This paper presents a stochastic model for scheduling predictive and risk-based maintenance activities in rail sector. The novelty of the approach consists of the risk concept introduction in railway maintenance scheduling, thus implying that the maintenance priorities are based on criticality of assets, determined by the relevant failure probability, related to asset degradation conditions, and by the consequent direct and indirect damages. This approach belongs to the framework of 'predictive maintenance' which aims at intervening when an asset has reached a certain degradation state, being the future track conditions forecasted by appropriate models. In particular, this work explicitly considers the stochastic nature of risk and of the real-world maintenance operations, introducing stochastic deadlines. In doing so, it is worth noting that, the adaptive rescheduling models only partially solve this issue, since they consider deterministic sub-problems of the overall problem and they cannot vary continuously the stochastic input variables. Therefore, to cope with this problem, in this paper, the risk-based maintenance planning problem is formulated in term of stochastic programming. After providing a formal methodology description, some experimental results are reported and some indications about its future developments are given.
Stochastic scheduling approach for predictive risk-based railway maintenance
CONSILVIO, ALICE;DI FEBBRARO, ANGELA;SACCO, NICOLA
2016-01-01
Abstract
This paper presents a stochastic model for scheduling predictive and risk-based maintenance activities in rail sector. The novelty of the approach consists of the risk concept introduction in railway maintenance scheduling, thus implying that the maintenance priorities are based on criticality of assets, determined by the relevant failure probability, related to asset degradation conditions, and by the consequent direct and indirect damages. This approach belongs to the framework of 'predictive maintenance' which aims at intervening when an asset has reached a certain degradation state, being the future track conditions forecasted by appropriate models. In particular, this work explicitly considers the stochastic nature of risk and of the real-world maintenance operations, introducing stochastic deadlines. In doing so, it is worth noting that, the adaptive rescheduling models only partially solve this issue, since they consider deterministic sub-problems of the overall problem and they cannot vary continuously the stochastic input variables. Therefore, to cope with this problem, in this paper, the risk-based maintenance planning problem is formulated in term of stochastic programming. After providing a formal methodology description, some experimental results are reported and some indications about its future developments are given.File | Dimensione | Formato | |
---|---|---|---|
ICIRT'16.pdf
accesso chiuso
Tipologia:
Documento in versione editoriale
Dimensione
871.49 kB
Formato
Adobe PDF
|
871.49 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.