Opportunistic inspection planning for Railway eMaintenance

Abstract: Railway infrastructure is a complex system that comprises of several subsystems which interacts in hierarchical, multi-distributive and multi-user environment. It is a difficult task to perform inspections for all the assets at an instant because the train management system decides when to conduct different types of inspection techniques on several assets in a particular track section. There are two main wastes of resources for inspection planning occurred in maintenance; under usage due to inaccurate prediction of failure and over usage because the necessary information already has been acquired from other sources. These irregularities lead to wastage of resources, for instance, human, machine and time that has tremendous implications on cost, availability and manpower. This paper proposes a methodology by using intelligent functional test outcome to assess the performability of an asset and integrating the data to the eMaintenance cloud platform of Swedish railway infrastructure. By implementing this methodology, we can achieve better planning of resources for optimal performance of assets. A case study is performed on Switches and Crossings of Swedish railway infrastructure for the applicability of the proposed methodology.

[1]  W. J. Moore,et al.  An intelligent maintenance system for continuous cost-based prioritisation of maintenance activities , 2006, Comput. Ind..

[2]  Ravdeep Kour,et al.  eMaintenance solution through online data analysis for railway maintenance decision-making , 2014 .

[3]  Ming Yang,et al.  Prioritization of environmental issues in offshore oil and gas operations: A hybrid approach using fuzzy inference system and fuzzy analytic hierarchy process , 2011 .

[4]  Benoît Iung,et al.  On the concept of e-maintenance: Review and current research , 2008, Reliab. Eng. Syst. Saf..

[5]  Enrico Zio,et al.  Multiobjective optimization of the inspection intervals of a nuclear safety system: A clustering-based framework for reducing the Pareto Front ☆ , 2010 .

[6]  Yili Hong,et al.  Reliability Meets Big Data: Opportunities and Challenges , 2014 .

[7]  A.M.N.D.B. Seneviratne and R.M. Chandima Ratnayake Classification of Static Mechanical Equipment using a Fuzzy Inference System: A Case Study from an Offshore Installation , 2015 .

[8]  Daniel Straub,et al.  Computational Aspects of Risk-Based Inspection Planning , 2006, Comput. Aided Civ. Infrastructure Eng..

[9]  J. McCall Operating Characteristics of Opportunistic Replacement and Inspection Policies , 1963 .

[10]  Ahmed Z. Al-Garni,et al.  Neural network-based failure rate prediction for De Havilland Dash-8 tires , 2006, Eng. Appl. Artif. Intell..

[11]  Uday Kumar,et al.  Railway Assets: A Potential Domain for Big Data Analytics , 2015, INNS Conference on Big Data.

[12]  Bikash Bhadury,et al.  Opportunistic maintenance of multi‐equipment system: a case study , 2000 .

[13]  Dragan Banjevic,et al.  Optimal inspection of a complex system subject to periodic and opportunistic inspections and preventive replacements , 2012, Eur. J. Oper. Res..

[14]  Marcantonio Catelani,et al.  Context awareness for maintenance decision making: A diagnosis and prognosis approach , 2015 .