The prediction capabilities of artificial neural networks in similitude field are investigated. They have been applied to plates in similitude with two objectives: prediction of natural frequencies and model identification. The results show that the method is able to give accurate predictions and that an experimental training set can be created if the models are well characterized.
INVESTIGATION ON THE ARTIFICIAL NEURAL NETWORKS PREDICTION CAPABILITIES APPLIED TO VIBRATING PLATES IN SIMILITUDE / Casaburo, A.; Petrone, G.; Meruane, V.; Franco, F.; De Rosa, S.. - (2020). (Intervento presentato al convegno 3rd Euro-Mediterranean Conference on Structural Dynamics and Vibroacoustics tenutosi a Napoli nel 17-19 February 2020).
INVESTIGATION ON THE ARTIFICIAL NEURAL NETWORKS PREDICTION CAPABILITIES APPLIED TO VIBRATING PLATES IN SIMILITUDE
A. Casaburo;G. Petrone;F. Franco;S. De Rosa
2020
Abstract
The prediction capabilities of artificial neural networks in similitude field are investigated. They have been applied to plates in similitude with two objectives: prediction of natural frequencies and model identification. The results show that the method is able to give accurate predictions and that an experimental training set can be created if the models are well characterized.| File | Dimensione | Formato | |
|---|---|---|---|
|
Casaburo_et_al_MEDYNA2020_machine_learning.pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Dominio pubblico
Dimensione
396.82 kB
Formato
Adobe PDF
|
396.82 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
