Centralized Maintenance Time Prediction Algorithm for Freight Train Wheels Based on Remaining Useful Life Prediction

Abstract

Many freight trains for special lines have in common the characteristics of a fixed group. Centralized Condition-Based Maintenance (CCBM) of key components, on the same freight train, can reduce maintenance costs and enhance transportation efficiency. To this end, an optimization algorithm based on the nonlinear Wiener process is proposed, for the prediction of the train wheels Remaining Useful Life (RUL) and the centralized maintenance timing. First, Hodrick–Prescott (HP) filtering algorithm is employed to process the raw monitoring data of wheel tread wear, extracting its trend components. Then, a nonlinear Wiener process model is constructed. Model parameters are calculated with a maximum likelihood estimation and the general deterioration parameters of wheel tread wear are obtained. Then, the updating algorithm for the drift coefficient is deduced using Bayesian formula. The online updating of the model is realized, based on individual wheel monitoring data, while a probability density function of individual wheel RUL is obtained. A prediction method of RUL for centralized maintenance is proposed, based on two set thresholds: “maintenance limit” and “the ratio of limit-arriving.” Meanwhile, a CCBM timing prediction algorithm is proposed, based on the expectation distribution of individual wheel RUL. Finally, the model is validated using a 500-day online monitoring data on a fixed group, consisting of 54 freight train cars. The validation result shows that the model can predict the wheels RUL of the train for CCBM. The proposed method can be used to predict the maintenance timing when there is a large number of components under the same working conditions and following the same path of degradation.

Systematic literature review of repair shops: focus on sustainability

“…From the circular economy point of view, the methods for both performance evaluation and optimization are the same except in papers (Riisgaard et al 2016;Turkeli et al 2019), who are the only ones to survey the implementation of circular strategies in several repair shop companies. The authors (Kleber et al 2011) and (Shi et al 2020) use non-linear programming, the first to optimize spare parts inventories and the second to reduce equipment downtime by predicting the remaining useful life of the equipment. Models using a non-linear algorithm are generally simplified, and the simulation results obtained have non-negligible errors that could be reduced with other methods.…”

“…Indeed, with a circular economy, the spare parts stock is not only made up of new components but also of repaired components. Remaining Useful Life Prediction is a way of studying the deterioration of components or equipment throughout their life cycle (Shi et al 2020).…”

“…17.9 (Chua et al 1993;Smith and Dekker 1997;Sleptchenko et al 2005; (Scudder 1984(Scudder , 1985Chua et al 1993 ;Smith and Dekker 1997 ;Guide et al 2000 ;Sleptchenko et al 2002Sleptchenko et al , 2005Sleptchenko et al , 2019 A generalized stochastic petri-net model for performance analysis and allocation optimization (Shi et al 2020) Unspecified (China)…”