UE Supervision and diagnosis

Diplômes intégrant cet élément pédagogique :

Descriptif

Safety, supervision and diagnosis of industrial plants 

The objective of this class is to introduce the concept of fault detection and fault diagnosis for complex systems and to present different classes of methods which have proven their performances in practical applications. 

Lesson Topic 
Introduction to supervision 
 Tasks of supervision, terminology.
Model-based fault detection 
 Parity equations, observers, on line estimation of model parameters.
Signal-based fault detection 
 Features extraction using time, frequency and time-frequency transformation, pattern comparison. Temporal change detection.
Data-driven fault detection methods 
 Fault diagnosis with pattern recognition, fault diagnosis with principal component analysis.
 SUPERVISION LABS  
Lab 1 Fault detection in a two-tanks system using a bank of observers 
Lab 2 On-line detection of deep sleep using EEG spectral power 
Lab 3 Diagnosis of a mineral treatment unit using pattern recognition 
Lab 4 Sensor fault detection in an air quality monitoring network using principal component analysis 

Bibliographie

  • S. Gentil (Ed.), "Supervision des procédés complexes", HERMES Systèmes automatisés, 2007.
  • Isermann, "Fault diagnosis systems", Springer, 2006.
  • Blanke, Kinnaert, Lunze, Staroswiecki, "Diagnosis and fault tolerant control", Springer, 2003.

Informations complémentaires

Langue(s) : Anglais