基于支持向量机的水下运载器平面操纵运动建模  

Modeling of Underwater Vehicles' Planar Maneuvering Motion Based on Support Vector Machines

作　　者：徐锋[1] 邹早建[1,2] 宋鑫[1] 

机构地区：[1]上海交通大学船舶海洋与建筑工程学院,上海200240 [2]上海交通大学海洋工程国家重点实验室,上海200240

出　　处：《上海交通大学学报》2012年第3期358-362,共5页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目(50979060,51079031)

摘　　要：应用卡尔曼滤波器对水下运载器操纵运动仿真试验数据进行预处理,应用最小二乘支持向量机(LS-SVM)对水下运载器的平面操纵运动方程进行参数辨识,并与传统的最小二乘法(LSM)的结果进行比较,验证了LS-SVM应用于水下运载器操纵运动建模的有效性.At first,Kalman filter was adopted for data preprocessing of underwater vehicle＇s simulation test.Then,least square support vector machines was applied to identifying the coefficients in the equations of planar maneuvering motion of underwater vehicles.The identification results were compared with those by using traditional least square method.It proves that the least square support vector machines is more effective.

关 键 词：卡尔曼滤波 水下运载器 支持向量机 参数辨识 

分 类 号：U661.33[交通运输工程—船舶及航道工程]