潜艇水下破损进水严重威胁其生命力，及时的决策响应至关重要。现有抗沉决策大多基于规则推理或案例匹配，因受限于规则库或案例库，对复杂动态工况的损伤应对能力明显不足。针对此问题，本文提出基于双重深度Q网络（Double Deep Q-Network，DDQN）的抗沉辅助决策方法。首先，通过破损进水机理构建多维状态空间，整合静力与动力抗沉措施并映射为离散化损管动作集合，创新设计考量生存能力核心要素的复合加权奖励函数；然后，结合随机经验回放与贪婪衰减探索机制，采用DDQN算法框架实现抗沉决策；最后，构建生命力评价指标，将所提方法与深度Q网络（Deep Q-Network，DQN）进行仿真对比。仿真结果表明，典型工况下DDQN抗沉决策使潜艇生命力指标更优，验证了方法的有效性和优越性。
Underwater damage and flooding of submarines pose a severe threat to their vitality, making timely decision-making responses crucial. Existing anti-sinking decision-making methods are mostly based on rule-based reasoning or case matching. However, limited by rule bases or case bases, their capability to respond to damage under complex dynamic operating conditions is significantly insufficient. To address this issue, this paper proposes an auxiliary anti-sinking decision-making method based on the Double Deep Q-Network (DDQN). First, a multi-dimensional state space is constructed based on the damage and flooding mechanism; static and dynamic anti-sinking measures are integrated and mapped into a discretized damage control action set; and a composite weighted reward function that takes into account the core elements of viability is innovatively designed. Second, by combining random experience replay and the epsilon-greedy exploration with decay mechanism, the DDQN algorithm framework is adopted to realize anti-sinking decision-making. Finally, vitality evaluation indicators are established, and a simulation comparison is conducted between the proposed method and the Deep Q-Network (DQN). The simulation results show that the DDQN-based anti-sinking decision-making yields better submarine vitality indicators under typical operating conditions, which verifies the effectiveness and superiority of the proposed method.
2026,48(7): 120-127 收稿日期：2025-7-31
DOI：10.3404/j.issn.1672-7649.2026.07.020
分类号：U66; TP391.9
作者简介：陈逸丰(2000-),男,硕士研究生,研究方向为潜艇损管辅助决策
参考文献：
[1] 孙玉山, 马陈飞, 张国成, 等. 潜艇抗沉性及抗沉辅助决策系统研究综述[J]. 舰船科学技术, 2019, 41(21): 1-4+14 SUN Y S, MA C F, ZHANG G C, et al. Research survey of submarine unsinkability and anti-sinking auxiliary decision system[J]. Ship Science and Technology, 2019, 41(21): 1-4+14
[2] 刘辉, 李志辉, 官东, 等. 潜艇高压气吹除主压载水舱应急挽回的运动规律和控制策略[J]. 海军工程大学学报, 2024, 36(1): 29-33 LIU H, LI Z H, GUAN D, et al. Emergency recovery motion law and control strategy of submarine high-pressure air blowing main ballast tank[J]. Journal of Naval University of Engineering, 2024, 36(1): 29-33
[3] GWINNER F, TOMITZA C, WINKELMANN A. Comparing expert systems and their explainability through similarity[J]. Decision Support Systems, 2024, 182: 114248
[4] SMITI A, ELOUEDI Z. Dynamic maintenance case base using knowledge discovery techniques for case based reasoning systems[J]. Theoretical Computer Science, 2020, 817: 24-32
[5] 李炳煌, 浦金云, 陈晓洪. 构建舰船抗沉智能决策支持系统[J]. 船海工程, 2006, 35(2): 81-83 LI B H, PU J Y, CHEN X H. Construction of anti-flooding intelligent decision support system[J]. Ship and Ocean Engineering, 2006, 35(2): 81-83
[6] 熊凯军, 浦金云, 蔡一轮, 等. 潜艇生命力决策辅助系统设计[J]. 船海工程, 2005, 34(1): 3-6 XIONG K J, PU J Y, CAI Y L, et al. Development of the decision-aided system of survivability for military submarines[J]. Ship and Ocean Engineering, 2005, 34(1): 3-6
[7] 赵占领. 基于专家系统的潜艇自主抗沉技术研究与仿真[D]. 哈尔滨: 哈尔滨工程大学, 2011.
[8] LI H, GUO J Y, YAZDI M, et al. Supportive emergency decision-making model towards sustainable development with fuzzy expert system[J]. Neural Computing and Applications, 2021, 33(22): 15619-15637
[9] ZHU L, REN K, PU J. Framework case decision reasoning method integrating multiple information[C]// 6th International Conference on Electromechanical Control Technology and Transportation, 2022, 12081: 1133–1142.
[10] LOUVROS P, STEFANIDIS F, BOULOUGOURIS E, et al. Machine learning and case-based reasoning for real-time onboard prediction of the survivability of ships[J]. Journal of Marine Science and Engineering, 2023, 11(5): 890
[11] 朱玲娜, 任凯, 浦金云. 基于案例推理的舰船管路破损应急决策模型研究[J]. 舰船电子工程, 2022, 42(9): 141-145 ZHU L N, REN K, PU J Y. Research on emergency decision-making model of ship pipeline damage based on case-based reasoning[J]. Ship Electronic Engineering, 2022, 42(9): 141-145
[12] 郝英泽, 林凡彩. 潜艇水下发生破损抗沉基本措施研究[C]// 2009航海技术理论研究论文集, 2009: 152-154. HAO Y Z, LIN F C. Research on basic measures for anti-sinking of submarines when damaged underwater[C]// Proceedings of 2009 Conference on Maritime Technology Theoretical Research, 2009: 152–154.
[13] 刘辉, 浦金云. 潜艇水下动力抗沉技术研究[J]. 舰船科学技术, 2008, 30(6): 66-69 LIU H, PU J Y. The research on underwater dynamic anti-sinking capability of submarine[J]. Ship Science and Technology, 2008, 30(6): 66-69
[14] 周宗和, 刘元, 李寒飞, 等. 艏部舱室破损下潜艇抗沉性研究[J]. 舰船科学技术, 2025, 47(6): 27-34 ZHOU Z H, LIU Y, LI H F, et al. Research of submarine anti-settling under the damage of bow cabin[J]. Ship Science and Technology, 2025, 47(6): 27-34
[15] 韩琨羽. 潜艇六自由度操纵运动预报及动力抗沉数值模拟[D]. 武汉: 武汉理工大学, 2022.
