TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publications
  4. Regularized machine learning for system identification of ship free-running manoeuvres from CFD-based synthetic data: a comparative study
 
Options

Regularized machine learning for system identification of ship free-running manoeuvres from CFD-based synthetic data: a comparative study

Citation Link: https://doi.org/10.15480/882.17286
Publikationstyp
Preprint
Date Issued
2026
Sprache
English
Author(s)
Suárez, R. F.  
Fluiddynamik und Schiffstheorie M-8  
Berndt, J.  
Fluiddynamik und Schiffstheorie M-8  
Abdel-Maksoud, M.  orcid-logo
Fluiddynamik und Schiffstheorie M-8  
TORE-DOI
10.15480/882.17286
TORE-URI
https://hdl.handle.net/11420/63441
Citation
R.F. Suárez, J.C. Berndt, and M. Abdel-Maksoud. Regularized machine learning for system identification of ship free-running manoeuvres from cfd-based synthetic data: A comparative study. Ocean Engineering, 2026. Manuscript submitted for publication.
Publisher
Elsevier
Peer Reviewed
false
This study investigates supervised machine learning techniques for identifying ship hydrodynamic coefficients from CFD-generated data from free-running simulations. Specifically, ordinary least squares and regularized regression methods are applied to Abkowitz-type manoeuvring models. Training and validation datasets are derived from URANS simulations of zig-zag and turning circle manoeuvres, which are validated against experimental benchmark data. The analysis evaluates the effects of coefficient set size, minimum training length required for predictive model training, and manoeuvre combinations on model performance. Results demonstrate the suitability of large-angle zig-zag manoeuvres for hydrodynamic system identification, provided that multicollinearity is addressed through appropriate coefficient selection, regression models, or input data variability. Larger coefficient sets offer greater model flexibility for variable conditions but are more prone to multicollinearity. Regularized regression techniques effectively mitigate multicollinearity and notably enhance prediction accuracy, as does incorporating more diverse manoeuvring data. Among tested models, Ridge regression provided the best compromise between computational efficiency and prediction accuracy.
Subjects
Ship Manoeuvring
System Identification
Abkowitz Model
Hydrodynamic Coefficients
Computational Fluid Dynamics
Machine Learning
DDC Class
623.8: Naval Architecture; Shipbuilding
Funding(s)
Strahl-VSP - Numerische Untersuchung der Strahlausbreitung von Voith-Schneider-Propellern  
Funding Organisations
Federal Ministry of Transport and Digital Infrastructure  
Lizenz
https://creativecommons.org/licenses/by/4.0/
Publisher‘s Creditline
R.F. Suárez: Conceptualization, Formal analysis, Investigation, Methodology, Resources, Visualization, Writing – original draft, review and editing.
J.C. Berndt: Conceptualization, Formal analysis, Investigation, Visualization, Methodology, Validation, Writing – original draft, review and editing.
M. Abdel-Maksoud: Investigation, Funding acquisition, Supervision, Writing - review and editing.
Publication version
submittedVersion
Loading...
Thumbnail Image
Name

Suarez_Berndt_Maksoud_2026-preprint.pdf

Type

Main Article

Size

52.96 MB

Format

Adobe PDF

TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback