2011 | OriginalPaper | Chapter
Application of Fault Diagnosis to Industrial Systems
Author : Gerasimos G. Rigatos
Published in: Modelling and Control for Intelligent Industrial Systems
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Applications of statistical methods for fault diagnosis are presented. First, the problem of early diagnosis of cascading events in the electric power grid is considered. Residuals are generated with the use of a nonlinear model of the distributed electric power system and the fault threshold is determined with the use of the generalized likelihood ratio assuming that the residuals follow a Gaussian distribution. Next, the problem of fault detection and isolation in electric motors is analyzed. It is proposed to use nonlinear filters for the generation of residuals and to derive a fault threshold from the generalized likelihood ratio without prior knowledge of the residuals statistical distribution.