Simultaneous fault diagnosis in chemical plants using a multilabel approach

Authors

  • Ignacio Yélamos,

    1. Chemical Engineering Dept.–CEPIMA, ETSEIB, Universitat Politècnica de Catalunya (UPC), Av. Diagonal 647, Barcelona 08028, Spain
    Search for more papers by this author
  • Moisès Graells,

    1. Chemical Engineering Dept.–CEPIMA, ETSEIB, Universitat Politècnica de Catalunya (UPC), Av. Diagonal 647, Barcelona 08028, Spain
    Search for more papers by this author
  • Luis Puigjaner,

    Corresponding author
    1. Chemical Engineering Dept.–CEPIMA, ETSEIB, Universitat Politècnica de Catalunya (UPC), Av. Diagonal 647, Barcelona 08028, Spain
    • Chemical Engineering Dept.–CEPIMA, ETSEIB, Universitat Politècnica de Catalunya (UPC), Av. Diagonal 647, Barcelona 08028, Spain
    Search for more papers by this author
  • Gerard Escudero

    1. Software Dept., EUETIB, Universitat Politècnica de Catalunya (UPC), Comte d'Urgell 187, Barcelona 08036, Spain
    Search for more papers by this author

Abstract

One of the main limitations of current plant supervisory control systems is the reliability and the correct management of simultaneous faults, which is crucial for supporting the plant operators' decision making. In this work, a MultiLabel approach that makes use of support vector machines as the learning algorithm is employed to arrange a novel fault diagnosis system (FDS). The FDS is trained to address a difficult control case study from industry widely studied in the literature, the Tennessee Eastman process. Successful results have been obtained when diagnosing up to four simultaneous faults. These results are very promising since they have been obtained by just using simple training sets consisting of single faults, thus proving a very high learning capacity. © 2007 American Institute of Chemical Engineers AIChE J, 2007

Ancillary