Search results

The development of the system is accompanied by the diagnostics of their achievement in the technical system. Using the possibility of identifying defects in nodal technical systems in the early stages of their occurrence in order to timely and promptly anticipate, the emergence of work productivity, identify simple repair time, identify material costs for replacement or deep restoration. Railway transport is also at the stage of a wide identification of various components and parts of the rolling stock. the appointment of diagnostic systems is a locomotive fleet, as a more identified technical unit. Today, the locomotive fleet uses hardware and software diagnostic complexes, microprocessor-based diagnostic systems, on-board and track monitoring systems that cover the entire range of diagnostic data of the main technical units. However, the use of the availability of systems requires constant improvement of the mathematical model of diagnosis. One of the options for choosing diagnostic models is the use of artificial intelligence research methods - sections of artificial neural networks, which, in comparison with the classical polynomial regression properties, are manifested by the properties of extrapolation accuracy and are applicable for predicting the values of diagnostic parameters according to the data that were due to the sampling of an artificial neural network. These characteristics make it possible to predict the development of defects and possible failures safely and accurately to obtain them and obtain an economic result. The paper presents an example of the development of a diagnostic artificial neural network model for diagnosing oil starvation of motor-axial bearings of the wheel-motor block of a cargo mainline electric locomotive of the 3ES5K «Ermak» series. This factor has a low level of reliability, so the use of continuous diagnostics is required, which requires the use of a point in time.

Wearing parts of the cylinder-piston group and crank mechanism is one of the main reasons for putting a diesel engine into repair. Timely detection of the occurrence of intense wear allows you to prevent negative consequences, make timely repairs, eliminate the likelihood of unplanned exit of the locomotive from service. As a result of the study of the intensity of accumulation of wear products in engine oil, a mathematical model has been developed, which is implemented with the use of an artificial neural network apparatus. Its use allows to carry out an operational assessment of the technical condition of diesel engine parts in an in dividing way and to improve the technological process of repairing diesel engines of the D49 type

The results of the study the possibility of using artificial neural networks in identification problems failure status diesel D49, the results of spectral analysis of the crankcase oil. The obtained results are needed to develop software for evaluation of the degree of wear and tear as a result of the diesel locomotive spectral analysis of engine oil.

In article process of expeditious calculation of capacity and intertrain intervals is considered within the concept of coordinate management of train service. The technique directed to the solution of problems of search of reliable intertrain intervals in real time, calculation of the postemergency set operation and estimation of reliability of traction power supply system, based on use of the device of artificial neural networks and modern means of interval regulation of the movement of railway transport is offered.

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 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.