On-board vibration-based remaining useful life estimation of hollow worn railway vehicle wheels

Abstract

The feasibility of on-board remaining useful life (RUL) estimation of hollow worn railway vehicle wheels under varying travelling speed using vibration signals from the vehicle’s bogie, is for the first time explored. A variant of the Multiple Model Power Spectral Density (MM-PSD) method is employed, treating RUL estimation as a multi-class classification problem, where each class corresponds to a specific condition of hollow worn wheels associated with an empirical remaining mileage. The method classifies the current, unknown, condition of hollow worn wheels to one of the available by examining the vehicular dynamics similarity among them through the amplitude of the sharp periodic valleys (antiresonances) induced due to the Wheelbase Filtering (WF) effect. The vibration signals are obtained from Monte Carlo experiments based on the high-fidelity SIMPACK software, while the remarkable performance of the method is demonstrated via thousands of inspection cases.

Remaining Useful Life Estimation of Hollow Worn Railway Vehicle Wheels via On-Board Random Vibration-Based Wheel Tread Depth Estimation

“…The comparison of the postulated method with a multi-health state classification-based RULE method, which is based on multiple, conventional, AutoRegressive models (MM–AR), is presented in this section. A non–parametric variant of this method with very promising results has been recently presented by the authors and collaborators of [ 16 ].…”

“…An alternative method [ 16 ] that has been recently introduced by the authors and collaborators tackles the RULE problem of hollow worn railway vehicle wheels as a multi-health state classification problem [ 17 , 18 , 19 , 20 ] demonstrating a promising performance. The method presents high sensitivity to the subtle effects of the hollow worn wheels on the vehicular dynamics, yielding from the fact that the Power Spectral Density obtained from acceleration signals on the vehicle bogie is employed as the main feature for the classification procedure, providing comprehensive information on the vehicular dynamics compared with static quantities such as the vibration signals RMS, the variance, and so on.…”

“…A single vibration signal is obtained from an accelerometer on the vehicle’s bogie in each simulation, while a wide range of railway wheel tread depths of hollow worn wheels is covered within the range mm using actual measurements obtained from the Attiko Metro S.A. maintenance operator (Athens, Greece). In addition, the introduced method is compared with the multi-health state classification RULE method of [ 16 ], which is based on multiple models for the representation of various hollow wear levels corresponding to distinct tread depth ranges. The selection of this recently introduced method is based on its promising results, which are presented in [ 14 ], while it is also the only available vibration-based method that employs measurements of wheel tread depth for the estimation of their remaining mileage that will allow a fair comparison with the method presented in this study.…”