Skip to main content

IMIS

A new integrated search interface will become available in the next phase of marineinfo.org.
For the time being, please use IMIS to search available data

 

[ report an error in this record ]basket (0): add | show Print this page

Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm
Chen, C.; Tello Ruiz, M.; Delefortrie, G.; Mansuy, M.; Mei, T.; Vantorre, M. (2019). Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm, in: ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering - Volume 7B: Ocean Engineering. pp. [1-9]. https://dx.doi.org/10.1115/OMAE2019-95565
In: (2019). ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering - Volume 7B: Ocean Engineering. ASME: [s.l.]. ISBN 978-0-7918-5885-1. , more

Available in  Authors 
Document type: Conference paper

Author keywords
    Ship motions model; NLSSVM; BAS; Parameter identification

Authors  Top 
  • Changyuan, C.
  • Tello Ruiz, M., more
  • Delefortrie, G., more

Abstract
    In order to identify more accurately and efficiently the unknown parameters of a ship motions model, a novel Nonlinear Least Squares Support Vector Machine (NLSSVM) algorithm, whose penalty factor and Radial Basis Function (RBF ) kernel parameters are optimised by the Beetle Antennae Search algorithm (BAS), is proposed and investigated. Aiming at validating the accuracy and applicability of the proposed method, the method is employed to identify the linear and nonlinear parameters of the first-order nonlinear Nomoto model with training samples from numerical simulation and experimental data. Subsequently, the identified parameters are applied in predicting the ship motion. The predicted results illustrate that the new NLSSVM-BAS algorithm can be applied in identifying ship motion’s model, and the effectiveness is verified. Compared among traditional identification approaches with the proposed method, the results display that the accuracy is improved. Moreover, the robust and stability of the NLSSVM-BAS are verified by adding noise in the training sample data.

All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors