Threat Evaluation in Air Defense Based on Improved KPCA-TOPSIS

Abstract

Listen

Translate article

Rapid and accurate threat evaluation(TE) of incoming targets is the key part in air defense. In order to evaluate the target threat effectively, a threat evaluation index system is constructed. On this basis, an improved kernel principal component analysis method (KPCA) based on hybrid kernel function is proposed to realize dimension reduction of the index data, particle swarm optimization (PSO) is utilized to optimize the parameters. The threat of targets is evaluated and ranked by the technique for order of reference by similarity to ideal solution method (TOPSIS) with the variance contributions of kernel principal components for weighing the processed data. The proposed method can avoid the subjectivity introduced by traditional methods and make dimension reduction of evaluation index data, thus decreasing the complexity of evaluation and improving real-time performance. The numerical experiment shows that the results obtained by this method are reasonable and realistic.