Fault detection and identification of gas turbines is a crucial process for providing engine safe operation and decreasing the maintenance costs. In studies conducted in the field of global optimization-based gas turbine fault diagnosis, the genetic algorithm as the most well-known evolutionary optimization algorithm is usually employed to identify the engine health parameters. However, because of the evolutionary and stochastic nature of this algorithm, the genetic-algorithm-based diagnosis usually suffers from computational burden and reliability. To mitigate this problem, in the present work, a comparative study has been performed on the global optimization-based gas turbine fault diagnosis, and it is shown that an innovative hybrid optimization algorithm as a fault detection and identification system can significantly enhance the performance of the conventional optimization-based diagnosis systems, even in the presence of measurement noise. The results obtained indicate that the fault detection and identification system based on the hybrid invasive weed optimization/particle swarm optimization algorithm outperforms all the examined diagnosis systems (i.e., the genetic-algorithm-based, particle-swarm-optimization-based, and invasive weed-optimization-based fault detection and identification system) in terms of accuracy, reliability, and especially computational cost. The results demonstrate that the genetic-algorithm-based fault detection and identification system showed the weakest performance among all the examined diagnosis systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Performance Enhancement of Global Optimization-Based Gas Turbine Fault Diagnosis Systems


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    2015-11-04


    Format / Umfang :

    11 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch