Risk-based optimal scheduling of maintenance activities in a railway network

Consilvio, Alice; Febbraro, Angela Di; Meo, Rossella; Sacco, Nicola

doi:10.1007/s13676-018-0117-z

Cited by 27 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the track circuits' case study, a One-Class Support Vector Machine [72,73] was applied to build the data-driven model, the Bayesian Network approach [74] was used for the modeling and simulation, and a mixed integer linear programming mathematical model [75] was developed for the optimization.…”

Section: Building the Dssmentioning

confidence: 99%

“…In this way, the criticality of the track circuit in terms of impact on the overall system is determined. Finally, the optimization was performed considering a risk-based scheduling model that allowed planning of the maintenance activities via a Mixed Integer Linear Programming (MILP) problem [75]. In the MILP problem the failure probability and the criticality of each track circuit, evaluated through the Bayesian Network, were then used to prioritize the interventions.…”

mentioning

confidence: 99%

See 1 more Smart Citation

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

et al. 2020

Self Cite

View full text Add to dashboard Cite

The objective of this study is to show the applicability of machine learning and simulative approaches to the development of decision support systems for railway asset management. These techniques are applied within the generic framework developed and tested within the In2Smart project. The framework is composed by different building blocks, in order to show the complete process from data collection and knowledge extraction to the real-world decisions. The application of the framework to two different real-world case studies is described: the first case study deals with strategic earthworks asset management, while the second case study considers the tactical and operational planning of track circuits’ maintenance. Although different methodologies are applied and different planning levels are considered, both the case studies follow the same general framework, demonstrating the generality of the approach. The potentiality of combining machine learning techniques with simulative approaches to replicate real processes is shown, evaluating the key performance indicators employed within the considered asset management process. Finally, the results of the validation are reported as well as the developed human–machine interfaces for output visualization.

show abstract

Section: Building the Dssmentioning

confidence: 99%

mentioning

confidence: 99%

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, data availability makes possible to introduce automated decision support systems based on predictive algorithms that use data from the field in order to predict rail faults, helping the IM in planning maintenance interventions in advance. 15–18 This leads to predictive maintenance strategies, avoiding failures and service disruptions and makes possible to shift from traditional maintenance procedures, often based on experts knowledge and common practices, to automated maintenance strategies based on decision support systems.…”

Section: Beyond the State Of Artmentioning

confidence: 99%

Real-time monitoring of the longitudinal strain of Continuous Welded Rail for safety improvement

Consilvio

Iovane³

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part F:

Self Cite

View full text Add to dashboard Cite

Continuous welded rail maintenance plays a significant role in ensuring high levels of rail traffic and safety. Temperature variations, excessive alignment defects, decreased fastening system resistance and train braking (always in the same stretches and in the same direction) may result in rail buckling or rail breaks. The current traditional monitoring systems and procedures for continuous welded rail consist of programmed discontinuous diagnostic surveys that require personnel intervention on site. Moreover, these traditional systems often imply destructive and invasive operations on the track that may lead to interruption of railway operations. This paper proposes a Rail Strain Monitoring System (RSMS) that performs a real-time rail strain monitoring and allows rail inspection without personnel on site. Using strain gauges and temperature sensors, placed on the rail in specific measurement points, the proposed Rail Strain Monitoring System performs a multi-parameter check by measuring, at the same time, the temperature, the rail strain and the neutral temperature of the rail. The paper describes the mode of operation of the Rail Strain Monitoring System, the calibration procedure and the results from the field, and highlights the advantages of this system in comparison to other traditional monitoring systems. The safety improvement that can be achieved with the application of the Rail Strain Monitoring System is analysed. In particular, the reliability of the system is evaluated and compared to the human error probability in the traditional manual inspections. Finally, the reduction of derailment risk and related economic damages is estimated.

show abstract

“…Other aspects were also considered in the maintenance-only case, such as e.g. repair team management (Peng et al, 2011;Ouyang, 2012, 2014), risk and other stochastic aspects, combined with operational aspects (Baldi et al, 2016;Consilvio et al, 2018;Xie et al, 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

Multi-objective model for optimizing railway infrastructure asset renewal

Sousa

Alçada-Almeida

Coutinho-Rodrigues

2018

Engineering Optimization

View full text Add to dashboard Cite

Multiobjective model for optimizing railway infrastructure asset renewal A multiobjective model for managing railway infrastructure asset renewal is presented. The model aims at optimizing three objectives, while respecting operational constraints: leveling investment throughout multiple years, minimizing total cost, minimizing work start postponements. Its output is an optimized intervention schedule. The model is based on a case-study from a Portuguese infrastructure management company, who specified the objectives and constraints, and reflects management practice on railway infrastructure. Results show that investment leveling greatly influences the other objectives and that total cost fluctuations may range from insignificant to important, depending on infrastructure condition. The results structure is argued to be general and suggests a practical methodology for analyzing trade-offs and selecting a solution for implementation.

show abstract

Risk-based optimal scheduling of maintenance activities in a railway network

Cited by 27 publications

References 28 publications

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

Real-time monitoring of the longitudinal strain of Continuous Welded Rail for safety improvement

Multi-objective model for optimizing railway infrastructure asset renewal

Contact Info

Product

Resources

About