基于航行逻辑划分语义标签的可视化分析方法  

Visual analysis semantic label method based on navigation logic division

作　　者：蔡智媛 余龙[1,2] 杨俊 张芮菡 吴曾宇 王宇林 李从波 CAI Zhiyuan;YU Long;YANG Jun;ZHANG Ruihan;WU Zengyu;WANG Yulin;LI Congbo(State Key Laboratory of Ocean Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration,Shanghai 200240,China;Chongqing Waterway Bureau of the Yangtz River,Chongqing 401147,China;Marine Design and Research Institute of China,Shanghai 200011,China)

机构地区：[1]上海交通大学海洋工程国家重点实验室,上海200240 [2]高新船舶与深海开发装备协同创新中心,上海200240 [3]长江重庆航道局,重庆401147 [4]中国船舶及海洋工程设计研究院,上海200011

出　　处：《中国舰船研究》2022年第6期59-69,共11页Chinese Journal of Ship Research

基　　金：MARIC-SJTU联合创新基金资助项目(MS202108)。

摘　　要：[目的]旨在探索处理内河实船数据、提高其可理解性和辅助研究识别船舶行为的新方法。[方法]通过构建航行逻辑层级和划分时序数据获得船舶行为的语义标签,设计航行逻辑可视化分析系统,将船舶航行状态与数据可视化相结合,辅助分析数据及研究船舶行为特征。最后,依托数字航道,选择船舶行为复杂的内河航道工作船的数据进行实例检验,利用所提系统分析异常数据并研究船舶行为。[结果]通过航行逻辑的交互可视化,可有效确定无规律的位置跳动异常数据产生的原因及特点,帮助进行异常数据处理,并经过定性分析特征和定量分析阈值,划分出了靠泊与直航状态数据,进一步丰富了船舶行为语义标签。[结论]结合船舶行为语义标签设计的可视化分析系统,通过人机自由交互,提高了数据的可理解性,可辅助异常数据分析处理及船舶行为研究,为数据分析人员提供研究工具。[Objectives]This paper aims to explore new methods for enhancing the abnormal data processing of real ships in inland rivers,improving data comprehension and assisting in ship behavior recognition research.[Methods]By constructing a navigation logic level,the time series data is divided to obtain the semantic label of the ship behavior.A navigation logic visualization analysis system is designed on the basis of semantic labels,and the navigation status of the ship is combined with data visualization to assist in analyzing data problems and studying ship characteristics.Relying on a digital waterway,the data of working ships with complex behavior in an inland waterway is selected for example-based testing,and the system is used to analyze abnormal data and conduct research on ship behavior.[Results]Through the interactive visualization of navigation logic,the causes and characteristics of abnormal data with position jumping can be effectively determined,thereby enhancing abnormal data processing.In addition,the qualitative analysis of features and quantitative analysis of thresholds effectively divides the berthing and direct sailing status data,further enriching the semantic labels of ship behavior.[Conclusions]The visual analysis system designed with semantic labels of ship behavior proposed herein improves data comprehensibility through free human-computer interaction.It can enhance abnormal data analysis and processing,assist in ship behavior recognition research and provide new research tools for data analysts.

关 键 词：航行逻辑 可视化分析系统 异常数据 船舶行为 语义标签 

分 类 号：U675.7[交通运输工程—船舶及航道工程]