Overlapping radar signal modulation type identification method based on adaptive threshold network

• Main Authors: YANG JIANYU, LIANG CAIYU, HUANG YULIN, PEI JIFANG, HUO WEIBO, WANG HAO, ZHANG YIN, YANG HAIGUANG
• Format: Patent
• Language: Chinese; English
• Published: 16.09.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses an overlapping radar signal modulation type identification method based on an adaptive threshold network. The method comprises the following steps: S1, simulating an original radar signal and a modulation parameter; s2, overlapping the original radar signals; s3, extracting time-frequency domain features; s4, constructing a basic module; s5, an Inception module is constructed; s6, constructing an adaptive threshold module; s7, constructing a probability module; s8, an SE-IncepAtNet network is formed; s9, an SE-IncepAtNet network is trained; and S10, adopting the SE-IncepAtNet network after training to identify the modulation type of the overlapping radar signal. According to the method, overlapping radar signal features are extracted by using a time-frequency analysis method, features of different receptive fields are extracted based on a deep convolutional network Inception module, noise influence is reduced by using an SE module, the problem of difficulty in threshold setting in a mu