Introduction. The prediction module generates possible future trajectories of dynamic objects that enables a self-driving vehicle to move safely on public roads. However, all modern prediction methods evaluate their performance only under urban conditions and do not consider their applicability to the domain of rural roads. This work examined the adaptability of existing methods to work under rural unstructured conditions and suggested a new, improved approach.Materials and Methods. As a solution, we propose to use a neural network that includes the following submodules: a graph-based scene encoder, a multimodal trajectory decoder, and a trajectory filtering module. Another proposed feature is to use an adapted loss function that penalizes the network for generating trajectories that go beyond the drivable area. These elements use standard practices for solving the prediction problem and adapting it to the domain of rural roads.Results. The presented analysis described the basic features of the prediction module in the rural road domain, showed a comparison of popular models, and discussed its applicability to new conditions. The paper describes the new approach that is more adaptive to the considered domain of study. A simulation of the new domain was performed by modifying existing public datasets.Discussion and Conclusion. Comparison to other popular methods has shown that the proposed approach provides more accurate results. The disadvantages of the proposed approach were also identified and possible solutions were described.

Introduction. The banking sector assigns high priority to data storage, as it is a critical aspect of business operations. The volume of data in this area is steadily growing. With the increasing volume of data that needs to be stored, processed and analyzed, it is critically important to select a suitable data storage solution and develop the required architecture. The presented research is aimed at filling the gap in the existing knowledge of the data base management system (DBMS) suitable for the banking sector, as well as to suggest ways for a fault-tolerant data storage cluster. The purpose of the work is to analyze the key DBMS for analytical queries, determine the priorities of the DBMS for the banking sector, and develop a fault-tolerant data storage cluster. To meet the performance and scalability requirements, a data storage solution with a fault-tolerant architecture that meets the requirements of the banking sector has been proposed.Materials and Methods. Domain analysis allowed us to create a set of characteristics that a DBMS for analytical queries (OnLine Analytical processing — OLAP) should correspond to, compare some popular DBMS OLAP, and offer a fault-tolerant cluster configuration written in xml, supported by the ClickHouse DBMS. Automation was done using Ansible Playbook. It was integrated with the Gitlab version control system and Jinja templates. Thus, rapid deployment of the configuration on all nodes of the cluster was achieved.Results. For OLAP databases, criteria were developed and several popular systems were compared. As a result, a reliable cluster configuration that met the requirements of analytical queries has been proposed for the banking industry. To increase the reliability and scalability of the DBMS, the deployment process was automated. Detailed diagrams of the cluster configuration were also provided.Discussion and Conclusions. The compiled criteria for the DBMS OLAP allowed us to determine the need for this solution in the organization. Comparison of popular DBMS can be used by organizations to minimize costs when selecting a solution. The proposed configuration of the data warehouse cluster for analytical queries in the banking sector will improve the reliability of the DBMS and meet the requirements for subsequent scalability. Automation of cluster deployment by the mechanism of templating configuration files in Ansible Playbook provides configuring a ready-made cluster on new servers in minutes.

Introduction. The development of the polar regions of the World Ocean contributed to an increased interest in studying wave processes in water bodies with ice cover caused by the action of a mobile load. In most papers of domestic and foreign scientists, the ice sheet was considered as an elastic or viscoelastic plate loaded with a rectilinearly moving vertical force. However, when modeling the impact of vehicles on the ice cover, it is of interest to investigate problems in which the force moves along a more complex trajectory. Therefore, this study aims at developing a method for studying the behavior of the ice cover under the action of a force moving along a trajectory of a complex shape, obeying an arbitrary law of motion.Materials and Methods. A method for solving problems of the action of an arbitrarily moving force on the ice cover of a reservoir of finite depth filled with an inviscid incompressible fluid is proposed. The ice cover was considered as a viscoelastic plate lying on the surface of a liquid in a state of potential flow. A concentrated force moving along an arbitrary closed trajectory and being periodic in time was applied to the upper surface of the plate. Hydrodynamic pressure acted on the lower surface of the plate from the liquid side. Due to the periodicity of the load applied to the plate, an integral time transformation was used to solve differential equations describing the behavior of this system. Further, using traditional methods, formulas were obtained for calculating stresses and displacements in the plate and components of the velocity vector of liquid particles. These formulas were presented in the form of an iterated integral. Numerical methods were used to calculate integrals.Results. Calculations showed that the deflection of the ice cover increased markedly with the growth of speed and tangential acceleration of the load movement. An increase in the relaxation time of ice and a decrease in the radius of the trajectory of the load also caused an increase in deflection. The distribution of the fluid particle velocity vector over the depth of the reservoir was calculated.Discussion and Conclusions. The proposed method has shown its efficiency in solving problems about the impact of a moving load on the ice cover of a reservoir. With its help, the influence of the curvature of the trajectory of motion and the mechanical properties of ice, the kinematic characteristics of the movement of the load on the deflection of the ice cover was investigated. The method simulates the impact of vehicles on the ice cover of a reservoir. The results of its application can be used under the construction of ice roads or airdromes on ice.

Introduction. Robotic technologies serve as an important indicator of the technological and economic state of the country, they also affect the lives of individuals. Their development is a promising and urgent task affecting many aspects of the life of modern society. Currently, robotics is going through another stage of development, which has its own characteristics, new directions. The work aims at analyzing the situation and ways of development of this industry in the world and in our country, as well as the attitude of people to the use of robotic systems and their willingness to improve them. The topic under consideration is understudied. Materials and Methods. In the presented work, the historical aspects of the formation of unique robotic technologies are defined, the ratio of the number of manufacturers and consumers of robotic products in the world is specified, the areas of the robotic technology application are named. The central place in the research is given to the results of an online survey conducted by the authors. Its statistical analysis made it possible to study, using specific data, the factors that influence the spread of robotic systems and robotic technologies and contribute to them. Results. The survey results, on the one hand, showed a high assessment of the prospects of robotic systems given by the respondents, and confirmed that young people have an interest in robot-making technologies. On the other hand, they allowed us to note the high level of knowledge in the field of robotic technologies among engineering students and the presence of more than elementary knowledge of these technologies among representatives of other special fields. In the opinion of the authors, there are all prerequisites for the further successful development of these technologies. Discussion and Conclusions. The analysis of the use of robotics in the world and in our country, as well as the results of the survey conducted by the authors, enable to conclude that these technologies are developing and will continue to develop actively, and the interest of current students in this, confirmed by the answers to the questionnaire, will contribute to the wider introduction of robots into the lives of future generations.

Introduction. Determining the tumor (nodule) characteristics in terms of the shape, location, and type is an essential step after nodule detection in medical images for selecting the appropriate clinical intervention by radiologists. Computer-aided detection (CAD) systems efficiently succeeded in the nodule detection by 2D processing of computed tomography (CT)-scan lung images; however, the nodule (tumor) description in more detail is still a big challenge that faces these systems.Materials and Methods. In this paper, the 3D clustering is carried out on volumetric CT-scan images containing the nodule and its structures to describe the nodule progress through the consecutive slices of the lung in CT images.Results. This paper combines algorithms to cluster and define nodule’s features in 3D visualization. Applying some 3D functions to the objects, clustered using the K-means technique of CT lung images, provides a 3D visual exploration of the nodule shape and location. This study mainly focuses on clustering in 3D to discover complex information for a case missed in the radiologist’s report. In addition, the 3D-Density-based spatial clustering of applications with noise (DBSCAN) method and another 3D application (plotly) have been applied to evaluate the proposed system in this work. The proposed method has discovered a complicated case in data and automatically provides information about the nodule types (spherical, juxta-pleural, and pleural-tail). The algorithm is validated on the standard data consisting of the lung computed tomography scans with nodules greater and less than 3mm in size.Discussion and Conclusions. Based on the proposed model, it is possible to cluster lung nodules in volumetric CT scan and determine a set of characteristics such as the shape, location and type.

Introduction. In sheet and hull structures operating under pressure, destruction, as a rule, is localized along the transition line from the base metal to the weld metal. Methods of increasing the durability of butt-welded joints, which are aimed at reducing stress concentration and creating favorable residual compression stresses, are described.Materials and Methods. The tests were carried out on an installation for biaxial bending, which created a biaxial stress field. Factory-made coupons and samples with an additionally processed transition zone from the weld metal to the base metal were tested. The effectiveness of further processing is shown by the following methods:– abrading;– grit hardening;– abrading with grit hardening;– melting of the fusion line in argon without filler wire;– melting of the fusion line in argon with filler wire EP-410U;– melting of the fusion line without filler wire with plastic deformation between narrow rollers.Results. The origin, development of destruction, and its features were analyzed using different methods of further processing of joint welds. Confidence spans (95 %) of the origin and development of failures for joint welds and base metal were calculated. The efficiency of the proposed methods for further processing was evaluated.Discussion and Conclusions. An analysis of the effectiveness of methods for increasing the durability of butt-welded joints has shown that the creation of a smooth transition from the weld metal to the base metal reduces significantly the stress concentration. This provides increasing the number of cycles before the onset of destruction and the survivability of compounds. Due to compressive stresses in the near-weld area, it is possible to increase the durability of joint welds. The most effective methods of further processing of welds combine the reduction of stress concentration and the creation of residual compression stresses. The high-tech solution is remelting the transition zone in an argon medium with an additional EP-410U filler wire.

Introduction. The article presents an overview of modern neural network models for natural language processing. Research into natural language processing is of interest as the need to process large amounts of audio and text information accumulated in recent decades has increased. The most discussed in foreign literature are the features of the processing of spoken language. The aim of the work is to present modern models of neural networks in the field of oral speech processing.Materials and Methods. Applied research on understanding spoken language is an important and far-reaching topic in the natural language processing. Listening comprehension is central to practice and presents a challenge. This study meets a method of hearing detection based on deep learning. The article briefly outlines the substantive aspects of various neural networks for speech recognition, using the main terms associated with this theory. A brief description of the main points of the transformation of neural networks into a natural language is given.Results. A retrospective analysis of foreign and domestic literary sources was carried out alongside with a description of new methods for oral speech processing, in which neural networks were used. Information about neural networks, methods of speech recognition and synthesis is provided. The work includes the results of diverse experimental works of recent years. The article elucidates the main approaches to natural language processing and their changes over time, as well as the emergence of new technologies. The major problems currently existing in this area are considered.Discussion and Conclusions. The analysis of the main aspects of speech recognition systems has shown that there is currently no universal system that would be self-learning, noise-resistant, recognizing continuous speech, capable of working with large dictionaries and at the same time having a low error rate.

