CN-121997080-A - Multi-frequency hopping signal sorting method, system, device and storage medium for complex electromagnetic environment

CN121997080ACN 121997080 ACN121997080 ACN 121997080ACN-121997080-A

Abstract

The application provides a multi-frequency hopping signal sorting method, a system, a device and a storage medium for a complex electromagnetic environment, which are used for realizing multi-frequency hopping signal sorting under the complex electromagnetic environment without any prior information. The method comprises the steps of obtaining multi-frequency hopping signal data in a complex electromagnetic environment, wherein the multi-frequency hopping signal data comprise effective signal data and noise signal data, conducting time-frequency analysis processing on the multi-frequency hopping signal data to obtain time-frequency data corresponding to the multi-frequency hopping signal data, predicting optimal radius parameters in a DBSCAN clustering algorithm by using a neural network learning method, conducting DBSCAN clustering algorithm processing on the time-frequency data based on the optimal radius parameters to obtain clusters of the effective signals, and extracting characteristic parameters of the effective signals based on the clusters of the effective signals.

Inventors

ZHANG BING
ZHAO LEI
Gai Xiaoting
JIA LIN
CAO YU
ZHOU SHUYONG

Assignees

北京无线电计量测试研究所

Dates

Publication Date: 20260508
Application Date: 20251216

Claims (10)

1. A method for multi-hop signal sorting in a complex electromagnetic environment, the method comprising: Acquiring multi-frequency hopping signal data in a complex electromagnetic environment, wherein the multi-frequency hopping signal data comprises effective signal data and noise signal data; Performing time-frequency analysis processing on the multi-frequency hopping signal data to obtain time-frequency data corresponding to the multi-frequency hopping signal data; predicting optimal radius parameters in a DBSCAN clustering algorithm by using a neural network learning method; Performing DBSCAN clustering algorithm processing on the time-frequency data based on the optimal radius parameter to obtain clusters of the effective signals; and extracting characteristic parameters of the effective signals based on the clusters of the effective signals.
2. The method of claim 1, wherein the multi-hop signal data is acquired by an electromagnetic signal reconnaissance device and/or an electromagnetic environment monitoring device.
3. The method for sorting multi-frequency hopping signals in a complex electromagnetic environment according to claim 1, wherein the method for performing time-frequency analysis processing on the multi-frequency hopping signal data comprises at least one or more of short-time fourier transform, wiener distribution and wavelet analysis.
4. The method for sorting multi-frequency hopping signals in a complex electromagnetic environment according to claim 1, wherein the predicting the optimal radius parameter in the DBSCAN clustering algorithm by using a neural network learning method comprises: Setting a plurality of radius parameters and constructing a scoring function; based on the plurality of radius parameters, respectively performing a DBSCAN clustering algorithm on the time-frequency data to obtain clustering analysis results respectively corresponding to the plurality of radius parameters; obtaining score function values respectively corresponding to the radius parameters based on the radius parameters and the clustering analysis results respectively corresponding to the radius parameters; constructing a sample data set based on the plurality of radius parameters and score function values respectively corresponding to the plurality of radius parameters; based on the sample set, parameters of a neural network are optimized, so that the neural network can predict a cluster analysis result after DBSCAN clustering algorithm is carried out on the time-frequency data according to the radius parameters, and the neural network can further predict the optimal radius parameters.
5. The method for multi-hop signal sorting in a complex electromagnetic environment according to claim 4, wherein said optimizing parameters of a neural network based on said sample set comprises: Inputting a sample subset in the sample set into the neural network model, and obtaining an output value corresponding to the radius parameter in the sample subset by the neural network according to the radius parameter in the sample subset; calculating a loss function based on an output value corresponding to a radius parameter in the sample subset and a score function value in the sample subset; and optimizing parameters of the neural network based on the loss function.
6. The method for multi-hop signal sorting in a complex electromagnetic environment according to claim 1, wherein the optimizing parameters of the neural network based on the loss function comprises: and optimizing parameters of the neural network by adopting a small-batch gradient descent algorithm and a reverse algorithm based on the loss function.
7. The method of claim 1, wherein the characteristic parameters of the effective signal include center frequency, occupied bandwidth, maximum frequency hopping interval, minimum frequency hopping interval, and frequency hopping rate.
8. A multi-hop signal sorting system for use in a complex electromagnetic environment, the system comprising: The acquisition module is used for acquiring multi-frequency hopping signal data in a complex electromagnetic environment, wherein the multi-frequency hopping signal data comprises effective signal data and noise signal data; The processing module is used for carrying out time-frequency analysis processing on the multi-frequency hopping signal data to obtain time-frequency data corresponding to the multi-frequency hopping signal data, predicting an optimal radius parameter in a DBSCAN clustering algorithm by utilizing a neural network learning method, and carrying out DBSCAN clustering algorithm processing on the time-frequency data based on the optimal radius parameter to obtain clusters of the effective signals; And the extraction module is used for extracting the characteristic parameters of the effective signals based on the clusters of the effective signals.
9. A multi-frequency hopping signal sorting apparatus for use in a complex electromagnetic environment, characterized in that the apparatus comprises means for performing the method according to any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a storage computer program or instructions which, when executed, cause the method of any of claims 1-7 to be performed.

Description

Multi-frequency hopping signal sorting method, system, device and storage medium for complex electromagnetic environment Technical Field The application relates to the field of electromagnetic signal sorting, in particular to a multi-frequency hopping signal sorting method, a system, a device and a storage medium for a complex electromagnetic environment. Background The frequency hopping communication technology has better anti-interference performance, is widely adopted in the fields of short wave and ultrashort wave communication radio stations and the like, and also brings great challenges to frequency hopping signal reconnaissance and analysis, especially multi-frequency hopping signal reconnaissance and analysis in a complex electromagnetic environment. In the process of reconnaissance and analysis of frequency hopping signals, the existing multi-frequency hopping signal sorting method mainly adopts a non-blind sorting method based on partial prior information (the number of signal sources or partial characteristic parameters of the signals), namely firstly, the multi-frequency hopping signals in a complex electromagnetic environment are extracted by using a time-frequency analysis method, then, the characteristic parameters of the frequency hopping signals including frequency parameters, period parameters, hopping moments and the like are measured and estimated, and finally, the sorting of the multi-frequency hopping signals is realized under the support of the prior information based on the measured characteristic parameters. However, the precondition for implementing multi-frequency hopping signal sorting is to have a certain multi-frequency hopping signal prior information. Therefore, how to realize multi-frequency hopping signal sorting in a complex electromagnetic environment without any prior information has become an important research point in the fields of reconnaissance and countermeasure. Disclosure of Invention The embodiment of the application provides a multi-frequency hopping signal sorting method used in a complex electromagnetic environment, which is suitable for realizing multi-frequency hopping signal sorting in the complex electromagnetic environment under the condition of no prior information. In order to achieve the above purpose, the application adopts the following technical scheme: In a first aspect, the present application provides a multi-frequency hopping signal sorting method for use in a complex electromagnetic environment, the method comprising obtaining multi-frequency hopping signal data in the complex electromagnetic environment, wherein the multi-frequency hopping signal data comprises effective signal data and noise signal data; performing time-frequency analysis processing on the multi-frequency hopping signal data to obtain time-frequency data corresponding to the multi-frequency hopping signal data; predicting optimal radius parameters in a DBSCAN clustering algorithm by using a neural network learning method; based on the optimal radius parameter, performing DBSCAN clustering algorithm processing on the time-frequency data to obtain clusters of effective signals; and extracting characteristic parameters of the effective signals based on the clusters of the effective signals. In one possible implementation, the method of the first aspect further includes that the multi-frequency hopping signal data is acquired by an electromagnetic signal reconnaissance device and/or an electromagnetic environment monitoring device. In one possible design, the method of the first aspect further comprises a method for performing time-frequency analysis processing on the multi-frequency hopping signal data, wherein the method comprises at least one or more of short-time Fourier transformation, wiggner distribution and wavelet analysis. A possible design solution, the method of the first aspect further includes predicting an optimal radius parameter in the DBSCAN clustering algorithm by using a neural network learning method, including: Setting a plurality of radius parameters and constructing a scoring function; based on a plurality of radius parameters, respectively performing a DBSCAN clustering algorithm on the time-frequency data to obtain clustering analysis results respectively corresponding to the plurality of radius parameters; obtaining score function values corresponding to the radius parameters based on the radius parameters and the clustering analysis results corresponding to the radius parameters; Constructing a sample data set based on the plurality of radius parameters and the score function values respectively corresponding to the plurality of radius parameters; Based on the sample set, parameters of the neural network are optimized, so that the neural network can predict a clustering analysis result after DBSCAN clustering algorithm is performed on time-frequency data according to the radius parameters, and the neural network can further predict the optimal radius