Search

The paper presents a new approach to recognize small parts from high-resolution 4K images grabbed by the embedded camera with trained convolutional network models. The main principle is a combination of standard machine vision techniques (OpenCV library) to identify blobs in the high-resolution image and parse to a suitable set of regions of interest, which are later recognized by trained convolutional neural network model (Tensorflow framework). The convolutional neural network model with single-shot detection was selected to identify the position of the object. 3D virtual models of parts with autogenerated orientations are used for simpler input data generation. Two embedded devices were selected for use in the experimental system. The first is NVidia Xavier dev board with 4K camera and integrated APU and the second is Raspberry PI 4 with external APU Intel Neural Compute Stick 2. The last part of the paper shows the implementation of the presented principle to the virtual device (HTC Vive Pro) for assisted assembly tasks to train and check workers during the teaching process.

The modern engineering educational environment ensures an extensive use of augmented reality for the successful and deep memorization of graphic material. There are many platforms for implementing augmented reality technology, the most popular of which were analyzed. As a result, the research work is devoted to the visualization of second-order surfaces and engineering objects. The article describes the scenario of augmented reality both with QR codes and authors’ markers. Moreover, the components of the markers and their significance in reproducing the image were described in detail. The proposed methodology includes a step-by-step approach for using the applications based on augmented reality for downloading through the public domain. As a result, the examples of tasks that can be performed using AR were realized. Finally, many markers are proposed in the article, which can be used in the engineering field’s educational process, especially with the mathematical peculiarities.

One of the essential characteristics of the pumps is the head–capacity curve. The shape of this characteristic depends on the type of pump, its design features, and other parameters. Nowadays, for obtaining the head–capacity curve, widely used computer simulation by using computer programs which base on the finite volume method. The most popular program for this aim is ANSYS CFX. The results of numerical simulation from the above program have a reasonable correlation of the experimental results. Pump design has an inducer and booster, which are considered in the article. For optimization of them designing by using the above program, the parametric geometries are necessary. Method for making them is described in the chapter.

Assurance of accuracy for machining parts and their work’s reliability is achieved using fixtures with the required accuracy of the locating and the workpiece reliable fixing. The expansion of state-of-the-art metal-cutting equipment’s technological capabilities necessitates using advanced fixture designs to be fully utilized. It requires the application of new approaches and the necessity of advanced fixture design. Fixture design for complex parts machining can reduce the auxiliary time for setup remains especially relevant. A flexible fixture design that provides tool accessibility multiaxis machining of fork-type parts for one setup is proposed. Refusal of full locating, application of industrial robots, and two fixtures for parts machining allows combining auxiliary time with cutting time. The numerical simulation results confirmed that the fixture meets all the strength, accuracy, and stiffness parameters. It allows the application of intensive cutting modes, which will provide the greatest efficiency when using modern machine tools and cutting tools. Oscillation amplitudes in the work surface positions do not exceed these surfaces’ size tolerances.

This book reports on topics at the interface between mechanical and chemical engineering, emphasizing design, simulation, and manufacturing. Specifically, it covers recent developments in the mechanics of solids and structures, numerical simulation of coupled problems, including fatigue, fluid behavior, particle movement, pressure distribution. Further, it reports on developments in chemical process technology, heat and mass transfer, energy-efficient technologies, and industrial ecology. Based on the 4th International Conference on Design, Simulation, Manufacturing: The Innovation Exchange (DSMIE-2021), held on June 8-11, 2021, in Lviv, Ukraine, this second volume of a 2-volume set provides academics and professionals with extensive information on trends, technologies, challenges and practice-oriented experience in the above-mentioned areas

The article presents the issue of providing comfortable conditions for passengers in coaches. At the same time, the main goal is to increase the efficiency of thermal energy use with the combined heating supply system. The research considers the analysis of thermal modes using the developed, comprehensive approach. This approach is based on both the numerical simulation and the regression analysis. The use of CFD analysis allowed analyzing the fields of temperature and air velocity in a coach. The simulation established that the use of the combined heating supply system causes turbulent airflow. A multifactor experiment was conducted to evaluate the impact of the radiator temperature on the internal one at different external temperatures. For the radiator temperature in a range of 20 ÷ 70 °C and the external temperature of –8 ÷ 24 °C, coefficients of the developed regression model were established. The obtained values allow estimating the thermal condition of the coach. Besides, the analytical dependence for the control of the radiator temperature, depending on the external temperature was obtained. The corresponding regulating curves and the transfer function were built. Overall, practical recommendations for compliance with sanitary and hygienic standards and providing comfortable conditions for coaches were formulated.

In the article, linear and nonlinear parameter identification methods were described relating to mathematical models of rotor oscillations for centrifugal pumps and turbochargers. For solving a nonlinear estimation problem, the combined use of several methods at each iteration step was proposed. In this regard, the determination of initial values for the estimated parameters was based on both the finite element and the discrete models. For studying the nonlinear rotor oscillations, a method for designing the discrete mathematical models was proposed based on the linear identification of equivalent masses using data obtained by the calculation of eigenfrequencies and mode shapes as a result of the finite element analysis. Using the artificial neural network, the methodology for estimating the inertia coefficients of rotor systems based on measurements of oscillation amplitudes at the frequency close to the critical one was developed. Finally, the proposed techniques were developed by implementing both quasilinear regression analysis and the artificial intelligence system. The corresponding program techniques were proved by the experimental research data of rotor oscillations using the accelerating and balancing stand with the vacuum camera. The developed methods and related program applications help evaluate the dynamic characteristics of pumps and turbochargers.

In this paper, ways for the improvement of technological equipment realizing the separation process in the oil and gas industry are considered. The refined mathematical model of dropping liquid motion is proposed in a two-dimensional formulation. Using the proposed design scheme, the kinematic parameters of the dropping fluid motion in a plane channel limited by two walls are considered. The model is based on the generalized Tchen’s equations with the correction of Corrsin–Lumley. As a result of integration for the given initial conditions, analytical dependencies for the velocity components are obtained, considering the nonstationary velocity components of the gas flow. Based on the obtained dependencies using the probabilistic approach, expressions for determining the rational geometry of the operating channel are obtained for ensuring the reliability of the vibration separation process. Particularly, an effective zone of vibration impact was found. Finally, the step of gutters and their effective width are determined to ensure the capture of the most amount of dropping liquid.

The research paper is aimed at improving the scientific and methodological approach for ensuring the reliability of technological equipment of energy-efficient modular separation devices by means of identifying the parameters of the refined mathematical models describing the main and secondary hydromechanical processes. Based on the critical review of the recent achievements in the field of separation and purification technologies, it is shown that combining vibrational-inertial separation allows one to increase both the separation efficiency and a range of the implementation of the corresponding technological equipment. Due to the object of study which is the separation processes of multicomponent heterogeneous systems, the assumption is that the separation efficiency can be increased by the proper organization of flow modes. As a result, the refined mathematical model of the gas-liquid flow is proposed. This model allows one to evaluate the total response of the dispersed phase on the vibrating wall and to determine the trajectories of dropping particles. Finally, the methodology for determining the separation time and the effective length of gutters for capturing dispersed liquid is presented.

This chapter deals with implementation of digital twin for experimental quality control system to remote monitoring, simulation, and optimization of real process. The main area of study is problem of connection and transformation of digital data from quality control process and product to digital twins and synchronization with Cloud Platform. Actual status of experimental quality control system is synchronized with digital twin for online interaction. Digitalized data must be stored in long-term horizon, which is performed by Cloud Platform, and it provides Big Data processing techniques. Digital twin of quality control system is transferred from 3D model to simulation software Tecnomatix. Interconnection between cloud control system and simulated Tecnomatix model (digital twin) is realized by OPC server. The technologies selected for data collection from experimental system are vision systems, RFID, and MEMS devices.

One of the promising methods for efficiency increase of heterogeneous systems separation is the gas-dynamic separation method. Devices that implement this method act like the automatic control systems that have as a controlled action (elastic force) and the regulating object (hydraulic resistance). It should be noted that calculations of these devices contain a number of difficulties with the solution of the aerohydroelasticity problem. To overcome the above difficulties, the process of the calculation methodology for this separation devices was divided into three stages. The first stage considers accounting only a gas phase, the second stage – both liquid and gas phase, and the third stage – the mechanical vibrations impact on the separation efficiency. This paper describes the development of the test stand for experimental studies of the dynamic separation devices, which is necessary at each stage. The designed test stand allows one to determine the deflections and stresses of deformable elements, amplitudes and frequencies of oscillations, as well as the gauge pressure and separation efficiency by using a single board computer Arduino MEGA 2560 uploaded software for collecting data from the sensors. The ADC Delta-Sigma Data Acquisition Shield for Arduino is used to achieve better accuracy through over-sampling, digital filtering, noise shaping, decimation, and synchronization of measurements from all connected sensors.

In this research work, hydrodynamic peculiarities of turbulent gas-dispersed flow were considered. Analysis of the existing assumptions and simplifications for modeling the process of turbulent transfer of dispersed particles in turbulent two-phase flow was carried out within the theoretical study of the dispersed particle motion in gas flow. As a result of the analytical solution, the trajectories of dispersed particles have been obtained. The dimensionless criterion for determining geometrical features of particles’ trajectories has been discovered. The dependences of the particle entrainment rate and overflow index on the diameter of dispersed particles were obtained. These dependencies are confirmed by the formulas determined previously by Brandt, Freund, and Hideman based on studying the vibration and acoustic impact on turbulent flow. The obtained results can also be applied to determine the Lagrangian frequency of turbulent pulsations by geometrical features of particles relative trajectories as Lissajous figures. Finally, the turbulent migration phenomenon for dispersed particles in gas-dispersed flow between vibrationally-weighted layers in the direction from the vibrating wall to the stationary one has been proved analytically.

This paper is aimed at the investigation of the two-phase upflow hydrodynamics in prismatic-shape apparatuses with the variable cross-section. To reach this aim, the mathematical model of the gas flow was developed based on the averaged in time and space velocities of the turbulent flow. This model is supplemented by the research of the solid particle movement in this flow. The research novelty of the proposed research is in the obtained dependencies for determining the velocity field of solid particles in a pneumatic classifier, as well as for estimating the friction coefficient. Additionally, equations for determining the velocity field of a gas phase were developed by velocity components of the two-dimensional gas flow. As a result, related graphical characteristics of the gas flow in the pneumatic classifier were built, and trajectories of solid particles were defined with respect to the apparatus width and height. The approach for evaluating empirical parameters was proposed based on the quasi-linear regression analysis. Moreover, the conducted regression analysis allows identifying the parameters of the mathematical model by the results of numerical simulations. The proposed approach will allow optimizing the technological and operating parameters of the pneumatic classification process and design of the related separation equipment.

The article is devoted to the study of fluid lift dynamics due to the capillary effect, as well as the development of the reliable mathematical model of capillary rising process based on parameter identification considering the experimental results data. The results of the research are applicable in evaporative cooling technologies, inertial-filtering separation, and filtration processes. Additionally, they can be applied in the fields of air conditioning, heat recovery, and electricity generation cycles. The practical significance of the obtained data is in relatively high performance (absorbency, thermal resistance, and liquid transportation capacity) of studied material samples for use in heat and mass transfer equipment. The experimental research consists of four stages for five samples of paper-like porous nanomaterial. The achieved results are used to evaluate the height of the liquid rising along capillary-porous material in time of the process. According to the results of analytical and experimental studies, the mathematical model was developed for the aim of estimating the parameters of the liquid’s movement. Particularly, the proposed approaches based on both quasi- and nonlinear, single- and multiparameter regression analyses, the rising-rate parameter and the maximum height of the liquid’s rise along the capillary plate were identified. Carrying out the validation of the proposed mathematical models with experimental results allows concluding that the two-parameter estimation of the operating parameters with the relatively high value of the r-Pearson correlation coefficient allows clarifying the proposed reliable mathematical model of liquid’s lifting process in capillary-porous media with enough accuracy.

According to modern technological requirements, the problem of increasing the efficiency of drilling-milling-boring machine tools is the first priority in multiproduct manufacturing. In this regard, the use of fixtures is an obvious stage in ensuring the quality and accuracy of engineering products. In this paper, the main objectives are related to the choice of locating charts in fixture design. Based on the developed algorithm, a reasonable choice of locating elements for parts is implemented using the 3-2-1 locating chart. Additionally, the decision-making sequence is given in the process of choosing the functional elements of the fixture using the database. The related algorithm considers the design and technological features of the workpiece. The practical significance of the research is in the application of CAFD for the proper choice of fixture locating elements. As a result, the proposed approach allows increasing the efficiency of designing technological equipment and reducing the complexity of technological preparation of the manufacturing process.

This paper considers modular dynamic separation devices as automatic control systems, which have hydraulic resistance as a regulation object and elastic forces as a control impact. The way for extension of the range of their efficient operation is proposed using vibration-inertia separation process. The related mathematical model of the abovementioned separation process is realized in three stages. This paper deals with numerical simulation of the aeroelastic interaction between gas flow and deformable elements in modular separation devices using the ANSYS Workbench software package. It should be noted that the modules Transient Structural and Fluent are used by system coupling combination. Two-way FSI method is chosen for simulation of aeroelasticity problem. Boundary conditions of symmetry are used for reducing of resource consumption of the problem solution. Methods of the dynamic meshes deforming are considered for additional preventing from negative volumes occurrence, as well as other significant settings for this type of problem are described. The oscillation frequencies of the deformable elements are determined according to the results of a numerical experiment for gas flow inlet velocity in the range from 3 to 6 m/s. The highest oscillation frequency 153 Hz is determined and observed for the inlet flow velocity equal to 4 m/s.

The article discusses the design features of vortex type liquid-vapor jet devices in the form of an oblique cut-off nozzle of the motive flow while entering the vortex chamber. Mathematical modeling allows proving the influence of the oblique cut to a deflection of the flow from the nozzle axis by a certain angle. This model is based on a continuity equation in the modified Baer’s form for the adiabatic process of discharge from the expanding nozzle with an oblique cut, as well as on the fundamental laws of thermodynamics for operating process. The proposed mathematical model allows determining the analytical dependence between the deflection angle of the flow from the nozzle axis in an oblique cut for an expanding nozzle and the following geometrical and physical parameters: the oblique angle of a nozzle, the taper angle of a nozzle, the initial pressure in front of the nozzle, the medium pressure at the outlet of the nozzle, the maximum nozzle expansion, and physical properties of the flow. The results of mathematical modeling of the flow deflection in an oblique cut of the expanding nozzle are presented analytically and graphically. Finally, it is proposed the methodology for numerical calculations of geometrical and operating parameters for ensuring the proper operating process, as well as it is described the technological features for designing the vortex type liquid-vapor jet apparatus.

This paper is devoted to developing the scientific approach of using artificial neural networks for solving a significant problem of vibration reliability of rotary machines that is urgently needed to improve the quality of their diagnosis and manufacturing. The proposed methodology integrates analytical dependencies, recent techniques of numerical simulations and artificial neural networks. The design schemes for realizing the related approach are presented on the example of the turbopump unit for liquid rocket engine. The main advantage of this approach in comparison with the traditional regression analysis and other existing techniques is absence of necessity for setting trial imbalances and carrying out additional initial starts of the turbopump unit. The mathematical model for identification nonlinear parameters of the dependence between bearing stiffness, deflection of the rotary axis, and rotor speed is presented. The proposed methodology is proved by the research of rotor dynamics on the example of turbopump units for liquid rocket engines and allows refining parameters of the nonlinear mathematical models describing forced oscillations of the rotor as a complicated mechanical system with nonlinearities. The results of the research can be used for carrying out the virtual balancing procedure for identification the system of imbalances by the reliable model of forced oscillation of the system “rotor – bearing supports”.

Computer-aided fixture design system is one of the elements of computer integrated manufacturing. It allows to implement the life cycle of fixtures from design stage to its manufacturing, using the geometric modeling and engineering analysis, process planning and automation of the manufacturing. With the aim to increase the productivity and quality of the production process, the CAFD system was developed. It consists of several main modules and they directly execute all the operating procedures. One of such module is aimed at organizing of the user’s work with the information system for fixture design process. This model determines the list of the stages and their order, establishes the informational and other relationships between them. All information for fixture design were grouped to 15 categories and include information about the fixture elements, workpiece, production conditions, and other auxiliary information. The interface of the system is made according to the MDI-application technology for ensuring the access to the auxiliary information throughout the operating process. The physical database model is realized by the open source relational database management system MySQL.

The chapter presents the mathematical models of free and forced oscillations of the comprehensive mechanical system “fixture–workpiece” describing the proposed adjustable locating-and-clamping module with a high level of flexibility for providing CNC multiaxis machining operation. With the aim to increase the fixture rigidity and detuning from a resonance mode, the eigenfrequencies and maximum displacements are determined using the numerical simulation model realized by the ANSYS software. The proposed mathematical model is proved by the results of numerical simulation on the example of fork-type parts considering contact stiffness of functional elements and values of clamping and cutting forces and moments. As a result, the advantage of the proposed manufacturing process in comparison on the typical one is justified. Particularly, the first eigenfrequency for the proposed manufacturing process is 1.64 times more than the same frequency for the typical manufacturing process. Additionally, the rigidity of a new fixture design is significantly increased, as well as detuning from a resonance mode is ensured. The proposed methodology allows estimating physical parameters of the proposed mathematical model by the results of numerical simulation and experimental research for ensuring dynamic stability of the highly complicated mechanical system “CNC machine tool–flexible fixture–spatial workpiece–precise cutting tool.”

Fixtures play an important role in the production of high-quality and competitive products, especially in the context of multiproduct manufacturing, which requires fast reequipment in the transition to the machining of parts of the other type. The article deals with the problem of determining the optimal dimensions of the fixture functional elements for machining of the lever-type parts within a given size group. The purpose of the research is to increase the efficiency of machining by optimizing the design of a flexible fixture through the proper choice of parameters of the fixture elements. Fixture configurations were analyzed by means of the parametric optimization algorithm. The reserves for fixture optimization were revealed, and possible variants of the fixtures for the limiting size of the levers within the given size group were investigated. Based on the research of static structural, modal, and harmonic analyses of fixture configurations, optimal parameters of each element of the flexible fixture were found out. The optimal design of the fixture is proposed, which can provide multiaxis machining of all sizes of levers within a given size group with the required accuracy.

One of the most monotonous activities in using convolutional neural networks for image recognition is preparation of the learning data. It involves creating samples (2D images of object) at different angles of view, different backgrounds/materials and partial overlay of the object. Input data must include a relatively large number of frames, typically about 100 and more images per object to make the learning precision useful. In the paper there is proposed a new approach to creating these data fully automated based on a virtual 3D model of the standardized parts. Automation principle is generating 2D images from the imported 3D construction model, including the following variable parameters: the angle of rotation, background and the material of the component. We used for verification pretrained DNN model Faster RCNN Inception v2 with single shot detection (SSD). The learned convolutional network was next tested by real samples to verify a new approach of learning by virtual models and recognition of real objects (parts).

The authors of the article present and prove the possibility of reducing the economic and environmental indicators in the processes of mineral fertilizers granulation by means of recycling and using organic agricultural waste. It is shown that such waste products are in the form of very moist suspensions, therefore, in order to minimize energy consumption for their processing, the optimal technology for granular product preparation is granulation in the fluidized bed apparatus. For this purpose there has been conducted the physical modelling of the granule formation process and one found out the conditions of suspended layer formation, which determine the nature of the dispersed suspension and dispersed solid phase interaction. One has experimentally established the temperature regimes of organic suspensions granulation and determined the operating parameters of the process. The kinetics of coarsening of granules was studied depending on the temperature of dehydration of organic suspensions. Analytical dependencies that are determined by the heat transfer coefficient are obtained to determine the time and temperature of granule heating.

The obtained solution of the mathematical model of liquid’s distribution and migration in the filter layer as flow model in the fibrous environment, which describes the non-pressure filtration motion in the gravity field of the separated liquid film from the gas-drop flow, allows to determine the saturation conditions of the free volume of the filter layer, distribution of speed and pressure under the conditions of free liquid’s movement in the filter layer, as well as to calculate the required cross-sectional area of the thin-layer fibrous filter element and the optimum height of the location of the overflow chutes for draining the separated liquid from the inertial-filtering to the drainage channels in order to avoid the secondary removal of droplets with the turbulent gas flow. As a result, the application rate of the separated liquid which falls from the filter element of the inertial-filtering separation channel to the drainage channels is obtained, as well as the dependence for the overflowed gutter of diverting the separated liquids from the inertial-filtering to the drainage channels is presented.

In this article the implementation of the mathematical model for rotor oscillations on non-linear bearing supports for the multistage centrifugal compressor is considered by using the computer program “Critical frequencies of the rotor”. It realized the finite element mathematical model, which allows taking into account the non-linear dependence of bearing stiffness on the rotor speed, as well as gyroscopic moments of inertia of impellers and shell-type parts. The artificial neural network “Virtual Gene Developer” software is proposed for evaluating the operating parameters of the approximating curve “bearing stiffness – rotor speed” by the dataset of numerical simulation results in the abovementioned software. Actual parameters of non-linear bearing stiffness are obtained by the results of the experimental research of rotor critical frequencies for the multistage centrifugal compressor 295GC2-190/44-100M on the experimental accelerating-balancing stand “Schenck”. The main advantages of the proposed approach and methodology for application of Artificial Neural Networks are stated.

The article is aimed at developing the scientific and methodological approach of using artificial neural networks (ANN) for solving applied problems in the field of mechanical engineering. This approach is based on the comprehensive implementation of ANN with the modern methods of numerical analysis (e.g., the finite element method) and analytical methods of the research with the use of mathematical modeling of the dynamic state for mechanical systems. Conceptual schemes for the implementation of the abovementioned approach are proposed for solving a number of interdisciplinary problems, such as investigation of the dynamics for rotary machines and hydroaeroelastic interaction of gas-liquid mixtures with deformable structural elements, as well as the dynamic analysis of fixtures. The main advantages of the proposed approach in comparison with the traditional regression analysis are the ability to learn and improve the ANN architecture, and to solve nonlinear problems of the parameters’ identification for mathematical models by using data of the results of physical experiments and numerical simulations. This approach allows refining parameters of the linear and nonlinear mathematical models describing the complicated mechanical and hydro-mechanical interactions under the impossibility of determination of an absolutely precise solution of the equations describing the process, as well as the incompleteness of the initial data.