|
Publications
Santos, P., Datia, N., Pato, M., Sobral, J., Leitão, N., Ramos Ferreira, M. and Gomes, N. (2023), Reliability analysis of an Electronic Portal Imaging Device (EPID) of a linear accelerator, 27th International Conference Information Visualisation (IV2023), 24-28 June, Tempere, Finland, pp. 1-6
In the domain of asset management, a Work Order (WO) is a document (paper or digital) that describes all the steps to complete a maintenance operation on a given physical asset. WOs are created by the technician, describing the problem and actions to be taken, using free text. The problem with this approach is that it hinders asset management automation, since each technician has his own way of describing problems and/or approaches alike. To solve the problem of automated WO analysis, Natural Language Processing (NLP) techniques are used to process the WOs, with the intent of recognising sentence parts that are relevant to action(s) and component(s) identification. In this paper we describe the Reliability Centred Maintenance for Assets (RCM4Assets) solution that uses a semi-automatic, human-in-the-loop process for determining a normalised and reduced set of actions and components. With this solution it is possible to decrease the manual work of WO analysis, enhancing the decision support and analytical processing of WO data.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|