Introduction. A gravity conduit with a control valve and a pressure regulator in the gravity water-supply pipe is considered under conditions when the hydraulic regime of the water-supply system is not disturbed. In relation to such a system, the problems of converting the energy of local artificial hydraulic resistance into electricity are investigated.Materials and Methods. Literature that highlights the possibility of using microturbines for power generation in water systems was studied. The actual values noted by the continuous pressure recorder (logger) for 12 hours were presented, as well as the water consumption by the turbine at a given unit section (the average for a year), and the pressure differential. It was noted that the use of small hydroelectric power plants in water supply systems significantly reduced the cost of their operation. The indicators of water consumption in the hydroturbine unit during the year, broken down by months, were given. The maximum power at the turbine inlet was calculated. The principles of selecting the type of hydraulic turbine were described. The average efficiency values for different elements of the hydroturbine plant, the average parameters of the power of the small hydro and the corresponding indicators of the average monthly electricity generation were indicated.Results. Equipping the units under study with specially designed turbines can enable to obtain electrical energy through converting artificially created by local resistance and extinguished mechanical energy. It is possible to apply the approaches described in this article when replacing many of the pressure control units of the Yerevan City Network system. The productivity of a small hydro power plant was predicted, as well as the terms of its construction and operation — for 2 years and 30 years, respectively. The construction and maintenance costs were calculated in advance. The expected data on income, expenses, and net profit are given. It is indicated that it will potentially be close to 6 million drams per year. The analysis of the data allowed us to conclude that the internal rate of return will be at the level of 10.4%, and the payback period is 9 years.Discussion and Conclusions. We recommend replacing the regulator with a hydroturbine having the same hydraulic resistance and automatic flow control in the system. The conclusions were confirmed by the energy and economic indicators of the hydroturbine plant located on the section of the Arzakan — Yerevan main water pipeline.

Introduction. Truss structures are widespread in construction due to a number of advantages, such as economy, versatility, and scalability. Accordingly, their modeling and calculation are urgent tasks in the design of building structures. Automatic solution to these problems causes an increase in design efficiency, calculation accuracy, and lower costs. The objective of the study is to examine the functionality and operation algorithm of the software module developed by the authors that generates the geometry of two-dimensional truss structures for subsequent modeling.Materials and Methods. Following the research of the widespread truss configurations, the classification of chords available in the software under consideration is given. The method of parameterizing a truss structure is provided. This method includes base geometric parameters of the structure such as dimensions, model construction rules, and additional features, as well as a comprehensive algorithm. The software is developed in JavaScript.Results. The software module has been integrated into a web application for calculating two-dimensional rod structures. To illustrate the functionality of the software, the examples of user interface are given as well as an example problem. The example includes configuration and calculation of an inclined truss structure. The results, such as support reactions and internal forces with axial force diagram, are provided.Discussion and Conclusions. Using this software module within the framework of the tool for calculating rod structures allows for the simplified process of modeling and calculating complex truss structures, design time, and resource reduction. The software module provides tools for specifying various types of structures, applying loads and assigning properties of a rod system, which makes it a useful instrument for design engineers.

Introduction. Welded joints in large-sized metal structures (e.g., in the structures of ship hulls) subject to low-cycle fatigue are considered. The characteristic appearance of soft interlayers, which are significantly plastically deformed under working loads, was noted. Deformation of the metal structure with damage, especially in the form of cracks, reduces the strength and reliability of structural elements and joints. Pre-deformation negatively affects plasticity; therefore, much depends on the residual plasticity of the cracking material. At the same time, with a decrease in residual plasticity, such an important reliability indicator as the resistance of the material to crack propagation — the fracture toughness – decreases. The paper is devoted to the development of a model that includes analytical dependences for assessing the crack resistance of metal structures and their welded joints with soft interlayers according to the crack resistance limit for all crack sizes.Materials and Methods. The theory and methods of linear mechanics of materials destruction, structural-mechanical approach are used. The calculation results were analyzed and compared to the experimental data and other analytical solutions. The numerical experiment was performed for the ferrite-perlite steel grades of 10, 50, 22K, St3sp, etc., widely used in industry, as well as for alloy steels hardened to medium and high strength of 30KhGSA, 37KhN3A, etc. Results. Analytical dependences are obtained for calculating the relative crack resistance limit according to three main known mechanical characteristics of the state of the material of the soft interlayer of the welded joint.Discussion and Conclusions. The results obtained can be used to assess the crack resistance of pre-deformed structural elements and welded joints (including those with soft interlayers) operating under a transverse load. The results of experimental data and analytical calculations are shown in dimensionless form, which enables to obtain invariant results with respect to the fracture toughness limit.