Secondary Radar Signal Denoising Method Based on Deep Residual Separation Convolutional Network
A secondary radar, convolutional network technology, applied in the field of radar, can solve the problem of weak signal, affecting the correct decoding and decoding of the response signal, affecting the signal clarity, etc., to achieve the effect of high denoising performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0028] Step 1: Data preprocessing:
[0029] The secondary radar response signal with Gaussian white noise with signal-to-noise ratio SNR=5 is used as the training data set, and the response signal without noise is used as the training label. The total number of data is 60000.
[0030] The dataset is divided into training set, validation set, and test set with a ratio of (0.6, 0.2, 0.2).
[0031] The training sample data of the response signal is randomly scrambled, and the dimension of the batch data is expanded to form a 3D tensor with a time axis (samples, timesteps, features).
[0032] Normalize the training data.
[0033] Step 2: Build a deep residual separable neural network:
[0034] figure 1 It is a schematic diagram of the structure of the deep residual separable network model, including three parts: shallow feature extraction, downsampling deep feature extraction, and upsampling feature fusion.
[0035] The shallow feature extraction part is composed of two convo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


