基于机器学习的联合作战任务筹划模型

Mission planning for joint operations based on machine learning

战争复杂性日益提高,快速完成作战任务筹划对于提高指挥效率至关重要。提出了联合作战任务矩阵分析模型,为作战任务筹划提供了一种理论方法;以此为基础,构建作战任务-支撑要素-威胁要素信念网络模型;设计了信念网络关键参数的贝叶斯学习方法,采用想象力机制来提高算法在自博弈学习中的收敛速度;给出了一种深度最小威胁生成树搜索算法,该算法能够通过平衡搜索误差和搜索速度,高效完成任务优先级排序。最后,通过仿真实验验证了上述模型和算法的有效性。

The complexity of modern war is increasing,and the rapid operational mission planning is of great importance to improve the efficiency of command and control.This paper presents a joint operational Task Matrix(TM)model,which is a theoretical method for mission planning.A belief network model is put forward to describe the relationship among the elements in TM model.A naive bayesian learning method for belief network is designed.A mechanism of imagination is put forward to speed up the learning process.A search algorithm named Deep Minimum Threat Generation Tree(DMTGT)is proposed,which can efficiently calculate task priority by balancing search error and search speed.Finally,the validity of above models and algorithms is verified by simulation experiments.