The research herein presented continues an initial work on this area performed at Politecnico di Torino in the past years and moves forward in the definition of an effective PHM system for Electro-Hydraulic Servo Actuators (EHSA). PHM of EHSAs is an area only little addressed, but of great interest for the aerospace industry and the air fleet operators. The PHM algorithm consists of three subroutines: the first subroutine extracts a set of relevant features from the data acquired by the sensors during a pre or post flight set of commands and mitigate their dependencies with environmental condition. Fault identification is then performed using mathematical data-driven techniques, three methods are presented: Nominal bands, Percentual error and Euclidean distance. Classification of a single and multiple degradations is performed by the second subroutine with the aid of two dual layer Neural Networks. Finally, the remaining useful life (RUL) is estimated by the third subroutine using a particle filter framework, where the feature evolution model is estimated online. Electrohydraulic Servo-valves (EHSV) faults are widely addressed with the aid of a nonlinear model and the performance of the PHM algorithm is assessed using relevant metrics
Prognostic and health management system for hydraulic servo-actuators for helicopters main and tail rotor / Macaluso, Andrea. - ELETTRONICO. - (2016), pp. 733-736. (Intervento presentato al convegno Third European Conference of the Prognostics and Health Management Society tenutosi a Bilbao (SP) nel July 5-6, 2016).
Prognostic and health management system for hydraulic servo-actuators for helicopters main and tail rotor
MACALUSO, ANDREA
2016
Abstract
The research herein presented continues an initial work on this area performed at Politecnico di Torino in the past years and moves forward in the definition of an effective PHM system for Electro-Hydraulic Servo Actuators (EHSA). PHM of EHSAs is an area only little addressed, but of great interest for the aerospace industry and the air fleet operators. The PHM algorithm consists of three subroutines: the first subroutine extracts a set of relevant features from the data acquired by the sensors during a pre or post flight set of commands and mitigate their dependencies with environmental condition. Fault identification is then performed using mathematical data-driven techniques, three methods are presented: Nominal bands, Percentual error and Euclidean distance. Classification of a single and multiple degradations is performed by the second subroutine with the aid of two dual layer Neural Networks. Finally, the remaining useful life (RUL) is estimated by the third subroutine using a particle filter framework, where the feature evolution model is estimated online. Electrohydraulic Servo-valves (EHSV) faults are widely addressed with the aid of a nonlinear model and the performance of the PHM algorithm is assessed using relevant metricsFile | Dimensione | Formato | |
---|---|---|---|
PHME16.pdf
accesso aperto
Descrizione: Articolo pricipale
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Creative commons
Dimensione
4.09 MB
Formato
Adobe PDF
|
4.09 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2645507
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo