Vol 15, No 2 (2025)

This article introduces novel computer software designed to optimize maintenance schedules for traction rolling stock (TRS). The software analyzes TRS failure/breakdown data, considering reliability and cost-efficiency parameters, to recommend optimal inter-repair mileage standards. It analyzes locomotive component reliability indicators, investigates failure distribution hypotheses, and offers cost-effective recommendations for adjusting maintenance intervals. This data-driven approach addresses the limitations of traditional, generalized maintenance schedules by dynamically adapting to specific operating conditions and leveraging statistical models like Weibull, exponential, and normal distributions to predict failure-free operation. The software aims to improve fleet management by reducing downtime, minimizing unscheduled repairs, and lowering overall maintenance costs.

Purpose. This article aims to present computer software designed to process traction rolling stock (TRS) failure data and optimize inter-repair mileage standards, considering both reliability and cost-effectiveness parameters. The software analyzes locomotive component reliability indicators, investigates failure distribution hypotheses within locomotive units, and generates recommendations for optimizing inter-repair mileage while minimizing maintenance and repair costs.

Materials and methods. Methods and Software Description: The software developed in this study employs a multi-stage analysis process to optimize the standards for inter-repair mileage of locomotives. The core methodology is based on the statistical analysis of reliability indicators, including failure rates and the time between failures for individual components. Data collection is performed by sorting failures according to their type and nature, allowing for the identification of recurring patterns and failure modes.

Results. This study has demonstrated the effectiveness of a software-based approach for optimizing inter-repair mileage standards for locomotives. By leveraging statistical failure analysis and integrating economic cost models, the software reduces both the frequency of unplanned repairs and overall maintenance costs. The improvements in locomotive reliability and operational efficiency underscore the value of this tool for railway operators. Furthermore, this software, optimizing inter-repair mileage norms with consideration for reliability indicators and calculating economic impact aimed at reducing downtime, offers significant potential for practical application. Its ability to analyze failure data and predict potential issues allows for proactive maintenance scheduling, minimizing disruptions to operations and maximizing resource utilization. This contributes directly to improved cost-efficiency by reducing the need for reactive repairs and associated expenses.

Background. The article examines current challenges in optimizing emergency medical services (EMS) transportation logistics in the Russian Federation. It analyzes the system's current state, identifying key issues such as uneven call distribution, suboptimal station placement, outdated vehicle fleets, and inefficient dispatch operations. The study proposes research directions and development approaches to enhance EMS efficiency, including differentiated optimization strategies based on service type (emergency vs. urgent care), queuing theory applications, station location optimization, advanced routing and dispatching methods, and artificial intelligence/neural network implementations. The work emphasizes the need for region-specific solution adaptation and suggests concrete topics for further research. This article aims to draw researchers' and practitioners' attention to critical EMS logistics improvement opportunities to enhance healthcare accessibility and quality for the population.

Purpose – development of scientifically grounded approaches to optimize emergency medical services transportation logistics in the Russian Federation, aimed at enhancing service efficiency, reducing response times, and improving the quality of medical care for the population.

Materials and methods. The primary research method is theoretical-statistical analysis of the current system state and identification of key optimization challenges in EMS transportation logistics in the Russian Federation. The study is based on a comprehensive set of sources including regulatory legal acts, official records, statistical and reference materials, and periodical publications.

Results. This paper presents an analysis of the current state of ambulance service transportation support, identifying several key challenges, including uneven call distribution, suboptimal station location, an aging vehicle fleet, inefficient dispatching, and limited funding. The proposed research and development directions, based on a differentiated approach to optimization depending on the type of care provided (emergency and urgent), application of queuing theory, optimized station placement, implementation of advanced routing and dispatching methods, and the utilization of artificial intelligence and neural networks, constitute a comprehensive action plan for improving the efficiency of ambulance service transportation support operations.

