Purpose of reseach. This work is devoted to solving one of the problems associated with the control of walking robots based on their dynamic mathematical model − the presence in it of obvious mechanical bonds due to reactions of bonds with the supporting surface. To solve this problem, it is proposed to use a fully connected neural network to evaluate the forces of normal reactions between the surface and the feet of a bipedal walking machine during its implementation of one step.

Methods. The paper considers two neural network architectures based on fully connected layers with ReLU activation functions. The architecture of the neural network includes five fully connected layers (input, output and three hidden), and an alternative architecture includes a thinning layer after each fully connected layer. The input data for the network are the state of the robot and the required control actions, and the output is the predicted reaction forces. The training sample is generated by modeling a complete dynamic model of the robot. The network is built and trained using machine learning libraries Keras and TensorFlow.

Results.The generation of training sample for neural network is described here, and it is carried out the training of two architectures of neural networks. Based on the simulation data, it was established that both trained neural networks are able to accurately predict the values of normal reactions using the values of generalized coordinates and velocities, as well as control actions as input, however, a static prediction error is observed.

Conclusion. The results obtained within the framework of the article can be further used to control the movement of bipedal walking machines on various types of surfaces.

Perpose of research.The extreme working conditions of the elements of modern designs, the complexity of their shape and large dimensions make it extremely difficult and expensive to carry out a full-scale or semi-natural experiment, especially when it comes to establishing ultimate (breaking) loads, therefore, in strength calculations, it is necessary to resort to numerical methods, which include the finite elements method. The finite elements method is not limited by either the form of the structure or the method of applying the load. The most critical part of the design is welded joints. There are frequent cases when the structural failure occurred in the field of welding. In this regard, this work is devoted to the stress analysis arising during loading in welded joints of pneumatic cylinder.

Methods.This article uses finite elements analysis of welded joints of a pneumatic cylinder in the APM FEM software package.

Results. The research results presented in the article show that the stress pattern in welded joints differs in different sections and arrangement in the structure.

Conclusion.The use of the finite elements method allows us to evaluate the stress pattern in a welded joint in a particular section and to select the necessary design and rationally position the welded joint.

Perpose of research. To study the particle size distribution of electroerosive chrome-containing powder, suitable for surfacing.

Methods.To carry out the planned studies, chrome-containing steel wastes were selected. The carbon-containing working fluid was chosen as the working fluid, namely, lighting kerosene. To obtain chrome-containing powder materials by electroerosive dispersion the device for EED of conductive materials was used. The dispersible material was poured into a desiccator, filled with a working fluid, namely, lighting kerosene. The authors studied the particle size distribution of the obtained powders by the method of dispersion in a liquid with ultrasound. Research technique (FR 1.27.2009.06762 “Methodology for measuring particle size in suspensions, emulsions and aerosols in the nanometer and colloidal ranges using the effect of dynamic light scattering”) has been used.

Results. It is experimentally established that the particle shape of the obtained powder material is due to the form in which the material is ejected from the hole during the EED process. It is also seen that particles having a regular spherical or elliptical shape prevail in the powder material. They are obtained by crystallization of the molten material (liquid phase). The particles formed during crystallization of the boiling material (vapor phase) have an irregular shape, an order of magnitude smaller than the particles formed by their liquid phase, and usually agglomerate with each other on the surface of other particles. In the EED process, such particles are most susceptible to chemical and phase changes.

Conclusion. Studies of the particle size distribution of chrome-containing powder material obtained by electroerosive dispersion of waste in lighting kerosene  under the following electrical parameters of the operation of the EED unit: capacity of discharge capacitors 45 μF, voltage at the electrodes 100 ... 110 V, pulse repetition rate of the generator 55 ... 65 Hz  determine the average particle size of the powder material and the specific surface area. The results will allow us to determine the rational area of their practical application.

Purpose of research.The article provides mathematical simulation and a study of the motion of the tiltrotor, constructed according to the quadcopter scheme, in transient modes. Under these modes, the moment of transition of the device from the vertical flight to the horizontal flight and back, performeddue to changing the direction of the thrust vector of the rotorsis meant.Theseissuesarenotsufficientlystudied, includingthefactthat, whenperformingsuchmaneuvers, asignificantdeviationofthetiltrotorfromthegiventrajectorycanoccur, andundercertainconditions, thelossofitscontrollabilityandfallcanhappen.Therefore, the purpose of this paper is to study the basic patterns of motion in transient modes and features of control algorithms based on mathematical models describing the controlled motion of small unmanned tiltrotors.

Methods.To solve these problems, methods of theoretical mechanics and mechanics of robots, a matrix approach to the determination of the radius-vectors and their derivatives for the main points of the mechanism pieces were used.The advantages of the matrix method are simplicity, universality ofthe rules for selecting coordinate axes for transition matricesgeneration. Studying the patterns of the motion of the tiltrotor, methods of mathematical simulation of dynamic systems considering the properties of electric drives, kinematics of rotation of the body, algorithms for the formation of control voltages, and external periodic disturbances,were used.When developing control algorithms, methods of the automatic control theory were applied;the control was performed applying software, using PID control allowing minimization ofthe actual and required values of the controlled variable.

Results.It is revealed that in case of the deviation of the rotor,coupled oscillations occur; the range of parameters of the control, at which these oscillations in the transition period are damped and the tiltrotor recovers equilibrium, are determined. Also, there were revealed dependences of deviations of the actual position of the device from the set position in coordinates OH, OY, when the values of the coefficient of differential and proportional components of the ACS control change respectively.The pattern of the change of the diagrams indicates a significant influence of thecontrol coefficients on the pattern of the transition process in terms of the amplitude values of the error and the time of the transition process.

Conclusion. A mathematical model is developed and mathematical simulation of the tiltrotor motion in transient modes is performed.It is shown that the control of the pitch angle, as well as the motion in the vertical plane consist of several loops of proportional-differential control, so it is necessary for each loopto have a circuit that prevents a significant deviation of the controlled parameters from the specified values, at which a stable transition of the tiltrotor to the horizontal position is provided. The parameters of the mean square error minimization are determined.

Purpose of research.The purpose of this work is to study the influence of the granulometric composition of electrospark cobalt-chromium poweders on the physico-mechanical properties of additive products.

Methods. Wastes of cobalt-chromium alloy“CELLIT" was chosen for this research.Butyl alcohol was chosen as a working fluid. To obtain cobalt-chromium powder materials by electrospark dispersion, a unit for ESD of conductive materials was used. The dispersed material was charged into a desiccator filled with butyl alcohol used as a working fluid for dispersion. Butyl alcohol C₄H₉OH belongs to monatomic alcohols. It is a colorless slightly viscous liquid with a peculiar smell of fusel oil,miscible with organic solvents.Butanol is used as a solvent in the paints and coatings industry, in the manufacture of resins and plasticizers, and in many other industries. To obtain experimental samples of additive products, the unit for lamination of powder materials by plasma was used. The authors studied the granulometric composition of the obtained powders by the method of ultrasonic dispersion in a liquid. The research methodology is FR 1.27.2009.06762 "Technique of particle size measurements in suspensions, emulsions and aerosols in nanometer and colloidal ranges with the use of dynamic light scattering effect".

Results. Experiments proved that the conditions of production and dispersion of powders determine their behavior during sintering.With the increase ofthe dispersion of the powder, sintering process accelerates and proceeds more actively, and the mechanical properties of the resulting products improve.Intensification of powder sintering is facilitated by oxides contained in large quantities in fine powders and reduced when heated during their sintering. The sponge metal surface, formed after the disappearance of the oxide, is more active than the surface, which is initially free from the oxide film.With the increase of dispersion and specific surface area of the powder, its penetration increases, the porosity decreases, and the microhardness increases. The presence of powder particles of different fractions increases the density of its shrinkage by filling cavities and micropores at the joints of large particles, which further leads to the decrease of the roughness of sintered products and the increase of the ultimate compressive and bending strength.

Conclusion. The conducted research reveals the relationship between the technology of electrospark cobalt-chromium powders production and physico-mechanical properties (porosity, microhardness, ultimate compressive strength, ultimate bendingl strength, roughness of the surface layer, etc.) of the experimental samples, and also allows controlling the process of the formation of structure and properties of products obtained by additive technologies.

Purpose of research.This article considers the influence of changes in the effective length of frame-rod structural systems elements operating under the conditions of constrained bifurcation.

Methods.A sign of the end moments and transverse forces has been taken as the criterion of the form of stability loss ofa frame-rod structural system element. Using this criterion, an expression has been obtained to assess the effect of changes in effective length of the frame struts on the critical parameters of the entire system, which allows varying the geometry of the structure to affect its performance.As an example, the critical parameters of the stability of a two-span frame designed from wood have been defined, to the middle element of which we apply central force Ркр, and to the extreme elements we apply forces multiplied by the coefficient α- αРкр. The type of elements’ bifurcation of the considered constructive system (constrained or forced) before and after the change of effective length of its elements has been revealed. The calculation of the unknown reactions and internal forces of the system were performed using special functions of the displacement method.

Results.Changes in efffective length of elements that lose stability passively do not significantly affect the critical stability parameters of the frame-rod structural system. At the same time, a 30% reduction in effective length of struts being in active bifurcation leads to a 50% reduction in the critical force.

Conclusion.Quite simple algebraic dependences are presented in the paper that allowus to identify elements of frame-rod systems. Their change in effective length has a significant impact on the critical parameters of the entire structure’ stability. At the same time, these criteria allow us to evaluate the resistance resource of centrally compressed elements of frame-rod structural systems.

Perpose of research. The aim of ourstudy is to establish the relationship between the standards of modern construction related to soil zoning and the activity of microorganisms that enhance nitrogen on MPA and KAA, and which are necessary for the healthy functioning of the environment.

Methods.At present, in the era of industrial technology the problem of the most efficient use of both industrial and natural resources has become a particularly relevant one. The efficient use lies not only in maximizing profit obtained from the objects of industrialization, but also in optimizing the interaction of such components of economic efficiency as the collections of the information base for calculation of efficiency, determining the effect of design construction as a proportion of total effect of the industrialization project.Social and environmental impacts of the investment project should also be taken into account. Today, the hierarchy of evaluation parameters is significantly different from the estimates of the early periods of project implementation and the social component is now a decisive one. Statistical methods of control and correlation and regression analysis were used in the calculation and construction of models.

Results.The social results of construction projects implementation is improving housing, working and cultural conditions of people, optimising the supply of settlements with certain goods and services, improving standard of living with minimal impact on the environment, which is the object targeted by the project of industrialization. The study develops the possibilities of alternative use of land resources depending on potential activity of chemoorganotrophic bacteria and actinomycetes, genesis of soils supposed for building in the territories alienated for these purposes.

Conclusion.The solution of one of the most important tasks in order to preserve land resources and fertile soil layer for modern society becomes even more urgent over time. Namely, this is the task of creating a comfortable living environment for humans, the maintenance of the biological cycle, the involvement of new assessment parameters in order to improve the quality and life expectancy.

Purpose of research.This article discusses various techniques for information security implementation used in certain countries; presents analysis and comparison of the degree of information security development in the Russian Federation. A brief history of the origin and subsequent dynamics of the development of this area in different countries is given. The objectives of this article are to analyze the legislation basis of different countries, namely the laws, regulations, decrees related to the sphere of information and personal data security and to develop a technique to increase the share of prevented attacks against information systems.

Methods.The peculiarities of forms of information security implementations in the Russian Federation, the United States of America, Germany,and  Francewas studied. The article analizes the current global international standards for standardization of security measures and systems related to the ISO / IEC 27000system, and the level of their implementation in Russia. The method of Saati hierarchies was chosen as the research method.

Results. Theconducted research allowed us to reveal possible shortcomings of information security implementation in Russia by means of drawing an analogy with other countries with a more developed information security systems. Russian legislative framework contains many laws and regulations that affect personal data protection and processing, but their number and arrangement clarity is not sufficient and needs to be enhanced.

Conclusion. As a result of the analysis it can be concluded that Russia pays considerable attention to information security implementation; different measures have been taken to its ensurance; a number of Federal laws have been enacted. However, the regulatory framework of the Russian Federation, the purpose of which is to protect information and personal data, has a relatively short history of development and needs enhancement.

Purpose of research. The paper attempts to formalize the management of the regional socio-economic system based on the principles and concepts of control theory.

Methods. The article shows that the description of elements and cause-and-effect relations in the management of the regional socio-economic system on the basis of the principles and concepts of control theory lends itself to a clear formalization. This approach provides a solution to the problem of regional public administration in terms of taking into account the impact of external disturbances. National projects of the Russian Federation, which through the control device form the control influence on the regional socio-economic system, act as a regulating influence. The negative feedback system allows to adjust the changes in the output coordinates of the control object in accordance with the targets of National projects. The external environment is considered as “interfering’in the system with the planned trajectory of the regional socio-economic systemdevelopment, producing the main disturbances and interferences. The objective task of the management system from the standpoint of control theory is formulated: to minimize the gap between the desired trajectory of development of the region, determined by National projects, and its real trends.

Results.The structure and functional components of the regional socio-economic management system are presented. The main elements are: the external environment, the control object (regional socio-economic system), the control device (decision support system “DATA”), the execution device (abstract civil servant), three measuring devices and three controlling devices. The principles of management of the developed system are presented. Classification features of the developed management of the regional socio-economic system as a complex system (decomposition, decentralization, hierarchical management and multi-mode management), as well as hierarchical problems being solved (at strategic, tactical and local levels) are given.

Conclusion. The application of control theory to formalize applied processes occurring in regional socio-economic systems allows us to prescribe internal relationships. It make sit possible to describe mathematical models of control object and external environment, and also to use DSS “DATA” in daily practice of regional management.

Perpose of research.The work is devoted to the development of algorithm for abnormal situations' prediction and prevention in industrial product movement control systems based on multicode marking data analysis.

Methods:Nowadays product labeling using bar code or radio frequency tags is mainly used to identify products. There are a lot of methods and algorithms for their detection, recognition and identification. But they are individual. Specifically, the product is identified by a certain label. The presence of a large number of labels on the product is due to the fact that each stage of the life cycle involves its own marking and identification mechanisms. Thus, at manufacturing site, the product is marked with a label, during transportation it can obtain another label related to the transport campaign software, during sales the product can have several more labels of the seller identification system, etc. Otherwise, multicode marking (different marks on one product) can be used to improve the reliability of identification system results and the speed of transportation by not turning the product to a label reader.

Results.This paper describes how to organize connection between different markings of the same product using methods of integrity control and combinatorics. The development of this approach is the use of simulation techniques to develop approaches for predicting and preventing of emergency situations during product movements. Experimental studies were carried out to determine the probability of identifying a bar code on the product to determine the minimum number of marks like bar code for marking metal pipes (OJSC "Vyksun Metallurgical Plant").

Conclusion. The article has a review and comparative analysis of analog systems. The algorithm of abnormal situations' prediction and prevention during product movement is described. The description is done on the basis of simulation model of product transportation process in the territory of CHPP-3 of OJSC "Vyksun Metallurgical Plant". Simulation results showed efficient use of proposed methods for further implementation at enterprises.

Purpose of research.One of the basic conditions for liquid friction occurrence is a variable gap, which is usually referred to as a geometric wedge. But this condition is not necessary and the effect of a geometric wedge can be replaced by a viscous wedge. The effect of a viscous wedge for Newtonian liquids can be caused by temperature non-uniformity. And non-uniformity of strain rate tensor can be an additional causefor non-Newtonianliquids. Thus, it is possible to provide an additional bearing capacity in the fluid friction supportby controlling the tempering field in the lubricating layer. It is also possible to minimize friction powerloss. The purpose of this work is to create controlled temperature-viscosity wedge in a fluid friction bearing. Physical realization of this effect is achieved by a multi-zone supply of variable temperature lubricant.

Methods.Experimental study planning and organization were used.Results analysis was carried out by means of paths construction and AFRC oscillatory patterns. Modern methods of machine learning are used in order to solve sensory and program determination problem of bearing and lubrication conditions.Artificial neural network of direct propagation with logistical activation functions has been developed.This network allows determining the method of lubricant supply from measurements of rotor vibration displacements and fluid pressure in the bearing. Methods of linear algebra and unconditional optimization methods are used as supplementary.

Results. Experimental apparatus in the form of rotor-support system with multizone lubricant supply with information-measuring system, which can receive rotor vibration displacement and liquid pressure supply has been developed. Mathematical model in the form of artificial neural network of direct distribution with one hidden layer was developed to monitor bearing and lubrication conditions.

Conclusion.Artificial temperature-viscosity wedge and multi-zone supply of lubricant to fluid friction bearing have a significant effect on hydro mechanical system. This effect, with an accuracy of more than 95%, was defined by an artificial neural network after processing the rotor vibration displacement and bearing fluid pressure measurements.