43documents trouvés
Sensor placement and fault detection using an efficient fuzzy feature selection approach
L.HEDJAZI, T.KEMPOWSKY, L. DESPENES, M.V.LE LANN, S.ELGUE, J.AGUILAR MARTIN
DISCO, LGC
Manifestation avec acte : IEEE Conference on Decision and Control (CDC 2010), Atlanta ( USA), 15-17 Décembre 2010, pp.6827-6832 , N° 10234
Diffusable
123374Fuzzy mechanisms for unified reasoning about heterogeneous data
L.HEDJAZI, J.AGUILAR MARTIN, M.V.LE LANN, T.KEMPOWSKY
DISCO
Manifestation avec acte : International Workshop on Qualitative Reasonning, Portland (USA), 8-10 Août 2010, 6p. , N° 10394
Diffusable
123242Vers un principe généralisé pour le traitement de données hétérogènes: application à la classification et la sélection d'attributs
L.HEDJAZI, M.V.LE LANN, T.KEMPOWSKY, J.AGUILAR MARTIN
DISCO
Rapport LAAS N°10361, Juin 2010, 20p.
Diffusable
121738Membership-margin based feature selection for mixed-type and high-dimensional data
L.HEDJAZI, J.AGUILAR MARTIN, M.V.LE LANN, T.KEMPOWSKY
DISCO
Rapport LAAS N°10151, Mars 2010, 33p.
Diffusable
120809Prognosis of breast cancer based on a fuzzy classification method
L.HEDJAZI, T.KEMPOWSKY, M.V.LE LANN, J.AGUILAR MARTIN
DISCO
Manifestation avec acte : 3rd International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2010) 1st International Conference on Bioinformatics (BIOINFORMATICS 2010), Valence (Espagne), 20-23 Janvier 2010, pp.123-130 , N° 09597
Diffusable
120358Classification floue de données intervallaires : application au pronostic du cancer
L.HEDJAZI, T.KEMPOWSKY, M.V.LE LANN, J.AGUILAR MARTIN
DISCO
Manifestation avec acte : XVIèmes Rencontres Francophones de la Société Francophone de Classification, SFC 2009, Grenoble (France), 2-4 Septembre 2009, pp.165-168 , N° 09213
Diffusable
Plus d'informations
Mots-Clés / Keywords
Analyse des données multi-variables; Classification floue; Similarité; Pronostic du cancer;
Contribution of fuzzy classification for the diagnosis of complex systems
C.ISAZA NARVAEZ, A.ORANTES, T.KEMPOWSKY, M.V.LE LANN
UTM, Mexico, DISCO, UDEA
Manifestation avec acte : SAFE PROCESS, Barcelone (Espagne), 30 Juin - 3 Juillet 2009, 6p. , N° 08692
Diffusable
Plus d'informations
Abstract
The diagnosis of processes can be defined as the identification of their functional states. When a mathematical model is difficult or not possible to obtain (which is generally the case for complex chemical processes), knowledge on the process behaviour can be extracted from historical measurements or complex simulators. This knowledge is then organized as a partition of the data set into classes representing the functional states of the process (normal or faulty operations). Among the data mining techniques, those including fuzzy logic present the advantages to express the data membership degree to several classes. This article presents a methodology that automatically finds an optimal space partition in terms of clusters compactness and separation using only the membership matrix obtained from a fuzzy classification. Test and validation results of this methodology applied to a continuous intensified chemical micro-reactor will be presented.
Mots-Clés / Keywords
Diagnosis; Fuzzy classification; Chemical micro-reactor;
Pronostic du cancer du sein à partir d'une méthode de classification floue
L.HEDJAZI, T.KEMPOWSKY, M.V.LE LANN
DISCO
Rapport LAAS N°09214, Mai 2009, 12p.
Diffusable
Plus d'informations
Mots-Clés / Keywords
Classification floue; Pronostic; Cancer du sein;
Conduite et diagnostic en temps réel sur microréacteur intensifié
T.KEMPOWSKY, M.V.LE LANN
DISCO
Rapport de Contrat : INPAC. projet Minefi/Simap. Convention n° 072906304, Mars 2009 , N° 08800
Non diffusable
117028Selection of sensors by a new methodology coupling a classification technique and entropy criteria
A.ORANTES, T.KEMPOWSKY, M.V.LE LANN, L.PRAT, S.ELGUE, C.GOURDON, M.CABASSUD
DISCO, UTM, Mexico, INPT, LGC, ENSIGC-LGC
Revue Scientifique : Chemical Engineering Research and Design: Transactions of the Institution of Chemical Engineers Part A , Vol.85, N°A6, pp.825-838, Novembre 2007 , N° 07321
Diffusable
Plus d'informations
Abstract
Complex industrial processes invest a lot of money in sensors and automation devices to monitor and supervise the process in order to guarantee the production quality and the plant and operators safety. Fault detection is one of the multiple tasks of process monitoring and it critically depends on the sensors that measure the significant process variables. Nevertheless, most of the work on fault detection and diagnosis found in literature place more emphasis on developing procedures to perform diagnosis given a set of sensors, and less on determining the actual location of sensors for efficient identification of faults. A methodology based on learning and classification techniques and on the information quantity measured by the Entropy concept, is proposed in order to address the problem of sensor location for fault identification. The proposed methodology has been applied to a continuous intensified reactor, the 'open plate reactor (OPR)', developed by Alfa Laval and studied at the Laboratory of Chemical Engineering of Toulouse. The different steps of the methodology are explained through its application to the carrying out of an exothermic reaction.
Mots-Clés / Keywords
Fault detection; Sensor location; Learning; Classification; Information theory;