Modern simulation model design involves a wide range of specialists from various fields. Additional resources are also required for the development and debugging of software code. This study is aimed at demonstrating the capabilities of large language models (LLM) applied at all stages of creating and using simulation models, starting from the formalization of dynamic systems models, and assessing the contribution of these technologies to speeding up the creation of simulation models and reducing their complexity.The model development methodology includes stages of formalization, verification, and the creation of a mathematical model based on dialogues with LLMs. Experiments were conducted using the example of creating a multi-agent community of robots using hybrid automata. The results of the experiments showed that the model created with the help of LLMs demonstrates identical outcomes compared to the model developed in a specialized simulation environment. Based on the analysis of the experimental results, it can be concluded that there is significant potential for the use of LLMs to accelerate and simplify the process of creating complex simulation models.

Keywords: Simulation modeling, large language model, neural network, GPT-4, simulation environment, mathematical model

The article discusses the application of neural network autoencoder in the problem of monochrome image colorization. The description of the network architecture, the applied training method and the method of preparing training and validation data is given. A dataset consisting of 540 natural landscape images with a resolution of 256 by 256 pixels was used for training. The results of comparing the quality of the outputs of the obtained model were evaluated and the average coefficients of metrics as well as the mean squared error of the VGG model outputs are presented.

Keywords: neural networks, machine learning, autoencoder, image quality analysis, colorization, CIELAB

Within the framework of the urban environment, the laws of distribution of the concentration of fine dust PM2.5, PM10 along road sections have been obtained. These data are necessary to assess the probability of exceeding the maximum permissible concentrations and to improve monitoring and control systems for atmospheric air. The analysis of the key factors influencing the content of PM2.5 and PM10 particles in the air of the territories adjacent to the roads has been carried out. Regression equations for total dust, PM2.5 and PM10 dust were obtained, allowing us to conclude that the concentration of PM2.5 and PM10 depends on total dust. The analysis showed that the mass content of PM10 in total dust pollution ranges from 73 to 81%, and the concentration of fine dust PM2.5 varies within two narrow ranges of about 11.6 and about 7 microns. A study of the proportion of PM2.5 of the total concentration showed that it is on average about 20%.

Keywords: dust, emissions, concentration, atmospheric air, roadway, climate, linear city, correlation coefficient, influencing factors

The article analyses the current state of automated control systems for street lighting: advantages and disadvantages, problems faced by manufacturers and operators of such systems. The article describes the basic principles of automated control systems, such as the use of motion sensors, light sensors and communication technology to optimise the operation of street lighting. The article also discusses the features and problems of designing street lighting based on automated lighting control systems, and possible problems associated with their implementation and operation.

Keywords: lighting control, digital twin, automation, sensor, light sources, LED lighting fixture

The article provides a brief description of the existing methods of vectorization of texts in natural language. The evaluation is described by the method of determining the similarity of words. A comparative analysis of the operation of several vectorizer models is carried out. The process of selecting data for evaluation is described. The results of evaluating the performance of the models are compared.

Keywords: natural language processing, vectorization, word-form embedding, semantic similarity, correlation

The article offers a variant of the development of lighting design projects for outdoor architectural lighting. Based on the modeling of light distribution in the DIALux 4.13 program, brushes have been created using specific lighting devices that simulate lighting effects from real lighting devices. A variant of the sketch of outdoor architectural lighting using Adobe Photoshop has been created with the implementation of local lighting techniques using the example of a drama theater building. Using a three-dimensional model of the object, a light design project was created in the DIALux EVO program. The proposed method of creating sketches is useful in professional activities related to the development of sketches of lighting design projects based on their high-quality photographs without the need to develop three-dimensional models, for conceptual proposals of fragments of the urban light environment and landscape territories. Having developed a base of brushes (based on real light distributions of lighting devices), it is possible to create sketches of architectural lighting of buildings that implement various lighting techniques.

Keywords: adobe photoshop, dialux 4.13, dialux evo, sketch, brush, building facade, outdoor architectural lighting, lighting effect, lighting technique, architectural lighting concept

The purpose of this work is to study the applicability of the U-Net architecture for automatically determining the contours of natural skins using the TensorFlow and Keras libraries in Python. A software application has been developed based on methods including OpenCV libraries, as well as a model for implementing a deep convolutional neural network. The dataset for training and testing the network was created using augmentation. Training was carried out using the stochastic gradient descent method after splitting the data sample into training and test images. In the future, the results obtained will be used to create an automated system that will make it possible to determine the contours of the skin and its defects, which in turn will open up the possibility of calculating the useful area of ​​the skin and creating an automated layout of patterns taking into account the identified defects.

Keywords: computer vision, edge detection, natural skin, machine learning, convolutional neural networks, U-Net architecture, deep learning

As the space industry accelerates the trend to reduce development and production costs and simplify the use of space hardware, small spacecraft, including CubeSats, have become popular representatives of this trend. Over the last decade, the development, production and operation of small spacecraft has become in demand because of a number of advantages: simplicity of design, short design and production times, and reduced development costs. The main problem in the design of CubeSats is their miniaturisation. This paper presents the results of the development of the optical cell of collecting and processing video information for remote sensing systems of the CubeSat 3U format satellite, with the aim of obtaining the maximum possible image characteristics, taking into account the strict physical limitations of the CubeSat unit. In the course of the work, using computer-aided design systems Altium Designer and Creo Parametric, the structural diagram, electrical circuit diagram, topology, 3D model, as well as the design of the housing of the cell of collection and processing of video information were developed. PCB size: 90x90 mm, PCB thickness: 1.9 mm, number of PCB layers: 10, accuracy class: 5, cell height: 20 mm, cell weight: 110 grams.

Keywords: space hardware, Earth remote sensing, small spacecraft, nanosatellite, printed circuit board, small satellite development trend, printed circuit board topology, CubeSat

The work is devoted to the study of the temperature distribution and equivalent voltage on the surface of a thermal radiation receiver during experimental and computational series. The experiments showed a qualitative and quantitative coincidence of the temperature data obtained by thermal imaging with the results of numerical modeling. The average error was 0.5℃, with a maximum deviation of 1.5℃ at individual points, which is due to edge effects and thermal insulation features. The computational model reproduces the main characteristics of the temperature field, including the effect of shielding, using a relatively low density of the computational grid. As part of the verification of the numerical model, the analysis of grid convergence was carried out, as well as the control of residuals and control of solution parameters were performed.

Keywords: heat exchanger, numerical and analytical calculation, convective and radiant heat transfer, efficiency improvement, outgoing flue gas, heat recovery, gas-liquid heat exchanger, numerical modeling, mathematical model, ANSYS Workbench software

In the process of ensuring information security, an important element is the protection of data from malicious influence. One of the stages of protection is to identify the source of the threat. The source of the threat may be the attacker himself, acting through his own user profile. Detecting and identifying a malicious profile in this case is a key element of building protection. In the context of user profiling, well-researched systems are social networks. Learning Management Systems (LMS), despite their similarity to social networks, remain devoid of scientific attention. Due to the similarity with social networks and the increasing introduction of learning management systems into information structures, this type of system is becoming a vulnerable point. There are several approaches and methods for detecting malicious activity, including statistical methods, machine learning methods, and rule-based methods. Our proposed approach combines a rule-based system with machine learning algorithms to improve the accuracy of detecting malicious activity. A rule-based system provides a detailed view of potential anomalies, while a machine learning algorithm provides a more detailed view of specific attacks. This paper highlights the aspects of determining malicious activity and user profiling in learning management systems and provides an example of one of the methods.

