Evaluating the Wheelset Health Status of Rail Transit Vehicles: Synthesis of Wear Mechanism and Data-Driven Analysis

Abstract

The security and reliability of rail transit vehicles in service are greatly affected by their wheel–rail contact. Thus, modeling the wear of wheelsets and monitoring their status is important for improving safety and reducing costs. A key issue involves evaluating the wheelset status accurately and using this as the basis for developing effective maintenance strategies and measures. However, the open nature of actual wheel–rail systems and their inconsistent environmental conditions make it difficult to construct a precise theoretical model that covers both wheelset wear and status evaluation. In this paper, a synthesis approach for evaluating the wheelset health status of rail transit vehicles is proposed. The wheelset health status is defined, and then a data-driven wheelset health evaluation model is developed. Potential causes of deviations between the model and reality are analyzed based on a theoretical wear mechanism, and application prerequisites for the proposed model are given. A case study involving the Shanghai Metro shows that the proposed approach operates well and can, therefore, be applied in practice.