All issues

This article studies a method of constructing a predictive neural network model of a time series based on determining the composition of input variables, constructing a training sample and training itself using the back propagation method. Traditional methods of constructing predictive models of the time series are: the autoregressive model, the moving average model or the autoregressive model — the moving average allows us to approximate the time series by a linear dependence of the current value of the output variable on a number of its previous values. Such a limitation as linearity of dependence leads to significant errors in forecasting.

Mining Technologies using neural network modeling make it possible to approximate the time series by a nonlinear dependence. Moreover, the process of constructing of a neural network model (determining the composition of input variables, the number of layers and the number of neurons in the layers, choosing the activation functions of neurons, determining the optimal values of the neuron link weights) allows us to obtain a predictive model in the form of an analytical nonlinear dependence.

The determination of the composition of input variables of neural network models is one of the key points in the construction of neural network models in various application areas that affect its adequacy. The composition of the input variables is traditionally selected from some physical considerations or by the selection method. In this work it is proposed to use the behavior of the autocorrelation and private autocorrelation functions for the task of determining the composition of the input variables of the predictive neural network model of the time series.

In this work is proposed a method for determining the composition of input variables of neural network models for stationary and non-stationary time series, based on the construction and analysis of autocorrelation functions. Based on the proposed method in the Python programming environment are developed an algorithm and a program, determining the composition of the input variables of the predictive neural network model — the perceptron, as well as building the model itself. The proposed method was experimentally tested using the example of constructing a predictive neural network model of a time series that reflects energy consumption in different regions of the United States, openly published by PJM Interconnection LLC (PJM) — a regional network organization in the United States. This time series is non-stationary and is characterized by the presence of both a trend and seasonality. Prediction of the next values of the time series based on previous values and the constructed neural network model showed high approximation accuracy, which proves the effectiveness of the proposed method.

Modern methods of complex planning the execution of task packages in multistage systems are characterized by the presence of restrictions on the dimension of the problem being solved, the impossibility of guaranteed obtaining effective solutions for various values of its input parameters, as well as the impossibility of registration the conditions for the formation of sets from the result and the restriction on the interval duration of time of the system operating. The decomposition of the generalized function of the system into a set of hierarchically interconnected subfunctions is implemented to solve the problem of scheduling the execution of task packages with generating sets of results and the restriction on the interval duration of time for the functioning of the system. The use of decomposition made it possible to employ the hierarchical approach for planning the execution of task packages in multistage systems, which provides the determination of decisions by the composition of task groups at the first level of the hierarchy decisions by the composition of task packages groups executed during time intervals of limited duration at the second level and schedules for executing packages at the third level the hierarchy. In order to evaluate decisions on the composition of packages, the results of their execution, obtained during the specified time intervals, are distributed among the packages. The apparatus of the theory of hierarchical games is used to determine complex solutions. A model of a hierarchical game for making decisions by the compositions of packages, groups of packages and schedules of executing packages is built, which is a system of hierarchically interconnected criteria for optimizing decisions. The model registers the condition for the formation of sets from the results of the execution of task packages and restriction on duration of time intervals of its operating. The problem of determining the compositions of task packages and groups of task packages is NP-hard; therefore, its solution requires the use of approximate optimization methods. In order to optimize groups of task packages, the construction of a method for formulating initial solutions by their compositions has been implemented, which are further optimized. Moreover, a algorithm for distributing the results of executing task packages obtained during time intervals of limited duration by sets is formulated. The method of local solutions optimization by composition of packages groups, in accordance with which packages are excluded from groups, the results of which are not included in sets, and packages, that aren’t included in any group, is proposed. The software implementation of the considered method of complex optimization of the compositions of task packages, groups of task packages, and schedules for executing task packages from groups (including the implementation of the method for optimizing the compositions of groups of task packages) has been performed. With its use, studies of the features of the considered planning task are carried out. Conclusion are formulated concerning the dependence of the efficiency of scheduling the execution of task packages in multistage system under the introduced conditions from the input parameters of the problem. The use of the method of local optimization of the compositions of groups of task packages allows to increase the number of formed sets from the results of task execution in packages from groups by 60% in comparison with fixed groups (which do not imply optimization).

The paper is devoted to convex-concave saddle point problems where the objective is a sum of a large number of functions. Such problems attract considerable attention of the mathematical community due to the variety of applications in machine learning, including adversarial learning, adversarial attacks and robust reinforcement learning, to name a few. The individual functions in the sum usually represent losses related to examples from a data set. Additionally, the formulation admits a possibly nonsmooth composite term. Such terms often reflect regularization in machine learning problems. We assume that the dimension of one of the variable groups is relatively small (about a hundred or less), and the other one is large. This case arises, for example, when one considers the dual formulation for a minimization problem with a moderate number of constraints. The proposed approach is based on using Vaidya’s cutting plane method to minimize with respect to the outer block of variables. This optimization algorithm is especially effective when the dimension of the problem is not very large. An inexact oracle for Vaidya’s method is calculated via an approximate solution of the inner maximization problem, which is solved by the accelerated variance reduced algorithm Katyusha. Thus, we leverage the structure of the problem to achieve fast convergence. Separate complexity bounds for gradients of different components with respect to different variables are obtained in the study. The proposed approach is imposing very mild assumptions about the objective. In particular, neither strong convexity nor smoothness is required with respect to the low-dimensional variable group. The number of steps of the proposed algorithm as well as the arithmetic complexity of each step explicitly depend on the dimensionality of the outer variable, hence the assumption that it is relatively small.

The problem of the combustion of a gas suspension with an inhomogeneous distribution of particles over space occurs exists for the coal dust suspension combustion in combustion chambers and burners. The inhomogeneous distribution of particles in space can significantly affect the combustion velocity of the aerosolve of coal dust. The purpose of the present work is the numerically study the effect of the inhomogeneous distribution of particles and the composition of the coal dust on the combustion velocity of the coal dust in the air.

The physical and mathematical model of combustion of air-coal dust mixture with an inhomogeneous distribution of coal dust particles over space has been developed. The physical and mathematical formulation of the problem took into account the release of combustible volatile components from the particles upon their heating, the subsequent reaction of volatile components with air, a heterogeneous reaction on the surface of the particles, and the dependence of the thermal conductivity of the gas on temperature.

A parametric study was made of the effect of mass concentration, the content of volatile and the particle size of coal dust on the burning speed of a suspension of coal dust in the air. It is shown that the burning rate is greater for particles with a lower content of volatile components. The influence of the spatial distribution of particles on the burning rate of the coal-air mixture is analyzed. It is shown that the propagation velocity of the combustion front with respect to the suspension with an inhomogeneous particle distribution is higher than the propagation speed of the combustion front with respect to the suspension with a homogeneous particle distribution.

The article proposes a model for assessing the potential strength of a composite material based on modern fibers with brittle fracture.

Materials consisting of parallel cylindrical fibers that are quasi-statically stretched in one direction are simulated. It is assumed that the sample is not less than 100 pieces, which corresponds to almost significant cases. It is known that the fibers have a distribution of ultimate deformation in the sample and are not destroyed at the same moment. Usually the distribution of their properties is described by the Weibull–Gnedenko statistical distribution. To simulate the strength of the composite, a model of fiber breaks accumulation is used. It is assumed that the fibers united by the polymer matrix are crushed to twice the inefficient length — the distance at which the stresses increase from the end of the broken fiber to the middle one. However, this model greatly overestimates the strength of composites with brittle fibers. For example, carbon and glass fibers are destroyed in this way.

In some cases, earlier attempts were made to take into account the stress concentration near the broken fiber (Hedgepest model, Ermolenko model, shear analysis), but such models either required a lot of initial data or did not coincide with the experiment. In addition, such models idealize the packing of fibers in the composite to the regular hexagonal packing.

The model combines the shear analysis approach to stress distribution near the destroyed fiber and the statistical approach of fiber strength based on the Weibull–Gnedenko distribution, while introducing a number of assumptions that simplify the calculation without loss of accuracy.

