2020. Т. 20, No 3. С. 39–46 39 Introduction The oil refining industry plays an important role in the country's economy and at the same time carries a danger as a source of fire and man-made accidents. The development of oil refineries increases the number and scale of fires and accidents, which cause damage both to the objects itself and to the surrounding buildings and structures, lives and health of people, environment. That is why increasing the level of fire protection systems at refineries remains one of the most important components of ensuring the protection of the population from anthropogenic threats [1]. Accidents and fires at oil refineries (Refineries) are difficult conditions with a rapid spread of fire to nearby areas and vehicles, which most often turn into a catastrophe whose material damage is huge. Refinery fires can be significant because of the large volume of flammable and combustible liquids stored in the territory [1].
{"title":"Integration of Fire Protection Systems Based on the Digital Automatic Model","authors":"K. Volkova","doi":"10.14529/ctcr200304","DOIUrl":"https://doi.org/10.14529/ctcr200304","url":null,"abstract":"2020. Т. 20, No 3. С. 39–46 39 Introduction The oil refining industry plays an important role in the country's economy and at the same time carries a danger as a source of fire and man-made accidents. The development of oil refineries increases the number and scale of fires and accidents, which cause damage both to the objects itself and to the surrounding buildings and structures, lives and health of people, environment. That is why increasing the level of fire protection systems at refineries remains one of the most important components of ensuring the protection of the population from anthropogenic threats [1]. Accidents and fires at oil refineries (Refineries) are difficult conditions with a rapid spread of fire to nearby areas and vehicles, which most often turn into a catastrophe whose material damage is huge. Refinery fires can be significant because of the large volume of flammable and combustible liquids stored in the territory [1].","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":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130160976","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}
Yu.V. Podpovetnaya, A. M. Najmiddinov, L.Yu. Ovsyanitskaya, A. D. Ovsyanitskiy
The documentation archive is an important base of accumulated knowledge and development of a company engaged in project activities. Given that the archive has diverse functions, it is quite difficult to organize clear work on structured storage, ensuring reliability of storage, confidentiality and differentiation of access rights, tracking the history of changes to documents, quick and easy search. Therefore, the article pays particular attention to solving the problem of improving the information system of an electronic archive of an enterprise. To solve the indicated problem, within the framework of this article, the functional requirements to the electronic archive of the enterprise are identified, the compliance of the existing system with the functional requirements is analyzed, measures are proposed to increase the efficiency of managing the electronic archive of documents. Based on the study of the electronic archive system of scientific and technical documentation (STD), the analysis and modeling of the structure of the electronic archive are carried out. The structure of the organizational part of the electronic STD archive, which regulates the life cycle of the document and the technical part responsible for the storage of documentation, is revealed. In order to improve the information system of the electronic archive of the enterprise, the models of business processes “Information Support”, “Management of storage and receipt of information” were built and the effectiveness of the developed models was evaluated. A comparative analysis of typical solutions of the electronic archive system is presented, which includes software products of the electronic archive STD: LOTSMAN: PLM Archive, STOR-M3 and TechnologiCS. As a result of the analysis, the correspondence of typical software products to the constructed business process models according to the required functionality is shown and the optimal system of electronic STD archive for implementation at the enterprise is selected.
{"title":"Совершенствование информационной системы электронного архива предприятия","authors":"Yu.V. Podpovetnaya, A. M. Najmiddinov, L.Yu. Ovsyanitskaya, A. D. Ovsyanitskiy","doi":"10.14529/CTCR190409","DOIUrl":"https://doi.org/10.14529/CTCR190409","url":null,"abstract":"The documentation archive is an important base of accumulated knowledge and development of a company engaged in project activities. Given that the archive has diverse functions, it is quite difficult to organize clear work on structured storage, ensuring reliability of storage, confidentiality and differentiation of access rights, tracking the history of changes to documents, quick and easy search. Therefore, the article pays particular attention to solving the problem of improving the information system of an electronic archive of an enterprise. To solve the indicated problem, within the framework of this article, the functional requirements to the electronic archive of the enterprise are identified, the compliance of the existing system with the functional requirements is analyzed, measures are proposed to increase the efficiency of managing the electronic archive of documents. Based on the study of the electronic archive system of scientific and technical documentation (STD), the analysis and modeling of the structure of the electronic archive are carried out. The structure of the organizational part of the electronic STD archive, which regulates the life cycle of the document and the technical part responsible for the storage of documentation, is revealed. In order to improve the information system of the electronic archive of the enterprise, the models of business processes “Information Support”, “Management of storage and receipt of information” were built and the effectiveness of the developed models was evaluated. A comparative analysis of typical solutions of the electronic archive system is presented, which includes software products of the electronic archive STD: LOTSMAN: PLM Archive, STOR-M3 and TechnologiCS. As a result of the analysis, the correspondence of typical software products to the constructed business process models according to the required functionality is shown and the optimal system of electronic STD archive for implementation at the enterprise is selected.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129669474","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 choosing the best prediction method of education results is major challenge of Educational Data Mining (EDM). This EDM paper compares the results of student's performance forecast produced by the individual binary classifiers (Naive Bayes, Decision Tree, Multi-Layer Perceptron, Nearest Neighbors, Support Vector Machine algorithms) and their ensembles, which are trained (tested) on dataset containing up to 38 input attributes (weekly attendance in mathematics, the intensity of study, interim assessment) of 84 (36) secondary school students from Nasiriyah, Iraq. The two-class school performance was predicted – passing or not passing on final exam. Three following stages of comparison were completed. Аt the first stage of the experiment, the dependence of classifiers from the input attributes was investigated. It was shown that the forecast accuracy rises from 61.1–77.7% when all 38 attributes were used, to 75.0–80.5%, if base classifier trained with five attributes pre-selected by Ranker Search method. Then, in second stage, to each of the basе classifier the AdaBoost M1 procedure has been applied and five homogenous ensembles were created. And only two of these ensembles demonstrated small rise of 3% in accuracy comparing to corresponding stand-alone classifier, but the overall maximal prediction accuracy of 80.5% stayed the same. Finally, comparing the accuracies of 77.7% and 83.3% achieved by the heterogeneous ensemble consisted of five simple voting base classifiers and by the heterogeneous meta-ensemble of five simple voting AdaBoost homogenous ensembles correspondingly, we conclude that improvement of the quality of the individual classifier or homogeneous ensembles allows to construct more powerful EDM prediction methods.
{"title":"Оптимизация конструкции ансамбля классификаторов: пример интеллектуального анализа образовательных данных","authors":"Y. K. Salal, S. Abdullaev","doi":"10.14529/CTCR190414","DOIUrl":"https://doi.org/10.14529/CTCR190414","url":null,"abstract":"The choosing the best prediction method of education results is major challenge of Educational Data Mining (EDM). This EDM paper compares the results of student's performance forecast produced by the individual binary classifiers (Naive Bayes, Decision Tree, Multi-Layer Perceptron, Nearest Neighbors, Support Vector Machine algorithms) and their ensembles, which are trained (tested) on dataset containing up to 38 input attributes (weekly attendance in mathematics, the intensity of study, interim assessment) of 84 (36) secondary school students from Nasiriyah, Iraq. The two-class school performance was predicted – passing or not passing on final exam. Three following stages of comparison were completed. Аt the first stage of the experiment, the dependence of classifiers from the input attributes was investigated. It was shown that the forecast accuracy rises from 61.1–77.7% when all 38 attributes were used, to 75.0–80.5%, if base classifier trained with five attributes pre-selected by Ranker Search method. Then, in second stage, to each of the basе classifier the AdaBoost M1 procedure has been applied and five homogenous ensembles were created. And only two of these ensembles demonstrated small rise of 3% in accuracy comparing to corresponding stand-alone classifier, but the overall maximal prediction accuracy of 80.5% stayed the same. Finally, comparing the accuracies of 77.7% and 83.3% achieved by the heterogeneous ensemble consisted of five simple voting base classifiers and by the heterogeneous meta-ensemble of five simple voting AdaBoost homogenous ensembles correspondingly, we conclude that improvement of the quality of the individual classifier or homogeneous ensembles allows to construct more powerful EDM prediction methods.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"17 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132974662","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}
Тимофеев Дмитрий Николаевич, Телегин Вадим Александрович, Телегин Александр Иванович, Пудовкина Светлана Геннадьевна
The new functionality of the SistemaTel software system (SS) has been described. An extensible markup language for three-dimensional vector graphics (X3D) for 3D modeling of controlled systems of bodies (ST) and scalar vector for 2D modeling of ST Graphics (SVG) have been used in this SS. A brief review of the SS of robots’ modeling using XML-oriented languages (URDF, SRDF, PLM) for marking the parameters of robots has been completed. The main difference between the SistemaTel and its analogues has been indicated. It depends on the fact that collisions are described as conditions for the transition from one ST structure to another one and are not intercepted in the process of graphical modeling, for example, as two-body collision events. An XsysTel language for marking ST has been proposed. It consists of the root node and nodes , . The nesting structure of the node declares the structure of the ST. The fields of the node expand its use to the description of the kinematic, static, and dynamic properties of ST. The node describes non-holding and dynamic bonds depending on the state and structure of the ST. Structural classification of the ST has been proposed. There distinguish ST with one Open Branch (STOB), ST with one Closed Branch (ST), Tree-like ST with Open Branches (TSTOB), Tree-like ST with open and closed Branches (with cycles) (TSTB) in the SistemaTel software system. Tree-like ST (TST) is a ST with the structure changing while the bodies’ moving. An example of the ST with a varying structure has been given. The transition conditions between structures can be geometric, kinematic and dynamic, for example, in the form of inequalities containing dynamic reactions in the joints of bodies. Examples of the XsysTel description of the ST in the plane (PST) have been given. An algorithm for XSLT conversion of the XsysTel description of the PST to the SVG-model of the PST has been developed.
{"title":"SVG-МОДЕЛИРОВАНИЕ УПРАВЛЯЕМЫХ СИСТЕМ ТЕЛ","authors":"Тимофеев Дмитрий Николаевич, Телегин Вадим Александрович, Телегин Александр Иванович, Пудовкина Светлана Геннадьевна","doi":"10.14529/CTCR190417","DOIUrl":"https://doi.org/10.14529/CTCR190417","url":null,"abstract":"The new functionality of the SistemaTel software system (SS) has been described. An extensible markup language for three-dimensional vector graphics (X3D) for 3D modeling of controlled systems of bodies (ST) and scalar vector for 2D modeling of ST Graphics (SVG) have been used in this SS. A brief review of the SS of robots’ modeling using XML-oriented languages (URDF, SRDF, PLM) for marking the parameters of robots has been completed. The main difference between the SistemaTel and its analogues has been indicated. It depends on the fact that collisions are described as conditions for the transition from one ST structure to another one and are not intercepted in the process of graphical modeling, for example, as two-body collision events. An XsysTel language for marking ST has been proposed. It consists of the root node and nodes , . The nesting structure of the node declares the structure of the ST. The fields of the node expand its use to the description of the kinematic, static, and dynamic properties of ST. The node describes non-holding and dynamic bonds depending on the state and structure of the ST. Structural classification of the ST has been proposed. There distinguish ST with one Open Branch (STOB), ST with one Closed Branch (ST), Tree-like ST with Open Branches (TSTOB), Tree-like ST with open and closed Branches (with cycles) (TSTB) in the SistemaTel software system. Tree-like ST (TST) is a ST with the structure changing while the bodies’ moving. An example of the ST with a varying structure has been given. The transition conditions between structures can be geometric, kinematic and dynamic, for example, in the form of inequalities containing dynamic reactions in the joints of bodies. Examples of the XsysTel description of the ST in the plane (PST) have been given. An algorithm for XSLT conversion of the XsysTel description of the PST to the SVG-model of the PST has been developed.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115357942","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}
Because the effectiveness of the methods and models of industrial enterprises management used now no longer provides a significant increase, and the methods and models themselves are actually outdated, there is an urgent need for new views and approaches to the management process. Native companies are in this situation even worse than foreign ones because of the policy of applying sanctions from Western countries, as well as due to the low level of technological development and the lack of investment in technological updating, which, in fact, most Russian companies do not carried out. In this article, the management of industrial enterprises is considered as one of the technologies in the framework of the adaptive-technological approach to management developed by the author, which represents the enterprise as a set of technologies (production, information, management, etc.) that obey the objective laws of development. The generalized definition of technology proposed in the article allows us to reduce any activity in the enterprise to this concept, including management. Moreover, management is essentially a process of transforming information about the system and the state of the external environment (information) into a control action (information). Thus, management technologies were assigned to a subclass of information technologies according to the classification proposed by the author, which distinguishes technologies depending on the environment undergoing transformation and the product that is available at the output. This made it possible to argue that the further development of managerial technologies will go along the path of increasingly introducing into the management advanced technologies developed in the IT industry.
{"title":"Management as a Technology within the Adaptive-Technological Approach","authors":"A. Hollay","doi":"10.14529/ctcr190415","DOIUrl":"https://doi.org/10.14529/ctcr190415","url":null,"abstract":"Because the effectiveness of the methods and models of industrial enterprises management used now no longer provides a significant increase, and the methods and models themselves are actually outdated, there is an urgent need for new views and approaches to the management process. Native companies are in this situation even worse than foreign ones because of the policy of applying sanctions from Western countries, as well as due to the low level of technological development and the lack of investment in technological updating, which, in fact, most Russian companies do not carried out. In this article, the management of industrial enterprises is considered as one of the technologies in the framework of the adaptive-technological approach to management developed by the author, which represents the enterprise as a set of technologies (production, information, management, etc.) that obey the objective laws of development. The generalized definition of technology proposed in the article allows us to reduce any activity in the enterprise to this concept, including management. Moreover, management is essentially a process of transforming information about the system and the state of the external environment (information) into a control action (information). Thus, management technologies were assigned to a subclass of information technologies according to the classification proposed by the author, which distinguishes technologies depending on the environment undergoing transformation and the product that is available at the output. This made it possible to argue that the further development of managerial technologies will go along the path of increasingly introducing into the management advanced technologies developed in the IT industry.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130528564","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}
It is known that the dynamic properties of industrial objects in control channels usually change significantly with a change in their mode of operation. Therefore, the indicators of quality of regulation with constant settings of automatic regulators also change, and, as a rule, they deteriorate during the operation of the units. In this connection, the problem arises of periodically adjusting the settings of regulators in the circuits of operating automatic control systems (ATS). This problem can be solved only by the actual dynamic parameters of the object being operated, therefore, the work considers the task of estimating these parameters, and according to the actual data of the operating closed system. In this case, a step perturbation is used either on the instructions or on the part of the regulator (on the load), the experienced reaction of the system to disturbances of any kind along the indicated channels can also be used. The control object is described by a second-order differential equation with delay. The parametric identification criterion is quadratic, either modular or minimax. The identification task is solved with the help of a program that implements the method of coordinate descent, the resulting one-dimensional minimization problems are solved with the help of a subroutine using the golden section method. For the numerical integration of the object equation, the Runge-Kutta method was used with an error proportional to the fifth power of the time step. In this paper, we tested the developed programs for parametric identification based on the experimental transient characteristics of ATS pressure in a metallurgical furnace. The numerical-analytical procedures for adjusting the regulators in the SAR by the found parameters of the control object are indicated.
{"title":"Параметрическая идентификация модели объекта управления по переходной функции работающей системы автоматического регулирования","authors":"V. I. Panferov, S. V. Panferov, K. S. Haldin","doi":"10.14529/CTCR190305","DOIUrl":"https://doi.org/10.14529/CTCR190305","url":null,"abstract":"It is known that the dynamic properties of industrial objects in control channels usually change significantly with a change in their mode of operation. Therefore, the indicators of quality of regulation with constant settings of automatic regulators also change, and, as a rule, they deteriorate during the operation of the units. In this connection, the problem arises of periodically adjusting the settings of regulators in the circuits of operating automatic control systems (ATS). This problem can be solved only by the actual dynamic parameters of the object being operated, therefore, the work considers the task of estimating these parameters, and according to the actual data of the operating closed system. In this case, a step perturbation is used either on the instructions or on the part of the regulator (on the load), the experienced reaction of the system to disturbances of any kind along the indicated channels can also be used. The control object is described by a second-order differential equation with delay. The parametric identification criterion is quadratic, either modular or minimax. The identification task is solved with the help of a program that implements the method of coordinate descent, the resulting one-dimensional minimization problems are solved with the help of a subroutine using the golden section method. For the numerical integration of the object equation, the Runge-Kutta method was used with an error proportional to the fifth power of the time step. In this paper, we tested the developed programs for parametric identification based on the experimental transient characteristics of ATS pressure in a metallurgical furnace. The numerical-analytical procedures for adjusting the regulators in the SAR by the found parameters of the control object are indicated.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115667069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A simulation is widely used as a basis for decision support systems. Many production systems may be considered as queuing systems if a time of processes more valuable than their physical meaning. Program models realized queuing systems are used in a planning and in optimization targets. But results of program simulation are not suitable for scientific qualification works according to traditions. Analytical conclusions are made using Kolvogorovs’ equations and some models derived from the one usually. But a question about possibility of using them with widespread statistical distributions is not quite explored. In this article we investigate a possibility of using the Kolmogorov's equations on a simple reproduction and death queuing system with some distributions. Numerical data is obtained from program models realized in GPSS and AnyLogic. Theoretical results in comparison with numerical data lead us to a conclusion. The possibility is present only when all statistical distributions in the model are exponential or very close to exponential. Else average error between the theory and the model is above 60%. So far as a small experimental data typical for observations in production systems does not allow to determine own statistical distribution surely, an uniform distribution is accepted as default, and Kolmogorov’s equations could not be used.
{"title":"Проверка возможности использования уравнения Колмогорова для расчета процессов гибели и размножения","authors":"A. V. Zatonskiy","doi":"10.14529/CTCR190306","DOIUrl":"https://doi.org/10.14529/CTCR190306","url":null,"abstract":"A simulation is widely used as a basis for decision support systems. Many production systems may be considered as queuing systems if a time of processes more valuable than their physical meaning. Program models realized queuing systems are used in a planning and in optimization targets. But results of program simulation are not suitable for scientific qualification works according to traditions. Analytical conclusions are made using Kolvogorovs’ equations and some models derived from the one usually. But a question about possibility of using them with widespread statistical distributions is not quite explored. In this article we investigate a possibility of using the Kolmogorov's equations on a simple reproduction and death queuing system with some distributions. Numerical data is obtained from program models realized in GPSS and AnyLogic. Theoretical results in comparison with numerical data lead us to a conclusion. The possibility is present only when all statistical distributions in the model are exponential or very close to exponential. Else average error between the theory and the model is above 60%. So far as a small experimental data typical for observations in production systems does not allow to determine own statistical distribution surely, an uniform distribution is accepted as default, and Kolmogorov’s equations could not be used.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"427 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122524889","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}
Stuck piping is a common problem with tremendous impact on drilling efficiency and costs in oil industry. Prediction of stuck at the stage of designing and in the process of drilling wells, minimizes the risk of the occurrence of sticking, due to the choice of the optimal method of prevention for specific geological and technical conditions. The article is devoted to the development of an artificial neural network for prediction of sticking of drill pipe columns. The paper provides a literature review of existing methods of prediction of sticks. As input data elements are used important and generalizing factors influencing the emergence of all types of sticks, which allows predicting all types of sticks of drill pipe columns. In order to increase the susceptibility of the input data to the neural network, the data elements are transformed and normalized. The type and architecture of the network, as well as its hyperparameters, are chosen by the experimental method. Assessment of the quality of the network is made by the method of k-fold cross-validation. In order to find the optimal combination of activation function with various optimizers, experimental research is carried out with the analysis of their results. The experiments were implemented in the Python programming language with KERAS, TensorFlow and Matplotlib library packages, as well as in the cloud platform Colaboratory from Google. A distinctive feature of the proposed method is that the resulting forecasting model can be easily adapted to new data, which often occurs when drilling wells in new fields.
{"title":"Разработка искусственной нейронной сети для прогнозирования прихватов колонн бурильных труб","authors":"Sh.Sh. Qodirov, A. L. Shestakov","doi":"10.14529/CTCR190302","DOIUrl":"https://doi.org/10.14529/CTCR190302","url":null,"abstract":"Stuck piping is a common problem with tremendous impact on drilling efficiency and costs in oil industry. Prediction of stuck at the stage of designing and in the process of drilling wells, minimizes the risk of the occurrence of sticking, due to the choice of the optimal method of prevention for specific geological and technical conditions. The article is devoted to the development of an artificial neural network for prediction of sticking of drill pipe columns. The paper provides a literature review of existing methods of prediction of sticks. As input data elements are used important and generalizing factors influencing the emergence of all types of sticks, which allows predicting all types of sticks of drill pipe columns. In order to increase the susceptibility of the input data to the neural network, the data elements are transformed and normalized. The type and architecture of the network, as well as its hyperparameters, are chosen by the experimental method. Assessment of the quality of the network is made by the method of k-fold cross-validation. In order to find the optimal combination of activation function with various optimizers, experimental research is carried out with the analysis of their results. The experiments were implemented in the Python programming language with KERAS, TensorFlow and Matplotlib library packages, as well as in the cloud platform Colaboratory from Google. A distinctive feature of the proposed method is that the resulting forecasting model can be easily adapted to new data, which often occurs when drilling wells in new fields.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233858","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}
Сергей Андреевич Кряжев, Дмитрий Иванович Левковский
This work is devoted to the development of information systems to support educational and methodological complexes of the discipline. The question of automating and typing a procedure for drawing up a work program for an educational institution is considered. The task of scientific research is to improve the quality of compilation and reduce the time spent on drawing up a work program for educational institutions, as well as to increase the convenience of updating the already created work programs. The object of the study is an automated information system to automate the compilation of the work program of the discipline. Subject of research – methods of unification of documents, methods for assessing the quality of the RP. The purpose of the work is to automate the procedure for drawing up a work program for educational directions for educational institutions and to simplify its maintenance and updating. As a research method, a modeling method was chosen. Modeling is a method for creating and researching models. The study of the model allows you to get new knowledge, new holistic information about the object. The first part of the work is devoted to the presentation of the results of the study of the subject area. In the course of the work, an analysis of the literature on the following topics was carried out: unification and assessment of the quality of documents; criteria for assessing the quality of documents; features of drawing up a work program discipline according to GOST. Highlights the main problems encountered in the preparation of the RP disciplines. The second part is devoted to the development of methods for assessing the quality of the work program document, and an analysis of the developed model has been conducted. The third part of the work includes the development of the basic elements of an information system and their description, as well as the development of system requirements, as well as its direct implementation. As a result of the study, an information system was designed and implemented, which allows to automate the process of creating a work program for the discipline by providing a partially completed template, as well as checking the compliance of hours with the work plan.
