Sequential Importance Sampling Based on a Committee of Artificial Neural Networks for Posterior Health Condition Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Sequential Importance Sampling Based on a Committee of Artificial Neural Networks for Posterior Health Condition Estimation

Abstract

The output of real-time diagnostic systems based on the interpretation of signals from a sensor network is often affected by very large uncertainties if compared with local non-destructive testing methods. Sequential Importance Resampling (SIR) is used in this study to filter the output distribution from a committee of Artificial Neural Networks. The methodology is applied to a helicopter panel subject to fatigue crack propagation. Strain signals are acquired during crack evolution and a diagnostic unit trained on simulated experience provides damage assessment in real-time. This information is filtered through a SIR routine, providing model identification, model parameter estimation and crack length probability density function updating, conditioned on the observations at discrete time steps.
Fichier principal
Vignette du fichier
0170.pdf (1.7 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01021052 , version 1 (09-07-2014)

Identifiers

  • HAL Id : hal-01021052 , version 1

Cite

Claudio Sbarufatti. Sequential Importance Sampling Based on a Committee of Artificial Neural Networks for Posterior Health Condition Estimation. EWSHM - 7th European Workshop on Structural Health Monitoring, IFFSTTAR, Inria, Université de Nantes, Jul 2014, Nantes, France. ⟨hal-01021052⟩
78 View
73 Download

Share

Gmail Facebook Twitter LinkedIn More