阅读说明：本技术 一种基于深度学习的跳频信号参数估计方法 (Frequency hopping signal parameter estimation method based on deep learning ) 是由 王燕 梁国龙 王哲睿 付进 张光普 王逸林 王晋晋 邹男 邱龙皓 郝宇 于 2021-07-07 设计创作，主要内容包括：本发明提供一种基于深度学习的跳频信号参数估计方法,属于电子对抗和通信技术领域,公开了一种,包括以下步骤：1)对接收到的跳频信号进行功率谱估计,得到跳频信号的频率集；2)以频率集中的频率个数来确定所需深度学习网络的个数,并构造对应频率集中各个频率的深度学习网络所需的训练集；3)将训练集输入各个网络中,完成深度学习网络的构建；4)将接收到的信号分别输入构建好的对应频率的网络中,从而获得各个频率所对应网络的输出；5)通过对各个网络的输出进行平滑处理,估计出接收跳频信号的时频参数。本发明对跳频信号在低信噪比条件下的时频参数具有较高的估计精度,对跳频信号的处理具有重要意义。(The invention provides a frequency hopping signal parameter estimation method based on deep learning, which belongs to the technical field of electronic countermeasure and communication and discloses a method, comprising the following steps of: 1) carrying out power spectrum estimation on the received frequency hopping signal to obtain a frequency set of the frequency hopping signal; 2) determining the number of required deep learning networks according to the number of frequencies in the frequency set, and constructing a training set required by the deep learning networks corresponding to each frequency in the frequency set; 3) inputting the training set into each network to complete the construction of the deep learning network; 4) inputting the received signals into the constructed networks with corresponding frequencies respectively, thereby obtaining the output of the network corresponding to each frequency; 5) and performing smoothing processing on the output of each network to estimate the time-frequency parameters of the received frequency hopping signal. The method has higher estimation precision on the time-frequency parameters of the frequency hopping signal under the condition of low signal-to-noise ratio, and has important significance on the processing of the frequency hopping signal.)

1. A frequency hopping signal parameter estimation method based on deep learning is characterized in that: the method comprises the following steps:

step 1: performing power spectrum estimation on the received frequency hopping signal by adopting an AR power spectrum estimation method, and setting a spectrum peak search condition to obtain a frequency set of the frequency hopping signal;

step 2: determining the number of required deep learning networks according to the number of frequencies in the frequency set, constructing a time domain waveform containing noise corresponding to each frequency in the frequency set, and constructing a training set required by the deep learning networks corresponding to each frequency in the frequency set;

and step 3: inputting the training set into each network to obtain a weight matrix and a bias vector of each network, and completing construction of a deep learning network;

and 4, step 4: inputting the received frequency hopping signals into the constructed networks with corresponding frequencies respectively to obtain the output corresponding to each frequency network;

and 5: and smoothing the output of each network to obtain the time domain distribution of the frequency corresponding to the network, and estimating the time-frequency parameters of the received frequency hopping signal.

2. The method according to claim 1, wherein the method comprises: in step 1, an AR power spectrum estimation method is adopted, the order of an AR model is determined through an AIC criterion, and the spectrum peak searching condition is set by using the frequency distribution characteristics of a frequency hopping signal.

3. The frequency hopping signal parameter estimation method based on deep learning according to claim 1 or 2, wherein: in step 2, a training set is constructed by using information obtained by receiving signals; assume a frequency in the frequency set of { f₁,f₂,…,f_nConstruction of f₁The training set of (a) is:

class 1: time domain signal containing useful signal and noise:

x₁(t)＝cos(2πf₁t)+n₁(t)；

class 0: time domain signal containing no useful signal but noise:

x₀(t)＝n₀(t)；

wherein: n (t) is white Gaussian noise; repeating the construction method for one hundred times to obtain the frequency f₁A training set containing one hundred class 1 samples and one hundred class 0 samples of the signal of (a): x is the number of_1,100One hundred samples, x, representing class 1_0,100The one hundred samples representing class 0; y is₁For corresponding to sample X₁The classification label of (1); assume a sample length of n_sLet n be_s＝n_w×f_sWherein n is_wIs a frequency of f₁The number of cycles of the cosine signal of f_sIs the sampling frequency, then X₁Is n_s×200，Y₁Is 1 × 200; other frequency signals in the frequency set are also used for constructing a training set in the same way to obtain n groups of training sets { X) corresponding to n carrier frequency frequencies₁，X₂，…，X_nAnd n sets of labels { Y }₁，Y₂，…，Y_n}。

4. The method according to claim 3, wherein the method comprises: in step 3, a deep neural network is respectively constructed for signals with different frequencies in the frequency set to classify time domain waveforms, the used neural network comprises two hidden layers, the number of nodes of the two hidden layers is 7 and 3 respectively, and a sigmoid function is adopted for an activation function of each layer.

5. The method according to claim 4, wherein the method comprises: in step 4, the received data are respectively input into the constructed neural network, and the length of a sample signal constructed by the training set is assumed to be n_sThe length of the signal to be measured passing through the window is n_sThen the signals intercepted by the sliding window are respectively input into the trained multilayer perceptron corresponding to n carrier frequencies to obtain n signals with the length of (t.f)_s-n_s+1) classification set.

6. The method according to claim 5, wherein the method comprises: in step 5, the obtained classification set is subjected to sliding average to eliminate the interference of random noise, and the classification set corresponding to n carrier frequencies obtained after the sliding average is assumed to be { C₁，C₂，…，C_nLet C be assumed₁For corresponding carrier frequency of f₁Classification set of (1), then C₁For corresponding carrier frequency of f₁In the time domain, if C₁If k points are classified as 1, the frequency of the frequency hopping signal is f₁Has a partial hold time of k/f_sSecond; classification set C₁The point of the first 1 classification in the sequence is the frequency f in the frequency hopping signal₁The carrier frequency of (2).

Technical Field

The invention belongs to the technical field of electronic countermeasure and communication, and relates to a frequency hopping signal parameter estimation method based on deep learning, which can be used for time-frequency parameter estimation of frequency hopping signals.

Background

The communication reconnaissance is a part of submarine communication countermeasure, and the frequency hopping signal is widely applied to the field of underwater acoustic communication due to strong multipath resistance, interference resistance, interception resistance and the like. Acquiring the parameters of the frequency hopping signal is a key link of communication countermeasure. For the underwater sound frequency hopping signal, the frequency, number, duration and other information of the signal are generally unknown, the underwater sound signal is greatly influenced by the channel and the background noise of the marine environment, and when the distance of the information source is long, the signal to noise ratio of the received signal is also greatly influenced, so that great difficulty is caused in analyzing the signal and extracting parameters. Under the complex conditions, the method has important significance for researching the time-frequency parameter estimation method of the underwater sound frequency hopping signal with the typical non-stationary characteristic under the complex conditions. Frequency hopping signals have a typical non-stationary characteristic and can be processed using time-frequency analysis methods. In the existing time-frequency estimation method, such as short-time Fourier transform (STFT) and Gabor transform, the window size is fixed, and the requirements of high time resolution and high frequency resolution cannot be met simultaneously; continuous Wavelet Transform (CWT), which can simultaneously obtain higher time-frequency resolution, but has a more serious influence on the performance of the algorithm at low signal-to-noise ratio; the WVD has better time-frequency aggregation, but has serious cross item interference to the time-frequency representation of frequency hopping signals; in the methods such as SPWVD and radial Gaussian kernel distribution, the kernel function is designed to carry out smooth filtering on the WVD, and although the cross term problem of the WVD can be well inhibited, the cross term inhibition method based on the kernel function can cause the reduction of time-frequency aggregation and is not beneficial to signal parameter estimation. In summary, the problems of the prior art are as follows: the performance of the algorithm for estimating the time-frequency parameters of the frequency hopping signals is obviously reduced under the condition of low signal-to-noise ratio.

Disclosure of Invention

The invention aims to overcome the defects of the prior art, and provides a frequency hopping signal parameter estimation method based on deep learning, which comprises the steps of firstly analyzing the power spectrum characteristics of a frequency hopping signal with a low signal-to-noise ratio under a Gaussian noise background to obtain a frequency set of the frequency hopping signal, and on the basis, constructing a training set of a frequency hopping signal time domain waveform according to the obtained frequency set; and then training the multilayer perceptron to obtain MLP weight matrixes and offset vectors of different frequency signal time domains, and further identifying the signals to be processed to obtain time domain distribution of different frequency signals, so that parameters such as the holding time and the hopping time of the frequency hopping signal are obtained. The time-frequency estimation performance of the method is simulated and analyzed, and the result shows that the method can effectively realize the time-frequency estimation of the frequency hopping signal under the condition of low signal-to-noise ratio.

The purpose of the invention is realized as follows: the invention provides a frequency hopping signal parameter estimation method based on deep learning, which comprises the steps of firstly analyzing the power spectrum characteristics of a frequency hopping signal with a low signal-to-noise ratio under a Gaussian noise background to obtain a frequency set of the frequency hopping signal, and on the basis, constructing a training set of a frequency hopping signal time domain waveform according to the obtained frequency set; and then training the multilayer perceptron to obtain MLP weight matrixes and offset vectors of different frequency signal time domains, and further identifying the signals to be processed to obtain time domain distribution of different frequency signals, so that parameters such as the holding time and the hopping time of the frequency hopping signal are obtained. The time-frequency estimation performance of the method is simulated and analyzed, and the result shows that the method can effectively realize the time-frequency estimation of the frequency hopping signal under the condition of low signal-to-noise ratio.

The method comprises the following specific steps:

step 1: performing power spectrum estimation on the received frequency hopping signal by adopting an AR power spectrum estimation method, and setting a spectrum peak search condition to obtain a frequency set of the frequency hopping signal;

step 2: determining the number of required deep learning networks according to the number of frequencies in the frequency set, constructing a time domain waveform containing noise corresponding to each frequency in the frequency set, and constructing a training set required by the deep learning networks corresponding to each frequency in the frequency set;

and step 3: inputting the training set into each network to obtain a weight matrix and a bias vector of each network, and completing construction of a deep learning network;

and 4, step 4: inputting the received frequency hopping signals into the constructed networks with corresponding frequencies respectively to obtain the output corresponding to each frequency network;

and 5: and smoothing the output of each network to obtain the time domain distribution of the frequency corresponding to the network, and estimating the time-frequency parameters of the received frequency hopping signal.

The invention also includes such structural features:

1. in step 1, an AR power spectrum estimation method is adopted, the order of an AR model is determined through an AIC criterion, and the spectrum peak searching condition is set by using the frequency distribution characteristics of a frequency hopping signal.

2. In step 2, a training set is constructed by using information obtained by receiving signals; assume a frequency in the frequency set of { f₁,f₂,…,f_nConstruction of f₁The training set of (a) is:

class 1: time domain signal containing useful signal and noise:

x₁(t)＝cos(2πf₁t)+n₁(t)；

class 0: time domain signal containing no useful signal but noise:

x₀(t)＝n₀(t)；

wherein: n (t) is white Gaussian noise; repeating the construction method for one hundred times to obtain the frequency f₁A training set containing one hundred class 1 samples and one hundred class 0 samples of the signal of (a): x is the number of_1,100One hundred samples, x, representing class 1_0,100Represents class 0The one hundred samples of (a); y is₁For corresponding to sample X₁The classification label of (1); assume a sample length of n_sLet n be_s＝n_w×f_sWherein n is_wIs a frequency of f₁The number of cycles of the cosine signal of f_sIs the sampling frequency, then X₁Is n_s×200，Y₁Is 1 × 200; other frequency signals in the frequency set are also used for constructing a training set in the same way to obtain n groups of training sets { X) corresponding to n carrier frequency frequencies₁,X₂,…，X_nAnd n sets of labels { Y }₁,Y₂,…，Y_n}。

3. In step 3, a deep neural network is respectively constructed for signals with different frequencies in the frequency set to classify time domain waveforms, the used neural network comprises two hidden layers, the number of nodes of the two hidden layers is 7 and 3 respectively, and a sigmoid function is adopted for an activation function of each layer.

4. In step 4, the received data are respectively input into the constructed neural network, and the length of a sample signal constructed by the training set is assumed to be n_sThe length of the signal to be measured passing through the window is n_sThen the signals intercepted by the sliding window are respectively input into the trained multilayer perceptron corresponding to n carrier frequencies to obtain n signals with the length of (t.f)_s-n_s+1) classification set.

5. In step 5, the obtained classification set is subjected to sliding average to eliminate the interference of random noise, and the classification set corresponding to n carrier frequencies obtained after the sliding average is assumed to be { C₁，C₂，…，C_nLet C be assumed₁For corresponding carrier frequency of f₁Classification set of (1), then C₁For corresponding carrier frequency of f₁In the time domain, if C₁If k points are classified as 1, the frequency of the frequency hopping signal is f₁Has a partial hold time of k/f_sSecond; classification set C₁The point of the first 1 classification in the sequence is the frequency f in the frequency hopping signal₁The carrier frequency of (2).

Compared with the prior art, the invention has the beneficial effects that: when the frequency hopping signal frequency set is extracted, the longer time integration is adopted, and compared with a windowing method which needs to give consideration to both time resolution and time resolution in short-time Fourier transform, the obtained frequency hopping signal carrier frequency is more accurate. Meanwhile, the characteristic of strong nonlinear classification performance of the deep neural network is utilized, the network is trained by establishing time domain waveforms of different carrier frequencies of frequency hopping signals, accurate time domain distribution of each carrier frequency can be obtained, frequency hopping signal time-frequency parameters can be estimated under the condition of low signal-to-noise ratio, the limitation of an uncertain principle to a linear time-frequency method can be overcome, the influence of nonlinear time-frequency estimation cross terms does not exist, and high estimation accuracy can be obtained in a time-frequency domain at the same time.

Drawings

FIG. 1 is a flow chart of an implementation of the present invention.

Fig. 2a and fig. 2b are both diagrams illustrating the influence of different training sample lengths on the estimation of the parameters of the frequency hopping signal.

FIG. 3 is a comparison of the STFT and SPWVD time-frequency plots of the present invention.

Fig. 4 a-4 c are graphs comparing the accuracy of parameter estimation according to the present invention with other methods.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.

Referring to fig. 1, a frequency hopping signal parameter estimation method based on deep learning includes the following steps:

step 1, performing power spectrum estimation on a received frequency hopping signal by adopting an AR power spectrum estimation method, and setting a spectrum peak search condition to obtain a frequency set of the frequency hopping signal;

specifically, an AR power spectrum estimation method is adopted, the order of an AR model is determined through an AIC criterion, and the spectrum peak searching condition is set by using the frequency distribution characteristics of a frequency hopping signal;

step 2, determining the number of required deep learning networks according to the number of frequencies in the frequency set, and constructing a time domain waveform containing noise corresponding to each frequency in the frequency set, so as to construct a training set required by the deep learning networks corresponding to each frequency in the frequency set;

in step 2, a training set is constructed by using information obtained from the received signal. Assume a frequency in the frequency set of { f₁，f₂，…，f_nConstruction of f₁The training set of (a) is:

class 1: time-domain signal containing useful signal and noise

x₁(t)＝cos(2πf₁t)+n₁(t)；

Class 0: time-domain signals containing no useful signal but only noise

x₀(t)＝n₀(t)；

Where n (t) is white Gaussian noise. Repeating the construction method for one hundred times to obtain the frequency f₁A training set containing one hundred class 1 samples and one hundred class 0 samples of the signal of (a): x is the number of_1,100One hundred samples, x, representing class 1_0,100Representing the one hundred samples of class 0. Y is₁For corresponding to sample X₁The classification label of (1). Assume a sample length of n_sLet n be_s＝n_w×f_sWherein n is_wIs a frequency of f₁The number of cycles of the cosine signal of f_sIs the sampling frequency, then X₁Is n_s×200，Y₁Is 1 × 200. Similarly, other frequency signals in the frequency set construct a training set in the same way to obtain n groups of training sets { X) corresponding to n carrier frequency frequencies₁，X₂,…,X_nAnd n sets of labels { Y }₁,Y₂,…,Y_n}。

The training sample length is determined by simulation:

the frequency point of the simulation carrier is {1.4,1.8,2.5,3.5} kHz, the carrier holding time is 50ms, and the take-off time T is₀The background noise is white gaussian noise and the SNR is-10 dB.

As can be seen from fig. 2(a), as the frequency increases, the minimum number of waveforms required for the training sample increases, and there is no fixed value for determining the training sample length. Definition k 1000 xn_w/f_cWherein f is_cFor the carrier frequency, by varying the size of the value of kThe change of the sample length is observed, and as can be seen from fig. 2(b), when k is 5, it can be ensured that the mean square error of the retention time of each frequency point is relatively small, and the length of the training sample is as short as possible, thereby reducing the computation amount when the multi-layer perceptron is trained. I.e. the length of the sample in the training set is n_s＝0.005×f_s。

Step 3, inputting the training set into each network to obtain a weight matrix and a bias vector of each network, and completing construction of a deep learning network;

in step 3, a deep neural network is respectively constructed for signals with different frequencies in the frequency set to classify time domain waveforms, the used neural network comprises two hidden layers, the number of nodes of the two hidden layers is 7 and 3 respectively, and a sigmoid function is adopted for an activation function of each layer.

Step 4, inputting the received frequency hopping signals into the constructed networks with corresponding frequencies respectively, thereby obtaining the output corresponding to each frequency network;

in step 4, the received data are respectively input into the constructed neural network, and the length of a sample signal constructed by the training set is assumed to be n_sThe length of the signal to be measured passing through the window is n_sThen the signals intercepted by the sliding window are respectively input into the trained multilayer perceptron corresponding to n carrier frequencies to obtain n signals with the length of (t.f)_s-n_s+1) classification set.

And step 5, smoothing the output of each network to obtain the time domain distribution of the frequency corresponding to the network, thereby estimating the time-frequency parameter of the received frequency hopping signal.

In step 5, the obtained classification set is subjected to sliding average to eliminate the interference of random noise, and the classification set corresponding to n carrier frequencies obtained after the sliding average is assumed to be { C₁,C₂,…,C_nLet C be assumed₁For corresponding carrier frequency of f₁Classification set of (1), then C₁For corresponding carrier frequency of f₁In the time domain, if C₁If k points are classified as 1, the frequency of the frequency hopping signal is f₁Has a partial hold time of k/f_sAnd second. Classification set C₁Of the first class 1The point is that the frequency of the frequency hopping signal is f₁The carrier frequency of (2).

The effectiveness of the invention can be verified by the following simulation:

1. the frequency hopping frequency is {1.3,1.7,1.4,1.9,1.8,1.6,1.2,1.5} kHz in sequence, and other simulation parameters are as follows: sampling frequency f_s20kHz, 400ms observation time T, and frequency hopping holding time T_k50ms, take-off time T₀0. The background noise is white gaussian noise, and the SNR is-10 dB.

FIG. 3 is a comparison between the time-frequency diagram of the STFT and SPWVD, wherein 3(a) is the time-frequency diagram obtained by STFT, and the time-frequency aggregation is poor; 3(b) is a time-frequency diagram obtained by SPWVD, and compared with STFT, the time-frequency aggregation is higher, but more cross item interference is generated; and 3(c) is the method provided by the invention, the time-frequency aggregation is better than that of the two previous traditional methods under the condition of the same signal-to-noise ratio, the time-frequency resolution is higher, and the time-frequency parameters can be estimated more easily.

2. The frequency hopping frequency is {1.3,1.7,1.4,1.9,1.8,1.6,1.2,1.5} kHz in sequence, and other simulation parameters are as follows: sampling frequency f_s20kHz, 400ms observation time T, and frequency hopping holding time T_k50ms, take-off time T₀0. The background noise is white gaussian noise, and 200 monte carlo experiments are carried out under different signal-to-noise ratios.

Fig. 4(a), fig. 4(b), and fig. 4(c) are diagrams illustrating the comparison between the STFD method and the improved time-frequency ridge line method, wherein the STFD method compares the frequency-hopping frequency retention time, the hopping time, and the estimation accuracy of the frequency-hopping frequency under different snr conditions. It can be seen that the method has higher estimation precision on the frequency hopping frequency holding time, the hopping time and the frequency hopping frequency under different signal-to-noise ratios.

The frequency hopping signal time-frequency parameter is estimated based on the deep learning method, so that the problem that the linear time-frequency method is restricted by an uncertain principle and is not influenced by nonlinear time-frequency estimation cross terms is solved, higher estimation precision can be obtained in the time-frequency domain, and higher time-frequency parameter estimation precision can be obtained under the condition of low signal-to-noise ratio.

In summary, the invention belongs to the technical field of electronic countermeasure and communication, and discloses a frequency hopping signal parameter estimation method based on deep learning, which comprises the following steps: 1) carrying out power spectrum estimation on the received frequency hopping signal to obtain a frequency set of the frequency hopping signal; 2) Determining the number of required deep learning networks according to the number of frequencies in the frequency set, and constructing a training set required by the deep learning networks corresponding to each frequency in the frequency set; 3) inputting the training set into each network to complete the construction of the deep learning network; 4) inputting the received signals into the constructed networks with corresponding frequencies respectively, thereby obtaining the output of the network corresponding to each frequency; 5) And performing smoothing processing on the output of each network to estimate the time-frequency parameters of the received frequency hopping signal. The method has higher estimation precision on the time-frequency parameters of the frequency hopping signal under the condition of low signal-to-noise ratio, and has important significance on the processing of the frequency hopping signal.