A Bayesian optimization strategy resulting in optimal sensor locations for impact localization under operational conditions is developed and presented. The impact detection methodology is based on developing meta-models utilizing artificial neural network (ANN) through the recorded sensor signals generated by various impact events. The novelty of the proposed method is to include the probability of one or more sensors failing under operation as well as non-uniform probability of impact occurrence in the structure. Finally, the proposed optimization algorithm is applied to a composite stiffened panel.

Sensor optimization for impact detection – A Bayesian approach

MALLARDO, Vincenzo;
2017

Abstract

A Bayesian optimization strategy resulting in optimal sensor locations for impact localization under operational conditions is developed and presented. The impact detection methodology is based on developing meta-models utilizing artificial neural network (ANN) through the recorded sensor signals generated by various impact events. The novelty of the proposed method is to include the probability of one or more sensors failing under operation as well as non-uniform probability of impact occurrence in the structure. Finally, the proposed optimization algorithm is applied to a composite stiffened panel.
978-84-946909-3-8
Impact detection, Passive sensing, Optimization, Bayesian approach
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11392/2373614
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact