This paper aims at proposing an effective approach, based on neural networks, to the fault diagnosis of Class-E DC AC resonant inverters. A MultiLayer artificial Neural Network based on MultiValued Neuron (MLMVN) with a complex QR-decomposition is used to identify parameter value changing (i.e. fault detection) on a Class-E resonant inverter through steady state measurements of voltages and currents.
Multilayer Neural Network with Multivalued Neurons MLMVN based CLASS-E Resonant Inverter Faults Detection / A. Reatti; S. Manetti; A. Luchetta; M. C. Piccirilli; M. K. Kazimierczuk. - ELETTRONICO. - (2016), pp. 251-256. (Intervento presentato al convegno IET 8th IET International Conference on Power Electronics Machines and Drives tenutosi a Glasgow nel 19-21 Aprile 2016).
Multilayer Neural Network with Multivalued Neurons MLMVN based CLASS-E Resonant Inverter Faults Detection
REATTI, ALBERTO;MANETTI, STEFANO;LUCHETTA, ANTONIO;PICCIRILLI, MARIA CRISTINA;
2016
Abstract
This paper aims at proposing an effective approach, based on neural networks, to the fault diagnosis of Class-E DC AC resonant inverters. A MultiLayer artificial Neural Network based on MultiValued Neuron (MLMVN) with a complex QR-decomposition is used to identify parameter value changing (i.e. fault detection) on a Class-E resonant inverter through steady state measurements of voltages and currents.
| File | Dimensione | Formato | |
|---|---|---|---|
|
A14.1.pdf
accesso aperto
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Creative commons
Dimensione
1.29 MB
Formato
Adobe PDF
|
1.29 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
