scispace - formally typeset
Search or ask a question

Showing papers by "Pavlo Maruschak published in 2022"



Journal ArticleDOI
07 Mar 2022-Machines
TL;DR: In this article , the impact of the illumination level on the quantitative indicators of mechanical damage of the rolled strip is investigated, and the obtained images of defects at light levels in the range of 2-800 lx were recognized by a neural network model based on the U-net architecture with a decoder based on ResNet152.
Abstract: The impact of the illumination level on the quantitative indicators of mechanical damage of the rolled strip is investigated. To do so, a physical model experiment was conducted in the laboratory. The obtained images of defects at light levels in the range of 2–800 lx were recognized by a neural network model based on the U-net architecture with a decoder based on ResNet152. Two levels of illumination were identified, at which the total area of recognized defects increased: 50 lx and 300 lx. A quantitative assessment of the overall accuracy of defect recognition was conducted on the basis of comparison with data from images marked by an expert. The best recognition result (with Dice similarity coefficient DSC = 0.89) was obtained for the illumination of 300 lx. At lower light levels (less than 200 lx), some of the damage remained unrecognized. At high light levels (higher than 500 lx), a decrease in DSC was observed, mainly due to the fact that the surface objects are better visible and the recognized fragments become wider. In addition, more false-positives fragments were recognized. The obtained results are valuable for further adjustment of industrial systems for diagnosing technological defects on rolled metal strips.

22 citations


Journal ArticleDOI
29 Apr 2022-Machines
TL;DR: The ResNet and DenseNet models were found to achieve the best generalizing properties for the authors' task, and the highest recognition accuracy was attained using the U-Net model with a ResNet152 backbone.
Abstract: The quality, wear and safety of metal structures can be controlled effectively, provided that surface defects, which occur on metal structures, are detected at the right time. Over the past 10 years, researchers have proposed a number of neural network architectures that have shown high efficiency in various areas, including image classification, segmentation and recognition. However, choosing the best architecture for this particular task is often problematic. In order to compare various techniques for detecting defects such as “scratch abrasion”, we created and investigated U-Net-like architectures with encoders such as ResNet, SEResNet, SEResNeXt, DenseNet, InceptionV3, Inception-ResNetV2, MobileNet and EfficientNet. The relationship between training validation metrics and final segmentation test metrics was investigated. The correlation between the loss function, the , , , and validation metrics and test metrics was calculated. Recognition accuracy was analyzed as affected by the optimizer during neural network training. In the context of this problem, neural networks trained using the stochastic gradient descent optimizer with Nesterov momentum were found to have the best generalizing properties. To select the best model during its training on the basis of the validation metrics, the main test metrics of recognition quality (Dice similarity coefficient) were analyzed depending on the validation metrics. The ResNet and DenseNet models were found to achieve the best generalizing properties for our task. The highest recognition accuracy was attained using the U-Net model with a ResNet152 backbone. The results obtained on the test dataset were and .

14 citations


Journal ArticleDOI
TL;DR: In this paper, the authors provide experimental data on the effective use of a new lubricating composition, which includes industrial oil of any brand with the addition of a nanometal of the component of a friction pair, which has a lower hardness.
Abstract: This paper provides experimental data on the effective use of a new lubricating composition, which includes industrial oil of any brand with the addition of a nanometal of the component of a friction pair, which has a lower hardness. It is shown that this composition significantly reduces the wear resistance of the rails and wheels of rolling stock during operation, prevents electrochemical corrosion of the friction pair wheel–rail and, most importantly, stabilizes the coefficient of friction at the optimum level after a relatively short operating time. The experiments were performed on the friction pair, “sample of the bandage material of the railway wheel—a sample of the rail material”, with a ratio of hardness of the bandage material (Rockwell hardness, HRC scale—35.3) to the hardness of the rail material of 1.1. Test results show that in the case of industrial lubricant, the BioRail brand, with the addition of a nanomaterial friction pair with lower wear hardness of the rail metal sample, after three hours in operation the wear was practically not observed. Moreover, the average value of the friction coefficient for three hours of operation was maintained at the level 0.25, which is optimal for the friction pair wheel–rail. Similar experiments using only the same lubricant brand showed much worse results.

