CN111884967A - QPSK signal demodulation method based on time-frequency analysis and convolutional neural network - Google Patents
QPSK signal demodulation method based on time-frequency analysis and convolutional neural network Download PDFInfo
- Publication number
- CN111884967A CN111884967A CN202010743782.3A CN202010743782A CN111884967A CN 111884967 A CN111884967 A CN 111884967A CN 202010743782 A CN202010743782 A CN 202010743782A CN 111884967 A CN111884967 A CN 111884967A
- Authority
- CN
- China
- Prior art keywords
- time
- frequency distribution
- neural network
- convolutional neural
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/18—Phase-modulated carrier systems, i.e. using phase-shift keying
- H04L27/22—Demodulator circuits; Receiver circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
A QPSK signal demodulation method based on time-frequency analysis and a convolutional neural network specifically relates to a QPSK signal demodulation method. In order to solve the problem that a QPSK signal is seriously polluted by same frequency interference and noise, the method comprises the steps of firstly carrying out time-frequency analysis on a received QPSK pulse forming signal to obtain a time-frequency diagram and preprocessing the time-frequency diagram; then inputting a pre-trained convolutional neural network to classify the time-frequency graph of the received signal, selecting a filtering pass domain according to a classification result, and controlling a time-varying filter to filter and demodulate the received signal to obtain demodulation data; finally, a symbol sample set to which the received signal belongs can be obtained according to the classification result, and further error correction can be carried out on the demodulated data through the symbol sample set. The method can effectively inhibit same frequency interference, improve the signal-to-interference-and-noise ratio performance of a receiving end and reduce the bit error rate. The invention is suitable for demodulation of QPSK signals.
Description
Technical Field
The invention relates to the field of mobile communication, in particular to a QPSK signal demodulation method.
Background
In various non-orthogonal resource sharing modes, signals of different users are overlapped on a time-frequency plane, and a receiving end distinguishes the signals of the different users through the difference of a code domain, a space domain and a power domain to realize useful signal recovery. However, through time-frequency analysis of signals, we find that energy concentration areas of different user signals on a time-frequency plane are different, and can further combine a time-varying filtering method to filter received signals according to time-frequency distribution of useful signals, so as to improve the signal-to-interference-and-noise ratio of the signals and further improve the error rate performance. However, when time-varying filtering is used in a communication system, a filtering pass-band that conforms to the time-frequency distribution characteristics of useful signals cannot be accurately obtained from signals polluted by interference and noise. This patent selects the filtering pass-through field that matches with the received signal through the convolutional neural network, and then accomplishes the time-varying filtering, realizes interference and noise suppression. In addition, the symbol sample set corresponding to the matched filtering pass domain can further correct the error of the QPSK demodulation data, and the error rate performance is improved.
Disclosure of Invention
The invention aims to solve the problem that QPSK signals are seriously polluted by same frequency interference and noise. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network includes the following steps:
(1) receiving signals at a receiving end, and intercepting the received signals;
(2) performing time-frequency analysis on the intercepted signals to generate a time-frequency distribution graph, and preprocessing the generated time-frequency distribution graph;
(3) inputting the preprocessed time-frequency distribution graph into a trained convolutional neural network for classification, and determining a filtering pass domain corresponding to a received signal according to a classification result;
(4) generating a time-varying filtering template according to the time-frequency distribution map of the corresponding category, and performing time-varying filtering on the received signal to finally obtain a demodulation symbol;
(5) and further calculating Hamming distances between the demodulation symbols and 4 symbol samples corresponding to the received signal time-frequency distribution diagram, and correcting the demodulation symbols according to the symbol samples corresponding to the minimum Hamming distance.
Further, the signal truncation described in step (1) has a length of 4 symbol periods.
Further, the pretreatment process in the step (2) comprises the following steps: and copying the images in the first half period of the time of each time-frequency distribution graph to the tail part of the time-frequency distribution graph on the time dimension, so that the time dimension of each image is extended from 4 symbol periods to 6 symbol periods.
Further, the training method of the trained convolutional neural network in the step (3) includes the following steps:
(3.1) generating n time-frequency distribution maps according to I, Q paths of all possible transmitted data of QPSK signals, classifying the data to be transmitted with the same time-frequency distribution maps into one class, and generating n' class time-frequency distribution maps together;
(3.2) preprocessing the n' class time-frequency distribution graph of the classified QPSK signals;
and (3.3) training the neural network, and taking the m samples of each class of the preprocessed n' class time-frequency distribution graph as the input of the convolutional neural network to obtain the optimal weight of the neural network.
Preferably, n time-frequency distribution graphs are generated in the step (3.1), wherein n is 64.
Preferably, the step (3.1) of generating an n 'class time-frequency distribution graph is performed, wherein n' has a value of 16.
Further, the pretreatment process of step (3.2) comprises the following steps: and copying the images in the first half period of the time of each time-frequency distribution graph to the tail part of the time-frequency distribution graph on the time dimension, so that the time dimension of each image is extended from 4 symbol periods to 6 symbol periods.
Preferably, the value of m in the step (3.3) satisfies that m is more than or equal to 100.
Further, the m samples in step (3.3) satisfy that all the samples are pure time-frequency distribution graphs without interference and noise, and each time-frequency distribution graph after preprocessing is copied m times to obtain the pure time-frequency distribution graph.
The invention has the beneficial effects that:
because the energy concentration areas of different user signals on a time-frequency plane are different, the invention provides a QPSK signal demodulation method based on time-frequency analysis and a convolutional neural network, and a filtering pass-domain which accords with the time-frequency distribution characteristics of useful signals is accurately obtained from signals polluted by interference and noise, thereby realizing the function of an error correcting code to a certain degree, effectively inhibiting same-frequency interference, improving the signal-to-interference-and-noise ratio performance of a receiving end and reducing the bit error rate.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a 16-class time-frequency distribution diagram of a QPSK signal; wherein FIG. 2a represents signal 000001,001111,110000,111110; FIG. 2b shows signal 000010,010111,101000,111101; FIG. 2c shows signal 000011,011111,100000,111100; FIG. 2d shows signal 000100,011000,100111,111011; FIG. 2e shows signal 000101,010000,101111,111010; FIG. 2f shows signal 000110,001000,110111,111001; FIG. 2g shows signal 000111,111000,111111,000000; FIG. 2h shows signal 001101,010001,101110,110010; FIG. 2i shows signal 001001,001110,110001,110110; FIG. 2j shows signal 001001,001110,110001,110110; FIG. 2k shows signal 001011,011110,100001,110100; FIG. 2l shows signal 001100,011001,100110,110011; FIG. 2m shows signal 010010,010101,101010,101101; FIG. 2n shows signal 010011,011101,100010,101100; FIG. 2o shows signal 010100,011010,100101,101011; FIG. 2p shows signal 011011,011100,100011,100100;
FIG. 3 is a CNN classification result for a time-frequency distribution graph without preprocessing;
FIG. 4 is a time-frequency distribution graph after three types of error classification sample preprocessing; wherein FIG. 4a represents signal 000011,011111,100000,111100; FIG. 4b shows signal 000110,001000,110111,111001; FIG. 4c shows signal 001001,001110,110001,110110;
fig. 5 shows the result of CNN classification of the preprocessed time-frequency distribution map.
Detailed Description
In a first specific embodiment, the QPSK signal demodulation method based on time-frequency analysis and convolutional neural network described in this embodiment is described with reference to fig. 1, and specifically includes the following steps:
(1) according to I, Q paths of possible transmitted data of QPSK signal, 64 time-frequency distribution graphs are generated, and data to be transmitted with the same time-frequency distribution graph is classified into one type, so that 16 types of time-frequency distribution graphs are generated in total, as shown in FIG. 2 a-FIG. 2 p. Wherein the time-frequency analysis tool is selected from time-frequency transformation with high time-frequency resolution and good aggregation, such as short-time Fourier transform (STFT) or Choi-Williams distribution for inhibiting cross terms;
(2) the class 16 time-frequency distribution pattern of the classified QPSK signal is preprocessed. Copying the images in the first half duration of each time-frequency distribution graph to the tail of the time-frequency distribution graph in the time dimension, so that the time dimension of each image extends from 4 symbol periods to 6 symbol periods, as shown in fig. 3, wherein the 6-bit stream in the diagram represents 6-bit data modulated by a QPSK signal. The reason for this is that there are 3 time frequency distribution diagrams, which are just horizontal inversion images of the other 3 time frequency distribution diagrams, i.e. 000011 is an inversion image of the time frequency distribution diagram corresponding to 000001, 000110 is an inversion image of the time frequency distribution diagram corresponding to 000100, and 001001 is an inversion image of the time frequency distribution diagram corresponding to 011011. When the convolutional neural network extracts features from the 3 time-frequency distribution maps, the extracted features are the same as the mapping time-frequency distribution maps, so that three time-frequency distribution maps are completely indistinguishable in classification, as shown in fig. 4 a-4 c. In order to solve the problem, the time-frequency distribution graph is preprocessed as above, so that any two time-frequency distribution graphs are not in a turnover mapping relation any more;
(3) and taking the preprocessed 16-class time-frequency distribution graph as the input of a convolutional neural network, and training the neural network to obtain the optimal weight of the neural network. The structure of the neural network is designed according to a network design method, and each class of 16 classes of time-frequency distribution graphs input into the convolutional neural network for training has m samples; according to the characteristics of the neural network, wherein m needs to meet the training requirement and cannot be too small, and m is more than or equal to 100; the m samples are pure time-frequency distribution graphs without interference and noise, each time-frequency distribution graph after preprocessing is obtained by copying m times, and the classification result after training according to the method is shown in FIG. 5;
(4) at a communication terminal, a signal which is received from an antenna and is polluted by interference and noise passes through a down-conversion unit and an A/D conversion unit to obtain a signal y (n), and the signal y (n) is sent to a buffer for buffering;
(5) and intercepting the received signal y (n) buffered in the buffer, wherein the length of an intercepting window is 4 symbol periods by using a sliding window. And performing time-frequency analysis on the intercepted signals to generate a time-frequency distribution graph. Preprocessing the generated time-frequency distribution map, copying an image in the first half period of time of each time-frequency distribution map to the tail of the time-frequency distribution map on a time dimension, extending the time dimension of each image from 4 symbol periods to 6 symbol periods, and generating the preprocessed time-frequency distribution map;
(6) inputting the obtained time-frequency distribution graph of the received signal into a trained convolutional neural network for classification, and determining a filtering pass domain corresponding to the received signal according to a classification result;
(7) and generating a time-varying filtering template according to the time-frequency distribution map of the corresponding category, and performing time-varying filtering on the received signal to finally obtain a demodulation symbol. The time-varying filtering method can be implicit filtering or explicit filtering, but the time delay generated by the time-varying filtering needs to meet the design requirement of the system.
(8) And sending the time-varying filtered received signal to a QPSK demodulation unit for data demodulation to obtain recovered data.
(9) And sending the demodulated data into a symbol sample error correction unit, comparing the demodulated data with 4 symbol samples corresponding to the received signal time-frequency distribution graph, calculating the Hamming distance between the demodulated symbol and each sample, and correcting the demodulated symbol according to the symbol sample corresponding to the minimum Hamming distance to realize the function of error correction to a certain extent.
The present invention is capable of other embodiments and its several details are capable of modifications in various obvious respects, all without departing from the spirit and scope of the present invention.