Background. The study considers the problem associated with the development of a control system for many unmanned aerial vehicles. An analysis of the possibilities of improving the efficiency of control of unmanned aerial vehicle systems is carried out. The role of classification methods in the rating assessment of the system of flying objects is shown. The structure of interaction between the control center and a set of unmanned aerial vehicles is presented. A description of approaches related to the assignment of a rating is given. The control center maintains monitoring of the efficiency of the functioning of aircraft. It is shown how the various stages of rating management of a set of unmanned aerial vehicles are interconnected. The general integral assessment has an impact on the partial integral assessment. If the rating of the aircraft coincides with the maximum integral score, it will be considered as having the highest rating.

Purpose. Development of a system on the basis of which many unmanned aerial vehicles are controlled.

Materials and methods. The main research methods are related to the use of set theory, rating approaches and expert methods.

Results. In this paper, the basic principles and features of the formation of a control system for a set of unmanned aerial vehicles are considered in detail. Depending on the initial conditions, you must specify the parameters that should be taken into account in the model. The results of the work can be used for a wide range of unmanned aerial vehicles.

Background. The study provides a rationale for the use of modern technologies that are being actively introduced into agriculture, especially in the context of global challenges such as climate change and tightening regulations. Agricultural drones are becoming one of the key tools, allowing farmers to obtain accurate data on the condition of their fields in real time. Thus, their use can be an important step towards sustainable and efficient agriculture.

Purpose – increasing the efficiency of agricultural enterprise management by using unmanned aerial vehicles for the tasks of agro-industrial complexes, significantly reducing the costs of agricultural production.

Materials and methods. The main research method is to determine the multitasking of UAVs - analysis of the necessary technologies used in agro-industrial complexes. The article is based on a set of sources presented by regulatory legal acts, office work, statistical and reference materials, periodicals.

Results. The analysis showed that UAVs are often used as aerial monitoring, which can perform the function of both aerial photography and the delivery of plant protection products and perform many necessary functions. Unmanned aerial vehicles are also conveniently used to create models of various agricultural objects (buildings, technological structures, melioration facilities and hydraulic structures).

Background. The article examines the influence of the dynamic properties of the technological module on the process of forming vertical vibrations of the wheel axis when moving along a given bearing surface. The following methods were used in the study: a mathematical model of half of the technological module, a bus model. The amplitude-frequency characteristics of the system and spectral densities for vertical displacement and acceleration of the wheel axis for four configurations are obtained when changing the parameter characterizing the dynamic properties of technological modules. Statistical dynamics methods were used to analyze the dependencies. With an increase in the mass of the technological module from 1429 kg to 3929 kg (to transfer the tractor from traction class 1.4 to traction class 2 and 3, respectively), when using 15.5R38 tires, there is a decrease in the natural frequency of the technological module from 24 to 14 rad/s and an increase in the maximum spectral density from 0.5*10-3 to 4*10-3. With an increase in the mass of the technological module from 2343 kg to 4847 kg (to transfer the tractor from traction class 3 to traction class 4 and 5, respectively), when using tires 21.3R24, there is a decrease in the natural oscillation frequency of the technological module from 18 to 12 rad/s and an increase in the maximum spectral density from 1.5 * 10-3 to 6*10-3. The spectral density (characterizing the distribution of process energy) of vertical vibrations of the support surface in the frequency range (0...5 rad/s) coincides with the spectral density of the wheel axis of technological modules of all configurations.

Purpose. Obtaining and analyzing statistical characteristics describing the dynamic properties of technological modules when moving along a given support surface.

Methodology. In the article were used the methods of mathematical modeling and also statistical methods of the analysis.

Results. Statistical characteristics describing the dynamic properties of technological modules when moving along a given support surface are obtained.

Practical implications. It is advisable to apply the results obtained to organizations and institutions involved in the development of methods and tools for studying the dynamics of tractors and automobiles.

Background. This study develops a comprehensive approach to traffic congestion forecasting using synthetic data that simulates the dynamics of urban traffic. A hybrid methodology is proposed that combines time series analysis and deep learning, which is highly relevant for modeling nonlinear dependencies and patterns in traffic data.

Purpose. The purpose of this study is to develop and test a predictive model capable of accurately forecasting traffic congestion levels while accounting for seasonal and weather-related factors.

Materials and methods. To identify patterns in the data, additive time series decomposition, spectral analysis based on the fast Fourier transform, and autocorrelation analysis were applied. The predictive model was implemented using a two-stage approach: the classical ARIMA algorithm was used for baseline forecasting, while an LSTM architecture with two recurrent layers and regularization was trained on 24-hour sequences. Additionally, to compare and validate the results, the ensemble method Random Forest was used, configured with the following hyperparameters: 200 trees, maximum depth of 12, minimum samples per leaf of 2.

Results. The results demonstrate the superiority of the LSTM model over ARIMA and Random Forest in terms of predictive accuracy, as confirmed by visual comparison of forecasts with test data and by the mean squared error metric. Key factors influencing congestion were identified, including daily traffic intensity cycles, increased load during precipitation events (up to 30% during snow and 20% during rain), as well as temperature-dependent modulation of traffic flow.

The study considers a methodical approach to control of production processes for maintenance and repair of cars at technical service enterprises. The approach is based on considering the enterprise as a complex organizational or cybernetic system. For the main process implemented by this system, the number of control points during the shift, the size and degree of delay of control actions are determined. To simulate the system operation, a simulation model is used that takes into account the gradual increase in the error of performers and its elimination when applying the control action. Taking into account the established indicator and the efficiency criterion, the optimal number of control system elements is determined depending on the intensity of car arrival in the service zone. Models of the established patterns are obtained, which are described by single-factor regression equations. Models of patterns of influence of control system parameters on the relative throughput of the system are developed. 
Purpose – to improve the efficiency of management of automobile transport enterprises by establishing patterns of influence of the number of vehicles arriving in the technical service area on the parameters of the enterprise's production process control system.
Methodology. The study uses the method of correlation-regression analysis, the methodology of experiment planning, simulation modeling, and system analysis.
Results. Patterns of influence of the number of vehicles arriving in the technical service area on the number of control points during a shift, on the magnitude of the control action, and on the degree of delay in the implementation of the control action were established. Patterns of influence of the number of control points during a shift, the magnitude of the control action, and the degree of delay in the implementation of the control action on the relative throughput of the system were established.
Practical implications. The results of the study can be used by the management of enterprises for technical maintenance and repair of vehicles in the operational management of technological processes.

Background. The main objective of this study is to develop a methodology for checking the actual reliability of road surfaces based on the dynamics of changes in pavement smoothness, estimated vehicle speed, and estimated service life. The study introduces proprietary quantitative criteria, such as the road structure operational reliability coefficient and the road surface service life coefficient. The study is related to observing changes in road surface smoothness and its impact on performance characteristics. Assessing the wear and tear that occurs during operation is especially important for determining repair periods and the required amount of work. The article provides examples of smoothness measurements on road sections with varying traffic intensities, which allows us to draw a conclusion about the different rates of pavement condition deterioration and identify areas that are most susceptible to deformation.

Purpose. Consists in developing and testing a methodology for assessing the condition of road surfaces, with an emphasis on analyzing the evenness and performance characteristics of road structures. The main task is to integrate quantitative indicators and mathematical models that will allow more accurate determination of the timing and volume of necessary repairs.

Materials and methods. The article presents a methodology for assessing the actual reliability of road surfaces, developed on the basis of the dynamics of changes in the smoothness of the pavement, the estimated speed of the vehicle and the estimated service life. The methodology includes the author's developed quantitative assessment criteria, which include the coefficient of operational reliability of the road structure, the operational service life of the pavement and the coefficient of the service life of the road pavement.

Results. Based on the results of the study, reliability assessment criteria have been developed that can be useful for road management bodies and for repair planning. These criteria allow not only to identify areas requiring repair, but also to optimize the resources spent on its implementation. The study proves that the use of mathematical models and quantitative indicators can significantly improve the road surface management system, increasing safety and comfort for users.