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 | Dimensione | Formato | |
---|---|---|---|
acceptedVersion.pdf
accesso riservato
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
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2958902