5 citations


Journal ArticleDOI
TL;DR: In this article , a general classification of grippers with features common to all PGD subtypes is proposed: PGD type, contact type, object base type; object centring type; specialisation type; working range; availability of additional devices; the number of the grippers; type of control; and type of attachment to the robot.
Abstract: Based on the literature review, the article presents the analysis of approaches to classifying Gripping Devices (GDs) of Industrial Robots (IRs) and substantiates the need for systematising Pneumatic GDs (PGDs). The authors propose a classification of well-known PGDs, in which the holding force of the Manipulated Object (MO) is formed under the action of gas-dynamic effects. A general classification of PGDs with features common to all PGD subtypes is proposed: PGD type; contact type; object base type; object centring type; specialisation type; working range; availability of additional devices; the number of grippers; type of control; type of attachment to the robot. Each feature of the general PGD classification, which affects PGD characteristics, is analysed, and a usage example is given. The advantages of each feature included in the general PGD classification are also considered. For a more detailed classification, PGDs are divided into the following types: Vacuum GDs (VGDs), Jet GDs (JGDs), Combined PGDs (CPGDs). For VGD, the main distinguishing features are highlighted, which are the vacuum creation method, effect/actuator, stepwise nozzle, suction cup type, suction material type. The main distinguishing features of JGDs include using a jet of compressed air, the shape of nozzle elements, the number of nozzle elements, the direction of gas flows, type of surface of the MO. The main distinguishing features of CPGD include the type of combination and function performed. The main features are given for each classification, and the advantages/disadvantages of the most typical representatives of GDs are described. The authors identify the main development directions for GDs at the present stage of robotisation of production processes, medicine, military and space technology, etc. Based on the analysis and systematisation of literature data, the authors define the main promising areas of research that will be actively developed soon: optimisation of grippers’ design, flexible grippers, additive manufacturing (3D-printing) when creating grippers, collaborative grippers, modular grippers, universal grippers, grippers based on new materials, new effects in grippers, bionic and medical grippers, simulation and rendering of the gripping process.

4 citations


Journal ArticleDOI
TL;DR: In this article , a method for increasing the wear resistance of heavy-loaded friction pairs by saturating industrial lubricants with the metallic nanopowder of the friction pair's component that has a lower hardness was proposed.
Abstract: The authors have previously proposed and tested a method for increasing the wear resistance of heavy-loaded friction pairs by saturating industrial lubricants with the metallic nanopowder of the friction pair’s component that has a lower hardness. To confirm the effectiveness of this concept, this paper presents the results of experimental investigations into the tribological characteristics of two medium carbon steels (rail steel K74 and structural steel 20) during sliding friction. Friction surfaces lubricated with compositions based on the Bio Rail industrial lubricant were saturated with nanopowder additives of copper, carbon, and magnesium alloy, as well as K74 and 20 steels. The research findings indicate that lubricants saturated with nanomaterials of K74 and 20 steels help achieve the highest wear resistance, as compared to lubricants based on pure grease and lubricating compositions based on copper, magnesium alloy and carbon powders. The test results confirmed that the mean friction coefficient of the rail steel remained at the level of 0.25 for three hours of operation, which is optimal for the “wheel–rail” friction pair. The proposed method of manufacturing lubricating compositions can be used to improve the efficiency of lubrication of railway rails and rolling stock wheels.

2 citations


Journal ArticleDOI
30 Jun 2022-Coatings
TL;DR: In this paper , the authors analyzed the mechanical properties of arc spraying cored wires (CW) with different charge compositions (the content of carbon, aluminum, and boron in CW charge varied).
Abstract: The mechanical properties (hardness, cohesion, and residual stresses) of arc coatings designed for operation under conditions of boundary friction and corrosive-abrasive wear are analyzed. The coatings were formed by arc spraying cored wires (CW) with different charge compositions (the content of carbon, aluminum, and boron in CW charge varied). It is shown that the hardness of the coatings increases with an increase in the carbon content in them up to 1 wt. %, and then decreased due to an increase in the content of residual austenite in their structure. The level of residual stresses of the first kind in such coatings increased by four times with an increase in the carbon content to 2 wt. %. The hardness of the coatings and the level of residual tensile stresses in them also increase with a decrease in the aluminum content in them. In this case, the cohesive strength of the coatings increased due to the implementation of aluminothermic reactions in the droplets of the CW melt during their flight and crystallization on the sprayed surfaces. However, then, with an increase in the aluminum content in the coatings of more than 2 wt. %, their cohesive strength decreased. The level of residual tensile stresses in coatings with a high content of retained austenite decreased after heat treatment (tempering) of the specimens. Sometimes, after tempering, these stresses even transformed into residual compressive stresses (in particular, under using CW C1.4Cr14Ni2). At the same time, the tempering of specimens with a predominance of ferrite in the coating structure increased the level of residual tensile stresses in them, which is due to the precipitation of finely dispersed carbides or borides. It has been shown that the addition of boron-containing components (ferrochromium-boron, chromium-boron) to the composition of the CW charge leads to a significant increase in the hardness of the coatings. Thus, an increase in the boron content in coatings from 0 to 4 wt. % leads to an increase in their hardness from 320 HV to 1060 HV. However, this is accompanied by an increase in tensile residual stresses in the coatings and a decrease in their cohesive strength.

