数实结合平行仿真特点及其可信度评估研究

doi:10.3969/j.issn.1009-086x.2026.02.019

现代防御技术 ›› 2026, Vol. 54 ›› Issue (2): 192-197.DOI: 10.3969/j.issn.1009-086x.2026.02.019

• 论文 • 上一篇

数实结合平行仿真特点及其可信度评估研究

韩进喜¹, 耿琳¹, 贾建光¹, 徐筠², 王子龙²

^1.中国人民解放军32801部队
^2.北京电子工程总体研究所，北京 100854

收稿日期:2025-09-11 修回日期:2026-03-05 出版日期:2026-04-28 发布日期:2026-04-30
作者简介:韩进喜(1978-)，男，河北深州人。副研究员，硕士，研究方向为装备试验设计、仿真试验与验证。

Research on Characteristics and Credibility Evaluation of Digital-Real Integrated Parallel Simulation

Jinxi HAN¹, Lin GENG¹, Jianguang JIA¹, Jun XU², Zilong WANG²

^1.PLA 32801 Troops
^2.Beijing Institute of Electronic System Engineering，Beijing 100854，China

Received:2025-09-11 Revised:2026-03-05 Online:2026-04-28 Published:2026-04-30

摘要/Abstract

摘要：

随着数字平行战场、装备数字孪生、数实融合试验等仿真应用的兴起，在综合分析现代军用仿真技术和系统发展趋势的基础上，重点论述了基于实况-虚拟-构造(live，virtual，construction, LVC)的数实结合平行仿真系统的主要特点及其可信度评估中出现的新问题，并提出相应的可信度评估框架，帮助提升军事训练、军事演习等领域复杂仿真系统的可信度。

关键词: 数实结合, 数字孪生, 平行系统, 军用仿真, 可信度, 校核验证

Abstract:

With the emergence of simulation applications such as digital parallel battlefields， equipment digital twins， and digital-real fusion tests， based on a comprehensive analysis of the development trends of modern military simulation technologies and systems， this paper focused on the main characteristics of the LVC（live virtual construstion）-based digital-real integrated parallel simulation system and the new problems emerging in its credibility evaluation. Moreover， it proposed a corresponding credibility evaluation framework to help enhance the credibility of complex simulation systems in fields such as military training and military exercises.

Key words: digital-real integration, digital twin, parallel system, military simulation, credibility, verification and validation

中图分类号:

TP391.9

韩进喜, 耿琳, 贾建光, 徐筠, 王子龙. 数实结合平行仿真特点及其可信度评估研究[J]. 现代防御技术, 2026, 54(2): 192-197.

Jinxi HAN, Lin GENG, Jianguang JIA, Jun XU, Zilong WANG. Research on Characteristics and Credibility Evaluation of Digital-Real Integrated Parallel Simulation[J]. Modern Defense Technology, 2026, 54(2): 192-197.

图/表 1

参考文献 21

[1]	LI Z. Knowledge-Guided Deep Reinforcement Learning for Military Decision-Making［J］. IEEE Transactions on Systems， Man， and Cybernetics： Systems， 2021， 51（8）： 4140-4151.
[2]	WANG Feiyue. Parallel Control and Management for Intelligent Transportation Systems： Concepts， Architectures， and Applications［J］. IEEE Transactions on Intelligent Transportation Systems， 2010， 11（3）： 630-638.
[3]	BATTAGLIA P W， HAMRICK J B， BAPST V， et al. Relational Inductive Biases， Deep Learning， and Graph Networks［EB/OL］. （2018-10-17）［2025-08-31］. .
[4]	BALCI O. Verification， Validation， and Accreditation of Simulation Models［C］∥Winter Simulation Conference. 1997： 135-141.
[5]	SARGENT R G. Verification and Validation of Simulation Models［J］. Journal of Simulation， 2013， 7（1）： 12-24.
[6]	KEENEY R L， RAIFFA H. Decisions with Multiple Objectives： Preferences and Value Trade-Offs［M］. Cambridge： Cambridge University Press， 1993.
[7]	FIGUEIRA J， GRECO S， EHROGOTT M. Multiple Criteria Decision Analysis： State of the Art Surveys［M］. New York： Springer， 2005.
[8]	LIU H C. A Hybrid Dynamic MCDM Method for Risk Assessment in Military Logistics Outsourcing Cybernetics［J］. IEEE Transactions on Engineering Management， 2019， 66（4）： 699-711.
[9]	WANG Quan， MAO Zhendong， WANG Bin， et al. Knowledge Graph Embedding： A Survey of Approaches and Applications ［J］.IEEE Transactions on Knowledge & Data Engineering， 2017， 29（12）：2724-2743.
[10]	LIU J. A Credibility Assessment Framework for Virtual Training Systems Based on Heterogeneous Data Fusion［J］. IEEE Access， 2021， 9： 12345-12356.
[11]	LIAO Shangzhi. Research of Parallel Simulation for Aviation Communication ［J］. Command Control & Simulation， 2023， 45（3）： 134-142.
[12]	LIU B. Credibility Assessment of Combat Simulation Systems Using Fuzzy AHP and Entropy Weight［J］. IEEE Transactions on Computational Social Systems， 2020， 7（4）： 1026-1036.
[13]	WANG Z. A Dynamic Credibility Evaluation Framework for LVC Training Systems［J］. IEEE Transactions on Systems， Man， and Cybernetics： Systems， 2023， 53（2）： 789-802.
[14]	FINN C， ABBEEL P， LEVINE S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks［C］∥Proceedings of the 34th International Conference on Machine Learning. Chia Laguna Resort： PMLR， 2017： 1126-1135.
[15]	ZHOU F. Meta-Learning with Generative Adversarial Networks for Few-Shot Classification［J］. Neural Networks， 2022， 148： 1-10.
[16]	GOODFELLOW I. Deep Learning［M］. Cambridge： MIT Press， 2020.
[17]	ZHANG H. Meta-learning with Bayesian Neural Networks for Combat Simulation Data Augmentation［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021， 32（6）： 2567-2581.
[18]	CONG Yuren， LIAO Wentong， ACKERMANN H， et al. Spatial-Temporal Transformer for Dynamic Scene Graph Generation［C］∥International Conference on Computer Vision （ICCV）， 2021： 16352-16362.
[19]	GUO K. Spatial-Temporal Transformer Networks for Battlefield Situation Prediction［J］. Expert Systems with Applications， 2022， 195： 116567.
[20]	VASWAN A. Transformers for Sequential Decision-making［J］. Artificial Intelligence， 2023， 316： 103842.
[21]	ZHANG Yu， YANG Qiang. A Survey on Multi-task Learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（12）： 5586-5609.

数实结合平行仿真特点及其可信度评估研究

Research on Characteristics and Credibility Evaluation of Digital-Real Integrated Parallel Simulation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 1

参考文献 21

相关文章 6

编辑推荐

Metrics

本文评价

[1]	杨科, 王刚, 周静, 车冠钰. 联合防空反导数字孪生作战实验体系架构研究[J]. 现代防御技术, 2025, 53(6): 171-178.
[2]	高慧芳, 谷国贤, 侯青剑, 周妍, 王亮亮. 基于数字孪生的数字平行战场系统构建方法研究[J]. 现代防御技术, 2025, 53(2): 82-90.
[3]	王帅, 王亚彬, 王金帼, 王茁, 赵建民. 陆军合成旅典型装备保障系统数字孪生模型[J]. 现代防御技术, 2023, 51(1): 96-106.
[4]	许瑞明. 无人机集群智能的生成样式研究[J]. 现代防御技术, 2020, 48(5): 44-49.
[5]	谢堂涛, 易方, 梅光焜. 平行系统理论在体系对抗训练中的应用初探[J]. 现代防御技术, 2020, 48(1): 100-106.
[6]	刘标, 许腾, 李光. D-S证据理论改进算法提高水下目标识别准确性[J]. 现代防御技术, 2018, 46(1): 120-124.