检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:温琦[1] 李洋[1] 马昕[2] 李俊漾 王暖升 WEN Qi;LI Yang;MA Xin;LI Junyang;WANG Nuansheng(Faculty of Information Science and Engineering,Ocean University of China,Qingdao,Shandong 266100,China;Key Laboratory of Physics and Ocean Education,Ocean University of China,Qingdao,Shandong 266100,China;Faculty of Oceanography and Atmosphere,Ocean University of China,Qingdao,Shandong 266100,China)
机构地区:[1]中国海洋大学信息科学与工程学部,山东青岛266100 [2]中国海洋大学物理海洋教育部重点实验室,山东青岛266100 [3]中国海洋大学海洋与大气学院,山东青岛266100
出 处:《航天器工程》2024年第1期146-152,共7页Spacecraft Engineering
摘 要:在精细化海洋观测领域,遥感卫星海浪方向谱的获取存在精度低、累积误差大等问题,设计了一种基于Transformer神经网络的海浪方向谱估计方法,通过引入稀疏自注意力机制以及物理引导模块等,实现海浪方向谱的高精度表达;海上试验测试结果表明,新提出的海浪方向谱估计方法与传统海浪方向谱估计方法相比,文章提出的模型估计方向谱更符合理论谱形,伪峰较少,平滑性和一致性方面表现较好,并且对数据噪声的容忍度更高。同时,设计了一种基于人工智能芯片的漂流波浪浮标系统,通过AI软硬件系统对不同任务进行动态调度分配,实现浮标低功耗运行,有效提升了波浪测量性能及海上工作时间,是遥感卫星高精度获取大范围、长时序全球性海洋观测数据的一种有效补充。In the field of refined ocean observation,the acquisition of direction spectrum of ocean waves by remote sensing satellites has some problems such as low accuracy and large cumulative errors.In this paper,a method for estimating the direction spectrum of ocean waves based on Transformer neural networks is designed,which introduces sparse self-attention mechanism and physical guidance module to achieve high-precision expression of ocean wave directional spectrum.The results of sea trial testing show that the newly proposed method for estimating the direction spectrum of ocean waves is more in line with the theoretical spectrum,with fewer pseudo peaks,better smoothness and consistency,and a higher tolerance for data noise compared to traditional methods.At the same time,a drift wave buoy system based on artificial intelligence chips is also designed,which dynamically schedules and allocates different tasks through AI software and hardware systems,achieving low-power operation of the buoy,effectively improving wave measurement performance and sea working time.It is an effective supplement to high-precision acquisition of large-scale,long-term global ocean observation data by remote sensing satellites.
分 类 号:TP751[自动化与计算机技术—检测技术与自动化装置]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:18.221.21.111