Diagnosis of oil starving of motor-axle bearings of the wheel-motor unit of electric locomotives series 3es5k «ermak»

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.