1 citations


Journal ArticleDOI
TL;DR: In this article , a comprehensive study of both internal technological processes and the state of equipment, as well as external influences has been conducted to improve the environmental risk management system in the oil and gas industry.
Abstract: The conditions of ecologically dangerous emergencies in the oil and gas industry have been investigated in the work. The high degree of environmental risk that is present in case of emergency requires measures to prevent their occurrence. To improve the environmental risk management system in the oil and gas industry, a comprehensive study of both internal technological processes and the state of equipment, as well as external influences has been conducted. The analysis of the causes of emergency oil and gas fountains at different stages of the life cycle of oil and gas wells have been carried out. The factors preceding the occurrence of gas-oil-water manifestations and open fountains in more than 100 wells in different conditions of their operation are given. Factors are grouped into separate areas and the most influential are highlighted. The main types of environmental hazards that occur during emergency oil and gas fountains have been identified.

1 citations


Journal ArticleDOI
TL;DR: In this article , the impact of the initial phase composition of alloys was evaluated, in particular, the content of Cu, Mn, and Mg in aluminum alloys D16ChATW, 2024-T351 and aluminum alloy T, which in its physical and mechanical characteristics is close to alloy 6013.
Abstract: The impact of the initial phase composition of alloys was evaluated, in particular, the content of Cu, Mn, and Mg in aluminum alloys D16ChATW, 2024-T351 and aluminum alloy T, which in its physical and mechanical characteristics is close to alloy 6013. The impact was evaluated on the effects manifested by yield sites that occur on aluminum alloys that were subject to the dynamic non-equilibrium processes (DNPs) at the expense of impact-oscillatory loading of different intensities under conditions of static tensioning, The one-time DNP, to which the investigated aluminum alloys were subjected at the pre-set levels of elastic strain followed by static tensioning, was found to cause yield sites formation. This is due to self-organization of the alloy structure, which contributes to alloy plasticization. The initial phase alloys composition impact on the yield sites, which occurs when impulse energy of a different intensity is applied to the alloys, was analyzed. The specimens from the aluminum alloys undergoing DNPs of the same level were compared. This made it possible to conclude that alloys D16ChATW and 2024-T351, which have a higher content of Cu, Mn, and Mg, have longer yield sites upon subsequent static tensioning. On the basis of the experimental results, in particular, physical studies, the authors derived a physical and mathematical model of the yield sites that appear after DNPs.

Journal ArticleDOI
TL;DR: In this article , the reliability of transport vehicles is improved by ensuring their durability while reducing metal consumption, and the authors propose a method to improve the durability of vehicles while reducing their metal consumption.
Abstract: Improving the reliability of transport vehicles requires ensuring their durability while reducing metal consumption [...]

Journal ArticleDOI
01 Nov 2022
TL;DR: In this article , the effect of heat treatment in oxygen-containing medium on fatigue properties of zirconium alloy samples was shown and it was explained by the formation of a hardened near-surface layer.
Abstract: Abstract The effect of heat treatment in oxygen-containing medium on fatigue properties of zirconium alloy samples was shown. This gas treatment improved fatigue life in pure bending and cyclic tensile testing. An increase in fatigue life was explained by the formation of a hardened near-surface layer. According to the data of fractographic studies of destroyed samples, it was found that treatment in an oxygen-containing medium contributes to the formation of a structure with a higher energy intensity of destruction.

Journal ArticleDOI
TL;DR: In this paper , the impact of varying intensity impactoscillatory loading on the variation of the mechanical and structural properties of the VT23 high-strength two-phase transverse-rolled sheet titanium alloy have been found.
Abstract: The main regularities in the impact of varying intensity impact-oscillatory loading on the variation of the mechanical and structural properties of the VT23 high-strength two-phase transverse-rolled sheet titanium alloy have been found. The intensity of the impulse introduction of energy into the alloy under the dynamic non-equilibrium process (DNP) was estimated by εimp (the increment of dynamic strain). The pulse intensity was found to change the shape of the static strain diagram with further tensioning, as compared to the initial state. This indicates the effect from the structure self-organization inherent in the VT23 titanium alloy upon the DNP. After the DNP (εimp = 1.44%), with further static deformation, the tensile diagram revealed yield sites up to 6.5% long. In most cases, the DNP was found to have a negative effect on the variation of the mechanical properties of the VT23 titanium alloy, especially if the latter was rolled in the transverse direction. The optimal DNP intensity is εimp~1.5%. In this case, the DNP can be used as an effective plasticization technology for the VT23 titanium alloy (regardless of the rolling direction) in the stamping of high-strength titanium alloys. Changes in the mechanical and structural condition of the VT23 titanium alloy subjected to the DNP were confirmed by the fractographic investigation of specimen fractures.

Book ChapterDOI
01 Jan 2022
TL;DR: In this article , a comprehensive risk management system has been proposed to increase the trouble-free operation of the gas transmission system, and investigations into the ecological condition of the ground layer of air are underway in Bogorodchany district.
Abstract: AbstractThe problem of ensuring technological reliability and environmental friendliness of the natural gas transportation process is considered along with the main approaches to risk assessment and management at industrial facilities. To increase the trouble-free operation of the gas transmission system, a comprehensive risk management system has been proposed. Investigations into the ecological condition of the ground layer of air are underway in Bogorodchany district. Maps representing the distribution of harmful matter concentrations, coefficients of concentrations, coefficients of ecological danger, and the map of total contaminating index are used in the investigations. General chart of ecological risk is represented here. In particular, the objects for transporting gas are analyzed. The method for calculating the area detonation and the explosive cloud distribution is considered during damage of the main gas pipeline. Area detonating and distance of mixture explosive cloud distribution are calculated at different wind speeds. KeywordsGas transportation systemsMain pipelinesEcological risk

Journal ArticleDOI
TL;DR: In this paper , a mathematical model of dynamic process of formation of a regular microrelief on an internal cylindrical surface of a detail is developed, where the point of application in relation to the part is constantly changing in radial and axial directions, and the mathematical model describing this process will be with a discrete right.
Abstract: An analysis of modern literature sources to search for mathematical models describing the dynamics of the process of forming a regular microrelief on the inner cylindrical surface of parts, gas transmission equipment operating in severe operating conditions, in order to increase their life. It is established that there are no mathematical models describing this process and the peculiarities of its implementation under the point action of the deforming element on the workpiece surface. The molding movements accompanying the process of forming a regular microrelief on the inner cylindrical surface of the workpiece are considered and the driving forces that accompany this process are analyzed. On the basis of the conducted analysis the mathematical model of dynamic process of formation of a regular microrelief on an internal cylindrical surface of a detail is developed. The peculiarity of this process is that the process of microrelief formation occurs by a concentrated force, the point of application of which in relation to the part is constantly changing in radial and axial directions, and then the mathematical model describing this process will be with a discrete right. It is proposed to model such an action using Dirac delta functions with linear and temporal variables, using the method of regularization of these features, in particular, existing methods of integrating the corresponding nonlinear mathematical models of torsional oscillations of a part. Analytical dependences are obtained, which describe these oscillations in the process of formation of a regular microrelief. Using Maple software, 3D changes in the torsion angle depending on different output values are constructed. The conducted researches will allow to consider torsional fluctuations that is especially actual for long cylindrical details, such as sleeves of hydraulic cylinders, details of drilling mechanisms and others.

Journal ArticleDOI
TL;DR: In this paper, a method of mathematical modeling of the ordered surface relief of titanium alloy Ti6Al4V after femtosecond laser treatment is proposed, which allowed obtaining the informative signs of the self-organized surface irregularities, taking into account the stochastic and cyclic nature of this process.
Abstract: A method of mathematical modeling of the ordered surface relief of titanium alloy Ti6Al4V after femtosecond laser treatment is proposed, which allowed obtaining the informative signs of the self-organized surface irregularities, taking into account the stochastic and cyclic nature of this process. An algorithm has been developed, and a package of computer programshas been created based on the proposed mathematical model. These methods make it possible to analyze the zone-spatial two-dimensional structure of the cyclic relief of the modified surface. They are also the basis for creating the specialized software forthe automated profilometric diagnostic systems.