Modulation signal denoising method based on self-encoding neural network

Abstract

The invention discloses a modulation signal denoising method based on a self-encoding neural network, and the method comprises the following steps: 1, simulating a general communication link structure through MATLAB simulation software, and generating a noisy sample data set and a pure sample data set of various communication modulation signals; step 2, performing [0, 1] normalization on each sample set; 3, constructing a modulation signal denoising automatic encoder based on the self-encoding neural network, and setting hyper-parameters; and 4, training the denoising model, and optimizing and updating the values of the parameters in the neural network by using a back propagation algorithm and a gradient descent method to obtain the denoising model. According to the method, the denoising network model based on the self-encoding neural network is used, the complex signal preprocessing process in a traditional modulation signal denoising algorithm is avoided, the overall structure process is simple, the network calculation amount is small, and the denoising speed is high.

Description

technical field [0001] The invention belongs to the technical field of communication signal processing, in particular to a modulation signal denoising method based on an autoencoder neural network. Background technique [0002] The modulation recognition technology of communication signals is the key step and basic link to realize signal detection and demodulation, and has a wide range of applications in the fields of spectrum sensing, electronic countermeasures and defense. In recent years, feature-based automatic modulation recognition technology has made great progress, such as methods based on instantaneous features, high-order cumulants, cyclic spectrum techniques, time-frequency analysis, wavelet transform, etc. These methods usually use noisy modulation signals as samples set, it is necessary to design complex algorithms to extract feature quantities, and these feature quantities are often affected by noise information in the signal, especially in a low signal-to-nois...

AI Technical Summary

Problems solved by technology

Although this method proposes a denoising method for modulated signals, there are still shortcomings in this method: the training data only contains a single pulse waveform, and the pulse width only contains 2 to 3 ns, which does not cover the modulation in actual multiple modulation modes The various complex situations of the signal do not mean that a good effect has been achieved for the modulated signal in the actual complex and changeable situation.

Images