Data driven prognostics using a Kalman filter ensemble of neural network models

Author

Peel, Leto

Author_Institution

Adv. Inf. Process. Dept., BAE Syst. Adv. Technol. Centre, Bristol

fYear

2008

fDate

6-9 Oct. 2008

Firstpage

1

Lastpage

6

Abstract

This paper details the winning method in the IEEE GOLD category of the PHM psila08 Data Challenge. The task was to estimate the remaining useable life left of an unspecified complex system using a purely data driven approach. The method involves the construction of Multi-Layer Perceptron and Radial Basis Function networks for regression. A suitable selection of these networks has been successfully combined in an ensemble using a Kalman filter. The Kalman filter provides a mechanism for fusing multiple neural network model predictions over time. The essential initial stages of pre-processing and data exploration are also discussed.

Keywords

Kalman filters; data handling; multilayer perceptrons; radial basis function networks; remaining life assessment; Kalman filter; data driven prognostics; data exploration; multilayer perceptron; neural network models; radial basis function networks; remaining useable life; Data visualization; Filters; Gold; Life estimation; Multilayer perceptrons; Neural networks; Predictive models; Prognostics and health management; Radial basis function networks; System testing; Ensemble; Kalman Filter; Multi-Layer Perceptron; Prognosis; Radial Basis Functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Prognostics and Health Management, 2008. PHM 2008. International Conference on

Conference_Location

Denver, CO

Print_ISBN

978-1-4244-1935-7

Electronic_ISBN

978-1-4244-1936-4

Type

conf

DOI

10.1109/PHM.2008.4711423

Filename

4711423