基于支持向量机的船舶操纵运动黑箱建模

徐锋; 邹早建; 徐小卡; 尹建川

基于支持向量机的船舶操纵运动黑箱建模

1.
上海交通大学船舶海洋与建筑工程学院, 上海 200240
2. 中国科学院声学研究所水声环境特性重点实验室, 北京 100190

基金项目: 国家自然科学基金资助项目（50979060，51079031）

详细信息

中图分类号: U661.33⁺1
计量
- 文章访问数: 1425
- HTML全文浏览量: 97
- PDF下载量: 426
- 被引次数: 0
出版历程
- 收稿日期: 2012-12-14
- 网络出版日期: 2013-11-30

Black-box modeling of ship manoeuvring motion based on support vector machines

1.
School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. Key Laboratory of Underwater Acoustic Environment, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China

摘要

摘要: 根据船舶自航模15°/5°Z形试验结果，应用最小二乘支持向量机对船舶操纵运动进行了黑箱建模，针对支持向量机参数选择的不确定性，使用网格搜索法进行了参数寻优；应用所建立的支持向量机回归模型对该自航模的10°/1°，25°/5°Z形试验及35°回转试验进行了操纵运动预报.预报结果同试验结果相比吻合良好，证明了支持向量机应用于船舶操纵运动黑箱建模的有效性，以及网格搜索法在支持向量机参数寻优中的可行性.
- 支持向量机 /
- 船舶操纵 /
- 黑箱建模 /
- 网格搜索
Abstract: Least square support vector machines(LS-SVM) was applied to black-box modeling of ship manoeuvring motion by using the 15°/5° zigzag test data of free-running model. To solve the problem of the uncertainty in choosing the parameters of SVM, grid search method was adopted for parameter optimization. The established model was used for predicting the 10°/1° and 25°/5° zigzag manoeuvres and 35° turning circle manoeuvre. The prediction results are in good agreement with the test data, which demonstrates the validity of LS-SVM in black-box modeling of ship maneuvering motion and the feasibility of grid search method in optimizing the parameters of SVM.
- support vector machines /
- ship manoeuvring /
- black-box modeling /
- grid search method

HTML全文

参考文献(12)

[1]	Haddara M R, Wang Y.Parametric identification of maneuvering models for ships[J].International Shipbuilding Progress, 1999, 46 (445):5-27
[2]	Mahfouz A B, Haddara M R.Effects of the damping and excitation on the identification of the hydrodynamic parameters for an underwater robotic vehicle[J].Ocean Engineering, 2003, 30 (8):1005-1025
[3]	Hess D, Faller W, Minnick L, et al.Maneuvering simulation of Sea Fighter using a fast nonlinear time domain technique[C]//9th International Conference on Numerical Ship Hydrodynamics.Michigan:University of Michigan, 2007
[4]	Hess D, Faller W, Lee J.Real-time nonlinear simulation of maneuvers for US navy combatant DTMB 5415[C]//SIMMAN 2008, Workshop on Verification and Validation of Ship Manoeuvring Simulation Methods, 2008
[5]	Luo W L, Zou Z J.Parametric identification of ship maneuvering models by using support vector machines[J].Journal of Ship Research, 2009, 53 (1):19-30
[6]	Luo W L, Zou Z J, Li T S.Application of support vector machine to ship steering[J].Journal of Shanghai Jiao Tong University:Science Edition, 2009, 14 (4):462-466
[7]	Vapnik V N.The nature of statistical learning theory[M].2nd ed.New York:Springer, 1999
[8]	李殿璞.船舶运动与建模[M].北京:国防工业出版社, 2008 Li Dianpu.Ship motion and modeling[M].Beijing:National Defense Industry Press, 2008 (in Chinese)
[9]	祁亨年.支持向量机及其应用研究综述[J].计算机工程, 2004, 30 (10):6-9 Qi Hengnian.Support vector machines and application research overview[J].Computer Engineering, 2004, 30 (10):6-9 (in Chinese)
[10]	Suykens J A, Vandewalle J, De Moor B.Optimal control by least squares support vector machines[J].Neural Networks, 2001, 14 (1):23-35
[11]	史峰, 王小川, 郁磊, 等.MATLAB神经网络30个案例分析[M].北京:北京航空航天大学出版社, 2010 Shi Feng, Wang Xiaochuan, Yu Lei, et al.MATLAB neural network analysis of 30 cases[M].Beijing:Beijing University of Aeronautics & Astronautics Press, 2010 (in Chinese)
[12]	SIMMAN 2008.Workshop on verification and validation of ship manoeuvring simulation methods.Copenhagen: [C/OL], 2008-04.