Feature Extraction And Fusion Recognition Of Radar Emitters Based On Cyclostationary Analysis

Radar emitters recognition is one of the key procedures of signal processing in ELINT, ESM and RWR systems. It is also the precondition and foundation of electronic interfering. The state of the art of radar emitter signal recognition corresponds to the technical merit of electronic reconnaissance equipment. As countermeasure activities in modern electronic warfare become more and more drastic, advanced radars increase rapidly and become the main component gradually. The validity of traditional recognition methods were weaken greatly. Therefore, the recognition of advanced radar emitter signals becomes a key problem to solve urgently in electronic warfare. Aiming at the key issue of electronic warfare, feature extraction and fusion recognition of radar emitters based on cyclostationary analysis are proposed in this dissertation.First of all, the individual characteristics of radar emitter based on cyclic spectral domain and cyclic bispectral domain was extracted. The experiment results show that the feature in cyclostationary domain can describe the fine characteristics of radar emitters more comprehensively and effectively.Secondly, the canonical correlation analysis and discriminate canonical correlation analysis are proposed and applied in feature fusion of radar emitters. Here, the correlation between two feature sets is used as discriminate information so as to extract effective combination feature. In addition, the feature-level fusion based on feature ranking and selection according to distance criterion is proposed aiming to solve the problem that the difference of two features sets is too large. The experiment results show that feature-level fusion can achieve both purposes of fusion of information and elimination of redundant information.At last, the rejection algorithm based on generalized confidence is brought up and the recognition performance of the whole classification system through kinds of evaluation parameters was valued.