复杂的海洋环境给精准提取舰船作业状态特征造成了困难，也影响了对舰船作业状态的判断效果。为解决这一问题，本文提出基于船位数据采集的舰船作业状态特征提取方法。首先，利用北斗导航卫星系统，采集舰船的经纬度、航速、航行方位角等船位数据；然后，从舰船的累计作业时长、位置、空间距离、平均作业速率4个方面，分析舰船的作业状态特征。根据船位点在不同速率区间出现的频数，确定舰船的平均速率阈值；最后，根构建包含输入层、隐含层、输出层在内的深度神经网络，利用船位数据训练深度神经网络，输出舰船作业状态特征的提取结果。实验结果表明，该方法能够有效提取舰船的作业状态特征，帮助舰船作业人员在复杂多变的海洋环境中做出更加明智和及时的决策。
The complex marine environment poses difficulties in accurately extracting ship operation status features and also affects the effectiveness of judging ship operation status. To address this issue, this study proposes a method for extracting operational status features of ships based on ship position data collection. Firstly, using the Beidou Navigation Satellite System, collect ship position data such as longitude and latitude, speed, and navigation azimuth; Then, analyze the operational status characteristics of the ship from four aspects: cumulative operating time, location, spatial distance, and average operating rate. Determine the average velocity threshold of the ship based on the frequency of occurrence of ship position points in different velocity intervals; Finally, a deep neural network is constructed that includes an input layer, a hidden layer, and an output layer. The deep neural network is trained using ship position data and outputs the extraction results of ship operation status features. The experimental results show that this method can effectively extract the operational status characteristics of ships, helping ship operators make more informed and timely decisions in complex and changing marine environments.
2025,47(6): 145-148 收稿日期：2024-9-13
DOI：10.3404/j.issn.1672-7649.2025.06.024
分类号：TP399
基金项目：江苏省高等学校基础科学（自然科学）研究重大项目（23KJA580002）；2023年江苏青年教师企业实践（苏高职培函〔2023〕10 号，2023QYSJ023）；2022江苏省“青蓝工程”优秀教学团队（苏教师函（2022） 29 号）
作者简介：颜悦（1985 – ），女，硕士，讲师，研究方向为人工智能
参考文献：
[1] 熊超, 周海峰, 郑东强, 等. 结合空洞编码器和特征金字塔的中心点船舶检测[J]. 船舶工程, 2023, 45(2): 154-161.
[2] 方小宇, 黄丽佳. 基于全局位置信息和残差特征融合的SAR船舶检测算法[J]. 系统工程与电子技术, 2024, 46(3): 839-848.
[3] 崔雷, 庄磊, 张泽栋, 等. 基于特征叠加网络的SAR海上舰船运动状态感知方法[J]. 上海航天(中英文), 2022, 39(6): 75-83.
[4] TRABATTONI A, BARRUOL G, RICHARD D, et al. Ship detection and tracking from single ocean-bottom seismic and hydroacoustic stations[J]. The Journal of the Acoustical Society of America, 2023, 153(1): 260-273.
[5] 王泳安, 李东光, 吴浩, 等. 一种自适应滤波与干扰观测器相结合的大型舰船状态估计算法[J]. 兵工学报, 2024, 45(7): 2318-2328.
[6] 杜晓佳, 李鹏, 倪家正, 等. 运动状态下舰船本体X波段RCS统计特征分析[J]. 中国舰船研究, 2023, 18(1): 163-169.
[7] 宁君, 张军, 李伟. 预设性能下的输出受限船舶航向切换容错控制[J]. 计算机仿真, 2024, 41(1): 385-389+451.
[8] 罗芳, 刘阳, 何道森. 复杂场景下自适应特征融合的多尺度船舶检测[J]. 计算机应用, 2023, 43(11): 3587-3593.
