Over het archief
Het OWA, het open archief van het Waterbouwkundig Laboratorium heeft tot doel alle vrij toegankelijke onderzoeksresultaten van dit instituut in digitale vorm aan te bieden. Op die manier wil het de zichtbaarheid, verspreiding en gebruik van deze onderzoeksresultaten, alsook de wetenschappelijke communicatie maximaal bevorderen.
Dit archief wordt uitgebouwd en beheerd volgens de principes van de Open Access Movement, en het daaruit ontstane Open Archives Initiative.
Basisinformatie over ‘Open Access to scholarly information'.
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. , meer
|
| Beschikbaar in | Auteurs |
|
Documenttype: Congresbijdrage
|
| Author keywords |
Ship motions model; NLSSVM; BAS; Parameter identification |
| Auteurs | | Top |
- Changyuan, C.
- Tello Ruiz, M., meer
- Delefortrie, G., meer
|
|
|
| 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. |
IMIS is ontwikkeld en wordt gehost door het VLIZ.
