一种基于聚类的航海雷达海面风速反演算法  

A clustering-analysis-based algorithm for wind speedestimation from nautical rardar images

作　　者：邱海洋 王慧 智鹏飞 朱琬璐 唐权 QIU Haiyang;WANG Hui;ZHI Pengfei;ZHU Wanlu;TANG Quan(School of Naval Architecture and Ocean Engineering,Guangzhou Maritime University,Guangzhou 510725,China;Ocean College,Jiangsu University of Science and Technology,Zhenjiang 212100,China)

机构地区：[1]广州航海学院船舶与海洋工程学院,广州510725 [2]江苏科技大学海洋学院,镇江212100

出　　处：《江苏科技大学学报（自然科学版）》2022年第6期58-63,共6页Journal of Jiangsu University of Science and Technology:Natural Science Edition

基　　金：国家自然科学青年基金资助项目(41906154,52101358)。

摘　　要：针对基于X波段航海雷达图像提取海面风速传统模型存在精度低和稳定性差的问题,综合考虑海面风速提取影响因素的情况,提出聚类算法重构海面风速提取模型.结合传感器及雷达图像信息对风速影响因素数据进行归一化,使数据在同一坐标范围内;基于聚类算法对数据进行分类,剔除异类数据对风速提取模型的影响;最后,针对海面风速与雷达回波强度的非线性关系,对剔除异类数据应用非线性二次函数确定海面风速提取模型.通过实测数据验证:聚类算法模型得到风速相对传统模型提取精度提高了74.3%,表现出更好的稳定性.In order to solve the problems of low accuracy and poor stability existing in the traditional model of sea surface wind speed retrieval based on X-band nautical radar image,this paper proposes a clustering algorithm to retrieve the sea surface wind speed extraction model under the comprehensive consideration of the influencing factors.Firstly,the data of sea surface influence factors are normalized by combining sensor and radar image information,so that the data are within the same coordinate range.Then,the data is classified based on the clustering algorithm,and the influence of outlier data of the retrieval model is eliminated.Finally,consider the nonlinear relationship between sea surface wind speed and radar echo intensity,the nonlinear quadratic function is applied to the processed data to determine the extraction model of sea surface wind speed.Two methods are verified by field measured data:the wind speed obtained by clustering algorithm is improved by 74.3%compared with the traditional model,and the algorithm better stability.

关 键 词：航海雷达 海面风速 聚类算法 雷达回波强度 

分 类 号：TN957.5[电子电信—信号与信息处理]