An Hybrid Model-Based/Data-Driven Approach for Fatigue Crack Growth Prognostics by Particle Filtering and Ensemble Neural Networks

Piero Baraldi, Enrico Zio, Michele Compare, and Sergio Sauco
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmce_12_012.pdf152.92 KBJune 7, 2012 - 7:41am

Particle Filtering (PF) is a model-driven approach widely used in prognostics, which requires models of both the degradation process and the measurement acquisition system. In many practical cases, analytical models are not available, but a dataset containing a number of pairs component state - corresponding measurement may be available.
In this work, a data-driven approach based on a bagged ensemble of Artificial Neural Networks (ANNs) is adopted to build an empirical measurement model of a Particle Filter for the prediction of the Residual Useful Life (RUL) of a structure whose degradation process is described by a stochastic fatigue crack growth model of literature. The work focuses on the investigation of the capability of the proposed approach to cope with the uncertainty affecting the RUL prediction.

Publication Year: 
2012
Publication Volume: 
3
Publication Control Number: 
012
Page Count: 
8
Submission Keywords: 
particle filtering
Ensemble of ANNs
RUL
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Model-based methods for fault detection, diagnostics, and prognosis
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed