Measurement Data-Driven Life-Cycle Management of Railway Track

Neuhold, Johannes; Landgraf, Matthias; Marschnig, Stefan; Veit, Peter

doi:10.1177/0361198120946007

Cited by 16 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Railway maintenance has always been a challenge for infrastructure managers and determining an appropriate maintenance planning scenario in which maintenance costs are minimal, while reliability and availability are maximal, is a fundamental issue ( 15 , 39 ). Accordingly, an attempt is made to develop a maintenance model with the aim of comparing different maintenance scenarios and examining their impact on important operational parameters.…”

Section: Problem Descriptionmentioning

confidence: 99%

Maintenance Decision Support Model for Railway Track Geometry Maintenance Planning Using Cost, Reliability, and Availability Factors: A Case Study

Kasraei

Zakeri²

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Determining the strategy and planning for maintenance operations on railway tracks is important given the increasing demand from both freight and passengers. An important prerequisite of maintenance planning is the ability to predict the overall and geometric conditions of the railway in the near future. It is, therefore, necessary to develop a degradation model and consider the effect of various maintenance operations using a recovery model. According to EN 13848-5, the alert limit (AL) can be used as an indicator to plan maintenance operations. The current paper benefits from this index as well as the effect of its changes on important parameters such as maintenance costs, availability, and reliability to present a maintenance decision support model. This model allows infrastructure managers to plan maintenance interventions under the conditions of their intended usage strategy. The results of this paper indicate that choosing suitable AL could affect total maintenance cost and availability by up to 57% and 33% respectively.

show abstract

Section: Problem Descriptionmentioning

confidence: 99%

Maintenance Decision Support Model for Railway Track Geometry Maintenance Planning Using Cost, Reliability, and Availability Factors: A Case Study

Kasraei

Zakeri²

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Railway systems are subject to harsh environments and high repetitive loads, which lead to accelerated deterioration, resulting in a degraded level of service and increased risks and costs [1]. Maintenance actions, which may reflect various intervention intensities (e.g., minor/major repair or complete overhaul), must be planned throughout the operating life-cycle of the tracks, and in compliance with the current railway conditions, in order to prevent deterioration effects and associated costs [2,3]. The resulting optimal maintenance planning in railway systems forms a complex sequential decision-making problem.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Value-Based and Policy-Based Reinforcement Learning for Monitoringinformed Railway Maintenance Planning

ARCIERI,

HOELZL,

SCHWERY

et al. 2023

Proceedings of the 14th International Workshop on Structural Health Monitoring

View full text Add to dashboard Cite

Optimal maintenance planning for railway infrastructure and assets forms a complex sequential decision-making problem. Railways are naturally subject to deterioration, which can result in compromised service and increased safety risks and costs. Maintenance actions ought to be proactively planned to prevent the adverse effects of deterioration and the associated costs. Such predictive actions can be planned based on monitoring data, which are often indirect and noisy, thus offering an uncertain assessment of the railway condition. From a mathematical perspective, this forms a stochastic control problem under data uncertainty, which can be cast as a Partially Observable Markov Decision Process (POMDP). In this work, we model the real-world problem of railway optimal maintenance planning as a POMDP, with the problem parameters inferred from real-world monitoring data. The POMDP model serves to infer beliefs over a set of hidden states, which aim to capture the evolution of the underlying deterioration process. The maintenance optimization problem is here ultimately solved via the use of deep Reinforcement Learning (RL) techniques, which allow for a more flexible and broad search over the policy space when compared to classical POMDP solution algorithms. A comparison of value-based and policy-based RL methods is also offered, which exploit deep learning architectures to model either action-value functions (i.e., the expected returns from an action-state pair) or directly the policy. Our work shows how this complex planning problem can be effectively solved via deep RL to derive an optimized maintenance policy of railway tracks, demonstrated on real-world monitoring data, and offers insights into the solution provided by different classes of RL algorithms.

show abstract

“…The technological development of humanity is faced with the need to provide an innovative and effective tool for productively solving the issues of ensuring the reliability, availability [1], maintainability [2][3][4][5], and safety of railway systems [6,7].…”

Section: Introductionmentioning

confidence: 99%

Using Detailing Concept to Assess Railway Functional Safety

Bondarenko¹,

Campisi

Tesoriere

et al. 2022

Sustainability

View full text Add to dashboard Cite

The ability to assess the risks of the functional safety of railway tracks allows harmonizing characteristics of track elements under certain operating conditions under certain maintenance for the efficient use of the track structure throughout its life cycle. The concept of detailing conditions of the interaction of the rolling stock and railway track was used for the productive solution of tasks of infrastructure functional safety assessment. The paper formed an approach to the analytical solution of determination problems of deformability parameters over time using the elastic waves theory. The formation method of interconnections between the technical and economic aspects of the operation of railway infrastructure was proposed. The criteria of deformability work and intensity of use were utilized for the effective use of the track structure through its life cycle. The results of calculations are presented to assess changes in the deformability behaviour of the track elements and structure when the force and speed parameters of the operating conditions change, as well as the algorithm of the method for estimating the operation deformability of the railway track. Thus, the proposed approach can be adapted to optimize objects by railway functional safety assessment at the stage of object operation simulation.

show abstract

Measurement Data-Driven Life-Cycle Management of Railway Track

Cited by 16 publications

References 9 publications

Maintenance Decision Support Model for Railway Track Geometry Maintenance Planning Using Cost, Reliability, and Availability Factors: A Case Study

Maintenance Decision Support Model for Railway Track Geometry Maintenance Planning Using Cost, Reliability, and Availability Factors: A Case Study

A Comparison of Value-Based and Policy-Based Reinforcement Learning for Monitoringinformed Railway Maintenance Planning

Using Detailing Concept to Assess Railway Functional Safety

Contact Info

Product

Resources

About