Fault prognosis based on fault reconstruction: Application to a mechatronic system

Author

Djeziri, M.A. ; Toubakh, Houari ; Ouladsine, Mustapha

Author_Institution

LSIS, Marseille, France

fYear

2013

fDate

29-31 Oct. 2013

Firstpage

383

Lastpage

388

Abstract

The fault prognosis method developed in this work has a horizontal structure, and aims the estimate the RUL by the reconstruction of the fault trend after detecting the degradation beginning. The diagnosis part is realized using a Principal Component Analysis (PCA), the fault reconstruction is done using the fault direction matrix, and the RUL is estimated using an Auto-Regressive Recurrent Radial Based Function (ARRRBF) neural network. The developed method is implemented on a mechatronic system dedicated to the prognosis, which offers the possibility of introducing gradual and controlled degradations.

Keywords

fault diagnosis; maintenance engineering; matrix algebra; mechanical engineering computing; mechatronics; principal component analysis; radial basis function networks; recurrent neural nets; ARRRBF neural network; PCA; RUL; auto-regressive recurrent radial based function neural network; fault direction matrix; fault prognosis; fault reconstruction; mechatronic system; principal component analysis; Degradation; Estimation; Market research; Neural networks; Principal component analysis; Prognostics and health management; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems and Control (ICSC), 2013 3rd International Conference on

Conference_Location

Algiers

Print_ISBN

978-1-4799-0273-6

Type

conf

DOI

10.1109/ICoSC.2013.6750887

Filename

6750887