{"title":"Информационная система поддержки рабочей программы дисциплины","authors":"Сергей Андреевич Кряжев, Дмитрий Иванович Левковский","doi":"10.14529/CTCR190313","DOIUrl":"https://doi.org/10.14529/CTCR190313","url":null,"abstract":"This work is devoted to the development of information systems to support educational and methodological complexes of the discipline. The question of automating and typing a procedure for drawing up a work program for an educational institution is considered. The task of scientific research is to improve the quality of compilation and reduce the time spent on drawing up a work program for educational institutions, as well as to increase the convenience of updating the already created work programs. The object of the study is an automated information system to automate the compilation of the work program of the discipline. Subject of research – methods of unification of documents, methods for assessing the quality of the RP. The purpose of the work is to automate the procedure for drawing up a work program for educational directions for educational institutions and to simplify its maintenance and updating. As a research method, a modeling method was chosen. Modeling is a method for creating and researching models. The study of the model allows you to get new knowledge, new holistic information about the object. The first part of the work is devoted to the presentation of the results of the study of the subject area. In the course of the work, an analysis of the literature on the following topics was carried out: unification and assessment of the quality of documents; criteria for assessing the quality of documents; features of drawing up a work program discipline according to GOST. Highlights the main problems encountered in the preparation of the RP disciplines. The second part is devoted to the development of methods for assessing the quality of the work program document, and an analysis of the developed model has been conducted. The third part of the work includes the development of the basic elements of an information system and their description, as well as the development of system requirements, as well as its direct implementation. As a result of the study, an information system was designed and implemented, which allows to automate the process of creating a work program for the discipline by providing a partially completed template, as well as checking the compliance of hours with the work plan.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115480650","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}
Логиновский Олег Витальевич, Шестаков Александр Леонидович, Голлай Александр Владимирович
This paper provides an overview of modern information technologies used for management in industrial enterprises and corporations, as well as in government bodies. Despite the progress achieved in the performance of computers and supercomputers, as well as data analysis systems of various kinds, the introduction of modern information technologies does not improve the quality of management of various organizational and corporate structures. The long-term practice of building and operating various automated, information-computational, analytical, expert and other systems has shown that the introduction of these systems did not always contribute to a significant improvement in the quality of organizational management and to achieving the goals of improving the efficiency of the structures in which these systems were introduced. In this regard, today it is extremely important to realize that the reasons for the not-too-successful results of introducing various types of information systems lie not in the technical capabilities of computers, but in the fact that methods, models and control technologies at all stages of preparation and decision making remained essentially the same as they were in the last quarter of the last century. The lag in the development of management methods and algorithms has led to the fact that the capabilities of computing technology are not fully realized. Thus, an important task of the theory and practice of management is to reduce the backlog of decision-making methods from the modern level of computing technology. The paper sets the task of ensuring the coordination of the development of computing technology with the processes of improving and implementing management algorithms. The reasons that led to such a lag are given, and recommendations are given to eliminate it.
{"title":"Modern Information Technologies and the Need to Improve the Quality of Management of Organizational and Corporate Structures","authors":"Логиновский Олег Витальевич, Шестаков Александр Леонидович, Голлай Александр Владимирович","doi":"10.14529/ctcr190311","DOIUrl":"https://doi.org/10.14529/ctcr190311","url":null,"abstract":"This paper provides an overview of modern information technologies used for management in industrial enterprises and corporations, as well as in government bodies. Despite the progress achieved in the performance of computers and supercomputers, as well as data analysis systems of various kinds, the introduction of modern information technologies does not improve the quality of management of various organizational and corporate structures. The long-term practice of building and operating various automated, information-computational, analytical, expert and other systems has shown that the introduction of these systems did not always contribute to a significant improvement in the quality of organizational management and to achieving the goals of improving the efficiency of the structures in which these systems were introduced. In this regard, today it is extremely important to realize that the reasons for the not-too-successful results of introducing various types of information systems lie not in the technical capabilities of computers, but in the fact that methods, models and control technologies at all stages of preparation and decision making remained essentially the same as they were in the last quarter of the last century. The lag in the development of management methods and algorithms has led to the fact that the capabilities of computing technology are not fully realized. Thus, an important task of the theory and practice of management is to reduce the backlog of decision-making methods from the modern level of computing technology. The paper sets the task of ensuring the coordination of the development of computing technology with the processes of improving and implementing management algorithms. The reasons that led to such a lag are given, and recommendations are given to eliminate it.","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":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123133960","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：