Railway maintenance especially on infrastructure produces a vast amount of data. However, having data is not synonymous with having information; rather, data must be processed to extract information. In railway maintenance, the development of key performance indicators (KPIs) linked to punctuality or capacity can help planned and scheduled maintenance, thus aligning the maintenance department with corporate objectives. There is a need for an improved method to analyse railway data to find the relevant KPIs. The system should support maintainers, answering such questions as what maintenance should be done, where and when. The system should equip the user with the knowledge of the infrastructure's condition and configuration, and the traffic situation so maintenance resources can be targeted to only those areas needing work. The amount of information is vast, so it must be hierarchized and aggregated; users must filter out the useless indicators. Data are fused by compiling several individual indicators into a single index; the resulting composite indicators measure multidimensional concepts which cannot be captured by a single index. The paper describes a method of monitoring a complex entity. In this scenario, a plurality of use indices and weighting values are used to create a composite and aggregated use index from a combination of lower level use indices and weighting values. The resulting composite and aggregated indicators can be a decision-making tool for asset managers at different hierarchical levels.

As rolling element bearings are key parts of rotating machinery, the estimation of their reliability is very important. In this context, different standards and research articles propose how to estimate fatigue life for different levels of reliability. However, when trying to do calculations based on data from a real system, there are many difficulties because of economic and safety reasons. Consequently, the use of physical models to simulate the cases that are difficult to reproduce in a real system allows us to generate synthetic data related to them. Thus, in this paper a synthetic failure rate of rolling element bearings is calculated using a physical modelling approach. A multi-body model of a bearing is used in order to obtain its dynamic response in non-stationary conditions and in different degradation levels. Thus, synthetic data are generated to cover a range of degradation related to geometric changes in the surface of the parts of the bearing. Some of the output variables of these synthetic data, such as vibration, are used as covariates of a proportional hazard model, which is then trained to estimate the reliability of the bearing. In this way, a synthetic failure rate is obtained in such a way that it can improve the failure rate given by the manufacturers.

The estimation of the life of rolling element bearings (REBs) is crucial to determine when maintenance is required. This paper presents a methodology to calculate the fatigue life of REBs considering non-stationary conditions. Instead of taking a constant value, the paper considers cyclic loading and unloading processes, as well as increasing and decreasing values of the speed of rotation. It employs a model-based approach to calculate contact loads between the different elements of the bearing, with a finite element model (FEM) used to calculate the contact stresses. Using this information, it then performs a fatigue analysis to study overloading in faulty bearings.

All assets necessarily suffer wear and tear during operation. Prognostics can assess the current health of a system and predict its remaining life based on features capturing the gradual degradation of its operational capabilities. Prognostics are critical to improve safety, plan successful work, schedule maintenance, and reduce maintenance costs and down time. Prognosis is a relatively new area but has become an important part of Condition-based Maintenance (CBM) of systems. Broadly stated, prognostic methods are either data-driven, rule based, or model-based. Each approach has advantages and disadvantages; consequently, they are often combined in hybrid applications. A hybrid model can combine some or all model types; thus, more complete information can be gathered, leading to more accurate recognition of the fault state. In this context, it is important to evaluate the consistency and reliability of the measurement data obtained during laboratory testing and the prognostic/diagnostic monitoring of the system under examination.This approach is especially relevant in systems where the maintainer and operator know some of the failure mechanisms with a sufficient amount of data, but the sheer complexity of the assets precludes the development of a complete model-based approach. This paper addresses the process of data aggregation into a contextual awareness hybrid model to get Residual Useful Life (RUL) values within logical confidence intervals so that the life cycle of assets can be managed and optimised.

Safety in transport is a key. Railway and aerospace sectors have a need for ways to predict the behaviour of trains and aircraft, respectively. With this information, maintenance tasks for the correct operation of the assets can be carried out, reducing the number of failures that can cause an accident. However, the lack of enough data of the faulty state of those systems makes this to be difficult. Because of that either hidden faults or unknown faults can occur. As regulations in transport are very restrictive, components are usually substituted in early states of their degradation, which implies a loss of useful life of those components.In this article a methodology to overcome this limitation is presented. This methodology consists in the fusion of data obtained from two sources: data acquired from the real system, and synthetic data generated using physical models of the system. These physical models should be constructed in such a way that they can reproduce the main failure modes that can occur in the modelled system. This data fusion, that creates a hybrid model, not only allows to classify the condition of the system according to the aforementioned failure modes, but also to define new data that do not belong to any of those failure modes as a new failure mode, improving diagnosis and prognosis processes.

La seguridad en el campo del transporte es un punto crítico. Así, el sector ferroviario y el de la aeronáutica precisan de formas para predecir el comportamiento de trenes y aeronaves, respectivamente. Con esta información se pueden llevar a cabo las gestiones de mantenimiento necesarias para el correcto funcionamiento de los activos y reducir el número de fallos que puedan causar un accidente.Sin embargo, la falta de datos suficientes sobre estados con fallo de dichos sistemas hace que esta tarea sea complicada.Esta carencia de información hace que se puedan producir fallos ocultos o fallos desconocidos. Al tratarse la normativa del sector del transporte muy restrictivaen este aspecto, se tiende a reemplazar los componentes en estados tempranos de su degradación, lo que supone un desaprovechamiento de la vida de dichos componentes.En el presente artículo se propone una metodología para abordar esa limitación. Dicha metodología consiste en la fusión de datos de dos fuentes: por un lado, los datos adquiridos del sistema real; y, por otro lado, datos sintéticos generados a través de modelos físicos. Dichos modelos físicos han de estar construidos de forma que sean capaces de reproducir los principales modos de fallo que pueden ocurrir en dichos sistemas.Esta fusión de datos, que formaun modelo híbrido, permite no sólo clasificar el estado del sistema según los modos de fallo previamente estipulados, sino también definirnuevos modos de fallo que no concuerden con ninguno de los modos de fallo anteriores, mejorando los procesos de diagnosis y prognosis.

Purpose:The purpose of this paper is to provide a literature review of the performance measurement in maintenance. The authors aim to discuss the background and development of the performance measurement for maintenance, besides defining the concept of performance measures for maintenance and the frameworks developed.Design/methodology/approach:A detailed and extensive literature search and study was undertaken by the authors on the concept and definition of performance measurement, performance indicators, maintenance performance indicators and various performance frameworks. The history and theory of performance measurement over different phases of business and technological developments have been critically examined and analysed in this review paper. Findings:This paper reviews and presents the different performance indicators (PIs) and performance measurement (PM) frameworks like; balanced scorecard, performance prism, performance pyramid and performance matrix etc, and identifies their characteristics and shortcomings. After considering related issues and challenges, frameworks and approaches for the maintenance performance measurement (MPM) are also presented, where the emerging techniques like; e-maintenance have also been discussed amongst others. More and more industries are applying the balanced and integrated MPM frameworks for their competitive survivability and sustainability.Practical implications:The concept, issues and approaches considered for the MPM frameworks can be adapted by the practicing managers, while trying to define and develop an MPM framework for the operation and maintenance activities. The considerations of the advantages and limitations of different frameworks can provide insights to the managers for implementation. Originality/value:Some literature reviews on MPM and MPM frameworks are available today. This paper makes an attempt to provide a detailed and relevant literature review, besides adding value in this new and emerging area.

Diagnosis and prognosis processes are necessary to optimise the dependability of systems and ensure their safe operation. If there is a lack of information, faulty conditions cannot be identified and undesired events cannot be predicted. It is essential to predict such events and mitigate risks, but this is difficult in complex systems.Abnormal or unknown faults cause problems for maintenance decision makers. We therefore propose a methodology that fuses data-driven and model-based approaches. Real data acquired from a real system and synthetic data generated from a physical model can be used together to perform diagnosis and prognosis.As systems have time-varying conditions related to both the operating condi- tions and the healthy or faulty state of systems, the idea behind the proposed methodology is to generate synthetic data in the whole range of conditions in which a system can work. Thus, data related to the context in which the system is operating can be generated.We also take a first step towards implementing this methodology in the field of rolling element bearings. Synthetic data are generated using a physical model that reproduces the dynamics of these machine elements. Condition indicators such as root mean square, kurtosis and shape factor, among others, are calculated from the vibrational response of a bearing and merged with the real features obtained from the data collected from the functioning systemFinally, the merged indicators are used to train SVM classifiers (support vector machines), so that a classification according to the condition of the bearing is made independently of the applied loading conditions even though some of the scenarios have not yet occurred.

Bearings are one of the most important components in a railway vehicle for safety, since a failsafe design is not available. Contact fatigue, internal clearance, corrosion, and contamination of the lubricating oil can cause bearing failures. Generally, failures show up as imperfections in the ball race, in the ball/roller or in the retainer. The more frequent defects are caused by contact fatigue [1]. The analytical methodology (Methodology I) is an alternative approach proposed by the authors [1], inspired by a procedure used to design rail shafts [2]. The purpose is to compare the obtained life using methodology I, with the life estimated by LKAB company. The latter uses a calculation method well-established in manuals of bearing manufacturers such as SKF and Timken. This is to avoid a drawback observed in this type of approach, namely, the lack of rigour in defining terms associated with the mathematical model used to estimate L10. The research goal is to perform an inspection and analysis of the functioning of the bearings most commonly used on railways in order to estimate the bearings' life under real operating conditions.

The assessment and analysis of railway infrastructure capacity is an essential task in railway infrastructure management carried out to meet the required quality and capacity demand of railway transport. For sustainable and dependable infrastructure management, it is important to assess railway capacity limitation from the point of view of infrastructure performance. However, the existence of numerous performance indicators often leads to diffused information that is not in a format suitable to support decision making. In this paper, we demonstrated the use of fuzzy inference system for aggregating selected railway infrastructure performance indicators to relate maintenance function to capacity situation.

The selected indicators consider the safety, comfort, punctuality and reliability aspects of railway infrastructure performance. The resulting composite indicator gives a reliable quantification of the health condition or integrity of railway lines. A case study of the assessment of overall infrastructure performance which is an indication of capacity limitation is presented using indicator data between 2010 and 2012 for five lines on the network of Trafikverket (Swedish Transport Administration).

The results are presented using customised performance dashboard for enhanced visualisation, quick understanding and relevant comparison of infrastructure conditions for strategic management. This gives additional information on capacity status and limitation from maintenance management perspective.

Many railway assets, such as wheels, suffer from increasing deterioration during operation. Good condition monitoring based on good decision-making techniques can lead to accurate assessment of the current health of the wheels. This, in turn, will improve safety, facilitate maintenance planning and scheduling, and reduce maintenance costs and down-time. In this paper, wheel/rail forces are selected as a parameter (feature) for the condition monitoring of wheel health. Once wheels are properly thresholded, determining their condition can help operators to define maintenance limits for their rolling stock. In addition, if rail forces are used as condition indicators of wheel wear, it is possible to use measurement stations that cost less than ordinary profile stations. These stations are located on ordinary tracks and can provide the condition of wheelsets without causing shutdowns or slowdowns of the railway system and without interfering with railway traffic. The paper uses the iron-ore transport line in northern Sweden as a test scenario to validate the use of wheel/rail forces as indicators of wagon and wheel health. The iron-ore transport line has several monitoring systems, but in this paper only two of these systems will be used. Wheel/rail force measurements are performed on curves to see how the vehicle negotiates the curve, and wheel profile measurements are done on tangent track not far away. The vehicles investigated are iron-ore wagons with an axle load of 30 tonnes and a loaded top speed of 60 km/h. The measurements are non-intrusive, since trains are moving and assets are not damaged during the testing process