基于动态灰色主成分分析的多时刻威胁评估

针对目标威胁评估问题的高维数、时变性等特点, 提出基于动态灰色主成分分析(dynamic grey principal component analysis, DG-PCA)的多时刻威胁评估方法。首先, 以潜艇为分析对象, 构建协同作战模式下的威胁评估指标体系。其次, 提出扩展灰色相似关联度用于表征指标间动态非线性相关度, 构建用于多元非线性时间序列分析的DG-PCA模型。最后, 结合层次分析法(analytic hierarchy process, AHP)与时间序列赋权, 建立基于加权DG-PCA的多时刻威胁评估模型。分析结果表明, 所提方法能够融合多时刻信息, 符合作战实际, 并且在小样本情况下具有较好的数据提取能力。

Multi-time threat assessment based on dynamic grey principal component analysis

Aiming at the high dimension and time-varying characteristics of target threat assessment,a multi-time threat assessment method based on dynamic grey principal component analysis(DG-PCA)is proposed.Firstly,the submarine is taken as the analysis object,and the threat assessment index system under the cooperative operation mode is constructed.Secondly,the extended grey similarity correlation degree is proposed to represent the dynamic nonlinear correlation among indexes,and the DG-PCA model for multivariate nonlinear time series analysis is constructed.Finally,combined with analytic hierarchy process(AHP)and time series weighting,a multi-time threat assessment model based on weighted DG-PCA is established.The analysis results show that the proposed method can fuse multi-time information,accord with the actual combat situation,and has good data extraction ability in the case of small samples.