基于遗传模糊系统的兵棋推演关键点推理方法

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。

Wargame key point reasoning method based on genetic fuzzy system

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.