基于遗传模糊系统的兵棋推演关键点推理方法

doi:10.3969/j.issn.1001-506X.2020.10.19

摘要/Abstract

摘要：

近年来,基于人工智能技术的自动化作战推演越发受到重视,但是由于有效地采集作战推演数据难度较大,许多依赖数据学习的人工智能技术效果不佳。在结合专家知识和作战推演数据的基础上研究作战推演中的人工智能技术,是一种可行的替代方案。为此,立足兵棋推演设计了关键点推理遗传模糊系统(genetic fuzzy system, GFS)框架,有效整合了对兵棋专家知识的建模和对兵棋复盘数据的学习,从而提高了关键点的推理质量。进一步以安全点为例,构建了安全点推理GFS,在初始化模糊系统规则库的基础上,通过合理设计遗传算法中的参数编码、适应度函数、遗传算子等,实现了安全点推理模糊系统的遗传调优算法。最后,通过实验仿真展示了所提方法的可行性和实用性。

关键词: 遗传模糊系统, 兵棋推演, 关键点推理, 作战推演, 遗传算法, 兵棋复盘数据

Abstract:

In recent years, more and more attention has been paid to automatic combat deduction based on artificial intelligence technology. However, due to the difficulty in collecting combat deduction data effectively, many artificial intelligence technologies that rely on data learning are ineffective. It is a feasible alternative to study the artificial intelligence technology in combat deduction based on expert knowledge and combat deduction data. Therefore, based on the wargame, a genetic fuzzy system (GFS) framework for key points reasoning is designed, which effectively integrates the knowledge modeling of wargame experts and the learning of wargame replay data, thus improving the reasoning quality of key points. And then, taking securing points as an example, a GFS for securing point reasoning is constructed. On the basis of initializing the rule base of the fuzzy system, by means of the reasonable design of parameter coding, fitness function and genetic operator in the genetic algorithm, the genetic tuning algorithm for securing point reasoning fuzzy system is implemented. Finally, the feasibility and practicability of the proposed model are demonstrated through the experimental simulation.

Key words: genetic fuzzy system (GFS), wargame, key point reasoning, combat deduction, genetic algorithm, wargame replay data

中图分类号:

TP273.4

张可, 郝文宁, 余晓晗, 靳大尉, 邵天浩. 基于遗传模糊系统的兵棋推演关键点推理方法[J]. 系统工程与电子技术, 2020, 42(10): 2303-2311.

Ke ZHANG, Wenning HAO, Xiaohan YU, Dawei JIN, Tianhao SHAO. Wargame key point reasoning method based on genetic fuzzy system[J]. Systems Engineering and Electronics, 2020, 42(10): 2303-2311.

图/表 14

图1

图2

图3

图4

表1

表2

图5

图6

表3

表4

图7

表5

表6

图8

参考文献 23

1	王键, 周静. 陆军作战实验现状及发展[J]. 国防科技, 2019, 40 (2): 45- 48.
	WANG J , ZHOU J . The status and development trend of army's combat experiment[J]. National Defense Science & Technology, 2019, 40 (2): 45- 48.
2	姚庆锴, 柳少军, 贺筱媛, 等. 基于深度学习的空中任务识别方法研究[J]. 系统仿真学报, 2017, 29 (9): 2227- 2231.
	YAO Q K , LIU S J , HE X Y , et al. Research of air mission recognition methon based on deep learning[J]. Journal of System Simulation, 2017, 29 (9): 2227- 2231.
3	李承兴, 高桂清, 鞠金鑫, 等. 基于人工智能深度增强学习的装备维修保障兵棋研究[J]. 兵器装备工程学报, 2018, 39 (2): 61- 65.
	LI C X , GAO G Q , JU J X , et al. Study on equipment maintenance and security based on artificial intelligence depth enhancement[J]. Journal of Ordnance Equipment Engineering, 2018, 39 (2): 61- 65.
4	CORDÓN O , GOMIDE F , HERRERA F , et al. Ten years of genetic fuzzy systems: current framework and new trends[J]. Fuzzy Sets and Systems, 2004, 141 (1): 5- 31.
5	HERRERA F . Genetic fuzzy systems: taxonomy, current research trends and prospects[J]. Evolutionary Intelligence, 2008, 1 (1): 27- 46.
6	KHAN A A , ABOLHASAN M , NI W , et al. A hybrid-fuzzy logic guided genetic algorithm (H-FLGA) approach for resource optimization in 5G VANETs[J]. IEEE Trans. on Vehicular Technology, 2019, 68 (7): 6964- 6974.
7	MOKEDDEM A S . A fuzzy classification model for myocardial infarction risk assessment[J]. Applied Intelligence, 2018, 48 (5): 1233- 1250.
8	HOSSEINI R , QANADLI S D , BARMAN S , et al. An automatic approach for learning and tuning Gaussian interval type-2 fuzzy membership functions applied to lung CAD classification system[J]. IEEE Trans. on Fuzzy Systems, 2012, 20 (2): 224- 234.
9	ECKERT J J , SANTICIOLLI F M , YAMASHITA R Y , et al. Fuzzy gear shifting control optimization to improve vehicle performance, fuel consumption and engine emissions[J]. IET Control Theory and Applications, 2019, 13 (16): 2658- 2669.
10	ZADEH L A . Fuzzy sets[J]. Information and Control, 1965, 8 (3): 338- 353.
11	王立新. 模糊系统与模糊控制教程[M]. 北京: 清华大学出版社, 2003.
	WANG L X . Fuzzy system and fuzzy control course[M]. Beijing: Tsinghua University Press, 2003.
12	WANG A Q , LIU L , QIU J B , et al. Event-triggered robust adaptive fuzzy control for a class of nonlinear systems[J]. IEEE Trans. on Fuzzy Systems, 2018, 28 (7): 1648- 1658.
13	CHERNIY S P, GUDIM A S, BUZIKAYEVA A V. Fuzzy multi-cascade AC drive control system[C]//Proc.of the International Multi-Conference on Industrial Engineering and Mo-dern Technologies, 2018.
14	SILVANA M, AKBAR R, DERISM A, et al. Development of classification features of mental disorder characteristics using the fuzzy logic mamdani method[C]//Proc.of the International Conference on Information Technology Systems and Innovation, 2018: 410-414.
15	NGUYEN T , HETTIARACHCHI I , KHATAMI A , et al. Classification of multi-class BCI data by common spatial pattern and fuzzy system[J]. IEEE Access, 2018, 6, 27873- 27884.
16	ASIMUZZAMAN M, NATH P D, HOSSAIN F, et al. Sentiment analysis of bangla microblogs using adaptive neuro fuzzy system[C]//Proc.of the International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, 2017: 1631-1638.
17	LAMBORA A, GUPTA K, CHOPRA K. Genetic algorithm-a literature review[C]//Proc.of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing, 2019: 380-384.
18	REY I M, GALENDE M, SAINZ G I, et al. Selection of rules by orthogonal transformations and genetic algorithms to improve the interpretability in fuzzy rule-based systems[C]//Proc.of the IEEE International Conference on Fuzzy Systems, 2013.
19	JARRAYA Y , BOUAZIZ S , HAGRAS H , et al. A multi-agent architecture for the design of hierarchical interval type-2 beta fuzzy system[J]. IEEE Trans. on Fuzzy Systems, 2019, 27 (6): 1174- 1188.
20	ZHAO W Q , NIU Q , LI K , et al. A hybrid learning method for constructing compact rule-based fuzzy models[J]. IEEE Trans. on Cybernetics, 2013, 43 (6): 1807- 1821.
21	CORDÓN O , HERRERA F , VILLAR P . Generating the know-ledge base of a fuzzy rule-based system by the genetic learning of the data base[J]. IEEE Trans. on Fuzzy Systems, 2001, 9 (4): 667- 674.
22	CASILLAS J , CORDÓN O , JESUS M J , et al. Genetic tuning of fuzzy rule deep structures preserving interpretability and its interaction with fuzzy rule set reduction[J]. IEEE Trans. on Fuzzy Systems, 2005, 13 (1): 13- 29.
23	MÁRQUEZ F A , PEREGRÍN A , HERRERA F . Cooperative evolutionary learning of linguistic fuzzy rules and parametric aggregation connectors for mamdani fuzzy systems[J]. IEEE Trans. on Fuzzy Systems, 2007, 15 (6): 1162- 1178.

模糊变量	论域	隶属度	参数
地形	{0, 1, 2, 3, 4}	很低	三角模糊数
		低	三角模糊数
		中	三角模糊数
		高	三角模糊数
		很高	三角模糊数
地貌	{0, 1}	低	三角模糊数
地貌	{0, 1}	高	三角模糊数
安全点可能性	[0, 1]	很低	三角模糊数
		低	三角模糊数
		中	三角模糊数
		高	三角模糊数

地貌对安全点的影响程度	地形对安全点的影响程度
地貌对安全点的影响程度	很低	低	中	高	很高
低	很低	很低	低	低	中
高	低	低	中	高	高

输入/输出	模糊变量	隶属度函数个数	模糊变量取值
输入	射击率	4	低、偏低、偏高、高
	通视率	3	低、中、高
	平均射击损伤	2	低、高
输出	安全程度标签	5	低、偏低、中、偏高、高

参数变量	取值
种群规模	100
遗传代数	150
交叉率	0.8
变异率	0.3

模糊变量	隶属度	参数
地形	很低	[0, 0, 0.44]
	低	[0.01, 1, 1.19]
	中	[0.02, 2, 3.15]
	高	[0.03, 3, 3.17]
	很高	[2, 4, 4]
地貌	低	[0, 0, 0.73]
地貌	高	[0.04, 1, 1]
安全点可能性	很低	[0, 0, 0.97]
	低	[0.08, 0.32, 0.98]
	中	[0.21, 0.98, 0.99]
	高	[0.86, 1, 1]