Hybrid Data-Driven and Physics-Based Modelling for Prescriptive Maintenance of Gas-Turbine Power Plant

Sergei Nikolaev, Sergei Belov, Mikhail Gusev, Ighor Uzhinsky

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

    3 Citations (Scopus)

    Abstract

    The methodology for prescriptive maintenance of complex technical systems is presented. The proposed methodology is based on a hybrid physics-based and data-driven modelling of complex systems. This approach integrates traditional physics-based simulation techniques such as finite-element modelling, finite-volume modelling, bond-graph modelling and data-driven models, with machine learning algorithms. Combined implementation of the both approaches results in the development of a set of reliable, fast and continuously updating models of technical systems applicable for predictive and prescriptive analytics. The methodology is demonstrated on the jet-engine power plant preventive maintenance case-study.

    Original languageEnglish
    Title of host publicationProduct Lifecycle Management in the Digital Twin Era - 16th IFIP WG 5.1 International Conference, PLM 2019, Revised Selected Papers
    EditorsClement Fortin, Louis Rivest, Alain Bernard, Abdelaziz Bouras
    PublisherSpringer
    Pages379-388
    Number of pages10
    ISBN (Print)9783030422493
    DOIs
    Publication statusPublished - 2019
    Event16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019 - Moscow, Russian Federation
    Duration: 8 Jul 201912 Jul 2019

    Publication series

    NameIFIP Advances in Information and Communication Technology
    Volume565 IFIP
    ISSN (Print)1868-4238
    ISSN (Electronic)1868-422X

    Conference

    Conference16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019
    Country/TerritoryRussian Federation
    CityMoscow
    Period8/07/1912/07/19

    Keywords

    • Hybrid modelling
    • Jet-engine simulation
    • Machine learning
    • Prescriptive analytics

    Fingerprint

    Dive into the research topics of 'Hybrid Data-Driven and Physics-Based Modelling for Prescriptive Maintenance of Gas-Turbine Power Plant'. Together they form a unique fingerprint.

    Cite this