AUTOMATED SYSTEM FOR QUALITY CONTROL OF TOOL PROCESSING IN GLOW DISCHARGE BASED ON NEURAL NETWORK MONITORING

2021 ◽  
Vol 2021 (3) ◽  
pp. 16-24
Author(s):  
Vladimir Logvin ◽  
Tatyana Karlova
Keyword(s):  
Neural Network ◽  
Glow Discharge ◽  
Continuous Monitoring ◽  
Network Monitoring ◽  
Plasma Generator ◽  
Automated System ◽  
Quality Of Control ◽  
Investigation Methods ◽  
Wide Range

Work purpose: improving effectiveness and quality in the control of engineering processes of tool working in the plasma generator of a glow discharge based on neural network monitoring. Investigation methods: use of nature and regularities of human thought at the development of the computer model of a neural network allowed realizing a cybernetic approach at real production object work modeling with the purpose of increasing effectiveness and quality of control at the management based on neural network monitoring. The essence of the modeling method consists in the development of such algorithms and programs which imitate the behavior of the plasma generator of a glow discharge, its characteristics in the structure, volume and field of technological parameter use essential for the research. Investigation results: the system offered for the control of effectiveness and quality of realizable engineering processes during plasma generator work based on neural network monitoring allows ensuring good repeatability of the results on tool strengthening. The defined sequence of engineering process operations of product working in the plasma generator of a glow discharge ensures the formation of specified structure and micro-hardness on the surface of products under processing. In the system offered control and management are formed on the basis of a neural network approach and imitate system behavior at all machining steps of processing. The results of continuous monitoring are shown with the essential discontinuity in on-line modes in the form of values and deviations of controlled technological parameters of the working process on the display of an electronic control unit. The generality and simultaneous uniqueness of the properties of continuous monitoring systems on applicability for real technological object control and range extension of problems solved with their help transforms them into compulsory means for complex automated device equipment. The modeling algorithm offered at the formation of an automated system to control effectiveness and quality in functioning plasma generator of a glow discharge for strengthening a wide range of tools with different profiles with machining steps differed in character of plasma impact, duration and their realization priority allowed optimizing the repeatability of results in ensuring specified properties in surface-bounded layers that satisfies conditions of the automated technological environment.

scholarly journals AUTOMATED EFFECTIVENESS CONTROL SYSTEM OF TOOL HOUSE FOR TOOL STRENGTHENING IN GLOW DISCHARGE

2021 ◽  
Vol 2021 (1) ◽  
pp. 19-27
Author(s):  
Vladimir Logvin ◽  
Tatyana Karlova
Keyword(s):  
Glow Discharge ◽  
Plasma Generator ◽  
Automated System ◽  
Time Duration ◽  
Technological Environment ◽  
Tool Materials ◽  
Investigation Methods ◽  
Wide Range ◽  
Control And Management ◽  
Plasma Generators

The work purpose consists in the increase of effectiveness and quality in the engineering process control of the tool house ensuring strengthening a wide range of different tools and tool materials in plasma-generators of a glow discharge. Investigation methods. The application of computer systems is for the simulation of real production object operation with the purpose of quality and effectiveness increase in these objects control as a method of investigations consisting in operation computer imitation of a tool house equipped with plasma-generators of a glow discharge both at separate stages of processing and in the course of the whole industrial process. It will allow developing an optimum system of quality control of engineering processes for processing a wide range of tools with different profiles and tool materials in plasma-generators of a glow discharge. The essence of a modeling method consists in the development of such algorithms and programs which imitate the behavior of the tool house equipped with plasma-generators of a glow discharge its properties necessary for investigations, amount and field of technological parameter changes Investigation results. Plasma formed in consequence of explosive emission has in its structure the whole essential spectrum of ions for the formation of specified physical-mechanical properties on working surfaces of tools under strengthening. It contributes to the formation of the essential structure of bombarding ion flow with the wide range of frequencies and energy. The state and value of the layer strengthened located under an oxide film and formed at the stage of previous working operations at manufacturing tools and their working parts. This layer is characterized with the increased density of dislocations in depth and micro-crack presence not only within grains but between them. The uniformity of force impact depending upon current strength stability in a discharge and voltage upon electrodes in the plasma-generator is to be adjusted at constant pressure by the rate of technological environment pumping through a plasma-generator. Conclusions. The application of some quickly reset plasma-generators in tool production ensures work effectiveness increase of the tool house at the expense of optimization of tool machining in different engineering processes and with different time duration carrying out pre-production operations in the course of the plasma-generators operation and carrying out their charging from the automated area of waiting. The simulation algorithm developed at the formation of the automated system for control and management of effectiveness and quality in tool house work in different tool strengthening in plasma-generators of a glow discharge with stages different in character of plasma impact, duration and sequence of their realization allowed optimizing tool house equipment. The development of the automated system for control and management of effectiveness and quality of the working operation of plasma-generators of a glow discharge allowed optimizing the formation of the stage sequence with quick-acting processes during processing tools with different shape ensuring the formation of specified properties in neighboring layers which meets the requirements of automated technological environment.

AUTOMATION OF CONTROL PROCESS TO ENSURE TOOL QUALITY DURING FINISHING WITH GLOW DISCHARGE PLASMA

2021 ◽  
Vol 2021 (8) ◽  
pp. 14-21
Author(s):  
Vladimir Logvin ◽  
Tatyana Karlova
Keyword(s):  
Neural Network ◽  
Quality Control ◽  
Control System ◽  
Glow Discharge ◽  
Discharge Plasma ◽  
Plasma Generator ◽  
Glow Discharge Plasma ◽  
Engineering Process ◽  
The Neural Network

Work purpose: the development of conditions for control automation ensuring tool essential qualities at the stage of finishing with glow discharge plasma. Investigation methods: based on the peculiarities of a human mental process the formation of an electronic model of a neural control system on the basis of engineering process monitoring in industry promoted cybernetic method carrying out for the increase of effectiveness and quality control during the management. The formation of an investigation process for computer technology use at the solution of the problem to ensure specified quality at the realization of engineering processes for metal working tool strengthening in the plasma generator of a glow discharge allowed creating an efficient system of control. The creation of conditions for the fulfillment of human cognitive potentialities with the high degree of similarity such as identification, accumulation and dissemination or transfer of information in the form of electromagnetic pulses similar to neural exchange allows optimizing a control system of quality of product strengthening in the plasma generator of a glow discharge. The formulation of a management solution in the form of the chain of commands in the neural network of the control system of the plasma generator of a glow discharge is formed in accordance with phenomena forming output responses and conditions ensuring their formation. Investigation results: for setting an optimum field of investigations and, accordingly, for increasing effectiveness of the automated control system of finishing quality under the glow discharge plasma impact during the whole engineering process the use of unique potentialities of continuous neural network monitoring is intended. The application of the neural network approach and its unique functions at the formation of the control system using the continuous monitoring of basic engineering process parameters of finishing ensuring specified quality of machining steps realized allows ensuring high repeatability at metal working tool strengthening. In the technological system developed all functions of control and management are based on the use of the neural network approach that allows visualizing its functioning on the monitor in the course of the whole engineering finishing process in the form of graphical dependence. Conclusions: 1. The use of unique potentialities of continuous neural network monitoring allows defining a optimum field of investigations at the lowest cost and accordingly increasing quality of the automated system of finishing quality control at the impact of glow discharge plasma. 2. Depending on material of a tool working part and conditions of tool operation in the surface layer there is formed an essential thermo-dynamic structure with the specified physical-mechanical properties that allows ensuring optimum repeatability. 3. The formation of conditions for the fulfillment with a high degree of similarity human cognitive potentialities such as identification, accumulation and dissemination or transfer of information in the form of electro-magnetic pulses similar to neural exchange allows optimizing a system of quality control of tools strengthened at the stage of glow discharge plasma finishing.

scholarly journals IMPROVING THE QUALITY OF CONTROL OF WELDED JOINTS IN THE PRODUCTION OF MECHANICAL ENGINEERING PRODUCTS

2021 ◽  
Vol 23 (3) ◽  
pp. 40-46
Author(s):  
I.V. Malkina ◽  
◽  
D.V. Zhdanov ◽  
Keyword(s):  
Quality Control ◽  
Welded Joints ◽  
Block Diagram ◽  
Programmable Logic Controller ◽  
Automated System ◽  
Programmable Logic ◽  
Sensors And Actuators ◽  
Quality Of Control ◽  
Automated Quality Control

The purpose of the work is to develop an automated quality control system for welded joints of cable car structures designed and manufactured at the Skado LLC enterprise (Samara) in order to improve the quality of control. The analysis of requirements for welded structures and welded joints of cable cars is carried out, methods of control of welded joints are considered. A block diagram of an automated system for quality control of welded joints based on the method of ultrasonic testing has been developed. The analysis of ultrasonic sensors on phased arrays is carried out. The sensors and actuators of the system are selected. A scheme for interfacing system elements with a programmable logic controller has been developed. The structure of the system and the scheme of interfacing the system elements with the programmable logic controller are described. A method for performing control has been developed.

scholarly journals MONITORING OF AUTOMATED TECHNOLOGICAL ENVIRONMENT FOR TOOL WORKING IN PLASMA-GENERATOR OF GLOW DISCHARGE BASED ON NEURONET APPROACH

2020 ◽  
Vol 2020 (12) ◽  
pp. 31-37
Author(s):  
Vladimir Logvin ◽  
Tatyana Karlova
Keyword(s):  
Glow Discharge ◽  
Plasma Generator ◽  
Current Strength ◽  
Engineering Process ◽  
Pumping Rate ◽  
Working Volume ◽  
Investigation Methods ◽  
Considerable Impact ◽  
Gas Environment ◽  
The Stability

The work purpose is to increase effectiveness and quality of engineering process control of tool working in a plasma-generator of a glow discharge based on a neuronet approach. Investigation methods: use of computer technologies based on an artificial neuronet system for the creation of control systems as an investigation method consisting in computer imitation of the process of plasma-generator operation at separate stages of processing. It will allow developing an optimum system for quality control and management of engineering processes performed for tool working in the plasma-generator of a glow discharge. The essence of the modeling method when using an artificial neuronet approach consists in the development of such algorithms and programs which imitate the behavior of the plasma-generator, its properties and characteristics in the composition essential for investigations, volume and field of technical parameter changes. Investigation results: the operation sequence of the engineering process for product working in the plasma-generator of a glow discharge ensures the formation of the specified structure and micro-hardness on the surface of products worked. A considerable impact upon working quality is made by the structure of technological gas environment and a rate of its pumping at constant pressure in a vacuum chamber for the formation of the essential flux of bombarding ions with the specified value of kinetic energy before a hit on a surface. During the development of working stage sequence there is taken into account a state and magnitude of the defected layer formed at the stages of previous working and ageing. The effectiveness of force impact is defined with the stability of current strength in the discharge and electrode voltage in the plasma-generator of a glow discharge. The fluctuations of current strength and voltage at discharge burning depends upon the stability of structure, pressure and a pumping rate of technological gas environment through a working volume of the plasma-generator.

scholarly journals Convolutional neural networks for improving image quality with noisy PET data

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Josh Schaefferkoetter ◽  
Jianhua Yan ◽  
Claudia Ortega ◽  
Andrew Sertic ◽  
Eli Lechtman ◽  
...  
Keyword(s):  
Neural Network ◽  
Ground Truth ◽  
Lesion Detection ◽  
Machine Learning Techniques ◽  
Noise Levels ◽  
Physician Performance ◽  
Learning Techniques ◽  
Wide Range ◽  
Image Ranking

Abstract Goal PET is a relatively noisy process compared to other imaging modalities, and sparsity of acquisition data leads to noise in the images. Recent work has focused on machine learning techniques to improve PET images, and this study investigates a deep learning approach to improve the quality of reconstructed image volumes through denoising by a 3D convolution neural network. Potential improvements were evaluated within a clinical context by physician performance in a reading task. Methods A wide range of controlled noise levels was emulated from a set of chest PET data in patients with lung cancer, and a convolutional neural network was trained to denoise the reconstructed images using the full-count reconstructions as the ground truth. The benefits, over conventional Gaussian smoothing, were quantified across all noise levels by observer performance in an image ranking and lesion detection task. Results The CNN-denoised images were generally ranked by the physicians equal to or better than the Gaussian-smoothed images for all count levels, with the largest effects observed in the lowest-count image sets. For the CNN-denoised images, overall lesion contrast recovery was 60% and 90% at the 1 and 20 million count levels, respectively. Notwithstanding the reduced lesion contrast recovery in noisy data, the CNN-denoised images also yielded better lesion detectability in low count levels. For example, at 1 million true counts, the average true positive detection rate was around 40% for the CNN-denoised images and 30% for the smoothed images. Conclusion Significant improvements were found for CNN-denoising for very noisy images, and to some degree for all noise levels. The technique presented here offered however limited benefit for detection performance for images at the count levels routinely encountered in the clinic.

scholarly journals Adaptive control systems for marine thermal installations

2021 ◽  
pp. 201-205
Author(s):  
С.А. Гордин ◽  
И.В. Зайченко ◽  
К.Д. Хряпенко ◽  
В.В. Бажеряну
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Control System ◽  
Control Systems ◽  
Pid Controller ◽  
Heat Supply System ◽  
Heating System ◽  
Thermal Loads ◽  
Quality Of Control

В статье рассмотрен вопрос повышения точности и качества управления приводом сетевых насосов в составе судовых тепловых установок в системе отопления судна путем применения адаптивной системы автоматического управления. При использовании классических систем управления на основе ПИД-регуляторов для управления мощностью электродвигателя по критерию обеспечения заданного давления в системе теплоснабжения в условиях резкопеременных тепловых нагрузок могут возникать ситуации разрегулирования системы вследствии возникновения дополнительного давления в тепловой установке при термическом расширении теплоносителя. Для обеспечения надежности и безаварийности работы судовых тепловых установок при резкоперменных нагрузках авторами рассматривается возможность использования для управления мощностью электропривода адаптивной системы управления. В статье рассмотрена схема управления с адаптацией коэффициентов ПИД-регулятора на базе нейронной сети (нейросетевой оптимизатор). Нейросетевой оптимизатор был применен как надстройка над ПИД-регулятором в схеме управления мощностью сетевого насоса в составе судовой тепловой установки. Рассмотрены зависимости характеристик систем управления от структуры и параметров модифицированных критериев точности и качества управления. Адаптация параметров регулирования позволяет обеспечить достижение желаемых параметров с меньшими затратами мощности при сохранении уровня надежности и исключить разрегулирование системы управления при резкопеременных тепловых нагрузках. The article discusses the issue of improving the accuracy and quality of control of the drive of network pumps as part of ship thermal installations in the ship's heating system by using an adaptive automatic control system. When using classical control systems based on PID regulators to control the power of the electric motor according to the criterion of providing a given pressure in the heat supply system under conditions of sharply varying thermal loads, situations of system maladjustment may occur due to the appearance of additional pressure in the thermal installation during thermal expansion of the coolant. To ensure the reliability and trouble-free operation of ship thermal installations under abruptly variable loads, the authors consider the possibility of using an adaptive control system to control the power of an electric drive. The article describes a control scheme with adaptation of the PID controller coefficients based on a neural network (neural network optimizer). The neural network optimizer was used as a superstructure over the PID controller in the power control circuit of a network pump as part of a ship's thermal installation. The dependences of the characteristics of control systems on the structure and parameters of the modified criteria for the accuracy and quality of control are considered. Adaptation of control parameters allows achieving the desired parameters with lower power consumption while maintaining the level of reliability and eliminating deregulation of the control system at abruptly varying thermal loads.

scholarly journals IMPROVEMENT OF INFORMATION SUPPORT FOR THE FUNCTIONING OF THE INCLUSIVE EDUCATION SYSTEM

2021 ◽  
pp. 82-92
Author(s):  
Andrii Lytvynchuk ◽  
◽  
Hanna Tereshchenko ◽  
Andrii Kyrianov ◽  
Ivan Gaiduk ◽  
...  
Keyword(s):  
Inclusive Education ◽  
Education System ◽  
Individual Development ◽  
Automated System ◽  
Information Support ◽  
Educational Services ◽  
Special Educational Needs ◽  
Data Set ◽  
Wide Range

The purpose of the article is to study current trends and ways of improving information support for the functioning of an inclusive education system in Ukraine. The automated system of inclusive resource center (AS «IRC») is defined as a set of software and hardware, based on information and telecommunication technologies provide for the creation of a single integrated information space in inclusive education for the processing of the information generated by the operation of the AS «IRC» and their information support. It is determined that through AS «IRC» teachers of general secondary education institutions and preschool institutions have the opportunity to compile individual development programs for children with special educational needs (SEN), using the findings previously developed by the experts of the inclusive resource centre. EMIS features are described in Ukraine, which operates by collecting information on enrolment, attendance, grade repetition, expulsion from school and graduation. A template is provided for the minimum recommended set of questions to identify children with SEN. Such monitoring makes it possible to identify and detail the difficulties faced by children / teachers, in contrast to the exclusive identification of disability (a certain nosology that is medically confirmed). The development of an inclusive education system in Ukraine is moving towards ensuring the availability and quality of educational services for children with SEN, which aims to improve the quality of information support. In the process of improving the functioning of the AS «IRC» indicators of inclusive education, it is necessary to ensure an organic combination of data already contained in the system with the data set (indicators) that will be collected to assess the effectiveness of educational services in the inclusive education segment. It is substantiated that data sets on the development of inclusive education should be clearly and consistently defined, and should include a wide range of information on children with SEN.

scholarly journals Relative control of an underactuated spacecraft using reinforcement learning

2020 ◽  
Vol 2020 (4) ◽  
pp. 43-54
Author(s):  
S.V. Khoroshylov ◽  
◽  
M.O. Redka ◽  
Keyword(s):  
Neural Network ◽  
Control System ◽  
Reinforcement Learning ◽  
Control Theory ◽  
Learning Algorithm ◽  
Control Algorithms ◽  
Iteration Algorithm ◽  
Quality Of Control ◽  
Control Actions

The aim of the article is to approximate optimal relative control of an underactuated spacecraft using reinforcement learning and to study the influence of various factors on the quality of such a solution. In the course of this study, methods of theoretical mechanics, control theory, stability theory, machine learning, and computer modeling were used. The problem of in-plane spacecraft relative control using only control actions applied tangentially to the orbit is considered. This approach makes it possible to reduce the propellant consumption of reactive actuators and to simplify the architecture of the control system. However, in some cases, methods of the classical control theory do not allow one to obtain acceptable results. In this regard, the possibility of solving this problem by reinforcement learning methods has been investigated, which allows designers to find control algorithms close to optimal ones as a result of interactions of the control system with the plant using a reinforcement signal characterizing the quality of control actions. The well-known quadratic criterion is used as a reinforcement signal, which makes it possible to take into account both the accuracy requirements and the control costs. A search for control actions based on reinforcement learning is made using the policy iteration algorithm. This algorithm is implemented using the actor–critic architecture. Various representations of the actor for control law implementation and the critic for obtaining value function estimates using neural network approximators are considered. It is shown that the optimal control approximation accuracy depends on a number of features, namely, an appropriate structure of the approximators, the neural network parameter updating method, and the learning algorithm parameters. The investigated approach makes it possible to solve the considered class of control problems for controllers of different structures. Moreover, the approach allows the control system to refine its control algorithms during the spacecraft operation.

scholarly journals AUTOMATIC CONTROL OF PARAMETERS OF A NON-STATIONARY OBJECT WITH CROSS LINKS

2018 ◽  
Vol 10 (1) ◽  
Author(s):  
A. Pavlov
Keyword(s):  
Neural Network ◽  
Automatic Control ◽  
Simulation Model ◽  
Limited Range ◽  
Normal Operation ◽  
Object Model ◽  
Stationary Object ◽  
Quality Of Control ◽  
Cross Links

Many objects automatic control unsteady. This is manifested in the change of their parameters. Therefore, periodically adjust the required parameters of the controller. This work is usually carried out rarely. For a long time, regulators are working with is not the optimal settings. The consequence of this is the low quality of many industrial control systems. The solution problem is the use of robust controllers. ACS with traditional PI and PID controllers have a very limited range of normal operation modes due to the appearance of parametric disturbances due to changes in the characteristics of the automated unit and changes in the load on it. The situation is different when using in the architecture of artificial neural network controllers. It is known that when training a neural network, the adaptation procedure is often used. This makes it possible to greatly expand the area of normal operating modes of ACS with neural automatic regulators in comparison with traditional linear regulators. It is also possible to significantly improve the quality of control (especially for a non-stationary multidimensional object), provided that when designing the ACS at the stage of its simulation in the model of the regulatory object model, an adequate simulation model of the executive device. It is also possible to significantly improve the quality of control (especially for a non-stationary multidimensional regulatory object model, an adequate simulation model of the executive device. Especially actual implementation of all these requirements in the application of electric actuators. This article fully complies with these requirements. This is what makes it possible to provide a guaranteed quality of control in non-stationary ACS with multidimensional objects and cross-links between control channels. The possibility of using a known hybrid automatic regulator to stabilize the parameters of a two-channel non-stationary object with two cross-linked. A simulation control system under the action of the object coordinate and parametric perturbations. The simulation showed that the quality control is not reduced

scholarly journals Application of Convolution Network Model Based on Deep Learning in Sports Image Information Detection

2021 ◽  
Vol 233 ◽  
pp. 02024
Author(s):  
Xiaoqiao Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Image Features ◽  
Convolution Neural Network ◽  
Image Information ◽  
Model Based ◽  
Wide Range ◽  
Information Detection

In recent years, convolution neural network has achieved great success in single image super-resolution detection. Compared with the traditional method, this method achieves better reconstruction detection effect. However, the network structure of the existing reconstruction model is shallow, and the convolution kernel has a small acceptance, so it is difficult to learn a wide range of motion image features, which affects the quality of motion image information detection. Aiming at the problems and shortcomings of the existing sports image information detection based on convolution neural network, this paper proposes the application of convolution network model based on deep learning in sports image information detection. In this paper, we get the average SSIM value from the data of set5, set14, bsd100 and urban100 by using the X4 model of different algorithms. The average SSIM value of set5 is 0.865, which shows that the quality of sports image reconstruction and the reconstruction efficiency of the model can be improved by using the local image features of different scales, which provides technical support for sports image information detection. The research in this paper has important practical significance for the further development of the two and the reform of the convolution network model in sports image information detection.

Sign in / Sign up

Export Citation Format

Share Document