Skip to Main content Skip to Navigation

Diagnostic des systèmes hybrides: développement d'une méthode associant la détection par classification et la simulation dynamique

Abstract : Hybrid systems involve both continuous and discrete variables. The continuous dynamics is generally given by differential-algebraic equations while the discrete dynamics is modelled by automata or input-output transition systems. For any industrial system, the early detection and diagnosis of faults is important, since a lot of damage and loss can result before a fault present in the system is detected. In addition, it becomes harder to distinguish the root cause of the fault as it propagates through the system. This is therefore more crucial in hybrid processes mixing both continuous and discrete aspects. This work presents the development of a methodology associating the fault detection performed by a datadriven technique with the dynamic hybrid simulation for the diagnosis step. The detection is generally performed by comparing process measurement and simulation result of the system in normal conditions. This phase identifies symptoms. The problem of diagnosis is then to link them to a precise dysfunction. A possibility is therefore to explore all possible scenarios of faults and compare with actual measurements. Nevertheless the number of possibilities increases in an exponential way. The aim of the developed methodology is to restrict the detected fault to a category of failures. Only these failures are then explored. The data-driven technique used in the proposed methodology is a fuzzy-classification method (LAMDA) enables to partition the data space in clusters related to identify symptoms. This method has the capacity to treat simultaneously quantitative and qualitative information and to propose automatic learning. It has been already used for detection of dysfunctions in complex chemical plants. The second step of the procedure involves the dynamic hybrid simulation performed only for the restricted faults. In the framework of this study, the simulation aspects are ensured by the general object-oriented environment PrODHyS(Process Object Dynamic Hybrid Si mulator), designed and developed within the LGC. Its major characteristic is its ability to simulate systems described with Object Differential Petri Nets (ODPN) formalism. Each fault of this set is simulated. Then, the simulated scenarios are compared to the observed behaviour through a criterion composed of residues (the squared difference between the variables measured and the variable simulated with the fault). Finally, the diagnosis of the fault is performed by choosing the fault with the smallest residue.
Document type :
Complete list of metadata

Cited literature [89 references]  Display  Hide  Download
Contributor : Arlette Evrard <>
Submitted on : Thursday, December 20, 2007 - 10:57:50 AM
Last modification on : Friday, October 23, 2020 - 4:52:02 PM
Long-term archiving on: : Monday, April 12, 2010 - 8:37:06 AM


  • HAL Id : tel-00200034, version 1


Aimed Mokhtari. Diagnostic des systèmes hybrides: développement d'une méthode associant la détection par classification et la simulation dynamique. Automatique / Robotique. INSA de Toulouse, 2007. Français. ⟨tel-00200034⟩



Record views


Files downloads