一种基于ML-PMRF的复杂仿真系统可信度智能分配方法

doi:10.12305/j.issn.1001-506X.2025.05.14

系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (5): 1516-1524.doi: 10.12305/j.issn.1001-506X.2025.05.14

• 系统工程 • 上一篇

一种基于ML-PMRF的复杂仿真系统可信度智能分配方法

张欢¹^,², 李伟¹^,², 张冰³, 马萍¹^,², 杨明¹^,²^,*

1. 哈尔滨工业大学航天学院, 黑龙江哈尔滨 150001
2. 复杂仿真系统建模与仿真全国重点实验室, 黑龙江哈尔滨 150001
3. 国家计算机网络应急技术处理协调中心, 北京 100029

收稿日期:2024-01-22 出版日期:2025-06-11 发布日期:2025-06-18
通讯作者: 杨明
作者简介:张欢 (1996—), 女, 博士研究生, 主要研究方向为复杂仿真系统可信度评估、仿真分析与评估
李伟 (1980—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为仿真实验设计、分析与评估、分布式仿真
张冰 (1973—), 男, 高级工程师, 博士, 主要研究方向为仿真分析与评估、分布式仿真
马萍 (1970—), 女, 教授, 博士研究生导师, 博士, 主要研究方向为分布式仿真系统设计与实现、复杂仿真系统可信度评估
杨明 (1963—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为复杂仿真系统可信度评估、飞行器制导与控制

An intelligent credibility allocation method based on ML-PMRF for complex simulation systems

Huan ZHANG¹^,², Wei LI¹^,², Bing ZHANG³, Ping MA¹^,², Ming YANG¹^,²^,*

1. School of Astronautics, Harbin Institute of Technology, Harbin 150001, China
2. National Key Laboratory of Modeling and Simulation for Complex Systems, Harbin 150001, China
3. National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing 100029, China

Received:2024-01-22 Online:2025-06-11 Published:2025-06-18
Contact: Ming YANG

摘要/Abstract

摘要：

为保证复杂仿真系统达到可信度要求和缩短开发周期，应在构建复杂仿真系统之初确定各个仿真子系统的可信度。为此，提出一种复杂仿真系统可信度智能分配方法，在明确复杂仿真系统总体可信度的情况下获取各仿真子系统的可信度分配结果。根据复杂仿真系统的组成和结构，提出基于多层成对马尔可夫随机场(multi-layer pairwise Markov random field, ML-PMRF)的复杂仿真系统可信度分配模型构建方法。基于最大后验推理和离散萤火虫群优化，提出一种面向ML-PMRF的智能推理方法。通过实例应用及对比实验，验证了所提方法的有效性和合理性。

关键词: 复杂仿真系统, 可信度分配, 多层成对马尔可夫随机场, 智能推理

Abstract:

In order to ensure that the complex simulation system can meet the credibility requirements, the credibility of each simulation sub-system should be determined at the beginning of the construction of the complex simulation system to shorten the development cycle. Therefore, a complex simulation system intelligent credibility allocation method is proposed, which can obtain the credibility allocation results of each simulation sub-system under the condition of the known whole credibility of the complex simulation system. According to the composition and structure of the complex simulation system, the credibility allocation model of the complex simulation system is proposed based on the multi-layer pairwise Markov random field (ML-PMRF). Based on the maximum a posteriori inference and the discrete glowworm swarm optimization, an intelligent inference method for ML-PMRF is proposed. The effectiveness and rationality of the proposed method are verified by practical examples and comparative experiments.

Key words: complex simulation system, credibility allocation, multi-layer pairwise markov random field (ML-PMRF), intelligence inference

中图分类号:

TP391.9

张欢, 李伟, 张冰, 马萍, 杨明. 一种基于ML-PMRF的复杂仿真系统可信度智能分配方法[J]. 系统工程与电子技术, 2025, 47(5): 1516-1524.

Huan ZHANG, Wei LI, Bing ZHANG, Ping MA, Ming YANG. An intelligent credibility allocation method based on ML-PMRF for complex simulation systems[J]. Systems Engineering and Electronics, 2025, 47(5): 1516-1524.

图/表 8

图1

图2

图3

图4

表1

图5

表2

表3

参考文献 33

1	杨明, 张冰, 王子才. 建模与仿真技术发展趋势分析[J]. 系统仿真学报, 2004, 16 (9): 1901- 1904.
	YANG M , ZHANG B , WANG Z C . The analysis of modeling and simulation development direction[J]. Journal of System Simulation, 2004, 16 (9): 1901- 1904.
2	TAO F , XIAO B , QI Q L , et al. Digital twin modeling[J]. Journal of Manufacturing Systems, 2022, 64, 372- 389. doi: 10.1016/j.jmsy.2022.06.015
3	李伟, 林圣琳, 周玉臣, 等. 复杂仿真系统可信度评估研究进展[J]. 中国科学: 信息科学, 2018, 48, 767- 782.
	LI W , LIN S L , ZHOU Y C , et al. Research progress on credibility assessment of a complex simulation system[J]. SCIENCE SINICA Informations, 2018, 48, 767- 782.
4	SORNETTE D , DAVIS A B , IDE K , et al. Algorithm for mod el validation: theory and applications[J]. Proceedings of the Nat ional Academic of Sciences of the United States of America, 2007, 104 (16): 6562- 6567.
5	REBBA R , MAHADEVAN S . Model predictive capability assessment under uncertainty[J]. AIAA Journal, 2006, 44 (10): 2376- 2384. doi: 10.2514/1.19103
6	宁小磊, 吴颖霞, 于天朋, 等. 基于改进灰色关联分析的仿真模型综合验证方法[J]. 兵工学报, 2016, 37 (2): 338- 347.
	NING X L , WU Y X , YU T P , et al. Research on comprehensive validation of simulation models based on improved grey rela tional analysis[J]. Acta Armamentarii, 2016, 37 (2): 338- 347.
7	魏华梁, 李钟武. 灰色关联分析及其在导弹系统仿真模型验证中的应用[J]. 系统工程与电子技术, 1997, 19 (2): 55- 61.
	WEI H L , LI Z W . Grey relational analysis and its application to the validation of computer simulation models for missile systems[J]. Systems Engineering and Electronics, 1997, 19 (2): 55- 61.
8	李伟, 焦松, 陆凌云, 等. 基于特征差异的仿真模型验证及选择方法[J]. 自动化学报, 2014, 40 (10): 2134- 2144.
	LI W , JIAO S , LU L Y , et al. Validation and selection of simu lation model based on the feature differences[J]. Acta Automa-tica Sinica, 2014, 40 (10): 2134- 2144.
9	ZHANG B Q , CHEN G P , GUO Q T . Static frame model validation with small samples solution using improved kernel density estimation and confidence level method[J]. Chinese Journal of Aeronautics, 2012, 25 (6): 879- 886. doi: 10.1016/S1000-9361(11)60458-5
10	LI W , LIN S L , QIAN X C , et al. An evidence theory-based validation method for models with multivariate outputs and uncertainty[J]. Simulation-Transactions of the Society for Modeling and Simulation International, 2021, 97 (12): 821- 834. doi: 10.1177/00375497211022814
11	MAHADEVAN S , REBBA R . Validation of reliability computational models using Bayes networks[J]. Reliability Engineering & System Safety, 2005, 87 (2): 223- 232.
12	JIANG X , MAHADEVAN S , URBINA A . Bayesian nonlinear structural equation modeling for hierarchical validation of dynamical systems[J]. Mechanical System and Signal Processing, 2010, 24 (4): 957- 975. doi: 10.1016/j.ymssp.2009.10.002
13	LIN S L , LI W , MA P , et al. Structural modelling and Bayes ian inference for model validation and confidence extrapolation[J]. Journal of Statistical Computation Simulation, 2020, 90 (2): 211- 233. doi: 10.1080/00949655.2019.1675662
14	王玉龙, 彭文成, 董志明, 等. 一种基于延迟的仿真交互可信度贝叶斯评估方法[J]. 火力与指挥控制, 2020, 45 (8): 161- 165.
	WANG Y L , PENG W C , DONG Z M , et al. A delay-based Bayesian evaluation method for simulation interaction credibility[J]. Fire Control & Command Control, 2020, 45 (8): 161- 165.
15	MA Y F, WU X F. Evaluation of system-of-systems using two layer fuzzy analytic network process model[C]//Proc. of the IEEE International Conference on Control Science and Systems Engineering, 2014.
16	JIANG S Q , YANG L , CHENG G , et al. A quantitative framework for network resilience evaluation using dynamic Bayesian network[J]. Computer Communications, 2022, 194 (1): 387- 398.
17	GAO S Y , ZHANG F R , NING W , et al. Optimization of cargo shipping adaptability modeling evaluation based on Bayesian network algorithm[J]. Sustainability, 2022, 14 (19): 12856. doi: 10.3390/su141912856
18	MENG M J , LIN Q Y , WANG Y M . The risk assessment of manufacturing supply chains based on Bayesian networks with uncertainty of demand[J]. Journal of Intelligent & Fuzzy Systems, 2022, 42 (6): 5753- 5771.
19	WANG H P , LU H C , SUN K , et al. Reliability evaluation method for distribution network with distributed generations considering feeder fault recovery and network reconfiguration[J]. IET Renewable Power Generation, 2023, 17 (14): 3484- 3495. doi: 10.1049/rpg2.12863
20	CHEN L P . Estimation of graphical models: an overview of se lected topics[J]. International Statistical Review, 2024, 92 (2): 194- 245. doi: 10.1111/insr.12552
21	WANG P , ROBINS G , PATTISON P , et al. Exponential random graph models for multilevel networks[J]. Social Networks, 2013, 35 (1): 96- 115. doi: 10.1016/j.socnet.2013.01.004
22	KIVELA M , ARENAS A , BARTHELEMY M , et al. Multilayer network[J]. Journal of Complex Networks, 2014, 2 (3): 203- 271. doi: 10.1093/comnet/cnu016
23	HERNANDEZ-LEMUS E . Random fields in physics, biology and data science[J]. Frontiers in Physics, 2021, 9, 641859. doi: 10.3389/fphy.2021.641859
24	GOMPERTZ B . On the nature of the function expressive of the law of human mortality and on a new model of determining life contingencies[J]. Philosophical Transactions of the Royal Socie ty B-Biological Sciences, 1825, 115 (1): 513- 583.
25	DAISUKE S . Discrete Gompertz equation and model selection between Gompertz and logistic models[J]. International Journal of Forecasting, 2021, 37 (3): 1192- 1211. doi: 10.1016/j.ijforecast.2021.01.005
26	LI S Z . Markov random field modeling in image analysis[M]. Berlin: Springer Science & Business Media, 2009.
27	PEYRARD N , CROS M J , DE-GIVRY S , et al. Exact or approximate inference in graphical models: why the choice is dictated by the treewidth, and how variable elimination can be exploited[J]. Australian & New Zealand Journal of Statistics, 2019, 61 (2): 89- 133.
28	冉家敏, 倪志伟, 彭鹏, 等. 考虑空间众包工作者服务质量的任务分配策略及其萤火虫群优化算法求解[J]. 计算机应用, 2021, 41 (3): 794- 802.
	RAN J M , NI Z W , PENG P , et al. Task allocation strategy considering service quality of spatial crowdsourcing workers and its glowworm swarm optimization algorithm solution[J]. Journal of Computer Applications, 2021, 41 (3): 794- 802.
29	HANSEN E A , SHI J C , KASTRANTAS J . Strategy graphs for influence diagrams[J]. Journal of Artificial Intelligence Research, 2022, 75, 1177- 1221. doi: 10.1613/jair.1.13865
30	YANG Y T, LIN Q X, MAO J, et al. An improved social at tribute inference scheme based on multi-attribute correlation[C]// Proc. of the IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation, 2021: 370-377.
31	WANG Y, CHEN J, ZHAO W F, et al. Research on force demand model of air defense system in important places[C]//Proc. of the World Conference on Intelligent and 3-D Technologies, 2023: 569-578.
32	郭蓬松, 龙光正, 赵博, 等. 地面防空作战部署评估仿真系统设计与实现[J]. 现代防御技术, 2014, 42 (6): 153- 159.
	GUO P S , LONG G Z , ZHAO B , et al. Design and implementation of simulation system on evaluation of ground to air de fense disposition[J]. Modern Defence Technology, 2014, 42 (6): 153- 159.
33	SELVAN R , KIPF T , WELLING M , et al. Graph refinement based airway extraction using mean-field networks and graph neural networks[J]. Medical Image Analysis, 2020, 64 (5): 101751.

仿真子系统可信度	智能推理方法	LBP	ICM
C_{sub, 1}	0.75	0.78	0.76
C_{sub, 2}	0.74	0.75	0.74
C_{sub, 3}	0.88	0.90	0.88
C_{sub, 4}	0.88	0.90	0.88
C_{sub, 5}	0.86	0.87	0.86
C_{sub, 6}	0.75	0.79	0.75
C_{sub, 7}	0.80	0.81	0.80
C_{sub, 8}	0.76	0.76	0.76
C_{sub, 9}	0.76	0.76	0.74
C_{sub, 10}	0.90	0.88	0.87
C_{sub, 11}	0.80	0.80	0.80
C_{sub, 12}	0.80	0.80	0.77
C_{sub, 13}	0.74	0.74	0.73

推理方法	目标函数最小值
智能推理方法	276.23
LBP	283.22
ICM	283.51

节点变量	分配结果	先验概率分布
作战空域	0.80	N(0.8, 0.1)
杀伤概率	0.67	N(0.65, 0.08)
目标综合识别概率	0.83	N(0.83, 0.05)
多目标分配能力	0.90	U(0.9, 1.0)
数据传输准确度	0.80	U(0.75, 0.9)
链路连通率	0.78	N(0.77, 0.06)

[1]	袁彰求, 杨朝旭, 荣海军. 面向定性与定量指标的轻量化高空飞艇效能评估方法[J]. 系统工程与电子技术, 2025, 47(3): 817-826.
[2]	陈夏瑢, 李际超, 陈刚, 刘鹏, 姜江. 基于异质网络的装备体系组合发展规划问题[J]. 系统工程与电子技术, 2025, 47(3): 855-861.
[3]	潘晨辉, 鲜勇, 马培洋, 倪晚成, 赵晓楠, 李少朋. 兵棋推演态势认知的态势数学表达方法[J]. 系统工程与电子技术, 2025, 47(3): 883-892.
[4]	陈志新, 陆凌云, 叶玲, 郑少秋, 王芳, 高鑫. 指挥控制系统数字孪生研究[J]. 系统工程与电子技术, 2025, 47(3): 912-922.
[5]	邹世培, 王玉惠, 刘鸿睿. 基于RF-XGBoost算法的无人机多回合攻防博弈决策[J]. 系统工程与电子技术, 2025, 47(2): 518-526.
[6]	熊宇涵, 李雄. 数字孪生战场: 概念、架构与技术[J]. 系统工程与电子技术, 2025, 47(1): 141-152.
[7]	王佩骐, 鞠儒生, 张淼, 段伟. 基于非支配遗传算法的HLA仿真系统数据采集策略[J]. 系统工程与电子技术, 2024, 46(9): 3103-3111.
[8]	费博雯, 包卫东, 刘大千, 朱晓敏. 面向动态目标搜索与打击的空地协同自主任务分配方法[J]. 系统工程与电子技术, 2024, 46(7): 2346-2358.
[9]	胡涛, 申立群, 朱镜达, 孙成会, 董伟锋. 基于FAST和Sobol指数法的雷达系统效能敏感性分析[J]. 系统工程与电子技术, 2024, 46(2): 561-569.
[10]	张宝琛, 惠建江, 张琦, 刘正雄, 黄攀峰. 面向冗余机械臂避障运动规划的触控交互技术[J]. 系统工程与电子技术, 2024, 46(1): 254-260.
[11]	胡涛, 申立群, 田宇阳, 董伟锋. 航天复杂系统测发控流程仿真引擎设计与评价[J]. 系统工程与电子技术, 2023, 45(12): 3866-3874.
[12]	高山, 智永锋, 张普, 左轩. 基于改进灰色关联分析的航天产品性能样机仿真结果一致性验证方法[J]. 系统工程与电子技术, 2023, 45(9): 2777-2783.
[13]	任浩亮, 张建超, 程会川. 基于SysML的武器装备体系能力需求建模分析方法[J]. 系统工程与电子技术, 2023, 45(9): 2843-2851.
[14]	黄炎焱, 王凯生, 史宇昂. 基于网络化指标的数据链作战保障能力评估模型研究[J]. 系统工程与电子技术, 2023, 45(8): 2361-2369.
[15]	杨帆, 马萍, 李伟, 杨明. 基于孪生网络的仿真模型智能排序评估方法[J]. 系统工程与电子技术, 2023, 45(7): 2060-2068.

一种基于ML-PMRF的复杂仿真系统可信度智能分配方法

An intelligent credibility allocation method based on ML-PMRF for complex simulation systems

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价