基于改进CRITIC-LRA和灰色逼近理想解排序法的空战威胁评估

Air Combat Threat Assessment of Improved CRITIC-LRA and Grey TOPSIS

针对当前空战威胁评估过程中采用主观赋权法确定指标权重时具有主观性、忽视指标间内在关联关系的问题,提出一种基于改进CRITIC-线性回归分析(LRA)确定指标权重的计算方法。根据CRITIC法的缺陷,引入基尼系数和肯德尔系数实现对CRITIC法的改进并确定指标初始权重;利用1阶LRA计算评估指标关联关系,通过削减指标权重降低指标关联性,实现对指标权重的修正,降低指标关联对评估造成的影响;为了克服逼近理想解排序法中采用欧式距离作为距离测度的缺点,采用指标间加权灰色关联度代替欧氏距离,计算相对贴近度,实现目标威胁排序。威胁评估算例表明,所提方法能够充分体现目标威胁区分度和对目标进行威胁排序,评估结果科学有效。

In view of the subjectivity of using index weight determination in the process of air combat threat assessment and the neglect of the internal relationship between the indexes,a calculation method of determining the index weight based on an improved criteria importance though intercriteria correlation-linear regression analysis(CRITIC-LRA)is proposed.The Gini coefficient and Kendall correlation coefficient are introduced to improve the CRITIC method and determine the initial weight of indexes in accordance with the defects of CRITIC;the first-order linear regression analysis(LRA)is used to calculate the correlation of evaluation indexes,and the indexes relevance is reduced by decreasing the index weight.In order to overcome the shortcomings of using Euclidean distance as a distance measure in the technique for order performance by similarity to ideal solution(TOPSIS),the weighted grey correlation degree between indexes is used to replace Euclidean distance,and the relative closeness degree is calculated to achieve the target threat ranking.The threat assessment example shows that the proposed method can fully reflect the target threat differentiation and rank the targets.