Search results

The paper describes the physical nature of the occurrence of disturbing forces in traction gears during intermating teeth and determination of the amplitude-frequency content of the spectrum. In addition, the experimentally determined defects arising elements locomotive traction gearing.

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.

Nowadays fuzzy neural networks are widely used for modeling of complex industrial processes. The paper considers the application of fuzzy logic to generate a mathematical model of electricity consumption in rail transport for example, traction substation Dorogino. Algorithm for choice of the structure of fuzzy neural network including the species and number of membership functions for input and the number of training cycles is presented. Comparative analysis of the structures by evaluating the mean square error is made.

The article deals with the analysis of methods for obtaining statistically reliable data on contact pressure, which are based on the results of inspection trips and data on the design values of the location of the contact wires in the vertical plane andin the path plan. A method for calculating contact pressing with artificial neural networks is proposed. The methods of obtaining statistically reliable data on the contact pressing of current collectors of electric rolling stock without the need for direct measurement, based on the video image of the current collection process and analysis of external factors (weather, operational) accompanying the interaction are considered.

The paper presents a comparative analysis of different methods of quantization of continuous signals, including optimal with the maximum entropy and the entropy – suboptimal, with various parameters of signal distribution.

A method for predicting the performance of the current collection with increasing speeds using machine learning is proposed. Methods for obtaining statistically reliable data on the contact pressure of current-carrying electric rolling stock without the need for direct measurement based on design data and analysis of external factors (weather, operational) accompanying the interaction are considered.

The paper proposes a method of measuring the transverse displacements of the rails. Made a priori error estimate. A version of the sensor and the concept of construction equipment.

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.

The article is devoted to the issue of power loss measurement in DC traction networks. The purpose of the work is to define the indicators characterizing the degree of determining the energy loss values accuracy when using the method of restoration of the train situation. In the article the analysis of methodical error the value arising at measurement of power losses in a traction DC network is conducted. The occurrence of the error is caused by the indirect measurement method, which is based on the principle of synthesis of instantaneous circuits in real time. The synthesis is based on direct measurements of currents and voltages on the busbars of adjacent feeding and switching points, for example, a traction substation and a sectionalizing station. The data obtained are processed in accordance with the algorithms adopted in the article, as a result of which the coordinates of loads and their current consumption are calculated. In the process of synthesizing instantaneous circuits, it is possible that such a train situation may occur, which will lead to the emergence of a methodical measurement error, due to the peculiarities of the logical and mathematical apparatus of the train situation recovery method. In this paper, has been performed a probabilistic analysis of the possibility of occurrence of methodological error when several traction loads will be present simultaneously on the measuring section, that is, the dependence of the occurrence of the measure of uncertainty on the daily size of train traffic and the dependence of the occurrence of the measure of uncertainty on the minimum inter-train interval. As a result of the study, the proposed method application the limits were established by energy loss measurement the permissible error the criterion. The methodological error the value of the measurement at different variants method of movement on the railroad studied section was assessed

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.

The authors consider the question of the limits of applicability of the capacitor method for measuring the real part of the dielectric constant of printed circuit boards and telecommunications cabled rail transport using the example of FR-4 fiberglass laminate and the cable PK-75-4-12 in the frequency range from 10 Hz to 100 MHz. The measurements were carried out at a constant temperature and humidity of a known material. Comparison of the obtained values with the passport data on the material is carried out; a measurement procedure is developed with overlapping frequency ranges by changing the values of the measuring resistors from larger to smaller with increasing frequency of the input signal. It is shown that in the high-frequency region, the measurement accuracy is directly affected by the parasitic inductance of the capacitor sample under study, as well as the active resistance of the leads and plates and its increase due to the skin effect. The article also discusses the ways of accounting and calculating the parasitic elements of a capacitor. One of these ways is to study the characteristics of the elements of the sample at the first proper serial resonance of the capacitor under study.