PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Colantonio S., Di Bono M. G., Pieri G., Salvetti O., Cavaccini G. System Health Monitoring using Multilevel Artificial Neural Networks. In: IEEE International Conference on Computational Intelligence for (Giardini Naxos - Taormina, SICILY, ITALY, 20-22 July 2005). Proceedings, vol. 1 pp. 50 - 55. IEEE (ed.). IEEE, 2005.
 
 
Abstract
(English)
The assessment of the health state of complex physical systems is of key importance for maintaining the same systems safe, less expensive, adequately equipped and operating. In this work, a methodology is defined for evaluating the structure and performance integrity of a physical system or its components. The monitoring activity is based on a Multilevel Artificial Neural Network for describing, diagnosing and predicting the state of the monitored system. Following a coarse-to-fine paradigm, artificial neural networks of different topologies and typologies are modularly and hierarchically combined to firstly process and validate the sensor measurements acquired on-field, then classify the validated measures and, at the end, predict the state of the system. In course tests on experimental data furnished by Alenia and regarding aircraft components have shown that the proposed method is a promising aid for the evaluation of the health state of a physical structure and that it can be integrated inside a single aircraft life cycle monitoring system.
Subject Multilevel Artificial Neural Network
Structural Health Monitoring
Life Cycle Monitoring
Aircraft Components
I.2.6 Learning
I.5.1 Models
I.5.4 Applications


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional