在开展一系列水下航行器模型试验的基础上，获取艇体、舵翼、推进器等的水动力参数，建立六自由度动力学模型。然后，基于RBF神经网络算法，对模型中的向心力、科氏力和阻尼项进行黑箱建模。通过水平面和垂直面的操纵运动仿真，对RBF神经网络在水下航行器黑箱建模中的有效性进行验证。
Based on a series of captive model tests for an underwater vehicle, the hydrodynamic parameters of the vehicle hull, rudder and thrust are all obtained, and the 6dof dynamic model is established. Then the black model of centripetal and Coriolis force as well as the damping term is calculated by using RBF neural network. By means of hydrodynamic simulation in the horizontal and vertical plane, the effectiveness of RBF neural network on underwater vehicle's black modeling is validated.
2018,40(9): 75-77,129 收稿日期：2018-03-24
DOI：10.3404/j.issn.1672-7649.2018.09.014
分类号：U661.33
基金项目：国家自然科学基金资助项目（NSFC51509193）
作者简介：孙新蕾(1985-),女,硕士,讲师,从事随机过程分析、模式识别研究
参考文献：
[1] FOSSEN T I. Marine control systems:Guidance, navigation and control of ships, rigs and underwater vehicles[M]. Marine Cybernetics Trondheim, Norway, 2002.
[2] FOSSEN T I. Guidance and control of ocean vehicles[M]. John Wiley & Sons, New York, 1994.
[3] SANDBERG I W. Structure theorems for nonlinear systems[J]. Multidimensional Systems and Signal Processing, 1991, 2(3):267-286
[4] 王波, 苏玉民, 秦再白. 微小型水下机器人操纵性能与运动仿真研究[J]. 系统仿真学报, 2009, 2(13):4149-4152
[5] YEO D J, RHEE K P. Sensitivity analysis of submersibles' manoeuvrability and its application to the design of actuator inputs[J]. Ocean Engineering, 2006, 33(17):2270-2286
