DocumentCode :
657945
Title :
Active fault diagnosis for immersed structure
Author :
Sidibe, Y. ; Druaux, Fabrice ; Lefebvre, Dimitri ; Leon, Florin ; Maze, G.
Author_Institution :
Groupe de Rech. en Electrotech. et Autom. du, Normandie Univ., Le Havre, France
fYear :
2013
fDate :
6-8 May 2013
Abstract :
The immersed system environment makes delicate their diagnosis. Such systems encountered in energy production sites (stream turbines), water treatment or oil platform are not easily accessible for diagnosis issues. Most of dedicated diagnosis techniques are expensive, need a precise positioning of sensors and present large delay. The need to develop alternative techniques is therefore justified. The proposed contribution is a part of this approach. It is based on active fault diagnosis and detection. The measurements are performed by ultrasonic echography. The proposed method combines signal-processing tools to characterize the measurements and artificial neural networks (ANNs) for classification and decision.
Keywords :
fault diagnosis; neural nets; signal processing; structural engineering computing; ultrasonic materials testing; ANN; active fault and detection; active fault diagnosis; artificial neural networks; diagnosis techniques; energy production sites; immersed structure; immersed system environment; oil platform; precise sensor positioning; signal-processing tools; stream turbines; ultrasonic echography; water treatment; Acoustics; Artificial neural networks; Equations; Fault detection; Fault diagnosis; Feature extraction; Unsupervised learning; Fault detection; artificial neural networks; classification; decision; fault isolation; immersed systems; signal processing; ultrasonic echography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control, Decision and Information Technologies (CoDIT), 2013 International Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-5547-6
Type :
conf
DOI :
10.1109/CoDIT.2013.6689522
Filename :
6689522
Link To Document :
بازگشت