﻿ 船舶拥堵水域通行能力预测技术
 舰船科学技术  2024, Vol. 46 Issue (12): 170-173    DOI: 10.3404/j.issn.1672-7649.2024.12.030 PDF

Prediction technology for traffic capacity in congested water areas of ships
LI Daoke
Navigation College, Fujian Chuanzheng Communications College, Fuzhou 350007, China
Abstract: Aiming at the problem of high difficulty in predicting traffic capacity in congested water areas due to high ship traffic flow and busy waters, a technology for predicting traffic capacity in congested water areas is proposed. Determine the ship's status and establish a ship navigation queue model by utilizing the ship's coordinate position and navigation speed. Based on the Fujino ship domain model, determine the elliptical area corresponding to ship navigation as the domain of ship congestion waters. Determine the relevant factors that affect the capacity of shipping channels within the field of ships. Set indicators such as ship density, ship speed, and other factors that affect water traffic capacity as inputs for the long short-term memory network. The long short-term memory network uses three gating units, namely the forget gate, input gate, and output gate, to select whether to retain or forget the input data, and output the prediction results of ship traffic capacity in congested water areas. The experimental results show that this technology can effectively predict the traffic capacity of ship congested waters, improve the utilization rate of waterways, and ensure the safety of water traffic.
Key words: ship congested waters     traffic capacity prediction     ship field     forgetting gate     gate control unit
0 引　言

1 拥堵水域通行能力预测 1.1 拥堵水域的船舶航行队列模型

 $x\left( t \right) = \left[ {\begin{array}{*{20}{c}} {{x_i}\left( t \right)} \\ {{v_i}\left( t \right)} \end{array}} \right] 。$ (1)

τi(t)为船舶直线航行时的推进力。船舶沿固定方向直线航行时，受到的干扰力表达式为：

 $e\left( t \right) = {x_i}\left( t \right){\tau _i}\left( t \right)。$ (2)

 $\dot x\left( t \right) = x\left( t \right) + {\tau _i}\left( t \right) + e\left( t \right)/m 。$ (3)

 $X = \left\{ {{{\dot x}_1}\left( t \right),{{\dot x}_2}\left( t \right), \cdots ,{{\dot x}_n}\left( t \right)} \right\} 。$ (4)
1.2 船舶拥堵水域通行能力的影响因素

 $C = {\rho _{\max }}LWX = \left[ {\frac{1}{{rs}}} \right]LWX 。$ (5)

 ${v_i} = \left\{ {\begin{array}{*{20}{c}} {v\left[ {m + \displaystyle\frac{{{\rho _{\max }}}}{\rho }} \right],{\rho _{\min }} \leqslant \rho < \displaystyle\frac{{1 - m}}{m}{\rho _{\max }}}，\\ {\displaystyle\frac{1}{4}mv\displaystyle\frac{{{\rho _{\max }}}}{\rho },\displaystyle\frac{{1 - m}}{m}{\rho _{\max }} \leqslant \rho \leqslant \displaystyle\frac{1}{2}{\rho _{\max }}}，\\ {mv\left( {1 - \displaystyle\frac{\rho }{{{\rho _{\max }}}}} \right),\displaystyle\frac{1}{2}{\rho _{\max }} < \rho \leqslant {\rho _{\max }}}。\end{array}} \right.$ (6)

 $\varphi = \alpha n\displaystyle\frac{{\rho {v_i}LW}}{{4LW}} 。$ (7)

1.3 基于长短时记忆网络的通行能力预测

 ${i_t} = \sigma \left( {W_x^i{x_t} + W_h^i{h_{t - 1}} + W_c^i{c_{t - 1}} + {b_i}} \right)，$ (8)

 ${f_t} = \sigma \left( {W_x^f{x_t} + W_h^f{h_{t - 1}} + W_c^f{c_{t - 1}} + {b_f}} \right) ，$ (9)

 ${c_t} = {f_t}{c_{t - 1}} + {i_t} {\mathrm{tan}}h \left( {W_x^c{x_t} + W_h^c{h_{t - 1}} + {b_c}} \right)，$ (10)

 ${o_t} = \sigma \left( {W_x^o{x_t} + W_h^o{h_{t - 1}} + W_c^o{c_t} + {b_o}} \right)，$ (11)

 ${h_t} = {o_t} {\mathrm{tan}}h \left( {{c_t}} \right)。$ (12)

2 实例分析

 图 1 研究区域海域图 Fig. 1 Sea area map of the study area

 图 2 船舶航速以及船间距变化 Fig. 2 Changes in ship speed and spacing

 图 3 不同水域的船舶密度 Fig. 3 Ship density in different waters

 图 4 船舶通行能力预测结果 Fig. 4 Prediction results of ship traffic capacity

 图 5 船舶通航量变化 Fig. 5 Changes in ship navigation volume
3 结　语

 [1] 杨琪森, 王慎执, 桑金楠, 等. 复杂开放水域下智能船舶路径规划与避障方法[J]. 计算机集成制造系统, 2022, 28(7): 2030-2040. YANG Qisen, WANG Shenzhi, SANG Jinnan, et al. Path planning and real-time obstacle avoidance methods of intelligent ships in complex open water environment[J]. Computer Integrated Manufacturing Systems, 2022, 28(7): 2030-2040. [2] 李光泽, 俞万能, 廖卫强, 等. 基于动态窗口法的近海水域船舶避障算法研究[J]. 中国舰船研究, 2024, 19(1): 230-237. LI Guangze, YU Wanneng, LIAO Weiqiang, et al. Obstacle avoidance algorithm for ships in complex waters based on dynamic window approach[J]. Chinese Journal of Ship Research, 2024, 19(1): 230-237. [3] 高飞德, 曹宇皓, 张鹏, 等. 基于扇形网格叠加计算的通航分道水域船舶领域[J]. 大连海事大学学报, 2023, 49(4): 88-94. GAO Feide, CAO Yuhao, ZHANG Peng, et al. Ship domain in traffic lane waters based on sector grid superposition calculatio[J]. Journal of Dalian Maritime University, 2023, 49(4): 88-94. [4] 王伟, 余志成, 张泰山, 等. 船舶交通量三阶段法预测模型及其应用[J]. 上海海事大学学报, 2021, 42(3): 23-28+35. WANG Wei, YU Zhicheng, ZHANG Taishan, et al. Three-stage prediction model of ship traffic volume and its application[J]. Journal of Shanghai Maritime University, 2021, 42(3): 23-28+35. [5] 黄金, 邓强, 许辰, 等. 限制水域船舶水动力干扰快速计算方法[J]. 哈尔滨工程大学学报, 2021, 42(5): 601-609. HUANG Jin, DENG Qiang, XU Chen, et al. Fast calculation method of ship-ship hydrodynamic interaction in restricted waters[J]. Journal of Harbin Engineering University, 2021, 42(5): 601-609.