The general problem of detecting the position of a shock by using a discrete set of real or virtual pressure sensors is studied numerically. A Machine Learning (ML) algorithm is trained by CFD simulations of the transonic flow in a duct with an embedded shock at different positions. The shock detection algorithm is validated by using discrete data collected at different duct locations, for simulating the outputs of a discrete number of pressure sensors placed along the duct. A noise model of the measured pressure values is introduced in order to emulate the sensor outputs and faults.

AI Assisted Detection of Shock Motions Inside a Transonic Duct / Resta, Emanuele; Ferlauto, Michele; Marsilio, Roberto. - ELETTRONICO. - 2424:(2022), p. 030005. ((Intervento presentato al convegno International Conference on Computational Intelligence and Computing Applications-21 (ICCICA-21) tenutosi a Virtual nel 18-19 June 2021 [10.1063/5.0076817].

AI Assisted Detection of Shock Motions Inside a Transonic Duct

Emanuele Resta;Michele Ferlauto;Roberto Marsilio
2022

Abstract

The general problem of detecting the position of a shock by using a discrete set of real or virtual pressure sensors is studied numerically. A Machine Learning (ML) algorithm is trained by CFD simulations of the transonic flow in a duct with an embedded shock at different positions. The shock detection algorithm is validated by using discrete data collected at different duct locations, for simulating the outputs of a discrete number of pressure sensors placed along the duct. A noise model of the measured pressure values is introduced in order to emulate the sensor outputs and faults.
File in questo prodotto:
File Dimensione Formato  
acceptedVersion.pdf

non disponibili

Descrizione: acceptedVersion
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 283.03 kB
Formato Adobe PDF
283.03 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/11583/2958902