Regresar

Power plant fault monitoring using Recursive Principal Component Analysis RPCA

Abstract:

Recursive Principal Components Analysis is explored as a method to identify and classify fault sources in a 12MW steam dual fuel power plant. The algorithm assessment is performed off-line by using data of relevant plant wide-information. A simple contributions matrix based in normalized data is proposed to diagnose plant faults. Results indicate it is possible to detect, classify and possibly even pbkp_redict sources of plant failure.

Año de publicación:

2016

Keywords:

    Fuente:

    scopusscopus

    Tipo de documento:

    Conference Object

    Estado:

    Acceso restringido

    Áreas de conocimiento:

    • Simulación por computadora
    • Aprendizaje automático

    Áreas temáticas:

    • Física aplicada
    • Métodos informáticos especiales

    Contribuidores:

    Mauricio RedrobánMauricio Redrobán
    Omar AguirreOmar Aguirre
    Alberto Sanchez TeranAlberto Sanchez Teran