Paper Title:
Multivariate Statistical Analysis for Detection and Identification of Faulty Sensors Using Latent Variable Methods
  Abstract

In this paper, three latent variable methods are implemented in a multivariate statistical analysis scheme for detecting and identifying faults in a multi-sensor network. The proposed methods are applied to a sensor network monitoring a MDOF dynamical system and the results are presented, compared and discussed.

  Info
Periodical
Edited by
Pietro VINCENZINI and Fabio CASCIATI
Pages
501-507
DOI
10.4028/www.scientific.net/AST.56.501
Citation
M. R. Hernandez-Garcia, S. F. Masri, "Multivariate Statistical Analysis for Detection and Identification of Faulty Sensors Using Latent Variable Methods", Advances in Science and Technology, Vol. 56, pp. 501-507, 2008
Online since
September 2008
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Zhi Xiong Li, Xin Ping Yan, Cheng Qing Yuan, Li Li
Abstract:Gearboxes are extensively used in various areas including aircraft, mining, manufacturing, and agriculture, etc. The breakdowns of the...
1033
Authors: Yi Liu, Hong Ying Deng, Zeng Liang Gao, Ping Li
Abstract:A novel two-level integrated soft sensor modeling method using kernel independent component analysis (KICA) and support vector regression...
560
Authors: Zhong Hai Li, Hao Fei Mao, Jian Guo Cui, Yan Zhang
Abstract:The paper presents a motor bearing fault diagnosis method based on MSICA (Multi-scale Independent Principal Component Analysis) and LSSVM...
747
Authors: Ying Hua Yang, Yong Lu Chen, Xiao Bo Chen, Shu Kai Qin
Control, Constitutive Modeling and Simulation
Abstract:In this paper, an approach for multivariate statistical process monitoring ans fault diagnosis based on an improved independent component...
110
Authors: Zhi Yang Jia, Pu Wang, Xue Jin Gao
Chapter 6: Navigation Systems, Monitoring and Detection Technology
Abstract:In the process monitoring and fault diagnosis of batch processes, traditional principal component analysis (PCA) and least-squares (PLS), are...
1783