系统仿真学报 ›› 2018, Vol. 30 ›› Issue (11): 4115-4123.doi: 10.16182/j.issn1004731x.joss.201811009

• 仿真建模理论与方法 • 上一篇    下一篇

基于兵棋推演的联合作战方案评估框架研究

刘海洋1,2, 唐宇波1, 胡晓峰1, 乔广鹏1   

  1. 1.国防大学 联合作战学院,北京 100091;
    2.航天工程大学 航天指挥学院,北京 101416
  • 收稿日期:2018-05-25 修回日期:2018-07-09 发布日期:2019-01-04
  • 作者简介:刘海洋(1983-),男,山东曲阜,博士生,讲师,研究方向为计算机战争模拟;唐宇波(1974-),男,四川南充,博士,高工,研究方向为兵棋推演与作战模拟;胡晓峰(1957-),男,山东栖霞,硕士,教授,博导,研究方向为计算机战争模拟。
  • 基金资助:
    国家自然科学基金(61403401, 61703412)

Research on Evaluation Framework of COA Based on Wargaming

Liu Haiyang1,2, Tang Yubo1, Hu Xiaofeng1, Qiao Guangpeng1   

  1. 1. College of Joint Operation, National Defense University, Beijing 100091, China;
    2. College of Space Command, Space Engineering University, Beijing 101416, China
  • Received:2018-05-25 Revised:2018-07-09 Published:2019-01-04

摘要: 针对联合作战中战役方案级指标评估问题,提出一种基于兵棋推演的作战方案评估框架。通过对兵棋推演数据进行多维分析,利用数据立方体模型快速生成基础特征项,结合基于复杂网络的体系特征项构建评估特征空间;采用兵棋推演实验的方法产生小批量方案级指标度量结果,通过数据拟合获取与评估特征空间数据对应的结果标签;利用两阶段的相关性分析对高维评估特征进行降维,并构建基于深度学习的评估模型,利用数据样本对评估模型进行训练。对于作战方案评估框架中存在的部分问题,给出了相应的解决办法。

关键词: 兵棋推演, 作战方案评估, 复杂网络, 深度学习

Abstract: Aiming at the evaluation problem of COA (course of action) level indicators in joint operation, an evaluation framework of COA based on wargaming was proposed. By multidimensional analysis of wargaming data, an evaluation feature space was constructed from basic features generated by data cube models and SoS (system of systems) features based on complex network. Wargaming experiments were used to generate small batch metrics results of COA level indicators, and the corresponding result labels of evaluation feature space data were generated by data fitting method. Two-phase correlation analysis was used for dimensionality reduction of high dimensional evaluation features. Evaluation model was constructed based on deep learning, and was trained by data samples. Corresponding solutions were given to solve some problems of evaluation framework of COA.

Key words: wargaming, evaluation of COA, complex network, deep learning

中图分类号: