面向故障传播风险抑制的舰船电子信息系统动态重构方法

doi:10.12305/j.issn.1001-506X.2026.07.16

摘要/Abstract

摘要：

针对新一代舰船电子信息系统动态重构策略忽视故障传播影响、可能导致系统可靠性下降的问题，提出一种融合故障传播风险评估的动态重构方法。首先，构建涵盖硬件资源、软件服务及其部署关系的系统形式化模型，提出量化系统可靠性的结构可靠性指标，以精准刻画系统部署关系对故障传播的影响。然后，在综合结构可靠性与负载均衡、迁移成本等关键运行指标的基础上，构建基于多目标协同优化重构模型，设计基于改进型价值分解网络的多智能体强化学习算法，实现故障传播抑制与系统重构效率的同步优化。实验结果表明，相较基准算法，所提方法能够有效抑制故障传播影响，可为重构舰船电子信息系统的可靠性保持与能力持续生成提供支撑。

关键词: 舰船电子信息系统, 动态重构策略, 故障传播模型, 多智能体强化学习

Abstract:

To address the issue that dynamic reconfiguration strategies for new-generation shipboard electronic information system overlook the impact of fault propagation, potentially leading to reduced system reliability, a dynamic reconfiguration method incorporating fault propagation risk assessment is proposed. Firstly, a formal system model is constructed encompassing hardware resources, software services, and their deployment relationships, and the structural reliability metrics is proposed to quantify system reliability, thereby accurately characterizing the impact of system deployment relationships on fault propagation. Then, based on key operational metrics such as comprehensive structural reliability, load balancing, and migration costs, a multi-objective collaborative optimization reconstruction model is constructed, and a multi-agent reinforcement learning algorithm based on an improved value decomposition network is designed to achieve synchronous optimization of fault propagation suppression and system reconstruction efficiency. The experimental results show that compared to the benchmark algorithm, the proposed method can effectively suppress the impact of fault propagation and provide support for the reliability maintenance and continuous generation of capabilities in the reconstruction of shipboard electronic information system.

Key words: shipboard electronic information system, dynamic reconfiguration strategy, fault propagation model, multi-agent reinforcement learning

中图分类号:

TP 302.7

杨京礼, 王莹, 高天宇, 方晓彤. 面向故障传播风险抑制的舰船电子信息系统动态重构方法[J]. 系统工程与电子技术, 2026, 48(7): 2307-2318.

Jingli YANG, Ying WANG, Tianyu GAO, Xiaotong FANG. Dynamic reconfiguration method for shipboard electronic information systems for fault propagation risk suppression[J]. Systems Engineering and Electronics, 2026, 48(7): 2307-2318.

图/表 14

图1

表1

图2

图3

图4

图5

图6

图7

表2

图8

图9

图10

图11

表3

参考文献 30

1	JIANG Z Y, ZHAO T D, WANG S H, et al. New model-based analysis method with multiple constraints for integrated modular avionics dynamic reconfiguration process[J]. Processes, 2020, 8 (5): 574. doi: 10.3390/pr8050574
2	KIM T. A practical cache partitioning method for multi-core processor on a commercial safety-critical partitioned RTOS[J]. IEEE Access, 2025, 13, 25505- 25519. doi: 10.1109/ACCESS.2025.3538540
3	STEWART D, LIU J J, COFER D, et al. AADL-based safety analysis using formal methods applied to aircraft digital systems[J]. Reliability Engineering & System Safety, 2021, 213, 107649.
4	YE Y G, LI H Q, WANG Q S, et al. Fault diagnosis of railway wheelsets: a review[J]. Measurement, 2025, 242, 116169. doi: 10.1016/j.measurement.2024.116169
5	YE M Y, YAN X A, HUA X, et al. MRCFN: a multi-sensor residual convolutional fusion network for intelligent fault diagnosis of bearings in noisy and small sample scenarios[J]. Expert Systems with Applications, 2025, 259, 125214. doi: 10.1016/j.eswa.2024.125214
6	KOUGIATSOS N, REPPA V. A distributed cyber-physical framework for sensor fault diagnosis of marine internal combustion engines[J]. IEEE Trans. on Control Systems Technology, 2024, 32 (5): 1718- 1729. doi: 10.1109/TCST.2024.3378992
7	SAMIR M, ELHATTAB M, ASSI C, et al. Optimizing age of information through aerial reconfigurable intelligent surfaces: a deep reinforcement learning approach[J]. IEEE Trans. on Vehicular Technology, 2021, 70 (4): 3978- 3983. doi: 10.1109/TVT.2021.3063953
8	SAFARI S, ANSARI M, KHDR H, et al. A survey of fault-tolerance techniques for embedded systems from the perspective of power, energy, and thermal issues[J]. IEEE Access, 2022, 10, 12229- 12251. doi: 10.1109/ACCESS.2022.3144217
9	WANG H C, NIU W S. A review on key technologies of the distributed integrated modular avionics system[J]. International Journal of Wireless Information Networks, 2018, 25 (3): 358- 369. doi: 10.1007/s10776-018-0412-5
10	PAUL S, CRUZ E, DUTTA A, et al. Formal verification of safety-critical aerospace systems[J]. IEEE Aerospace and Electronic Systems Magazine, 2023, 38 (5): 72- 88. doi: 10.1109/MAES.2023.3238378
11	ZHAO C, ZIO E, SHEN W M. Domain generalization for cross-domain fault diagnosis: an application-oriented perspective and a benchmark study[J]. Reliability Engineering & System Safety, 2024, 245, 109964.
12	LIU Y P, JIANG H K, YAO R H, et al. Counterfactual-augmented few-shot contrastive learning for machinery intelligent fault diagnosis with limited samples[J]. Mechanical Systems and Signal Processing, 2024, 216, 111507. doi: 10.1016/j.ymssp.2024.111507
13	HAN P J, HU W T, ZHAI Z J, et al. A model-based optimization method of ARINC 653 multicore partition scheduling[J]. Aerospace, 2024, 11 (11): 915. doi: 10.3390/aerospace11110915
14	PEIERRA R, BECKER L B, LISBOA C A. Optimization of task and message scheduling in IMA systems using a genetic algorithm with adaptive operators[J]. IEEE Trans. on Industrial Informatics, 2022, 18 (8): 5304- 5314.
15	MATEI I, PIOTROWSKI W, PEREZ A, et al. System resilience through health monitoring and reconfiguration[J]. ACM Transactions on Cyber-Physical Systems, 2024, 8 (1): 7.
16	ZHAO C X, DONG L, LI H, et al. Safety assessment of the reconfigurable integrated modular avionics based on STPA[J]. International Journal of Aerospace Engineering, 2021, 2021 (1): 8875872.
17	QASIM L, HEIN A M, OLARU S, et al. An ontology for system reconfiguration: integrated modular avionics IMA case study[M]//MADNI A M, BOEHM B, ERWIN D, et al, ed. Recent Trends and Advances in Model Based Systems Engineering. Cham: Springer International Publishing, 2022: 189−198.
18	TRIVEDI A, SRINIVASAN D, SANYAL K, et al. A survey of multiobjective evolutionary algorithms based on decomposition[J]. IEEE Trans. on Evolutionary Computation, 2016, 21 (3): 440- 462.
19	HE Z M, LI J C, WU F, et al. DeRL: coupling decomposition in action space for reinforcement learning task[J]. IEEE Trans. on Emerging Topics in Computational Intelligence, 2023, 8 (1): 1030- 1043.
20	ZHANG Y, ZHU H H, TANG D B, et al. Dynamic job shop scheduling based on deep reinforcement learning for multi-agent manufacturing systems[J]. Robotics and Computer-Integrated Manufacturing, 2022, 78, 102412. doi: 10.1016/j.rcim.2022.102412
21	LI J C, SHI H B, HWANG K S. Using goal-conditioned reinforcement learning with deep imitation to control robot arm in flexible flat cable assembly task[J]. IEEE Trans. on Automation Science and Engineering, 2023, 21 (4): 6217- 6228.
22	SILVA F L D, COSTA A H R. A survey on transfer learning for multiagent reinforcement learning systems[J]. Journal of Artificial Intelligence Research, 2019, 64 (1): 645- 703.
23	LIANG J X, MIAO H T, LI K, et al. A review of multi-agent reinforcement learning algorithms[J]. Electronics, 2025, 14 (4): 820. doi: 10.3390/electronics14040820
24	LI C, DONG S K, YANG S D, et al. Coordinating multi-agent reinforcement learning via dual collaborative constraints[J]. Neural Networks, 2025, 182, 106858. doi: 10.1016/j.neunet.2024.106858
25	HU K, XU K, XIA Q F, et al. An overview: attention mechanisms in multi-agent reinforcement learning[J]. Neurocomputing, 2024, 598, 128015. doi: 10.1016/j.neucom.2024.128015
26	ALBRECHT S V, CHRISTIANOS F, SCHAFER L. Multi-agent reinforcement learning: foundations and modern approaches[M]. Cambridge: MIT Press, 2024.
27	RASHID T, SAMVELYAN M, SCHROEDER D W C, et al. QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning[J]. IEEE Access, 2018, 7, 4295- 4304.
28	ZHAO T Y, CHEN T, ZHANG B. QMIX-GNN: a graph neural network-based heterogeneous multi-agent reinforcement learning model for improved collaboration and decision-making[J]. Applied Sciences, 2025, 15 (7): 3794. doi: 10.3390/app15073794
29	YANG Y, LI J T, PAN L L. Multi-robot path planning based on a deep reinforcement learning DQN algorithm[J]. CAAI Transactions on Intelligence Technology, 2020, 5 (3): 177- 183. doi: 10.1049/trit.2020.0024
30	ALMAHAMID F, GROLINGER K. Agile DQN: adaptive deep recurrent attention reinforcement learning for autonomous UAV obstacle avoidance[J]. Scientific Reports, 2025, 15 (1): 18043. doi: 10.1038/s41598-025-03287-y

参数类别	参数名称	参数值
网络结构	输入层维度	84
	隐藏层1维度	128
	隐藏层2维度	64
	输出层维度	18
优化器配置	优化器	均方根传播
	竞争学习率	0.0005
	合作学习率	0.001
经验回放	经验回放缓冲区大小	10000
经验回放	批次大小	16
优先回放与经验积累	优先经验回放α	0.6
	优先经验回放β	0.4
	平均累积经验条L	10
训练参数	目标网络更新间隔	20
	训练轮数	2000
	合作起始轮数	1500

算法	总得分	负载均衡得分	迁移成本得分	可靠性得分
IQMIX	0.8891	0.9417	0.7959	0.9122
IQMIX1	0.8839	0.9350	0.7810	0.9025
IQMIX2	0.8735	0.9210	0.8030	0.8950

${\lambda _1}$	${\lambda _{\text{2}}}$	${\lambda _{\text{3}}}$	总得分	负载均衡	迁移成本	系统可靠性
0.2	0.2	0.6	0.8825	0.8914	0.7841	0.9123
0.2	0.6	0.2	0.8609	0.9437	0.8152	0.9151
0.4	0.3	0.3	0.8891	0.9417	0.7959	0.9122
0.6	0.2	0.2	0.9014	0.9329	0.7761	0.9120
0.34	0.33	0.33	0.8891	0.9417	0.7959	0.9122

[1]	杨大鹏, 龚资浩, 王小也, 郭正玉, 罗德林. 基于多智能体强化学习的无人机协同截击机动决策研究[J]. 系统工程与电子技术, 2025, 47(9): 3076-3085.
[2]	曾斌, 张鸿强, 李厚朴. 针对无人潜航器的反潜策略研究[J]. 系统工程与电子技术, 2022, 44(10): 3174-3181.
[3]	李琛, 黄炎焱, 张永亮, 陈天德. Actor-Critic框架下的多智能体决策方法及其在兵棋上的应用[J]. 系统工程与电子技术, 2021, 43(3): 755-762.
[4]	宋波, 叶伟, 孟祥辉. 基于多智能体强化学习的动态频谱分配方法综述[J]. 系统工程与电子技术, 2021, 43(11): 3338-3351.