A Suicide Unmanned Vessel Defense Strategy Based on Sea and Air Unmanned Cluster
-
摘要: 近期俄乌战场上无人艇的运用被高度关注, 针对反无人自杀艇袭扰的考虑, 文中通过“无人对无人”的思想, 提出一种以无人艇、无人机等低成本平台为基础, 具备“协同赋能、自主管控、敏捷响应”的新型反水面无人自杀艇袭扰的概念。统筹运用多个轻量化、具备简单交互和自主决策能力的无人艇、无人机等无人平台, 通过分析典型水面无人自杀艇能力, 研究海空协同任务分配与规划以及跨平台协同侦察定位等关键技术, 构建新型侦察防御无人系统, 不仅能够全天候实时覆盖重点防御区域, 针对可疑入侵目标做到敏捷确认、即察即打, 还能够拓展高价值目标的防御纵深, 构建多层防御带, 应对无人自杀艇集群的“狼群”式袭击。Abstract: Recently, the use of unmanned surface vessel on the Russia-Ukraine conflict has received high attention, with consideration given to anti unmanned suicide vessel attacks, this paper introduces a new concept of countering unmanned suicide vessel harassment against surface targets, based on low-cost platforms such as unmanned surface vessel and unmanned aerial vehicle, employing the idea of "unmanned versus unmanned". It advocates for the coordinated use of multiple lightweight unmanned platforms with simple interaction and autonomous decision-making capabilities. By analyzing the typical capabilities of unmanned suicide vessels, it investigates key technologies such as sea-air coordinated task assignment and planning, cross-platform collaborative reconnaissance positioning, to construct a new type of reconnaissance and defense unmanned system. This system not only provides all-weather quasi-real-time coverage of key defense areas but also achieves agile confirmation and immediate response to invading suspicious targets. Furthermore, it expands the defense depth of high-value targets by establishing multiple layers of defense against clusters of unmanned suicide vessels in a "wolf pack" style attack.
-
Key words:
- Unmanned suicide vessel /
- Unmanned cluster /
- Defense
-
表 1 典型水面无人自杀艇能力分析表
Table 1. Analysis of the capability of typical unmanned suicide vessel on water surface
无人艇型号 半潜式 MAGURA -V5 SEABABY 艇长(米) 5.5 5.5 -- 排水量(千克) 1 000 -- -- 作战半径(千米) 400 -- -- 最大航程(千米) 800 830 -- 续航时间(小时) 60 60 -- 最大航速(节) 42 40 -- 通信手段 星链 星链 星链 控制方式 可自主航行 可自主航行 可自主航行 传感器 光电、红外 光电、红外 光电、红外 有效载荷(千克) 200 320 800 表 2 典型“扫描鹰”无人侦察机性能参数
Table 2. Performance parameters of the “Scanning Eagel” unmanned reconnaissance aircraft
长(m) 1.2 翼展(m) 3.1 空重(kg) 12 最大起飞重量(kg) 18 任务载荷(kg) 3.2 巡航速度(km/h) 90 最大飞行速度(km/h) 120 最大飞行高度(m) 4 800 表 3 基于目标分配算法的作战资源分配部署的流程
Table 3. The process of deployment of combat resource allocation based on the target allocation algorithm
输入: 打击链中各要素的编码方式和每个种群遗传算法的运算参数。
输出: 输出最优个体。
1. 初始化: 确定打击链中各要素的编码方式和每个种群遗传算法的运算参数, 其中包括: 交叉概率$ {p_c} $、变异概率$ {p_m} $、遗传运算的终止进化代数T以及种群规模M等。
2. 生成: 通过匈牙利算法生成p个精英染色体, 并随机生成n-p个个体, 共同构成初始打击链种群$ {X_i}(0) = \{ {X^1}, {X^2}, \cdots, {X^n}\} $, $ {X^k}(k = 1, 2, \cdots, $$ M) $表示为种群中的第k个体。
3. 计算: 计算第t代种群$ {X_i}(t) $中每个个体的适应度值$ f({X^k}) $, 选出各个种群中适应度值最好的染色体, 判断是否在第t次迭代中搜索到了最优个体, 若找到, 则结束算法并输出最优个体, 否则继续步骤4。
4. 遗传操作: 对每个种群进行遗传操作, 经过选择、交叉和变异操作得到新一代的种群$ {X_i}(t + 1) $。
5. 算法终止准则判断: 判断算法是否满足终止准则, 若不满足, 则令$ t = t + 1 $, 并转到步骤3; 否则结束算法, 输出最优个体。表 4 第1波次打击处置统计表
Table 4. Table for the first batch of strike damage
目标ID 是否击毁 距离防御中心距离(m) 0001 击毁 10 353.2 0002 未击毁 / 0003 击毁 10 195.0 0004 击毁 11 459.5 表 5 第2波次打击处置统计表
Table 5. Table for the second batch of strike damage
目标ID 是否击毁 距离防御中心距离(m) 0002 击毁 6 623.4 0005 击毁 7 284.6 0006 击毁 10 777.7 -
[1] 李楠, 陈练, 庞衍鹏, 等. 无人艇装备技术发展与作战运用探析[J]. 舰船科学技术, 2019, 41(23): 6. doi: CNKI:SUN:JCKX.0.2019-23-008Li Nan, Chen Lian, Pang Yanpeng, et al. Analysis of the development and operational application of unmanned boat equipment technology[J]. Ship Science and Technology, 2019, 41(23): 6. doi: CNKI:SUN:JCKX.0.2019-23-008 [2] 李伟, 徐轩彬, 郑振宇. 世界无人艇技术研发动态与作战使用分析[J]. 舰船电子工程, 2022, 42(4): 4. doi: 10.3969/j.issn.1672-9730.2022.04.002Li Wei, Xu Xuanbin, Zheng Zhenyu. Research and development dynamics and operational use analysis of world unmanned boat technology[J]. Ship Electronic Engineering, 2022, 42(4): 4. doi: 10.3969/j.issn.1672-9730.2022.04.002 [3] 佟海鹏, 徐海刚, 刘兆平. 海战场环境下舰载巡飞弹技术分析[J]. 飞航导弹, 2012(1): 4.Tong Haipeng, Xu Haigang, Liu Zhaoping. Technical Analysis of Shipborne Patrol Missiles in Marine Battlefield Environment[J]. Aviation Missile, 2012(1): 4. [4] 田呈培. 交通场景下的运动目标检测与跟踪的算法研究[D]. 杭州电子科技大学, 2016.Tian Chengpei. Algorithm research on motion target detection and tracking in traffic scenes [D]. Hangzhou University of Electronic Science and Technology, 2016. [5] Huang F, Lv X, Zhang L. Coarse-to-fine sparse self-attention for vehicle re-identification[J]. Knowl. Based Syst., 2023, 270: 110526. doi: 10.1016/j.knosys.2023.110526 [6] 高金玉. 多无人艇协同控制中的任务分配方法研究[D]. 哈尔滨工程大学, 2024.Gao Jinyu. Research on task allocation method in multi unmanned vehicle collaborative control [D]. Harbin Engineering University, 2024. [7] Wu J, Yu Y, Ma J, et al. Autonomous Cooperative Flocking for Heterogeneous Unmanned Aerial Vehicle Group[J]. IEEE Transactions on Vehicular Technology, 2021(70-12). [8] 姜燕, 王道波, 林飞, 等. 基于匈牙利融合遗传算法的多无人机不平衡目标分配[J]. 电光与控制, 2023, 30(5): 6-10. doi: 10.3969/j.issn.1671-637X.2023.05.002Jiang Yan, Wang Daobo, Lin Fei, et al. Unbalanced target allocation of multiple unmanned aerial vehicles based on hungarian fusion genetic algorithm[J]. Electro Optics and Control, 2023, 30(5): 6-10 doi: 10.3969/j.issn.1671-637X.2023.05.002 [9] 谷稳. 基于进化匈牙利算法的目标分配问题研究及应用[D]. 西安电子科技大学, 2024.Gu Wen. Research and application of target allocation problem based on evolutionary hungarian algorithm [D]. Xi'an University of Electronic Science and Technology, 2024. [10] 刘琨. 多无人艇协同搜索与围捕方法研究[D]. 哈尔滨工程大学, 2019.Liu Kun. Research on collaborative search and encirclement methods of multiple unmanned boats [D]. Harbin Engineering University, 2019 [11] 刘召庆, 张芳, 朱镭, 等. 巡飞弹目标定位精度分析[J]. 应用光学, 2022, 43(4): 7.Liu Zhaoqing, Zhang Fang, Zhu Lei, et al. Analysis of target positioning accuracy of patrol missiles[J]. Applied Optics, 2022, 43(4): 7. [12] 徐艺博, 于清华, 王炎娟, 等. 基于多源信息融合的巡飞弹对地目标识别与毁伤评估[J]. 系统仿真学报, 2024, 36(2): 511-521.Xu Yibo, Yu Qinghua, Wang Yanjuan, et al. Ground target recognition and damage assessment of cruise missiles based on multi-source information fusion[J]. Journal of System Simulation, 2024, 36(2): 511-521.