The paper describes the procedure for conducting a competition for regression models based on statistical data for the East Siberian Railway. At the same time, it is assumed to build a set of additive alternative versions of the model with the subsequent choice of the best option based on the involvement of a number of adequacy criteria. The unloading of wagons is singled out as the output variable of the model, and the input variables are: the average gross weight of a freight train, cases of failures of technical means of the 1st – 2nd category of operational nature, the working fleet of freight wagons. The implementation of the model competition allowed us to build over two hundred alternative options, from which the best alternative was selected using multi-criteria selection methods based in this case on a continuous criterion of consistency of behavior.
Keywords: railway transport, mathematical model, regression analysis, least squares method, model competition, adequacy criteria, multi-criteria selection
The researches directed on control by gelation, regulating of composition and properties of swelling up fireproof composite coatings (fireproof composites) for security of fire-resistant building constructions are presented. In-process on the basis of the topological analysis and gelation modelling component composition schungite in fireproof aggregates with demanded thermal and hardness in performances is optimised. The interconnection of structural performances, modifications of mineralno-phase composition and properties of fireproof aggregates is experimentally positioned at high-temperature impact. The rated-analytical method positions efficiency of fireproof aggregates for raise of flame-resistance of reinforced concrete constructions. The obtained data have allowed to develop representations about the gelation gear at interacting of corpuscles schungite in swelling up cement system at high-temperature heat and justify to approach to creation of effective fireproof aggregates for fire-resistant building constructions.
Keywords: fireproof composites, swelling up coatings, schungite, granulometry of components, composition optimisation, structure modelling, gelation of aggregates, mineralno-phase composition, properties of composite, fire-resistant of constructions
The article is devoted to solving the problem of organizing the separate collection of municipal solid waste. The obstacles that arise in the implementation of separate waste collection are analyzed. The existing foundations of waste sorting, laid down in the cities of the Republic, are considered. Variants of a system for the separate collection of municipal solid waste, which can be used in the Luhansk region, are proposed. Particular attention is paid to sorting complexes, which act as an auxiliary facility for optimizing the collection of certain types of waste and the recycling of secondary materials. As a result of the study, it was proposed to use such a method of thermal processing of municipal solid waste as pyrolysis.
Keywords: municipal solid waste, separate collection, sorting, heat treatment of waste
To create composite building materials with a polymer matrix, various fillers of both plant (wood-polymer composites - WPC) and mineral (mineral-polymer composites - MPC) origin can be used. The article evaluates the feasibility of using twelve different minerals in MPC from the standpoint of strength, cost and weight of the resulting materials in comparison with similar indicators of WPC. By sequentially considering each of the evaluated parameters, the sample of fillers is reduced by excluding combinations with characteristics worse than those of the reference material - a wood-polymer binary composite consisting of wood flour and polypropylene. It has been shown that one of the most effective mineral fillers can be waste from construction industry enterprises, as well as structures recycled during the demolition of buildings and structures.
Keywords: composite, matrix, filler, mineral, wood flour, dust, cost, volumetric weight, strength, elastic modulus, Poisson's ratio
The article discusses the features of constructing a special connection based on fiber-optic communication lines. An analysis is conducted on the reliability of using fiber-optic communication lines in terms of the possibility of unauthorized interception of transmitted information. The advantages of practical use of communication systems based on fiber-optic lines are presented. The methods of protecting fiber-optic communication lines from unauthorized access are considered, where the priority method of protecting information is encryption using various methods. In conclusion, the measures necessary for building a reliable communication system based on fiber-optic lines are emphasized.
Keywords: information, special communication, communication segments, public communication, optical fiber, fiber-optic lines, unauthorized access, encryption, communication system construction, cryptographic protocols
The development of a decision support system for evaluating a fashionable image of a person is described. This is done by selecting a set of visual attributes from an image and comparing this set with "fashionable" patterns. Fashion patterns are set by the user himself. These are images that are defined in the system as reference images. This paper provides an overview of decision-making methods, analyzes the relevance of decision-making systems in different spheres of society. The algorithm of the program and the tools with which the image is first preprocessed are considered, then the visual attributes are highlighted. The method of making decisions for different types of attributes is given. The comparison of colors in HSL notation is considered.
Keywords: decision support system, decision making methods, machine learning, Python, model learning, image, fashion, information and analytical system, k-means method
Research subject. The influence of the intensity of the light source and the direction of its beam on the process of object recognition by machine vision sensors - visible spectrum cameras and light detection and ranging systems (LiDAR) has been studied. Factors such as the intensity of light, its trajectory and the angle of the beam relative to the horizon are taken into account. Method. The solution to the problem of analyzing the ability of machine vision sensors to recognize the ArUco marker under conditions of various levels of illumination is based on empirical research methods. The main results. During the recognition of objects by a machine vision camera at a high level of illumination, a distortion of the light flux on the camera matrix occurred. Bugs in the operation of LiDAR were also found. Practical significance. Obtaining research results was used to develop a means of assessing a high level of assessment of a high degree of probability of detecting objects of sensory vision.
Keywords: machine vision, LiDAR, influence of light, empirical study
The article discusses the developed model for recognizing a clothing brand by image. The model not only predicts the type and brand of clothing, but can also determine their similarity. At the initial stage, a dataset was collected containing images of clothing from various brands with a total volume of 9,000 images. In this work, the ViT (Vision Transformer) neural network architecture was used, a model for working with images, which was presented by experts from Google Brain. The vit-base-patch16-224 model acted as a representative of the transformer architecture. Before training, all images were converted to black and white, and data augmentation was also used: image rotation by a random angle, mirror transformation. All photos have been normalized – pixel coordinates have been adjusted to the interval [0,1].
Keywords: neural network, model, machine learning, Vision Transformer, fashion industry, clothing brand prediction, clothing type prediction, brand similarity determination
The actualization of industrial development in the Far North poses many key tasks to the construction industry. Concreting is one of such tasks, the performance of which is much more difficult during construction at low temperatures. Based on this, it is necessary to design and develop innovative tools to optimize or rationalize work on construction sites in these conditions. The scientific significance of the presented article consists in an attempt to design a software solution that allows au-tomating the calculation of the parameters of the heating wire during winter con-creting. The practical value of the work lies in the possibility of using the presented materials as a basis for the practical implementation of this program.
Keywords: сonstruction, Far North, calculation automation, heating wire, program, algorithm, winter concreting
The features of classification of construction products and construction materials are considered, and optimization of their existing classification structure is proposed. The analysis of existing domestic and international systems of classification of construction information, domestic normative and technical literature is carried out and classification features for construction material and construction product are determined. The optimization of the classification tables (CTs) based on the application of the principles of the ISO 81346 standard series and the refusal to duplicate the structure of the construction resources classifier, on reducing the number of classes and subclasses taking into account the ISO 81346 criteria and moving classes and subclasses within CTs with the corresponding changes in the code designations is suggested.
Keywords: construction information classifier, information modeling, information model of capital construction object, classification of construction materials and products
The text describes software tools for analyzing the structure of metallic materials, including ferrous and non-ferrous metals. It presents image processing methods for edge detection and segmentation of structural elements on the metal surface. A Python program is described, which applies watershed algorithms and searches for white and black grains to segment metal images. The program performs analysis of grain sizes and shapes, and the results are presented visually and for further use. This tool is crucial for quality control and optimization of the properties of metallic materials.
Keywords: software tool, metal, quantitative analysis of microstructure, computer program, Python programming language
The transitional type of pavement of highways is widespread in Russia. At the same time, the increased estimated time between repairs cannot be fully ensured by the adoption of existing design solutions for the installation of transitional pavement pavements. This is confirmed by the dynamics of changes in the operational state, presented on the example of the road of regional importance Birakan - Kuldur in the section km 0+000 - km 25+000 in the Jewish Autonomous Region. Non-failure operation during the estimated overhaul and estimated service life of the pavement is assessed by the destruction coefficient, the limit values of which are set in the regulatory documentation. A significant decrease in the pavement destruction coefficient during the first few years of operation indicates insufficient strength and stability of the transition pavement pavement, which determines the need to develop special measures to ensure them.
Keywords: road, pavement, transitional type of pavement, pavement, destruction coefficient, overhaul life, longitudinal evenness, strength
When choosing an intensification method, the assessment of thermal-hydraulic efficiency is an important criterion. In this paper, the thermal-hydraulic efficiency of the pulsating method of heat transfer intensification was assessed as applied to an in-line tube bundle. The thermohydraulic efficiency was estimated by comparing the ratio of the increase in the Nusselt number to the increase in the coefficient of friction factor in a pulsating flow compared to a stationary flow. The coefficient of friction factor was determined by numerical simulation in AnsysFluent. The results of a numerical study showed that an increase in the product of the pulsation amplitude and the Strouhal number leads to a decrease in the thermal-hydraulic efficiency at all values of the Reynolds number, while the thermal-hydraulic efficiency is higher at the minimum values of the Reynolds number.
Keywords: Reynolds analogy factor, flow pulsation, heat transfer enhancement, thermal hydraulic efficiency.
Digital twins of railway stations are necessary for planning work and taking the most effective management actions. An important factor is the compliance of the planned time costs with the actual ones. One of the tasks that are difficult to formalize at railway stations is the process of holding the rolling stock. This is due to the fact that the holding time depends on the human factor and the holding rolling stock. To create an automated station controlled by a digital twin, it is necessary to develop an automated holding system. One of the tasks in developing such a system is the problem of device location. This problem can be formulated as follows: it is necessary to place the minimum allowable number of holding devices in the controlled area in such a way that reliable holding is provided for any configuration of the rolling stock. As a tool for solving this problem, the most effective will be the use of methods of genetic algorithms. In this article, the authors consider the relevance of this study and the relevance of automating the holding of rolling stock.
Keywords: digital railway station, automation, brake shoes, UTS-380, DUZS, traffic safety.
In the work, a method was implemented that allowed estimating the parameters of a control object based on the objective function, the least squares method, and the solution to the system of nonlinear equations was the Levenberg-Marquardt method. The numerical and laboratory experiments carried out allow us to speak about the effectiveness of the proposed method.
Keywords: identification, optimization, least squares method, Levenberg-Marquardt method, differential equation