Search results

Annually locomotive-building plants, equipment suppliers and service companies develop organizational and technical measures aimed at improving the reliability of products. Thus, within the framework of the contract for the supply and maintenance of electric locomotives of the ERMAK series, a number of corrective measures have been implemented in more than thirty directions, many of which have achieved a positive result. However, during the long-term operation, more and more new hidden technical defects are revealed, and in rare cases, the measures taken are not enough. The manifestation of systemic inconsistencies is random in nature, thereby they negatively affect the dynamics of the average daily mileage and the linear mileage completed over the entire life cycle, causing unpredictable fluctuations, and as a result, the organization of service planning and budgeting to support the life cycle of locomotives. Therefore, there is a need to develop a model for a more accurate forecast of the average daily mileage for a long period, considering the impact of system inconsistencies and corrective measures to improve the reliability of nodes. The article uses the Pareto principle to analyze system malfunctions of locomotives manufactured by PC NEVZ LLC for the period of operation from 2018 to 2021, analyzes the dynamics of the average daily mileage of the locomotive fleet of the Far Eastern Traction Directorate with the use of a statistical and analytical method, analyzes the impact of failures on the average daily mileage using the Fourier time series forecasting method. On the example of malfunctions of power current-carrying buses of a rectifier-inverter converter and malfunctions of latches of a high-voltage vacuum circuit breaker, the influence of malfunctions of critical nodes is evaluated.

The results of the train traction electricity consumption forecasting, which were obtained on the basis of existing methods and the interval regression method, was analyzed. The errors of forecasting according to three methods compared with the real electricity consumption were determined. The authors put forward the software for calculating the predicted values of electricity consumption for train traction, taking into account the operational indicators of the electrified railroad under conditions of uncertainty in the initial data.

The article presents the results of the study of the influence of deviations of certain design parameters of bogie from established normative values on a relative offset from the crests of wheel pair in mezhdurelsovom space of railway transport. Such deviations occur in the process of the gradual wear of moving parts in real-world conditions of rolling stock and lead to a change of kinematic parameters of bogie. An analysis of dependence of lateral displacement relative to the wheelset of railway track from the difference between the diameters of the tapered surfaces of wheelset, skating from lack of alignment of wheelsets and difference coefficients rigidity of springs of bogie. The proposed mathematical model allows to not only diagnose technical condition of wagon bogies during their movements on the straight section of railway track, but also forecast the rolling stock maintenance dates the whole on the basis of position measurements of wheel pairs regarding railway track.

A significant share of JSCo «Russian Railways» expenses falls on the purchase of diesel fuel and electric power for train traction. In this connection, the task of ensuring rational consumption of energy resources acquires special importance. Its solution is impossible without a well-functioning system for planning and forecasting the energy efficiency of locomotives. The article proposes a method for predicting specific energy consumption (SEC) for train traction, based on determining predicted values of transportation work and fuel and energy resources consumption by extrapolating time series, which consists in spreading the trends in changes in the values established in the past to the future period. A distinctive features of the developed method is the determination of seasonality indices and consideration of the rhythm of changes in the indicators. In cases where the forecast period includes months of the first or fourth quarters, a formula is proposed for determining the forecast value of the SEC, taking into account the influence of the atmospheric air temperature. The calculations performed showed that the application of the proposed method for structural divisions with different volume and nature of transportation work and the level of the SEC ensures a sufficiently high accuracy of train traction energy cost forecasting. The method is included in the Methodology for Analysis and Prediction of Fuel and Energy Resources Consumption for Traction of Trains developed by OmGUPS and implemented in the railroad network of the Russian Federation.

In this paper we propose an electric load forecasting algorithms based on artificial neural networks. An improved method for selecting the most appropriate structure of the neural network based on the coefficient characterizing the homogeneity of the samples is proposed.

Purpose. Constructing a model for predicting a quantitative indicator of the pre-discharge state of the upper structure of the track based on a statistical analysis of the seasonal dynamics of this indicator. Forecasting involves identifying bottlenecks for timely corrective action. This approach allows you to refine the construction of algorithms of the functional risk assessment system on the infrastructure of Russian Railways for managing the technical condition of the railway track and safety and is considered as an element of digitalization of the risk assessment of traffic safety in the Railway Infrastructure Directorate. The development is carried out on the basis of accepted existing regulatory documents and classifiers of risk factors operating for the infrastructure management at Russian Railways. Methods. regression analysis, data validation, modeling based on regression analysis. Results. Dependence was identified and a forecast model of the dynamics of the number of deviations of the 2nd degree rail gauge geometry (GRK) was built based on the use of actual data from the automated system Path (APCS P) of Russian Railways. Testing of the approach was carried out on the basis of the Directorate of Infrastructure of the North Caucasus Railway. The identified dependence allows you to give a fairly accurate forecast of the state of traffic safety and the development of GRK deviations on the 2nd degree for use in practice, effective planning of material costs for planned preventive work and overhaul at linear enterprises, on a specific railway adopted for calculation and on the network of Russian Railways. Practical significance. The constructed model allows predicting the intensity of the risk factor on an objective basis of seasonal patterns, as well as the volume of control impacts on the current content of the upper track structure. The presence of such a forecast will make it possible to establish a relationship between the indicator of the dynamics of the number of deviations of the 2nd degree rail gauge geometry, including seasonal dynamics, and the risk factor, that is, the number of GRK deviations of the 3rd degree used in the risk assessment on the infrastructure. The result of this approach is the solution of a system of tasks that affect the values that reflect the level of risks, and as a result, effective management of financial flows for the maintenance of infrastructure, reduction and prevention of traffic safety incidents.

The authors propose the methodology of transportation on railway transport forecasting based on the construction of temporal trends.

The calculation of the forecast demand for electric energy by energy systems and complexes of the constituent entities of the Russian Federation is an urgent task. The use of deterministic methods for objects of a similar scale is practically excluded due to the absence or significant incompleteness of the source data. Statistical data available in official sources in an unchanged format is usually presented for a period of 3 - 5 years, which is insufficient for the use of artificial neural networks. The article attempts to study the properties of similar energy systems and complexes. Modern power systems and complexes belong to closed subsystems, the set of elements and connections of which is equivalent to the set of elements of local subsystems of a higher level energy system. This means the inadmissibility of drawing up predictive rules of functioning without taking into account heterogeneous external influences. The system and subsystems are presented as a "black box". Interactions between the system and the external environment and within the system are carried out by the transmission of signals, which are described by a finite set of factors available for analysis and forecasting. The analysis of the possibility of supplementing the general population with statistical data on other objects with a similar structure is carried out. The property of heteromorphism of energy systems and complexes is confirmed. The example of energy systems in the regions of the Russian Federation shows the possibility of a similar approach if non-collinear groups of factors are applied to the analysis. The results of 15 calculations of the most energy-intensive entities of the country are presented, in 28 % of cases the accuracy of forecasted power consumption accuracy is less than 5 %. A further increase in the accuracy of the forecast should develop in the direction of increasing the number of input factors, subject to the condition of the absence of their collinearity and multicollinearity. It is shown that energy systems and complexes of various scales can be described by non-Gaussian stable distributions with infinite dispersion of non-Gaussian distributions, which makes incorrect the use of such methods as the simple extrapolation method, as well as statistical methods based on the assumption that the random distribution law is normal.