Browsing by Author "Bevilacqua, Maurizio"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    An autonomous system for maintenance scheduling data-rich complex infrastructure: Fusing the railways' condition, planning and cost
    (Elsevier, 2018-02-22) Durazo-Cardenas, Isidro; Starr, Andrew; Turner, Christopher J.; Tiwari, Ashutosh; Kirkwood, Leigh; Bevilacqua, Maurizio; Tsourdos, Antonios; Shehab, Essam; Baguley, Paul; Xu, Yuchun
    National railways are typically large and complex systems. Their network infrastructure usually includes extended track sections, bridges, stations and other supporting assets. In recent years, railways have also become a data-rich environment. Railway infrastructure assets have a very long life, but inherently degrade. Interventions are necessary but they can cause lateness, damage and hazards. Every day, thousands of discrete maintenance jobs are scheduled according to time and urgency. Service disruption has a direct economic impact. Planning for maintenance can be complex, expensive and uncertain. Autonomous scheduling of maintenance jobs is essential. The design strategy of a novel integrated system for automatic job scheduling is presented; from concept formulation to the examination of the data to information transitional level interface, and at the decision making level. The underlying architecture configures high-level fusion of technical and business drivers; scheduling optimized intervention plans that factor-in cost impact and added value. A proof of concept demonstrator was developed to validate the system principle and to test algorithm functionality. It employs a dashboard for visualization of the system response and to present key information. Real track incident and inspection datasets were analyzed to raise degradation alarms that initiate the automatic scheduling of maintenance tasks. Optimum scheduling was realized through data analytics and job sequencing heuristic and genetic algorithms, taking into account specific cost & value inputs from comprehensive task cost modelling. Formal face validation was conducted with railway infrastructure specialists and stakeholders. The demonstrator structure was found fit for purpose with logical component relationships, offering further scope for research and commercial exploitation.
  • Thumbnail Image
    ItemOpen Access
    Context-based and human-centred information fusion in diagnostics
    (Elsevier, 2016-12-16) Emmanouilidis, Christos; Pistofidis, Petros; Fournaris, Apostolos; Bevilacqua, Maurizio; Durazo-Cardenas, Isidro; Botsaris, Pantelis N.; Katsouros, Vassilis; Koulamas, Christos; Starr, Andrew G.
    Maintenance management and engineering practice has progressed to adopt approaches which aim to reach maintenance decisions not by means of pre-specified plans and recommendations but increasingly on the basis of best contextually relevant available information and knowledge, all considered against stated objectives. Different methods for automating event detection, diagnostics and prognostics have been proposed, which may achieve very high performance when appropriately adapted and tuned to serve the needs of well defined tasks. However, the scope of such solutions is often narrow and without a mechanism to include human contributed intervention and knowledge contribution. This paper presents a conceptual framework of integrating automated detection and diagnostics and human contributed knowledge in a single architecture. This is instantiated by an e-maintenance platform comprising tools for both lower level information fusion as well as for handling higher level knowledge. Well structured maintenance relationships, such as those present in a typical FMECA study, as well as on the job human contributed compact knowledge are exploited to this end. A case study presenting the actual workflow of the process in an industrial setting is employed to pilot test the approach.
  • Thumbnail Image
    ItemOpen Access
    Data fusion strategy for precise vehicle location for intelligent self-aware maintenance systems
    (Institute of Electrical and Electronics Engineers, 2015) Bevilacqua, Maurizio; Tsourdos, Antonios; Starr, Andrew G.; Durazo-Cardenas, Isidro
    Abstract— Nowadays careful measurement applications are handed over to Wired and Wireless Sensor Network. Taking the scenario of train location as an example, this would lead to an increase in uncertainty about position related to sensors with long acquisition times like Balises, RFID and Transponders along the track. We take into account the data without any synchronization protocols, for increase the accuracy and reduce the uncertainty after the data fusion algorithms. The case studies, we have analysed, derived from the needs of the project partners: train localization, head of an auger in the drilling sector localization and the location of containers of radioactive material waste in a reprocessing nuclear plant. They have the necessity to plan the maintenance operations of their infrastructure basing through architecture that taking input from the sensors, which are localization and diagnosis, maps and cost, to optimize the cost effectiveness and reduce the time of operation.
  • Thumbnail Image
    ItemOpen Access
    Precise vehicle location as a fundamental parameter for intelligent selfaware rail-track maintenance systems
    (Elsevier, 2014-10-31) Durazo-Cardenas, Isidro; Starr, Andrew G.; Tsourdos, Antonios; Bevilacqua, Maurizio; Morineau, Julien
    The rail industry in the UK is undergoing substantial changes in response to a modernisation vision for 2040. Development and implementation of these will lead to a highly automated and safe railway. Real-time regulation of traffic will optimise the performance of the network, with trains running in succession within an adjacent movable safety zone. Critically, maintenance will use intelligent trainborne and track-based systems. These will provide accurate and timely information for condition based intervention at precise track locations, reducing possession downtime and minimising the presence of workers in operating railways. Clearly, precise knowledge of trains’ real-time location is of paramount importance. The positional accuracy demand of the future railway is less than 2m. A critical consideration of this requirement is the capability to resolve train occupancy in adjacent tracks, with the highest degree of confidence. A finer resolution is required for locating faults such as damage or missing parts, precisely. Location of trains currently relies on track signalling technology. However, these systems mostly provide an indication of the presence of trains within discrete track sections. The standard Global Navigation Satellite Systems (GNSS), cannot precisely and reliably resolve location as required either. Within the context of the needs of the future railway, state of the art location technologies and systems were reviewed and critiqued. It was found that no current technology is able to resolve location as required. Uncertainty is a significant factor. A new integrated approach employing complimentary technologies and more efficient data fusion process, can potentially offer a more accurate and robust solution. Data fusion architectures enabling intelligent self-aware rail-track maintenance systems are proposed.