Title :
Diagnosing from descriptive knowledge bases
Author :
Filev, Dimitax P.
Author_Institution :
Ford Motor Co., Detroit, MI, USA
Abstract :
Deals with a diagnostic method using so-called descriptive knowledge bases. It is based on the concept of using a MIMO (multiple-input, multiple output) fuzzy model to represent the information contained in the knowledge base. The model structure and initial parameter values are estimated by applying FMEA (failure mode and effect analysis). Finer parameter estimates are obtained by using a backpropagation learning algorithm. Rules for learning the parameters of a MIMO fuzzy model are derived. An actual diagnostic problem is solved by using an an optimization algorithm for inverting the MIMO fuzzy model
Keywords :
MIMO systems; backpropagation; diagnostic expert systems; diagnostic reasoning; failure analysis; fault diagnosis; fuzzy logic; knowledge representation; optimisation; parameter estimation; MIMO fuzzy model; backpropagation learning algorithm; descriptive knowledge bases; diagnostic method; failure mode and effect analysis; information representation; initial parameter value estimation; model inversion; model structure estimation; optimization algorithm; Backpropagation algorithms; Diagnostic expert systems; Failure analysis; Kernel; Knowledge engineering; MIMO; Manufacturing industries; Parameter estimation; Personnel; Virtual manufacturing;
Conference_Titel :
Fuzzy Information Processing Society, 1997. NAFIPS '97., 1997 Annual Meeting of the North American
Conference_Location :
Syracuse, NY
Print_ISBN :
0-7803-4078-7
DOI :
10.1109/NAFIPS.1997.624081