Keywords: information security, information system, social network, learning management system, user profiling, malicious behavior, classification

The article describes the main problems associated with the principles of calculation and design of building structures of buildings and structures in seismically active areas in accordance with the provisions of the regulatory document SP 14.13330.2018. The difficulties that may arise when using foreign regulatory requirements in terms of design and calculation are noted. The calculation of a flat steel multi-story frame for the main and special combination of loads and impacts is considered. The frame calculation for a special combination is performed according to SP 14.13330.2018 with and without taking into account the additional requirements of foreign design standards ASCE / SEI 7-22, ANSI / AISC 341-22. The requirements of foreign standards were not taken into account in full, but only in terms of increasing the reliability of the structure, for certain positions. The change in the parameter of the frame metal consumption for various calculation options is analyzed. Conclusions are formulated and recommendations are given on how to reduce the metal consumption when calculating for seismic impact, taking into account the increase in the reliability of building structures.

Keywords: finite-element schemes, columns, crossbars, seismic action, steel frames, flat frames, design, limit states, material consumption, optimization, reliability, special combinations, combination factors

The article considers one of the problems hindering the use of ceramic piezoelectric materials based on the BiFeO3 - BaTiO3 phases, which is caused by high values ​​of the dielectric loss tangent of these materials. It is assumed that this is due to different electrical conductivity of individual grains of this type of piezoelectric ceramics (Maxwell-Wagner effects), caused by the presence of iron ions in their composition, which have different oxidation states. In order to equalize the oxidation states of iron ions found in the grains of the considered ceramics, we used annealing of its samples in an atmosphere formed as a result of thermal decomposition of ammonium carbonate. It was found that this technique allows: a) to reduce the values ​​of tgδ of the CPM by 6 - 7 times; b) increase the polarizing field strength by at least 40%, and the value of the longitudinal piezoelectric modulus to 140 pC/N.

Keywords: piezoelectric material, electrical conductivity, dielectric loss, defect, iron ions, Maxwell-Wagner effect, reducing atmosphere, ammonium carbonate

The paper presents the results of the survey of consoles of precast reinforced concrete columns of an industrial building under construction. The consequences arising from errors during the manufacture of columns, as well as the method of calculating the console are described. The survey was carried out in order to detect the position of the reinforcement in the consoles of reinforced concrete columns. When performing a survey of the technical condition, the following tasks were set: to determine the actual condition of the supporting structures, their mating nodes at the time of the survey, to establish the actual reinforcement of the structures, to give recommendations for the restoration (strengthening) of the bearing capacity of the column consoles.

Keywords: inspection, load-bearing capacity, concrete, column, reinforcement, strengthening

The article proposes an approach to determining the level of developer brand protection, which is understood as the reputation of the developer in relation to the regional market, formed in the Internet. The level of protection of the developer's brand takes into account the Gunning Nebula Index of text reviews about the developer, the average volume of words in text reviews about the developer, the number of negative text reviews about the developer, the total number of text reviews about the developer and the degree of competitiveness of the real estate market in the region. Estimates of the level of brand protection of developers in Perm and Yekaterinburg are given and analyzed. To reduce reputational risks and increase the level of brand protection, if it is not high enough, developers are recommended to regularly collect positive customer feedback, conduct brand protection audits, collect and classify negative feedback into true and false. True negative reviews should be discussed with customers, address the cause of the negative review, and then invite customers to remove or correct the negative review. When dealing with false negative reviews, you should seek their removal or publish detailed reasoned rebuttals to them online.

Keywords: real estate developer, online reviews, Gunning Nebula Index, brand protection, degree of competitiveness in the market, reputational risk management

The paper presents the results of the survey of the reinforced concrete monolithic foundation of a ball mill with central unloading. The consequences of errors made during the construction of the foundation of machines with dynamic loads, as well as the foundation monitoring methodology, are described. The survey was carried out due to an increase in the vibration level of the equipment installed on the foundation and the detection of foundation defects in the form of cracks and chips in concrete. When performing the technical condition survey, the following tasks were set: to determine the actual condition of the supporting structure at the time of the survey, to establish the physical and mechanical characteristics of the materials of the structure, to indicate the characteristics and dimensions of damage sufficient to determine the volume of repair and restoration work, to develop recommendations for further safe operation of the structure.

Keywords: inspection, bearing capacity, foundation, dynamic load, concrete, reinforcement, strengthening