Identification of submarine´s response model in vertical plane based on support vector machines

Author

Xu Feng ; Zou Zao-Jian ; Song Xin

Author_Institution

Sch. of Naval Archit., Ocean & Civil Eng., Shanghai Jiao Tong Univ., Shanghai, China

fYear

2011

fDate

27-29 June 2011

Firstpage

455

Lastpage

458

Abstract

In this paper, submarine´s response model in vertical plane is transferred into state space model using ´white box´ theory of linear system. Least square support vector machine (LS-SVM) is used to identify zigzag test of submarine´s response model in vertical plane and the identification results verify the validity of this method. The difference of model identification between fixed rudder angle and variable rudder angle is pointed out. Therefore, an emendatory method which is proved to be proper in the simulation test is put forward.

Keywords

identification; least squares approximations; linear systems; support vector machines; underwater vehicles; LS-SVM; fixed rudder angle; least square support vector machine; linear system; state space model; submarine response model identification; variable rudder angle; white box theory; zigzag test identification; Artificial neural networks; Mathematical model; Oceans; Predictive models; Support vector machines; System identification; Underwater vehicles; Model Identification; Response model; Support Vector Machine; Vertical Plane;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Service System (CSSS), 2011 International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-9762-1

Type

conf

DOI

10.1109/CSSS.2011.5972146

Filename

5972146