Radar high-resolution range profile recognition method based on graph neural network

Abstract

The invention discloses a radar high-resolution range profile recognition method based on a graph neural network, and the method comprises the following steps: S1, data preprocessing, S2, feature extraction, S3, classification result output, and S4, repeating the steps S1-S3 to complete a test, classifying HRRP test data through the step S1-1, and then sending the data into a model trained in the steps S1-S3 to perform a test. By adopting the technical scheme, the invention provides a sequence construction graph (seq2graph) method, the relation weight between the nodes is extracted from transformer, and the relation weight and the node features form graph structure data, so that a graph neural network method is conveniently utilized for processing, and a foundation is laid for improving the recognition effect and reducing the calculation amount.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a radar high-resolution range image recognition method based on a graph neural network. Background technique [0002] The high-resolution range profile (HRRP) is the sum of the scattered point echoes generated after the high-resolution radar scans the target. Since the range resolution of the high-resolution bandwidth radar is much smaller than the target size, the fluctuations and peak reflections in the high-resolution radar echo The relative geometric relationship of the target structure. In addition, apart from the signal bandwidth, there are no other strict requirements on the radar, and the HRRP data of the target can be easily obtained, and the HRRP data is one-dimensional, so the data can be stored conveniently, and the calculation amount is relatively reduced. From the above advantages, the radar automatic target recognition method based on HRRP has bec...

AI Technical Summary

Problems solved by technology

For the rookie BERT in NLP, it is mainly based on the transformer network structure, which is formed by the accumulation of multiple transformers in multiple dimensions. The transformer can effectively extract the features between two scattered points far apart in the HRRP sample, resulting in a relatively large Good results, but due to the stacking of a large number of transformers, the amount of calculation and memory consumption cannot be ignored

Images