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

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 in questo prodotto:
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/867051
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact