Ensemble neural network-based particle filtering for prognostics - CentraleSupélec Access content directly
Journal Articles Mechanical Systems and Signal Processing Year : 2013

Ensemble neural network-based particle filtering for prognostics


Particle Filtering (PF) is used in prognostics applications by reason of its capability of robustly predicting the future behavior of an equipment and, on this basis, its Residual Useful Life (RUL). It is a model-driven approach, as it resorts to analytical models of both the degradation process and the measurement acquisition system. This prevents its applicability to the cases, very common in industry, in which reliable models are lacking. In this work, we propose an original method to extend PF to the case in which an analytical measurement model is not available whereas, instead, a dataset containing pairs "state - measurement" is available. The dataset is used to train a bagged ensemble of Artificial Neural Networks (ANNs) which is, then, embedded in the PF as empirical measurement model. The novel PF scheme proposed is applied to a case study regarding the prediction of the RUL of a structure, which is degrading according to a stochastic fatigue crack growth model of literature.
Fichier principal
Vignette du fichier
mssp_REV1.pdf (858.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00872747 , version 1 (14-10-2013)



Piero Baraldi, Michele Compare, Sergio Sauco, Enrico Zio. Ensemble neural network-based particle filtering for prognostics. Mechanical Systems and Signal Processing, 2013, 41 (1-2), pp.288-300. ⟨10.1016/j.ymssp.2013.07.010⟩. ⟨hal-00872747⟩
145 View
1169 Download



Gmail Facebook X LinkedIn More