Show simple item record

AuthorNavi, M.
AuthorDavoodi, M.
AuthorMeskin, Nader
Available date2022-04-14T08:45:42Z
Publication Date2015
Publication Name2015 IEEE Conference on Prognostics and Health Management: Enhancing Safety, Efficiency, Availability, and Effectiveness of Systems Through PHAf Technology and Application, PHM 2015
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/ICPHM.2015.7245022
URIhttp://hdl.handle.net/10576/29799
AbstractIn this paper, partial kernel principal component analysis (PKPCA) is studied for sensor fault detection and isolation (FDI) of an autonomous underwater vehicle (AUV). Principal component analysis (PCA) is an effective health monitoring tool which can achieve acceptable results only for linear processes. In the case of nonlinear systems such as autonomous underwater vehicles, kernel PCA approach can be used which leads to more accurate health monitoring and fault diagnosis. In order to achieve fault isolation, partial KPCA is proposed where a set of residual signals is generated based on the parity relation concept. The simulation studies demonstrate that using the proposed methodology, the occurrence of sensor faults in the nonlinear six degrees of freedom (DOF) model of an AUV can be effectively detected and isolated. 2015 IEEE.
SponsorQatar National Research Fund
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectData handling
Degrees of freedom (mechanics)
Electric fault currents
Fault detection
Health
Principal component analysis
Systems engineering
Vehicles
Autonomous underwater vehicles (AUV)
Fault detection and isolation
Health monitoring
Kernel principal component analyses (KPCA)
Sensor fault detection
Sensor fault detection and isolations (FDI)
Simulation studies
Six degrees of freedom
Autonomous underwater vehicles
TitleSensor fault detection and isolation of an autonomous underwater vehicle using partial kernel PCA
TypeConference Paper
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record