少量样本条件下模拟训练航迹点生成算法

Simulated training path generation algorithm under the condition of small number of samples

为解决少量样本条件下船舶航迹点数量较少的问题,以单船进出港为例,在无确定度的逆向正态云算法和二维正向正态云生成算法基础上,提出基于少量样本的单船进出港航迹点云图生成算法,并通过算例验证算法的实用性,为从航迹角度定量评价驾驶员航行过程奠定了基础.

To deal with the problem of less tracking points under the condition of small number of samples,taking a single ship inward/outward port as an example,according to uncertain reverse normal cloud algorithm and two-dimension positive normal cloud algorithm,a track point cloud image generation algorithm for the single ship＇s inward/outward port was proposed based on small number of samples,and the practicability of the algorithm was verified through numerical examples,which gives a solid foundation for evaluating the navigation process from angle of the track.