基于NSGA-Ⅲ的UUV集群打击任务分配模型

吴思聪; 吴曦

doi:10.11993/j.issn.2096-3920.2023-0023

基于NSGA-Ⅲ的UUV集群打击任务分配模型

doi: 10.11993/j.issn.2096-3920.2023-0023

吴思聪^{1, 2,},
吴曦¹

1.
国防大学联合作战学院, 北京, 100091
2.
国防大学研究生院, 北京, 100091

详细信息

作者简介:
吴思聪(1995-), 男, 在读硕士, 主要研究方向为联合作战体系仿真

中图分类号: TJ67; U674.941; E843
计量
- 文章访问数: 292
- HTML全文浏览量: 211
- PDF下载量: 67
- 被引次数: 0
出版历程
- 收稿日期: 2023-03-09
- 修回日期: 2023-05-09
- 录用日期: 2023-05-11
- 网络出版日期: 2023-05-25

UUV Cluster Strike Task Allocation Model Based on NSGA-Ⅲ

WU Sicong^{1, 2
,},
WU Xi¹

1.
School of Joint Operation, National Defense University, Beijing, 100091
2.
Graduate College, National Defense University, Beijing, 100091

摘要

摘要: 无人水下航行器(UUV)集群将成为未来水下作战的重要力量, UUV集群的打击任务分配问题是UUV运用过程中的关键问题之一, 可以看作为一个武器-目标分配问题, 也是一个多约束多目标优化问题。因此, 考虑UUV对敌舰探测概率、载弹量、弹药成本、杀伤概率和目标价值, 以及UUV对鱼雷的拦截概率等因素, 建立打击收益和弹药消耗成本2个目标函数, 构建了UUV集群打击任务分配模型。引入多目标优化算法——第3代非支配排序遗传算法(NSGA-Ⅲ)对该模型进行求解, 分析了编码策略、约束处理方法以及NSGA-Ⅲ的流程和关键步骤。仿真结果表明，与NSGA-Ⅱ、自适应形状估计多目标进化算法(AGE-MOEA)相比, 该算法在运行时间和反世代距离2项指标上表现更好, 能够更好地为决策提供支撑。
- 无人水下航行器 /
- 武器-目标分配 /
- 任务分配 /
- 多目标优化 /
- 非支配排序遗传算法
Abstract: The unmanned undersea vehicle(UUV) cluster will become important in future underwater operations. The task allocation of the UUV cluster is a key problem in the application of the UUV cluster, and it can be regarded as a weapon–target assignment problem and a multiconstraint and multiobjective optimization problem. Therefore, considering factors such as the detection probability, ammunition load, ammunition cost, kill probability, target value of enemy ships, and interception probabilities of torpedoes around the UUV, two objective functions for the attack income and ammunition consumption cost are established, and a UUV cluster strike task allocation model is constructed. A multiobjective optimization algorithm, i.e., the non-dominated sorting genetic algorithm-III(NSGA-III), is introduced to solve the model. The coding strategy, constraint processing method, process, and key steps of NSGA-III are analyzed. Simulation results indicate that this algorithm outperforms NSGA-II and AGE-multi-objective evolutionary algorithms(AGE-MOEA) in terms of the running time and inverted generational distance and thus can support effective decision making.
- unmanned undersea vehicle /
- weapon-target assignment /
- task allocation /
- multi-objective optimization /
- non-dominated sorting genetic algorithm

HTML全文

图 1 NSGA-Ⅲ算法流程

Figure 1. Flowchart of NSGA-Ⅲ

下载: 全尺寸图片幻灯片

图 2 UUV打击任务分配pareto前沿

Figure 2. Pareto frontier of UUV strike task allocation

下载: 全尺寸图片幻灯片

图 3 3种算法IGD指标对比

Figure 3. Comparison of IGD indicators among three algorithms

下载: 全尺寸图片幻灯片

表 1 pareto前沿对应函数值

Table 1. Pareto Frontier corresponding function value

序号	$ {f_1} $	$ {f_2} $
1	−3.113 24	16 800
2	−3.083 38	16 200
3	−3.053 37	15 600
4	−3.019 74	15 000
5	−2.975 77	14 200

下载: 导出CSV

表 2 平均总运行时间

Table 2. Average total running time

算法名称	种群规模	迭代次数	时间/s
NSGA-Ⅱ	50	5 000	0.249 8
	50	10 000	0.477 4
	100	5 000	0.186 3
	100	10 000	0.384 5
NSGA-Ⅲ	50	5 000	0.237 9
	50	10 000	0.469 0
	100	5 000	0.182 2
	100	10 000	0.377 2
AGE-MOEA	50	5 000	0.318 0
	50	10 000	0.479 4
	100	5 000	0.272 0
	100	10 000	0.735 8

下载: 导出CSV

参考文献(22)

[1]	吴志飞, 吴迪. 未来水下作战的发展趋势及启示[J]. 海军工程大学学报(综合版), 2020, 17(4): 21-24. doi: 10.13678/j.cnki.issn1674-5531.2020.04.006 Wu Zhifei, Wu Di. Development trend of future underwater warfare and its enlightenment[J]. Jouranal of Naval University of Engineering, 2020, 17(4): 21-24. doi: 10.13678/j.cnki.issn1674-5531.2020.04.006
[2]	朱新华, 左社强, 潘凯星, 等. 美军深海战场建设发展及启示[J]. 数字海洋与水下攻防, 2022, 5(3): 196-201. doi: 10.19838/j.issn.2096-5753.2022.03.002 Zhu Xinhua, Zuo Sheqiang, Pan Kaixing, et al. Development and enlightenment of U.S. deep-sea battlefield construction[J]. Digital Ocean & Underwater Warfare, 2022, 5(3): 196-201. doi: 10.19838/j.issn.2096-5753.2022.03.002
[3]	王骏. 多UCAV对地打击协同任务分配方法[D]. 长沙: 国防科技大学, 2019.
[4]	Ke Y, Wu R, Guo X, et al. Research on multi-objective task assignment scheme based on group isomorphism UUV[C]//2021 IEEE 7th International Conference on Control Science and Systems Engineering(ICCSSE). Qi- ngdao, China: IEEE, 2021: 153-158.
[5]	范学满, 薛昌友, 张会. 基于多种群遗传算法的多UUV任务分配方法[J]. 水下无人系统学报, 2022, 30(5): 621-630. doi: 10.11993/j.issn.2096-3920.202107001 Fan Xueman, Xue Changyou, Zhang Hui. Task assignment method for multiple UUVs based on multi-population genetic algorithm[J]. Journal of Unmanned Undersea Systems, 2022, 30(5): 621-630. doi: 10.11993/j.issn.2096-3920.202107001
[6]	魏娜, 刘明雍, 张帅, 等. 基于协同对抗的水下博弈策略优化[J]. 西北工业大学学报, 2019, 37(1): 63-69. doi: 10.3969/j.issn.1000-2758.2019.01.010 Wei Na, Liu Mingyong, Zhang Shuai, et al. Optimizing underwater game strategy based on cooperative confrontation[J]. Journal of Northwestern Polytechnical University, 2019, 37(1): 63-69. doi: 10.3969/j.issn.1000-2758.2019.01.010
[7]	马硕, 马亚平. 基于分层聚类拍卖的集群UUV多目标分配方法[J]. 舰船科学技术, 2019, 41(9): 70-75. doi: 10.3404/j.issn.1672-7649.2019.05.014 Ma Shuo, Ma Yaping. A hierarchical clustering auction approach for UUVs multi-objects allocation[J]. Ship Science and Technology, 2019, 41(9): 70-75. doi: 10.3404/j.issn.1672-7649.2019.05.014
[8]	Zhou Z, Shen G, Niu W, et al. A task assignment strategy for multi-AUV collaborative hunting problem[C]//Oceans 2022. Hampton Roads, VA, USA: IEEE, 2022: 1-6.
[9]	Zhu D, Qu Y, Yang S X. Multi-AUV SOM task allocation algorithm considering initial orientation and ocean current environment[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(3): 330-341.
[10]	刘西, 李贤, 陈伟, 等. 基于NSGA-Ⅲ算法的多目标分配方法研究[J]. 空天防御, 2021, 4(1): 109-114. doi: 10.3969/j.issn.2096-4641.2021.01.018 Liu Xi, Li Xian, Chen Wei, et al. Research on multi-objective assignment method based on NSGA-Ⅲ algorithm[J]. Air & Space Defense, 2021, 4(1): 109-114. doi: 10.3969/j.issn.2096-4641.2021.01.018
[11]	周晶, 赵晓哲, 党延忠, 等. 基于分布式NSGA-III算法的无人机群高维多目标任务分配方法[J/OL]. 系统工程与电子技术: 1-11[2023-05-07]. http://kns.cnki.net/kcms/detail/11.2422.TN.20210204.1034.005.html.
[12]	张晓杰, 郑纪彬, 苏涛, 等. 无人机集群协同搜索跟踪任务规划方法[J]. 雷达科学与技术, 2022, 20(5): 480-491. Zhang Xiaojie, Zheng Jibin, Su Tao, et al. Mission planning for cooperative search-track of UAV swarms[J]. Radar Science and Technology, 2022, 20(5): 480-491.
[13]	Guo B, Wang S, Ding Y, et al. Concurrent order dispatch for instant delivery with time-constrained actor-critic reinforcement learning[C]//2021 IEEE Real-Time Systems Symposium(RTSS). Dortmund, DE: IEEE, 2021: 176-187.
[14]	Deb K, Jain H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: Solving problems with box constraints[J]. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 577-601. doi: 10.1109/TEVC.2013.2281535
[15]	王楠, 戴江斌. 基于INSGA-Ⅱ算法的武器-目标分配方法[J]. 云南大学学报(自然科学版), 2022, 44(6): 1155-1165. Wang Nan, Dai Jiangbin. Weapon-target assignment method based on INSGA-Ⅱ[J]. Joural of Yunnan University: Natural Sciences Edition, 2022, 44(6): 1155-1165.
[16]	Jain H, Deb K. An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, part II: Handling constraints and extending to an adaptive approach[J]. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 602-622. doi: 10.1109/TEVC.2013.2281534
[17]	Srinivas N, Deb K. Muiltiobjective optimization using nondominated sorting in genetic algorithms[J]. Evolutionary Computation, 1994, 2(3): 221-248. doi: 10.1162/evco.1994.2.3.221
[18]	Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197. doi: 10.1109/4235.996017
[19]	Tian Y, Xiang X, Zhang X, et al. Sampling reference points on the pareto fronts of benchmark multi-objective optimization problems[C]//2018 IEEE Congress on Evolu-tionary Computation(CEC). Rio de Janeiro: IEEE, 2018: 1-6.
[20]	王雪峰. 用于函数优化问题的实数编码遗传算法的改进及并行化实现[D]. 保定: 河北大学, 2019.
[21]	Tian Y, Cheng R, Zhang X, et al. PlatEMO: A MATLAB platform for evolutionary multi-objective optimization [Educational Forum][J]. IEEE Computational Intelligence Magazine, 2017, 12(4): 73-87. doi: 10.1109/MCI.2017.2742868
[22]	反世代距离评价指标IGD-腾讯云开发者社区-腾讯云[EB/OL]. (2021-05-21)[2022-12-30]. https://cloud.tencent.com/developer/article/1827360.