| 基于支持向量机的船舶操纵运动黑箱建模 |
| |
| 引用本文： | 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[J].北京航空航天大学学报,2013,39(11):1553-1557. |
| |
| 作者姓名： | 徐锋 邹早建 徐小卡 尹建川 |
| |
| 作者单位： | 上海交通大学船舶海洋与建筑工程学院,上海,200240;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） |
| |
| 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.
|
| 关 键 词： | 支持向量机 船舶操纵 黑箱建模 网格搜索 |
| 收稿时间： | 2012-12-14 |
Black-box modeling of ship manoeuvring motion based on support vector machines |
| |
| Xu Feng,Zou Zaojian,Xu Xiaoka,Yin Jianchuan.Black-box modeling of ship manoeuvring motion based on support vector machines[J].Journal of Beijing University of Aeronautics and Astronautics,2013,39(11):1553-1557. |
| |
| Authors: | Xu Feng Zou Zaojian Xu Xiaoka Yin Jianchuan |
| |
| Institution: | 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 |
| |
| 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. |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《北京航空航天大学学报》浏览原始摘要信息 |
| 点击此处可从《北京航空航天大学学报》下载免费的PDF全文 |
