Feature-level fusion recognition method of radar jamming signal based on deep convolutional neural network
A convolutional neural network and radar jamming technology, applied in the field of radar jamming signal feature-level fusion recognition, can solve the problems of features susceptible to noise, redundancy, etc., to improve robustness and robustness, improve fault tolerance and robustness Stickiness, the effect of improving the accuracy of interference identification
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0042] Specific implementation mode 1. Combination figure 1 and figure 2 As shown, the present invention provides a feature-level fusion identification method of radar jamming signals based on a deep convolutional neural network, including establishing a radar jamming time domain data set, and analyzing the radar jamming time domain data in the radar jamming time domain data set with two Extract feature vectors in different forms, and then fuse the two extracted feature vectors in series; use the fused feature vectors to train a support vector machine to obtain a trained radar interference signal feature-level fusion recognition model;
[0043] The two extracted feature vectors include: a feature vector extracted by a one-dimensional convolutional neural network and an expert feature vector extracted manually;
[0044] Or the feature vector extracted by one-dimensional convolutional neural network and the time-frequency domain feature vector extracted by deep convolutional n...
specific Embodiment 1
[0049] combine figure 1 As shown, for the feature vector extracted by one-dimensional convolutional neural network and the expert feature vector extracted manually, the process of obtaining the feature-level fusion recognition model of radar interference signal includes:
[0050] The artificial feature parameter extraction is performed on the radar jamming time domain data, and the obtained expert feature vectors include the time domain moment skewness, the time domain moment kurtosis, the time domain signal envelope fluctuation, the mean value of the time domain jamming signal and the variance of the time domain jamming signal. ;
[0051] At the same time, the radar interference time domain data is divided into training set, validation set and test set;
[0052] Using a one-dimensional convolutional neural network to extract the training sample feature vector from the data in the training set, perform PCA processing on the training sample feature vector, and then fuse the PC...
specific Embodiment 2
[0070] combine figure 2 As shown, for the feature vector extracted by the one-dimensional convolutional neural network and the time-frequency domain feature vector extracted by the deep convolutional neural network, the process of obtaining the feature-level fusion recognition model of the radar interference signal includes:
[0071] Divide the radar interference time domain data into time domain training set, time domain validation set and time domain test set;
[0072] Using a one-dimensional convolutional neural network to extract the time-domain training sample feature vector from the data in the time-domain training set;
[0073] At the same time, the time-frequency transform of the radar jamming time domain data is performed to obtain the radar jamming time-frequency domain data, and the radar jamming time-frequency domain data is divided into a time-frequency domain training set, a time-frequency domain verification set and a time-frequency domain test set;
[0074] U...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com