It is assumed that the stress concentration on the adjacent fiber increases the probability of its destruction in accordance with the Weibull distribution, and the number of such fibers with an increased probability of destruction is directly related to the number already destroyed before. All initial data can be obtained from simple experiments. It is shown that accounting for redistribution only for the nearest fibers gives an accurate forecast.

This allowed a complete calculation of the strength of the composite. The experimental data obtained by us on carbon fibers, glass fibers and model composites based on them (CFRP, GFRP), confirm some of the conclusions of the model.

The paper provides a method for selecting the composition of a refrigerant with a given isobaric cooling curve using an artificial neural network (ANN). This method is based on the use of 1D layers of a convolutional neural network. To train the neural network, we applied a technological model of a simple heat exchanger in the UniSim design program, using the Peng – Robinson equation of state.We created synthetic database on isobaric boiling curves of refrigerants of different compositions using the technological model. To record the database, an algorithm was developed in the Python programming language, and information on isobaric boiling curves for 1 049 500 compositions was uploaded using the COM interface. The compositions have generated by Monte Carlo method. Designed architecture of ANN allows select composition of a mixed refrigerant by 101 points of boiling curve. ANN gives mole flows of mixed refrigerant by composition (methane, ethane, propane, nitrogen) on the output layer. For training ANN, we used method of cyclical learning rate. For results demonstration we selected MR composition by natural gas cooling curve with a minimum temperature drop of 3 К and a maximum temperature drop of no more than 10 К, which turn better than we predicted via UniSim SQP optimizer and better than predicted by $k$-nearest neighbors algorithm. A significant value of this article is the fact that an artificial neural network can be used to select the optimal composition of the refrigerant when analyzing the cooling curve of natural gas. This method can help engineers select the composition of the mixed refrigerant in real time, which will help reduce the energy consumption of natural gas liquefaction.

A mathematical model of two-phase capillary-nonequilibrium isothermal flows of incompressible phases in a double porosity medium is constructed. A double porosity medium is considered, which is a composition of two porous media with contrasting capillary properties (absolute permeability, capillary pressure). One of the constituent media has high permeability and is conductive, the second is characterized by low permeability and forms an disconnected system of matrix blocks. A feature of the model is to take into account the influence of capillary nonequilibrium on mass transfer between subsystems of double porosity, while the nonequilibrium properties of two-phase flow in the constituent media are described in a linear approximation within the Hassanizadeh model. Homogenization by the method of formal asymptotic expansions leads to a system of partial differential equations, the coefficients of which depend on internal variables determined from the solution of cell problems. Numerical solution of cell problems for a system of partial differential equations is computationally expensive. Therefore, a thermodynamically consistent kinetic equation is formulated for the internal parameter characterizing the phase distribution between the subsystems of double porosity. Dynamic relative phase permeability and capillary pressure in the processes of drainage and impregnation are constructed. It is shown that the capillary nonequilibrium of flows in the constituent subsystems has a strong influence on them. Thus, the analysis and modeling of this factor is important in transfer problems in systems with double porosity.

In the paper, it is represented a linearization method for the stress-strain curves of nonlinearly deformable beams and circular plates in order to generalize the pure bending vibration equations. It is considered composite, on average isotropic prismatic beams of a constant rectangular cross-section and circular plates of a constant thickness made of nonlinearly elastic materials. The technique consists in determining the approximate Young’s moduli from the initial stress-strain state of beam and plate subjected to the action of the bending moment.

The paper proposes two criteria for linearization: the equality of the specific potential energy of deformation and the minimization of the standard deviation in the state equation approximation. The method allows obtaining in the closed form the estimated value of the natural frequencies of layered and structurally heterogeneous, on average isotropic nonlinearly elastic beams and circular plates. This makes it possible to significantly reduce the resources in the vibration analysis and modeling of these structural elements. In addition, the paper shows that the proposed linearization criteria allow to estimate the natural frequencies with the same accuracy.

Since in the general case even isotropic materials exhibit different resistance to tension and compression, it is considered the piecewise-linear Prandtl’s diagrams with proportionality limits and tangential Young’s moduli that differ under tension and compression as the stress-strain curves of the composite material components. As parameters of the stress-strain curve, it is considered the effective Voigt’s characteristics (under the hypothesis of strain homogeneity) for a longitudinally layered material structure; the effective Reuss’ characteristics (under the hypothesis of strain homogeneity) for a transversely layered beam and an axially laminated plate. In addition, the effective Young’s moduli and the proportionality limits, obtained by the author’s homogenization method, are given for a structurally heterogeneous, on average isotropic material. As an example, it is calculated the natural frequencies of two-phase beams depending on the component concentrations.

This article discusses the mechanical properties of carbon nanotube (CNT)-reinforced platinum under uniaxial tensile loading using the molecular dynamics method. A review of current computational and experimental studies on the use of carbon nanotube-reinforced composites from a structural point of view. However, quantitative and qualitative studies of CNTs to improve the properties of composites are still rare. Composite selection is a promising application for platinum alloys in many cases where they may be subjected to mechanical stress, including in biocompatibility sources. Pt-reinforced with CNTs may have additional possibilities for implantation of the implant and at the same time obtain the required mechanical characteristics.

The structure of the composite is composed of a Pt crystal with a face-centered cubic lattice with a constant of 3.92 Å and a carbon nanotube. The Pt matrix has the shape of a cube with dimensions of $43.1541 Å \times 43.1541 Å \times 43.1541 Å$. The hole size in the average platinum dimension is the radius of the carbon nanotube of the «zigzag» type (8,0), which is 2.6 Å. A carbon nanotube is placed in a hole with a radius of 4.2 Å. At such parameters, the maximum energy level was mutually observed. The model under consideration is contained in 320 atomic bombs and 5181 atomic platinum. The volume fraction of deaths in the Pt-C composite is 5.8%. At the first stage of the study, the strain rate was analyzed for stress-strain and energy change during uniaxial action on the Pt-C composite.

Analysis of the strain rate study showed that the consumption yield strength increases with high strain rate, and the elasticity has increased density with decreasing strain rate. This work also increased by 40% for Pt-C, the elasticity of the composite decreased by 42.3%. In general, fracture processes are considered in detail, including plastic deformation on an atomistic scale.

We propose a three-component discrete-time model of the phytoplankton-zooplankton community, in which toxic and non-toxic species of phytoplankton compete for resources. The use of the Holling functional response of type II allows us to describe an interaction between zooplankton and phytoplankton. With the Ricker competition model, we describe the restriction of phytoplankton biomass growth by the availability of external resources (mineral nutrition, oxygen, light, etc.). Many phytoplankton species, including diatom algae, are known not to release toxins if they are not damaged. Zooplankton pressure on phytoplankton decreases in the presence of toxic substances. For example, Copepods are selective in their food choices and avoid consuming toxin-producing phytoplankton. Therefore, in our model, zooplankton (predator) consumes only non-toxic phytoplankton species being prey, and toxic species phytoplankton only competes with non-toxic for resources.

We study analytically and numerically the proposed model. Dynamic mode maps allow us to investigate stability domains of fixed points, bifurcations, and the evolution of the community. Stability loss of fixed points is shown to occur only through a cascade of period-doubling bifurcations. The Neimark – Sacker scenario leading to the appearance of quasiperiodic oscillations is found to realize as well. Changes in intrapopulation parameters of phytoplankton or zooplankton can lead to abrupt transitions from regular to quasi-periodic dynamics (according to the Neimark – Sacker scenario) and further to cycles with a short period or even stationary dynamics. In the multistability areas, an initial condition variation with the unchanged values of all model parameters can shift the current dynamic mode or/and community composition.

The proposed discrete-time model of community is quite simple and reveals dynamics of interacting species that coincide with features of experimental dynamics. In particular, the system shows behavior like in prey-predator models without evolution: the predator fluctuations lag behind those of prey by about a quarter of the period. Considering the phytoplankton genetic heterogeneity, in the simplest case of two genetically different forms: toxic and non-toxic ones, allows the model to demonstrate both long-period antiphase oscillations of predator and prey and cryptic cycles. During the cryptic cycle, the prey density remains almost constant with fluctuating predators, which corresponds to the influence of rapid evolution masking the trophic interaction.