This paper presents a new method for fault diagnosis in linear and non-linear analog circuits that is based on artificial neural networks. A fault dictionary in the frequency domain, previously constructed, represents the set of supervised data for learning. Feedforward networks acting as autoassociators with one hidden layer, trained by backpropagation, are used in order to identify the most likely faulty element causing the failure of the electronic circuit under test. Copyright © 1996 Elsevier Science Ltd.
Catelani, M., Gori, M. (1996). On the application of neural networks to fault diagnosis of electronic analog circuits. MEASUREMENT, 17(2), 73-80 [10.1016/0263-2241(96)00012-7].
On the application of neural networks to fault diagnosis of electronic analog circuits
Gori M.
1996-01-01
Abstract
This paper presents a new method for fault diagnosis in linear and non-linear analog circuits that is based on artificial neural networks. A fault dictionary in the frequency domain, previously constructed, represents the set of supervised data for learning. Feedforward networks acting as autoassociators with one hidden layer, trained by backpropagation, are used in order to identify the most likely faulty element causing the failure of the electronic circuit under test. Copyright © 1996 Elsevier Science Ltd.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/18604
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo