基于GA-BP的浮标折线拦截阵布阵规划

doi:10.12305/j.issn.1001-506X.2025.12.04

摘要/Abstract

摘要：

传统的声纳浮标折线拦截阵存在搜索概率低、搜索效能低的问题，基于此，使用遗传算法（genetic algorithm，GA）优化的反向传播（back propagation，BP）神经网络对传统的浮标折线拦截阵进行优化。针对BP神经网络的固有问题进行改进：一是用动态调整的学习率来解决固定学习率的问题，并对其损失函数进行改进；二是使用GA优化BP神经网络，解决BP神经网络初始权重和阈值随机的问题。将所提方法与传统GA优化浮标折线阵及传统浮标折线阵方法进行对比。仿真结果表明，所提方法不但提高了搜索概率，同时规划的浮标折线拦截布阵时间大大缩减，即基于GA-BP的浮标折线拦截阵布阵规划方法可有效提高搜潜效能。

关键词: 浮标布阵, 遗传算法, 神经网络, 搜潜概率

Abstract:

Traditional sonobuoy polyline interception arrays suffer from low search probability and low search efficiency. Based on this, a back propagation (BP) neural network optimized by genetic algorithm (GA) is employed to enhance the performance of conventional buoy polyline interception arrays. Improving the inherent problems of BP neural network, firstly, using dynamically adjusted learning rate to solve the problem of fixed learning rate, and improving its loss function. The second is to use GA to optimize BP neural network and solve the problem of initial weight and random threshold in BP neural network. The proposed method is compared with the traditional GA optimized buoy polyline array and the traditional buoy polyline array method. The simulation results show that the proposed method not only improves the search probability, but also greatly reduces the planned buoy polyline interception array deployment time. Therefore, the GA-BP based buoy polyline interception array deployment planning method can effectively improve the submarine search efficiency.

Key words: buoy deployment, genetic algorithm, neural network, submarine search probability

中图分类号:

TN 06

吴芳, 高青伟, 吴铭, 安舒. 基于GA-BP的浮标折线拦截阵布阵规划[J]. 系统工程与电子技术, 2025, 47(12): 4034-4039.

Fang WU, Qingwei GAO, Ming WU, Shu AN. Deployment planning buoy polyline interception array based on GA-BP[J]. Systems Engineering and Electronics, 2025, 47(12): 4034-4039.

图/表 10

图1

图2

图3

图4

表1

表2

图5

图6

表3

表4

参考文献 30

1	唐晨, 孙秀文, 王旅. 反潜巡逻机对潜应召搜索声呐浮标布放阵位优化问题研究[J]. 舰船电子工程, 2022, 42 (2): 62- 65.
	TANG C, SUN X W, WANG L. Research on optimization position of sonobuoy in anti-submarine call-search by anti-submarine patrol aircraft[J]. Ship Electronic Engineering, 2022, 42 (2): 62- 65.
2	QIN R T, ZHAO Y, CAI Q Y, et al. A multistatic buoy placement optimization algorithm[C]//Proc. of the 6th International Workshop on Advanced Algorithms and Control Engineering, 2022: 739−744.
3	NIU Y L, ZHANG K, MU Y, et al. The array optimization model for distributed antisubmarine of non-cluster USV based on coverage[C]//Proc. of the International Conference on Autonomous Unmanned Systems, 2022: 2402−2412.
4	SUN N. Autonomous mobile sonobuoy and its combat application prospect[C]//Proc. of the IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, 2023: 268−272.
5	MA Y, MAO Z Y, QIN J, et al. A quick deployment method for sonar buoy detection under the overview situation of underwater cluster targets[J]. IEEE Access, 2019, 8, 11- 25.
6	SUN Y Q, GAI J F, LIU H Y. An intelligence target situation assessment method for cooperative search by ASW patrol aircraft[C]//Proc. of the 14th International Conference on Machine Learning and Computing, 2022: 278−283.
7	王磊, 吴福初, 陈钰宁, 等. 基于声纳浮标的反潜直升机应召搜潜仿真研究[J]. 指挥控制与仿真, 2010, 32 (2): 84- 88.
	WANG L, WU F C, CHEN Y N, et al. Simulative research of on-call antisubmarine of ASW helicopter using sonar buoy[J]. Command Control & Simulation, 2010, 32 (2): 84- 88.
8	LEE C Y, JUNG H J, OH E S, et al. Simulated target device for anti-submarine training[P]. Korea: KR20130099977, 2015.
9	BEN Y R. Anti-submarine warfare search models[D]. Monterey, California: Naval Postgraduate School, 2016.
10	LEE J. Deploying autonomous sonobuoys optimally on a linear array via assignment problem[J]. International Journal of Advanced Manufacturing Technology, 2018, 99, 2181- 2192. doi: 10.1007/s00170-018-2348-4
11	胡平, 顾雪峰, 刘凯, 等. 国外航空反潜装备现状及发展趋势[J]. 舰船电子工程, 2022, 42 (9): 10- 12，86.
	HU P, GU X F, LIU K, et al. Current situation and development trend of foreign aviation anti-submarine equipment[J]. Ship Electronic Engineering, 2022, 42 (9): 10- 12，86.
12	IQBAL K, ZHANG M H, PIAO S C, et al. Evolution of sonobuoy through history & its applications: a survey[C]//Proc. of the 17th International Bhurban Conference on Applied Sciences and Technology, 2020: 543−554.
13	DAVIS L E, ENGERMAN S L. Naval blockades in peace and war[M]. New York: Cambridge University Press, 2006: 321−382.
14	VERBURGT P W. Introduction to the theme airborne anti-submarine warfare[J]. U. S. Navy Journal of Underwater Acoustics, 2014, 62 (3): 2074- 2085.
15	HEW P, YIAP N. Optimally randomized patrolling of chokepoints for theatre antisubmarine warfare[J]. Military Operations Research, 2018, 23 (1): 49- 56.
16	TAYLOR C M, MASKELL S, RALPH J F. Using hybrid multiobjective machine learning to optimise sonobuoy placement patterns[J]. IET Radar, Sonar & Navigation, 2023, 17(3): 374−387.
17	QIN R T, ZHAO Y N, CAI Q, et al. A multistatic buoy placement optimization algorithm[C]//Proc. of the 6th International Workshop on Advanced Algorithms and Control Engineering, 2022: 739−744.
18	樊振凯. 固定翼飞机声呐浮标布阵优化研究[J]. 西北工业大学学报, 2017, 35 (9): 82- 87.
	FAN Z K. Study on sonar buoy arraying optimization for fixed wing aircraft[J]. Journal of Northwestern Polytechnical University, 2017, 35 (9): 82- 87.
19	闫明松, 杨曦中, 姚子羽, 等. 基于神经网络的最优浮标布阵智能决策方法[J]. 航空电子技术, 2018, 49 (3): 12- 18.
	YAN M S, YANG X Z, YAO Z Y, et al. An optimal sonobuoy array intelligent decision-making method based on neural networks[J]. Avionics Technology, 2018, 49 (3): 12- 18.
20	湛文静, 李泳科. 基于改进遗传算法的路径规划问题相关研究综述[J]. 计算机与数字工程, 2023, 51 (7): 1544- 1550.
	ZHAN W J, LI Y. Summary of related research on path planning based on improved genetic algorithm[J]. Computer & Digital Engineering, 2023, 51 (7): 1544- 1550.
21	李辰, 高超仪. 基于平面图形的典型浮标规划算法[J]. 航空电子技术, 2022, 53 (2): 47- 52.
	LI C, GAO C Y. Typical buoy array algorithm based on the plane figure[J]. Avionics Technology, 2022, 53 (2): 47- 52.
22	敬玉平, 巩健文, 范赵鹏, 等. 应召反潜条件下浮标阵型规划研究[J]. 火力与指挥控制, 2020, 45 (3): 59- 63.
	JING Y P, GONG J W, FAN Z P, et al. Research on sonobuoy array in call searching submarine[J]. Fire Control & Command Control, 2020, 45 (3): 59- 63.
23	曹越, 高超仪, 李建波. 基于TOPSIS法的浮标拦截布阵方案效能评估研究[J]. 航空电子技术, 2021, 52 (1): 42- 47.
	CAO Y, GAO C Y, LI J B. Research on the effective reconnaissance of buoy interception array based on TOPSIS[J]. Avionics Technology, 2021, 52 (1): 42- 47.
24	张丹, 时光, 余义德, 等. 基于插值法的浮标优化布放[J]. 无线电工程, 2019, 49 (3): 215- 218.
	ZHANG D, SHI G, YU Y D, et al. Optimal placement of sonobuoy based on interpolation algorithm[J]. Radio Engineering, 2019, 49 (3): 215- 218.
25	MCCULLOCH W S, PITTS W H. A logical calculus of the ideas immanent in nervous activity[J]. The Bulletin of Mathematical Biophysics, 1943, 5, 115- 133. doi: 10.1007/BF02478259
26	CHU Y D, FEI J T, HOU S X. Adaptive global sliding-mode control for dynamic systems using double hidden layer recurrent neural network structure[J]. IEEE Trans. on Neural Networks and Learning Systems, 2020, 31 (4): 1297- 1309. doi: 10.1109/TNNLS.2019.2919676
27	RAFI S H, MASOOD N A, DEEBA S R. An effective short-term load forecasting methodology using convolutional long short term memory network[C]//Proc. of the 11th International Conference on Electrical and Computer Engineering, 2020: 278−281.
28	SINHA T, VERMA B. A non-iterative radial basis function based quick convolutional neural network[C]//Proc. of the International Joint Conference on Neural Networks, 2020.
29	ZHANG Z H. Heterogeneous graph neural network based on hierarchical attention mechanism[C]//Proc. of the IEEE International Conference on Electrical, Automation and Computer Engineering, 2023: 485−489.
30	劳伦斯·D·斯通. 最优搜索理论[M]. 吴晓峰, 译. 北京: 海潮出版社, 1990.
	STONE D L. Theory of optimal search[M]. WU X F, trans. Beijing: Haichao Press, 1990.

参数名	参数值	参数名	参数值
学习率	自适应	损失函数	$ E({\boldsymbol{\theta}}(x,y)) $
训练次数	200	输入批量	16

参数名	参数值	参数名	参数值
种群数量	50	变异率	$ P_{ {{\mathrm{mutate}} }} $
交叉率	$ P_{ {{\mathrm{cross}} }} $	最大迭代次数	200

算法	浮标数量/枚	规划时间/s	搜索概率/%
传统布阵	13	246	61.6
遗传算法	9	183.3	78.9
本文算法	9	1.788	79.8

仿真	规划时间/s	搜潜概率/%
仿真1	1.873	79.6
仿真2	1.739	75.9
仿真3	1.692	77.1
仿真4	1.806	77.2
仿真5	1.838	78.8
仿真6	1.786	76.3
仿真7	1.677	76.8
仿真8	1.814	79.8
仿真9	1.792	79.6
仿真10	1.866	78.4
平均值	1.7883	77.95

[1]	黄庚, 李旦, 张建秋. 时变二次规划的鲁棒归零神经网络求解模型[J]. 系统工程与电子技术, 2025, 47(9): 2775-2784.
[2]	石文强, 雷迎科, 金虎, 滕飞. 基于自适应小波分解和轻量化网络架构的特定辐射源识别算法[J]. 系统工程与电子技术, 2025, 47(9): 2785-2796.
[3]	蒋明煜, 张顺生, 肖思瑶. 面向轻量级交叉注意力卷积网络的SAR目标识别[J]. 系统工程与电子技术, 2025, 47(9): 2853-2861.
[4]	张国庆, 徐轶晖, 李纪强, 张显库, 邱斌. 基于异步搜寻制导的机/船协同事件触发控制[J]. 系统工程与电子技术, 2025, 47(9): 3058-3065.
[5]	陈文洁, 张浦, 史高翔, 刘林, 刘烜. 基于余弦校验关系的卷积神经网络LDPC码盲识别[J]. 系统工程与电子技术, 2025, 47(9): 3117-3125.
[6]	王奇, 潘宇宁, 郑峻峰, 王力. 考虑力学形变的相控阵天线波束控制实现策略[J]. 系统工程与电子技术, 2025, 47(8): 2421-2428.
[7]	张梦泽, 田黎育. 基于高分辨谱估计的雷达目标分类方法[J]. 系统工程与电子技术, 2025, 47(7): 2146-2153.
[8]	魏波, 胡财富, 任芮彬. 面向不平衡数据的二阶段网络入侵检测新方法[J]. 系统工程与电子技术, 2025, 47(6): 2065-2075.
[9]	付留芳, 许林周, 周明, 董晓明, 寇祝. 基于二次优化的T-Rⁿ型多基地声纳部署方法[J]. 系统工程与电子技术, 2025, 47(5): 1600-1608.
[10]	段阿敏, 张朝辉. 基于二次分解的混合神经网络蜂窝流量预测[J]. 系统工程与电子技术, 2025, 47(5): 1687-1697.
[11]	孙正阳, 杜晔. 基于改进萤火虫算法的卫星网络路由优化方法[J]. 系统工程与电子技术, 2025, 47(4): 1346-1354.
[12]	陈凯, 张德平. 基于图神经网络的导弹时序规划方法[J]. 系统工程与电子技术, 2025, 47(3): 862-870.
[13]	郭鹏飞, 靳锴, 陈琪锋, 魏才盛. 基于噪声元学习的卫星遥测信号异常检测方法[J]. 系统工程与电子技术, 2025, 47(2): 352-359.
[14]	吴浩南, 韩维, 潘子双, 郭放, 苏析超. 基于多层编码遗传算法的舰载机群兵力行动规划方法[J]. 系统工程与电子技术, 2025, 47(2): 555-567.
[15]	祁新宇, 张智, 尚晓兵, 张艺琼, 姜立超, 周悦欣. 基于多项式混沌展开的船舶避碰鲁棒轨迹规划[J]. 系统工程与电子技术, 2025, 47(2): 621-632.