The importance of testability analysis in neural network based fault diagnosis of DC-DC converters is discussed in this paper. Theoretical fundamentals and an applicative example are presented, by taking into account the single-fault hypothesis. A program for testability analysis of switched DC-DC converters is used in the example. It relies on symbolic analysis techniques, which may be used to simulate switched circuits in a very easy and fast way.

Testability Analysis in Neural Network Based Fault Diagnosis of DC-DC Converter / Aizenberg I.; Bindi M.; Grasso F.; Luchetta A.; Manetti S.; Piccirilli M.C.. - ELETTRONICO. - (2019), pp. 265-268. (Intervento presentato al convegno 5th International Forum on Research and Technologies for Society and Industry, RTSI 2019 tenutosi a FIRENZE nel 2019) [10.1109/RTSI.2019.8895583].

Testability Analysis in Neural Network Based Fault Diagnosis of DC-DC Converter

Aizenberg I.
Conceptualization
;
Bindi M.
Writing – Original Draft Preparation
;
Grasso F.
Validation
;
Luchetta A.
Writing – Original Draft Preparation
;
Manetti S.
Investigation
;
Piccirilli M. C.
Writing – Review & Editing
2019

Abstract

The importance of testability analysis in neural network based fault diagnosis of DC-DC converters is discussed in this paper. Theoretical fundamentals and an applicative example are presented, by taking into account the single-fault hypothesis. A program for testability analysis of switched DC-DC converters is used in the example. It relies on symbolic analysis techniques, which may be used to simulate switched circuits in a very easy and fast way.
2019
5th International Forum on Research and Technologies for Society and Industry: Innovation to Shape the Future, RTSI 2019 - Proceedings
5th International Forum on Research and Technologies for Society and Industry, RTSI 2019
FIRENZE
2019
Aizenberg I.; Bindi M.; Grasso F.; Luchetta A.; Manetti S.; Piccirilli M.C.
File in questo prodotto:
File Dimensione Formato  
08895583.pdf

Accesso chiuso

Descrizione: Articolo
Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 552.68 kB
Formato Adobe PDF
552.68 kB Adobe PDF   Richiedi una copia

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1181808
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? ND
social impact