Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537341
A. Marakhtanov, Evgeny O. Parenchenkov, N. Smirnov
This paper deals with the task of classification of accounts registered in e-commerce systems. The authors consider solving this problem with different machine learning algorithms and LSTM recurrent neural network. A brief description of machine learning algorithms and LSTM neural network used during the research is given in the paper. The dataset and algorithm of its preprocessing are described, additional features are introduced. The paper presents the results of numerical experiments: confusion matrices and classification metrics received with considered algorithms. Comparing of the models has been conducted on the basis of received metrics. The algorithm that provides the best metrics is selected. The SMOTE and ADASYN resampling algorithms are applied to the dataset, the received classification metrics are provided. The methods of improving classification results are proposed.
{"title":"Detection of Fictitious Accounts Registration","authors":"A. Marakhtanov, Evgeny O. Parenchenkov, N. Smirnov","doi":"10.1109/RusAutoCon52004.2021.9537341","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537341","url":null,"abstract":"This paper deals with the task of classification of accounts registered in e-commerce systems. The authors consider solving this problem with different machine learning algorithms and LSTM recurrent neural network. A brief description of machine learning algorithms and LSTM neural network used during the research is given in the paper. The dataset and algorithm of its preprocessing are described, additional features are introduced. The paper presents the results of numerical experiments: confusion matrices and classification metrics received with considered algorithms. Comparing of the models has been conducted on the basis of received metrics. The algorithm that provides the best metrics is selected. The SMOTE and ADASYN resampling algorithms are applied to the dataset, the received classification metrics are provided. The methods of improving classification results are proposed.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126312601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537381
S. Efimov, V. Terskov, K. Yarkov
The article aims to optimize the reliability of multiprocessor hardware and software systems with n-version software designed for real-time control systems. The reliability of real-time systems is critical. The reliability of the hardware and software complex of the control system can be ensured by means of hardware redundancy and the use of an n-version approach in software development. To find the composition of the hardware and software system that provides the specified reliability, it is proposed to use a mathematical model that takes into account the failures and recovery of hardware and software components of the computing system. At the same time, with such an approach to ensuring reliability, the cost of developing and operating a control system may increase unreasonably. Further, an optimization problem is formulated in which maximization of reliability is chosen as the optimality criterion, and the performance and cost criteria are translated into constraints. There is the conclusion that this problem can be effectively solved with the help of evolutionary optimization methods.
{"title":"Improving the Reliability of Real-Time Hardware and Software Systems","authors":"S. Efimov, V. Terskov, K. Yarkov","doi":"10.1109/RusAutoCon52004.2021.9537381","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537381","url":null,"abstract":"The article aims to optimize the reliability of multiprocessor hardware and software systems with n-version software designed for real-time control systems. The reliability of real-time systems is critical. The reliability of the hardware and software complex of the control system can be ensured by means of hardware redundancy and the use of an n-version approach in software development. To find the composition of the hardware and software system that provides the specified reliability, it is proposed to use a mathematical model that takes into account the failures and recovery of hardware and software components of the computing system. At the same time, with such an approach to ensuring reliability, the cost of developing and operating a control system may increase unreasonably. Further, an optimization problem is formulated in which maximization of reliability is chosen as the optimality criterion, and the performance and cost criteria are translated into constraints. There is the conclusion that this problem can be effectively solved with the help of evolutionary optimization methods.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122271292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537425
Yaroslava K. Starostina
This article consider a new construction of the device which helps with implementation of smooth amplitude start-up of asynchronous engines, allowing to minimize the quantity of force semiconductor keys and to meet requirements for electromagnetic compatibility. The ways of reducing mass-dimensional indexes of a booster transformer (the constructive foundation of the offered device) by the drive elimination of a network low frequency tension component in its primary winding are shown. The effectiveness of this decision is confirmed by analyzing the core magnetic status of the transformer in the starting mode, considering hysteresis and subsequent comparing patterns of direct and smooth start-up of the asynchronous engine in the computer program Matlab/Simulink.
{"title":"The Application of Volt-Booster Transformer as a Part of Asynchronous Motors Control Devices","authors":"Yaroslava K. Starostina","doi":"10.1109/RusAutoCon52004.2021.9537425","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537425","url":null,"abstract":"This article consider a new construction of the device which helps with implementation of smooth amplitude start-up of asynchronous engines, allowing to minimize the quantity of force semiconductor keys and to meet requirements for electromagnetic compatibility. The ways of reducing mass-dimensional indexes of a booster transformer (the constructive foundation of the offered device) by the drive elimination of a network low frequency tension component in its primary winding are shown. The effectiveness of this decision is confirmed by analyzing the core magnetic status of the transformer in the starting mode, considering hysteresis and subsequent comparing patterns of direct and smooth start-up of the asynchronous engine in the computer program Matlab/Simulink.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132234721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537533
M. Urakseev, K. Vazhdaev, A. Sagadeev
The work is devoted to the analysis of sources of error of displacement sensors, to use the data obtained in the design of new devices, to determine the parameters of future sensors in their design. The paper considers modern designs of displacement sensors with an acousto-optic transducer, briefly examines the principle of operation of sensors with an indication of structural diagrams. The main sources of error of displacement sensors with an acousto-optic transducer are determined. The analysis of each type of sources, their influence on the measurement error of displacement is carried out, analytical expressions are constructed to determine the magnitude of the error, graphs of the dependence of changes in the parameters of the measuring system on the change in the value of the influencing factor are presented.
{"title":"Analysis of Error Sources for Acousto-Optic Displacement Sensors","authors":"M. Urakseev, K. Vazhdaev, A. Sagadeev","doi":"10.1109/RusAutoCon52004.2021.9537533","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537533","url":null,"abstract":"The work is devoted to the analysis of sources of error of displacement sensors, to use the data obtained in the design of new devices, to determine the parameters of future sensors in their design. The paper considers modern designs of displacement sensors with an acousto-optic transducer, briefly examines the principle of operation of sensors with an indication of structural diagrams. The main sources of error of displacement sensors with an acousto-optic transducer are determined. The analysis of each type of sources, their influence on the measurement error of displacement is carried out, analytical expressions are constructed to determine the magnitude of the error, graphs of the dependence of changes in the parameters of the measuring system on the change in the value of the influencing factor are presented.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132289189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537318
Nikolay Mestnikov, A. Alzakkar, I. Valeev, V. Maksimov
The article presents the results of experimental studies on electrical energy operations of solar power with a capacity 150 W, with which experimental studies were carried out in the form of a change in the angle of inclination of the solar panel relative to the surface of the earth, during sunny weather in summer. In the course of these experimental studies, we used:(computing and measuring equipment, polycrystalline solar panel 150 W, charge controller, inverter and energy storage system in the form of a battery with a capacity of 75 Ah). The results of these studies were addressed by analyzing the resulting curves and the impact of the resulting values on the external parameters in the form of regression equation depending on the programs (Microsoft Office Excel - Mathcad Professional).
{"title":"Assessment of the Performance of the Solar Power Plant with a Capacity 150W","authors":"Nikolay Mestnikov, A. Alzakkar, I. Valeev, V. Maksimov","doi":"10.1109/RusAutoCon52004.2021.9537318","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537318","url":null,"abstract":"The article presents the results of experimental studies on electrical energy operations of solar power with a capacity 150 W, with which experimental studies were carried out in the form of a change in the angle of inclination of the solar panel relative to the surface of the earth, during sunny weather in summer. In the course of these experimental studies, we used:(computing and measuring equipment, polycrystalline solar panel 150 W, charge controller, inverter and energy storage system in the form of a battery with a capacity of 75 Ah). The results of these studies were addressed by analyzing the resulting curves and the impact of the resulting values on the external parameters in the form of regression equation depending on the programs (Microsoft Office Excel - Mathcad Professional).","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134292726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537509
L. Ginis, L. Gordienko, Vadim Kudryakhin
The article is devoted to the description of the development of a geographic information project as a tool for supporting decision-making in the cadastral area. It is determined that such a GIS project can be included in an intelligent information-control system. Development of theoretical-multiple description of an intelligent information-control system based on metamodel is proposed. The cognitive theoretical-multiple approach allows you to fill the elements of the metamodel by choosing the mathematical apparatus necessary to solve problems in a certain subject area. The composition of the decision-making model for the subject area is specified - the task of determining the cadastral value of the land plot. It is proposed to use the analytic hierarchy process and cluster analysis, which allow taking into account objective (quantitative) and subjective (expert) criteria and factors in solving the task. It describes the creation of a geographic information project that allows taking into account such features of the subject area. The conceptual model of the geodata database and algorithm of GIS project operation using UML-diagram are presented. Important entities of the developed geodata database are described. A functional set is presented and an example of how the GIS project works. Such formalization and the GIS project can serve as a basis for the further development of an intelligent information-control system.
{"title":"Development of a Geoinformation Project as a Tool for Support Decision Making in the Subject Area","authors":"L. Ginis, L. Gordienko, Vadim Kudryakhin","doi":"10.1109/RusAutoCon52004.2021.9537509","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537509","url":null,"abstract":"The article is devoted to the description of the development of a geographic information project as a tool for supporting decision-making in the cadastral area. It is determined that such a GIS project can be included in an intelligent information-control system. Development of theoretical-multiple description of an intelligent information-control system based on metamodel is proposed. The cognitive theoretical-multiple approach allows you to fill the elements of the metamodel by choosing the mathematical apparatus necessary to solve problems in a certain subject area. The composition of the decision-making model for the subject area is specified - the task of determining the cadastral value of the land plot. It is proposed to use the analytic hierarchy process and cluster analysis, which allow taking into account objective (quantitative) and subjective (expert) criteria and factors in solving the task. It describes the creation of a geographic information project that allows taking into account such features of the subject area. The conceptual model of the geodata database and algorithm of GIS project operation using UML-diagram are presented. Important entities of the developed geodata database are described. A functional set is presented and an example of how the GIS project works. Such formalization and the GIS project can serve as a basis for the further development of an intelligent information-control system.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"95 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133837083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537370
A. Nikolaev, M. V. Bulanov, P. Tulupov, I. Lozhkin
In recent decades, the steel industry has seen a steady increase in the share of steel produced in electric arc furnaces followed by out-of-furnace melt treatment in ladle-furnaces. It should be noted that electric arc furnaces are characterised by significant energy consumption. Therefore, the task of reducing costs in conjunction with an increase in productivity, which is achieved by reducing the time of under current operation, becomes relevant. The paper describes an improved algorithm for controlling electric furnace modes on the temperature data basis of water-cooled panels and harmonic composition of electric arc current. A description of existing electrical mode control systems for an electric arc furnace is presented in the article. The authors consider the structure of the improved control algorithm applied at one of the metallurgical enterprises of the Russian Federation. The application efficiency of this algorithm has been evaluated on the basis of experimental data obtained at an operating electric arc furnace of a shaft type.
{"title":"An Improved Algorithm for Arc Furnace Mode Control with Dynamic Arc Length Correction at Metal Refining Period","authors":"A. Nikolaev, M. V. Bulanov, P. Tulupov, I. Lozhkin","doi":"10.1109/RusAutoCon52004.2021.9537370","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537370","url":null,"abstract":"In recent decades, the steel industry has seen a steady increase in the share of steel produced in electric arc furnaces followed by out-of-furnace melt treatment in ladle-furnaces. It should be noted that electric arc furnaces are characterised by significant energy consumption. Therefore, the task of reducing costs in conjunction with an increase in productivity, which is achieved by reducing the time of under current operation, becomes relevant. The paper describes an improved algorithm for controlling electric furnace modes on the temperature data basis of water-cooled panels and harmonic composition of electric arc current. A description of existing electrical mode control systems for an electric arc furnace is presented in the article. The authors consider the structure of the improved control algorithm applied at one of the metallurgical enterprises of the Russian Federation. The application efficiency of this algorithm has been evaluated on the basis of experimental data obtained at an operating electric arc furnace of a shaft type.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"44 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114007965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537373
N. Aizenberg, E. Stashkevich, I. Ilyukhin
The development of the modern electric power industry is aimed at applying artificial intelligence technologies to manage the smart grid with distributed generation plants and electricity storage units. Part of the smart grid are clusters (microgrids) that combine consumers of electricity, networks, electricity storage units, and distributed generation plants. The paper presents a description of a microgrid model with a built-in forecasting and intelligent load management module for multiple facilities simultaneously, including those with distributed generation. Decisions are made a day in advance, thus shaping the strategy of the generation profile and management of current-using equipment items. The above timing is due to the information available to the intelligent system: a forecast of demand and price of electricity from the centralized electric power system for each hour of the next day. We describe special aspects of switching during peak times to additional power sources along with distribution by microgrids. The forecast is based on two approaches: the method of least squares and machine learning using built-in Python 3 options and external open-source components.
{"title":"A Microgrid Model with an Integrated Forecasting and Intelligent Load Management Module","authors":"N. Aizenberg, E. Stashkevich, I. Ilyukhin","doi":"10.1109/RusAutoCon52004.2021.9537373","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537373","url":null,"abstract":"The development of the modern electric power industry is aimed at applying artificial intelligence technologies to manage the smart grid with distributed generation plants and electricity storage units. Part of the smart grid are clusters (microgrids) that combine consumers of electricity, networks, electricity storage units, and distributed generation plants. The paper presents a description of a microgrid model with a built-in forecasting and intelligent load management module for multiple facilities simultaneously, including those with distributed generation. Decisions are made a day in advance, thus shaping the strategy of the generation profile and management of current-using equipment items. The above timing is due to the information available to the intelligent system: a forecast of demand and price of electricity from the centralized electric power system for each hour of the next day. We describe special aspects of switching during peak times to additional power sources along with distribution by microgrids. The forecast is based on two approaches: the method of least squares and machine learning using built-in Python 3 options and external open-source components.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115533962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537472
O. V. Zakharov, K. Pugin, L. Seliverstova
At the design, manufacturing and assembly stages of products, an analysis of the assembly accuracy is performed. When designing an assembly, you assign tolerances to the dimensions, shape, orientation, and location of parts. In the manufacture and assembly of products, you ensure quality by optimizing parameters. This article presents a new mathematical model based on a difference surface and an iterative algorithm for finding contact points. The difference surface was used to find the three starting points of contact. The initial plane equation was defined by these three points, that can support the part in a stable manner. It was assumed, that when mating, the moving part rotates relative to the stationary part by an angle, determined by the initial plane. The iterative algorithm repeats the search for contact points and the construction of a new plane. The orientation and location errors of the assembly of flat parts were studied using the developed mathematical model, taking into account the real geometry of the parts. The assembly of two planes after grinding was analyzed using numerical simulation. The analysis is statistically confirmed using the generated MATLAB simulation program. The results were showed that, in most cases, the assembly error is less than the form error of constituent planes.
{"title":"A Mathematical Model of the Assembly Error for Flat Surfaces","authors":"O. V. Zakharov, K. Pugin, L. Seliverstova","doi":"10.1109/RusAutoCon52004.2021.9537472","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537472","url":null,"abstract":"At the design, manufacturing and assembly stages of products, an analysis of the assembly accuracy is performed. When designing an assembly, you assign tolerances to the dimensions, shape, orientation, and location of parts. In the manufacture and assembly of products, you ensure quality by optimizing parameters. This article presents a new mathematical model based on a difference surface and an iterative algorithm for finding contact points. The difference surface was used to find the three starting points of contact. The initial plane equation was defined by these three points, that can support the part in a stable manner. It was assumed, that when mating, the moving part rotates relative to the stationary part by an angle, determined by the initial plane. The iterative algorithm repeats the search for contact points and the construction of a new plane. The orientation and location errors of the assembly of flat parts were studied using the developed mathematical model, taking into account the real geometry of the parts. The assembly of two planes after grinding was analyzed using numerical simulation. The analysis is statistically confirmed using the generated MATLAB simulation program. The results were showed that, in most cases, the assembly error is less than the form error of constituent planes.","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"234 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115753957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1109/RusAutoCon52004.2021.9537556
Zhilov Ruslan
The paper considers the construction of an intelligent testing system for robotic systems based on sigma-pi neural networks. When robots are used on industrial production lines, the task of testing industrial robots for performance arises. There are two ways to solve this problem: routine checks of robots or constant observation of the operator at the robotic line. In this work, an intelligent system based on sigma-pi neural networks is being built, which will be able to solve a similar problem using readings from sensors located at different nodes of the robot. A neural network, pre-trained according to the algorithm that is given in the work, can continuously monitor the state of the robotic complex and make a decision to stop the line in case of suspicion of a breakdown. As an example of the operation of a sigma-pi neural network in this work, an example is given based on 5 input data, that is, data from 5 sensors, normalized according to the principle "there is a signal" or "there is no signal".
{"title":"Building an Intelligent Testing System for Robotic Systems Based on Sigma-Pi Neural Networks","authors":"Zhilov Ruslan","doi":"10.1109/RusAutoCon52004.2021.9537556","DOIUrl":"https://doi.org/10.1109/RusAutoCon52004.2021.9537556","url":null,"abstract":"The paper considers the construction of an intelligent testing system for robotic systems based on sigma-pi neural networks. When robots are used on industrial production lines, the task of testing industrial robots for performance arises. There are two ways to solve this problem: routine checks of robots or constant observation of the operator at the robotic line. In this work, an intelligent system based on sigma-pi neural networks is being built, which will be able to solve a similar problem using readings from sensors located at different nodes of the robot. A neural network, pre-trained according to the algorithm that is given in the work, can continuously monitor the state of the robotic complex and make a decision to stop the line in case of suspicion of a breakdown. As an example of the operation of a sigma-pi neural network in this work, an example is given based on 5 input data, that is, data from 5 sensors, normalized according to the principle \"there is a signal\" or \"there is no signal\".","PeriodicalId":106150,"journal":{"name":"2021 International Russian Automation Conference (RusAutoCon)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123159776","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：