基于强制稀疏自编码神经网络的作战态势评估方法研究

Situation Assessment Approach for Air Defense Operation System Based on Force-Sparsed Stacked-Auto Encoding Neural Networks

针对传统数据挖掘方法无法解决态势评估中防空体系特征自主挖掘和生成机理分析的问题,提出一种基于强制自编码神经网络的态势评估方法。结合大数据与复杂网络技术,构建强制自编码深度学习网络模型,形式化描述体系能力指标之间的级联涌现关系,在战场态势预测分析的基础上,进一步深入分析体系能力生成机理及贡献度,并通过仿真数据对模型进行验证。该模型对体系能力指标涌现的形式化描述,不仅体现了涌现过程的非线性、不确定性等复杂性特征,还赋予指标体系相对明确的物理含义,为辅助指挥员深入认知复杂战场态势提供了可行的方法手段。

Aiming at the difficulty of feature extraction and related generation mechanism analysis for complex Air Defense System of Systems （ADSOS） using traditional data mining method, a novel situation assessment approach based on Force-Sparsed Stacked-Auto Encoding Neural Networks （FS-SAE） is proposed. Combined with big data and complex networks technology, FS-SAE situation assessment model is built. The emergence relations between the capacity indexes of ADSOS are formalized. And then, the formation mechanism and the contribution rate of capacity indexes are studied and the validity of this approach is validated by the simulation data. The experimental results show that formalized presentation for the emergence process of capacity indexes of ADSOS based on the proposed model not only reflects the complexity characteristics of non-linear and uncertainty in emergence process, but also gives general-defined meaning for indexes structure of ADSOS. It provides a feasible method for the commanders to deeply understand, manage and control the complex operation system.