This work proposes a mechanism able to automatically categorize different types of faults occurring in critical infrastructures and especially water distribution networks. The mechanism models the relationship exhibited among the sensor datastreams based on the assumption that its pattern alters depending on the fault type. The first phase includes linear time invariant modeling which outputs a parameters vector. At the second phase the evolution of the parameter vectors is captured via hidden Markov modeling. The methodology is applied on data coming from the water distribution network of the city of Barcelona. The corpus contains a vast amount of data representative of nine network states. The nominal is included for enabling fault detection. The achieved classification rates are quite encouraging and the system is practical.

Automatic fault identification in sensor networks based on probabilistic modeling / S. Ntalampiras, G. Giannopoulos (LECTURE NOTES IN COMPUTER SCIENCE). - In: Critical Information Infrastructures Security / [a cura di] C.G. Panayiotou, G. Ellinas, E. Kyriakides, M.M. Polycarpou. - [s.l] : Springer Verlag, 2016. - ISBN 9783319316635. - pp. 344-354 (( Intervento presentato al 9. convegno International Conference on Critical Information Infrastructures Security tenutosi a Limassol nel 2014 [10.1007/978-3-319-31664-2_35].

Automatic fault identification in sensor networks based on probabilistic modeling

Ntalampiras, Stavros;
2016

Abstract

This work proposes a mechanism able to automatically categorize different types of faults occurring in critical infrastructures and especially water distribution networks. The mechanism models the relationship exhibited among the sensor datastreams based on the assumption that its pattern alters depending on the fault type. The first phase includes linear time invariant modeling which outputs a parameters vector. At the second phase the evolution of the parameter vectors is captured via hidden Markov modeling. The methodology is applied on data coming from the water distribution network of the city of Barcelona. The corpus contains a vast amount of data representative of nine network states. The nominal is included for enabling fault detection. The achieved classification rates are quite encouraging and the system is practical.
Linear time invariant modeling; Hidden Markov model; Fault diagnosis; Critical infrastructure protection
Settore INF/01 - Informatica
FP7 Network of Excellence CIPRNet
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Ntalampiras-Giannopoulos2016_Chapter_AutomaticFaultIdentificationIn.pdf

non disponibili

435.02 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/615058
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact