Radar Radiator Individual Identification Method and Device Based on Unintentional Phase Modulation Characteristics

Abstract

The invention belongs to the technical field of radar signal processing, and particularly relates to a method and device for individual identification of radar radiation sources based on unintentional phase modulation characteristics. Training data set; use the training data set to conduct offline training on the constructed convolutional network model; extract the characteristics of the unintentional phase modulation sequence of the target signal, use the trained convolutional network model to conduct online identification, and obtain the individual identification result of the radiation source. Considering the situation of intentional modulation, the present invention provides a simplified observation model of intra-pulse signal phase, and performs demodulation processing on the observed phase sequence to extract the noise-containing estimation of unintentional phase modulation; uses Bezier curve to fit unintentional phase modulation, reducing Finally, the convolutional network is used to extract the joint features of the unintentional phase modulation sequence to realize the individual identification of radar emitters. The feasibility and effectiveness of the scheme are verified through simulation experiments, which has a good prospect of engineering application.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing, in particular to a method and device for individual identification of radar radiation sources based on unintentional phase modulation characteristics. Background technique [0002] Specific Emitter Identification (SEI) refers to the process of measuring and analyzing the emitter signal intercepted by the receiver, and identifying individuals based on the existing prior information. Situational awareness and threat assessment provide decision support. Individual identification of early radar emitters was mainly achieved by template matching with conventional parameters such as carrier frequency, pulse width, and pulse repetition period. With the improvement of radar technology, new system radars continue to appear, and the electromagnetic environment is increasingly dense and complex. The traditional method based on the measurement of external characteristic parameters has been di...

AI Technical Summary

Problems solved by technology

But there are still the following deficiencies: (1) The UPMOP characteristic curve extraction process is only suitable for the situation where there is no intentional modulation in the pulse. Extract the UPMOP characteristic curve of the pulse; (2) The algorithm uses time-domain windowing to smooth the UPMOP characteristic curve for noise reduction processing, which is greatly affected by noise, and when the signal-to-noise ratio is relatively low, the UPMOP characteristic curve remains unchanged after noise reduction. Bending jitter is obvious, which is not conducive to classifier learning; 3) The classification algorithm uses the nearest neighbor algorithm based on Euclidean distance, but the UPMOP characteristic curve is a typical time series, and all its information is included in the changes at different times. The relevance of the above is very important, and the traditional nearest neighbor classification algorithm based on Euclidean distance cannot solve this problem well.

Images