Pantograph Sliding Strips Failure—Reliability Assessment and Damage Reduction Method Based on Decision Tree Model

Abstract

Damage to the pantograph or sliding strip may cause the blocking of the railway line. This is the main reason for which the prediction of pantographs’ failure is important for railway carriers and researchers. This article presents a sliding strips failure prediction method as a main means of preventing disruptions to the transport chain. To develop the best predictive model based on the decision tree, the complex tree, medium tree and simple tree machine learning methods were tested. Using a decision tree, the categorization of the given technical conditions can be properly realized. The obtained results showed that the presented model can reduce sliding strip failure by up to 50%. Special attention was paid to the current collector (AKP-4E, 5ZL type), measured during periodic reviews of locomotives EU07 and EU09. To assess the reliability of the selected pantograph strips, a non-destructive degradation analysis was carried out. On the basis of the wear measurements of the strips and the critical value of wear, a failure distribution model was developed. Operational data, collected during periodic technical reviews, were provided by one of the biggest railway carriers in Poland. The results of the performed analyses may be used to build a preventive maintenance strategy to protect pantographs. The applied reliability models of wear propagation can be extended by the parameters of the cost and repair time becoming the basis for estimating the costs of operation and maintenance.

A Method of Predicting Wear and Damage of Pantograph Sliding Strips Based on Artificial Neural Networks

“…Reliability assessment and knowledge of experts allowed us to prepare identification algorithms for technical conditions and for replacement causes. The exemplary algorithms are shown below [ 51 ]: where: Wop replacement of the pantograph Wn replacement of the pantograph sliding strip Nl the locomotive number Nop the pantograph number Top the type of pantograph Gn1 thickness of the first carbon sliding strip Gn2 thickness of the second carbon sliding strip N1 replacement of the sliding strip due to even wear of the sliders N2 replacement of the sliding strip due to detachment of a fragment of the sliding strip, material extraction or burning of the sliding strip N3 replacement of the sliding strip due to uneven wear of the sliders i the measure number …”

“…As part of this article, research was carried out only on regression models based on artificial neural networks. The classification method using decision trees was described in the article [ 51 ].…”

“…Reliability assessment and knowledge of experts allowed us to prepare identification algorithms for technical conditions and for replacement causes. The exemplary algorithms are shown below [51]:…”

Study of the Possibilities of Improving Maintenance of Technological Equipment Subject to Wear

“…The procedure frequently used in the assessment of the causes of faults (failures) that occur during the operation of machines and machineries is the Fault Tree Analysis (FTA) [11,12].…”

“…The Reliability Centered Maintenance method [8,9] does not consider only the parameters characterizing each component of the equipment (failure rate, reliability, mean time between failures, availability, etc. ), but it studies the mode of failing as well, and its effects [10][11][12][13][14][15] (fault tree analysis, analysis of the behavior in case of failure, cause-effect diagram, Pareto diagram, etc. ).…”