Condition monitoring based on incremental learning and domain ontology for condition-based maintenance

Christos Emmanouilidis, Luca Fumagalli, Erkki Jantunen, Petros Pistofidis, Marco Macchi, Marco Garetti

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    Abstract

    The paper defines the main elements of a generic condition monitoring system, as an abstraction of data and services. The key target is how to facilitate asset self-awareness, to support production-level sustainable machinery operation. The proposed approach involves knowledge-rich computational elements, capable of performing incremental model building in order to capture the specific characteristics of the monitored asset behaviour. Coupled with adequate data and knowledge modelling, by means of dedicated ontology, this abstraction mechanism is envisioned to facilitate the rapid development of condition monitoring systems for diverse application needs.
    Original languageEnglish
    Title of host publicationProceedings of APMS 2010 International Conference on Advances in Production Management Systems
    Subtitle of host publicationCernobbio, Como, Italy, 11-13.10.2010
    Publication statusPublished - 2010
    MoE publication typeA4 Article in a conference publication

      Fingerprint

    Keywords

    • condition-based maintenance
    • condition monitoring
    • incremental learning
    • novelty detection
    • diagnosis and prognosis
    • ontology

    Cite this

    Emmanouilidis, C., Fumagalli, L., Jantunen, E., Pistofidis, P., Macchi, M., & Garetti, M. (2010). Condition monitoring based on incremental learning and domain ontology for condition-based maintenance. In Proceedings of APMS 2010 International Conference on Advances in Production Management Systems: Cernobbio, Como, Italy, 11-13.10.2010