Title :
Dynamic GMDH neural networks and their application in fault detection systems
Author :
Korbicz, J. ; Kus, J.
Author_Institution :
Dept. of Robot. & Software Eng., Tech. Univ. of Zielona Gora, Gora, Poland
fDate :
Aug. 31 1999-Sept. 3 1999
Abstract :
In this paper, the problem of the dynamic GMDH (Group Method and Data Handling) neural networks and their application in fault detection systems is presented. Such networks can be considered as feedforward networks with a growing structure during the training process. The GMDH networks application in fault detection systems improves their efficiency with lack of information regarding the structure and dynamics of the diagnosed system. The proposed networks have been implemented in fault detection systems using the real data from the Lublin sugar factory.
Keywords :
data handling; fault diagnosis; feedforward neural nets; learning (artificial intelligence); production engineering computing; sugar industry; Lublin sugar factory; dynamic GMDH neural networks; fault detection systems; feedforward networks; group method and data handling; training process; Biological neural networks; Fault detection; Heuristic algorithms; Network synthesis; Neurons; Polynomials; Sugar; dynamic GMDH algorithm; fault diagnosis; neural networks;
Conference_Titel :
Control Conference (ECC), 1999 European
Conference_Location :
Karlsruhe
Print_ISBN :
978-3-9524173-5-5
