators, is performed. These regular expressions are used in software for analytical modeling of manipulator, in particular, for the analytical solution of problems of statics of a manipulator. The method of analytical verification of the prescribed formulas is described. The tasks of writing out optimal formulas for calculating the projections of static reaction forces in joints have been solved. And the tasks of writing out optimal formulas for calculating active forces in progressive joints of universal manipulators with six degrees of freedom, operating in Cartesian, cylindrical, spherical and angular coordinate systems, have been solved also. Analytical verification of the derived equations of stat-ics is performed. Examples of the reuse of the derived formulas for manipulators with the same kin-ematic schemes of their subsystems. Conclusion. Expressions of the equations of statics of manipu-lators through the guide cosines of the axes of the associated coordinate systems of their bodies al-low us to write these equations through the known parameters of body orientation. The recurrent formulas for calculating directional cosines allows to use recursive functions in their software im-plementation, i.e. to increase the computational efficiency of the software.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126980418","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：