Number of hours
- Lectures 4.0
- Projects 14.0
- Tutorials 0
- Internship 0
- Laboratory works 2.0
- Written tests 0
ECTS
ECTS 2.0
Goal(s)
- define the problem of system monitoring and diagnosis
- complete the tools and methods necessary for this type of application
- acquire autonomy through practical experiences
Content(s)
- introduction to system monitoring and diagnosis (lecture)
- sequential change detection in signals (lecture/labworks)
- problem statement
- CuSum type algorithms
- GLR type algorithms
- projects of system monitoring and diagnosis (project)
Prerequisites
- basics of data science (correlation, spectral analysis, filtering, ...)
- basics of estimation theory (maximum likelihood estimator)
- basics of detection theory (binary hypothesis testing)
Session normale / First session
Evaluation rattrapable (ER) / ER assessment : 1 project / 1 project
Si situation 100% distancielle / If distant learning mandatory:
Evaluation rattrapable (ER) / ER assessment : 1 projet / 1 project
Moyenne de l'UE / Course Unit assessment = ER 100%
--------------------------------------------------------------------------------
Session 1 :
si cours en présence : rapport de projet (100%)
si cours à distance : rapport de projet (100%)
Session 2 :
si présentiel possible : rapport de projet (100%)
si distanciel imposé : rapport de projet (100%)
Detection of Abrupt Changes - Theory and Application. Michèle Basseville, Igor Nikiforov. Prentice Hall - http://people.irisa.fr/Michele.Basseville/kniga/, 1993.
Statistical inference for engineers and data scientists. Pierre Moulin, Venugopal V. Veeravalli. Cambridge University Press, 2019.
The CuSum algorithm - A small review. Pierre Granjon. Technical report - https://hal.archives-ouvertes.fr/hal-00914697, 2013