noiseNet: A neural network to predict marine propellers’ underwater radiated noise

Publikationstyp
Journal Article
Date Issued
2021-09-15
Sprache
English
Author(s)
Wang, Youjiang  orcid-logo
Wang, Keqi  
Abdel-Maksoud, Moustafa  orcid-logo
Institut
Fluiddynamik und Schiffstheorie M-8  
TORE-URI
http://hdl.handle.net/11420/10111
Journal
Ocean engineering  
Volume
236
Article Number
109542
Citation
Ocean Engineering 236: 109542 (2021-09-15)
Publisher DOI
10.1016/j.oceaneng.2021.109542
Scopus ID
2-s2.0-85111185395
A dedicated neural network architecture called noiseNet has been developed to predict URN (Underwater Radiated Noise) of cavitating marine propellers. The noiseNet predicts the sound pressure level at the first three blade passing frequencies with knowing the propeller geometry, ship hull wake field and working conditions. The physical mechanism of the URN generation is firstly analyzed. Thereafter, the physical knowledge about the hydrodynamics and hydroacoustics of marine propellers are used to develop the noiseNet architecture. A dataset obtained with the boundary element method and Ffowcs Williams–Hawkings acoustic analogy is used for the training and evaluation. The evaluation conducted on fully unseen cases shows a mean absolute error of 7.34 dB.
Subjects
Cavitation
Machine learning
Marine propeller
Neural network
Noise
DDC Class
000: Allgemeines, Wissenschaft