The article considers the possibility of modeling the random forest machine learning algorithm using the mathematical apparatus of Petri net theory. The proposed approach is based on the use of three types of Petri net extensions: classical, colored nets, and nested nets. For this purpose, the paper considers the general structure of decision trees and the rules for constructing models based on a bipartite directed graph with a subsequent transition to the random forest machine learning algorithm. The article provides examples of modeling this algorithm using Petri nets with the formation of a tree of reachable markings, which corresponds to the operation of both decision trees and a random forest.

Keywords: Petri net, decision tree, random forest, machine learning, Petri net theory, bipartite directed graph, intelligent systems, evolutionary algorithms, decision support systems, mathematical modeling, graph theory, simulation modeling

Asphalt concrete mixes are the primary construction material for road surfaces, and precise design of their composition plays a key role in the quality and durability of road pavements. This article discusses the challenges associated with designing asphalt concrete mix compositions and presents a developed system for automatic mix selection. The automatic asphalt concrete mix composition selection system is a powerful tool for optimizing the material selection process used in road construction. This system can calculate the optimal mix composition, taking into account technical and economic constraints, leading to increased accuracy and reliability in mix selection. The advantages of this system include reducing the time and cost of the selection process, enabling testing and analysis of various mix options, ultimately improving the quality and durability of road pavements.

Keywords: asphalt concrete, asphalt concrete mix, composition selection, least squares method, linear programming method, software, automation, Python, Microsoft Access

The oil and gas engineering industry is undergoing changes that are associated with the introduction of innovative technologies, methods and tools to improve production processes and systems. All changes make it possible to achieve an increase in the average resource, durability and profit of the enterprise as a whole. Processing parts of the oil and gas complex and reducing all types of wear on the cutting part of the tool currently remains the most pressing topic. The continuous operation of a cutting tool is influenced by many factors. The relationship between cutting speed and tool life allows you to select the optimal speed. The work identifies the main directions of research on the selection of wear-resistant coatings for cutters to improve the accuracy of metalworking. The research was carried out using modern computer programs, which made it possible to draw certain conclusions, derive dependencies and determine the range of tasks for further research. Application of the main results will improve the processing efficiency and surface quality of parts in the oil and gas sector.

Keywords: durability, cutting mode, cutter, optimization, experiment, methodology, accuracy, processing, coatings, deformation

The article discusses the process of applying a radio-absorbing coating to the surface of plastic. Vacuum plasma methods make it possible to effectively apply thin films to various surfaces. The main parameters affecting the quality and effectiveness of the properties of the applied coatings are considered.The result of the studied coatings obtained by the vacuum-plasma method showed that a sample coated with aluminum nitride, the transmission coefficient through which has not changed compared to the case of free space, is not shielding, and a sample coated with titanium metal, introducing additional attenuation of the order of 5 dB indicates the presence of absorption.

Keywords: electromagnetic radiation, thin films, application technology, radio-absorbing coating, radiation protection, magnetron.

The article proposes new compositions of a fast-hardening concrete mixture using Portland cement, fine and coarse aggregates, basalt fiber, a complex modifying additive including acetone-formaldehyde resins and magnesium chloride (bischofite). The results of scientific and experimental studies are presented and the influence of the proposed additives on the formation of the structure, rheological and physico-mechanical properties of fast-hardening concrete is determined. Analysis of the test results showed that the proposed formulations, including a complex additive and basalt fiber, contributed to a decrease in the water-cement ratio, increased mobility of the mixture and increased strength of hardened concrete in the early and final hardening periods.

Keywords: concretes, oil and gas storage, modifying additives, fiber, mobility, setting time, strength

The cause of failures of building structures is design errors (18 - 51%). For metal structures the most frequent (22 - 44%) reason of failures is the loss of stability of its elements. At the conceptual design stage, it is important to have simple ways of determining design lengths of compressed structural members. A single-span two-storey hinge supported frame is considered. The magnitude of the critical load on the frame depends on the distribution of concentrated forces over the frame nodes. Doing a series of calculations, we find that: the minimum value of critical load is obtained when the force F of the left post of the second floor is loaded; maximum value is obtained by loading the first floor props with the same forces F/2. For practically important cases the parameters determining the critical load differ from one another by no more than 5% . The notion of ro-similar frames as frames with the same ratio of linear rigidity of a transom and a column is introduced. It is shown that the parameter, determining the critical load on the frame, is the same for ro-similar frames. For almost important cases, approximate formulas have been obtained, allowing to determine the critical load parameter and the calculated lengths of compressed rods with an error of not more than 5%.

Keywords: flat frame, loss of stability, critical force, design lengths, stability equation, ro-similar frames, approximation, least squares method.

The paper considers mathematical models obtained on the basis of experimental studies of electrical sheet steel. The models reflect the error in determining the main magnetization curve of electrical steel. The magnetic properties are determined in the center and at the edge of the cut of sheet samples with a size of 150 × 150 mm, made by cutting with guillotine shears and laser cutting. The choice of scale factors for calculating the main magnetization curve with an error of ± 5% according to the measured Weber-ampere characteristic has been substantiated. The study was carried out using a device for express control of the magnetic characteristics of electrical sheet steel. The main curve of magnetization of the sample material from sheet electrical steel was determined in an alternating magnetic field with a frequency of 50 Hz, along the direction of rolling. Investigated samples of isotropic sheet electrical steel grade 2212.

Keywords: mathematical model, electrical steel, magnetic properties, magnetization curve

The analysis of the use of renewable energy sources in Russia is carried out. The main features of the use of energy-efficient technologies in construction are considered. On the example of the construction of a 9-storey residential building, a comprehensive analysis of the construction area is performed. Solutions with the use of energy-efficient and green technologies are proposed.

Keywords: construction, energy-efficient technologies, green technologies, renewable energy sources, energy saving, energy efficiency

This article briefly discusses recurrent neural networks and bidirectional recurrent neural networks. A conditional random field is also described. In particular, we consider the vector representation in the form of the ELMo model, the bidirectional language model and its fine-tuning. A diagram of the architecture of a bidirectional recurrent neural network with CRF is also given.

Keywords: named entity recognition, neural network, word vector representation, language model, conditional random field, neural network architecture, recurrent neural network, natural language processing, bidirectional recurrent neural network

This article discusses the algorithms used for the operation of the chatbot. Within the framework of these algorithms, a general approach to the operation of dialog systems is considered. And the algorithm of the dialog system is proposed, based on a general approach, which includes a natural language processing module. The algorithms that will be applied to the chatbot to search for products of interest to the user are also presented. Among the considered algorithms are such as the algorithm of interaction between the user and the chatbot, the processing of user requests and the algorithm of natural language processing. A modified algorithm for natural language processing is also presented, taking into account the necessary requirements.

Keywords: chatbot, natural language processing, user request processing, named entity recognition, dialog manager, dialog system

The problem of searching over encrypted data using homomorphic encryption in distributed software systems is addressed. The paper considers the application of the approach developed by the authors for the implementation of a distributed system prototypes for issuing digital diplomas and certificates for obtaining competencies with recording in IPFS and an Ethereum smart contract and a search engine for recruiting personnel. The prototype of the system presented in the article demonstrates the use of homomorphic encryption, which allows the search engine and users to interact with the directly transformed data in public blockchain networks without performing the reverse transformation, ensuring their security.

Keywords: blockchain, distributed software systems, cloud computing, homomorphic encryption, mathematical model, transactions, smart contracts, digital diploma, recruiting

In this work, a survey of the hot water supply system from the boiler house No. 2 of Energoservice LLC was carried out. The daily schedule of hot water released for sanitary needs is given. The existing scheme of the boiler burner on-off control system is considered. A method for stabilizing the hot water preparation process by increasing the burner shut-off settings at the hour of the highest water consumption is found and described, and their values are found experimentally. A scheme has been developed, assembled and tested that allows you to adjust the operating mode of boilers at a strictly specified time of day. The proposed measure allowed us to solve the problem of selling hot water to consumers of a given quality during the maximum water intake period. In addition, the reduction in the generation of thermal energy for heating hot water at night and on weekends allowed for a 13.87% reduction in natural gas consumption in 2020.

Keywords: hot water supply, fuel consumption, pumping station, circulation line, conditional fuel, mode, boiler unit

The study is devoted to the analysis of satellite observations data assimilation to discover the necessary information for developing and verifying mathematical models of hydrodynamics and biological shallow-water kinetics. The use of satellite earth sensing data is taken to enhance information base. The possible use of neural networks with optical flow computation is considered in the study. The objective of the study is to develop a software tool used to identify the initial conditions in mathematical modeling of hydrobilogical shallow-water processes. The article illustrates the relevance of applying the observational data processing from satellite earth sensing. There are considered the necessity and possibility of using the neural network approach with the optical flow computation in solving problems of information processing from gray-scale snapshots.

Keywords: mathematical modeling, shallow water body, satellite sensing data, neural network, contour, image processing

The paper is devoted to the analysis of methods of adoption of satellite observation data in order to identify the required information used in the development and verification of mathematical models of hydrodynamics and biological kinetics of shallow water reservoirs. For the information accumulation, we consider the use of remote sensing data. The aim of the paper is to identify the best implementation method for software tools in order to improve the quality of assimilation of date of satellite sensing of the Earth relating to hydrobiological processes in a shallow water reservoir. The results of the work indicate the clarity and relevance of the use of high-tech methods for filtering ERS images. The modern methods of accentuation of contours of objects based on discontinuities in the brightness of a halftone image, used in real time or time close to it, have been considered, and their algorithms have been briefly described.

Keywords: mathematical modeling, shallow water reservoir, satellite sensing data, filtering methods, Kirsch, Sobel, LoG, LBP, operator, recognition, contour

The article considers the trends in the development of coastal management in the United States, great Britain and Australia, and analyzes the current situation of the coastal zone of Volgograd. Recommendations are offered based on the experience of foreign countries.

Keywords: coastal zone, management program, coastline, waterfront area environment, sustainable planning, design approach, architectural environment, waterfront