Search results

The article discusses the criteria used to calculate the probability of failures of devices of the current collection system due to ice and frost deposits on a catenary. The purpose of the work is to determine the influence of climatic and operational factors (including the number of vibrating pantographs, pneumatic drums on electric locomotives within the boundaries of the Directorate for power supply and devices for mechanical cleaning of ice at power supply distances) on the probability of the occurrence of failures of the current collection system and their severity, which will allow to increase the reliability of operation of traction power supply devices in conditions of ice formation and the efficiency of investments by Transenergo and the Traction Directorate for the purchase of these funds. To determine the likelihood of failures of current collection devices due to the formation of ice on the wires of the contact network, it is proposed to divide all factors into climatic and operational. The choice of factors in predicting failures was carried out using a probabilistic Bayesian network based on statistical methods of data processing, as well as correlation and regression analysis. As a result of the research, the factors influencing the likelihood of failures of current collection devices have been determined, and their significance has been assessed using the calculated variances. A method is given for calculating the probability of failure for a conditional distance of power supply, which makes it possible to assess the adequacy of the equipment of Transenergo and Traction Directorates with devices for mechanical cleaning of ice from a contact wire, vibropantographs and pneumatic drums.

The article examines the technique of designing diagnostic system of infrastructure of electrical railways based on use of bayesian networks for prediction of probabilities of failures. To achieve maximum effectiveness of diagnosis we should minimize the number of input parameters, while maintaining the required accuracy. It is proposed to create a mathematical model of the diagnostic system, that will allow to evaluate the influence of each parameter on the accuracy of prediction of failures. To compensate the lack of source data we can use the advantage of bayesian networks - the opportunity to generate network structure by the method of expert evaluations. Generated bayesian network will perform the failure probability calculation with limited information.