Claims (9)
1. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network is characterized by comprising the following steps:
(1) receiving signals at a receiving end, and intercepting the received signals;
(2) performing time-frequency analysis on the intercepted signals to generate a time-frequency distribution graph, and preprocessing the generated time-frequency distribution graph;
(3) inputting the preprocessed time-frequency distribution graph into a trained convolutional neural network for classification, and determining a filtering pass domain corresponding to a received signal according to a classification result;
(4) generating a time-varying filtering template according to the time-frequency distribution map of the corresponding category, and performing time-varying filtering on the received signal to finally obtain a demodulation symbol;
(5) and further calculating Hamming distances between the demodulation symbols and 4 symbol samples corresponding to the received signal time-frequency distribution diagram, and correcting the demodulation symbols according to the symbol samples corresponding to the minimum Hamming distance.
2. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 1, wherein the length of the signal truncation in step (1) is 4 symbol periods.
3. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 1, wherein the preprocessing of step (2) comprises the following steps: and copying the images in the first half period of the time of each time-frequency distribution graph to the tail part of the time-frequency distribution graph on the time dimension, so that the time dimension of each image is extended from 4 symbol periods to 6 symbol periods.
4. The QPSK signal demodulation method according to claim 1, wherein the training method of the trained convolutional neural network in step (3) comprises the following steps:
(3.1) generating n time-frequency distribution maps according to I, Q paths of all possible transmitted data of QPSK signals, classifying the data to be transmitted with the same time-frequency distribution maps into one class, and generating n' class time-frequency distribution maps together;
(3.2) preprocessing the n' class time-frequency distribution graph of the classified QPSK signals;
and (3.3) training the neural network, and taking the m samples of each class of the preprocessed n' class time-frequency distribution graph as the input of the convolutional neural network to obtain the optimal weight of the neural network.
5. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 4, wherein n time-frequency distribution maps are generated in step (3.1), wherein n is 64.
6. The QPSK signal demodulation method according to claim 4, wherein the n 'class of time-frequency distribution patterns are generated in step (3.1), wherein n' is 16.
7. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 4, wherein the preprocessing of step (3.2) comprises the following steps: and copying the images in the first half period of the time of each time-frequency distribution graph to the tail part of the time-frequency distribution graph on the time dimension, so that the time dimension of each image is extended from 4 symbol periods to 6 symbol periods.
8. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 4, wherein the value of m in step (3.3) satisfies that m is greater than or equal to 100.
9. The QPSK signal demodulation method based on time-frequency analysis and convolutional neural network of claim 4, wherein the m samples in step (3.3) satisfy a clean time-frequency distribution map without interference and noise, and are obtained by duplicating each time-frequency distribution map after preprocessing m times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010743782.3A CN111884967B (en) | 2020-07-29 | 2020-07-29 | QPSK signal demodulation method based on time-frequency analysis and convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010743782.3A CN111884967B (en) | 2020-07-29 | 2020-07-29 | QPSK signal demodulation method based on time-frequency analysis and convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111884967A true CN111884967A (en) | 2020-11-03 |
| CN111884967B CN111884967B (en) | 2022-07-01 |
Family
ID=73201078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010743782.3A Active CN111884967B (en) | 2020-07-29 | 2020-07-29 | QPSK signal demodulation method based on time-frequency analysis and convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111884967B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116260547A (en) * | 2023-05-11 | 2023-06-13 | 武汉能钠智能装备技术股份有限公司四川省成都市分公司 | System and method for inhibiting same-frequency interference |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2375663A1 (en) * | 2010-04-01 | 2011-10-12 | Rohde & Schwarz GmbH & Co. KG | Method for classifying signals according to the modulation type used |
| CN105162434A (en) * | 2015-09-22 | 2015-12-16 | 哈尔滨工业大学 | Time-variant filtering parameter generating and realizing system and method based on time frequency analysis |
| CN107147600A (en) * | 2017-04-28 | 2017-09-08 | 电子科技大学 | A kind of digital modulation signals demodulator and its demodulation method based on neutral net |
| CN108764077A (en) * | 2018-05-15 | 2018-11-06 | 重庆邮电大学 | A kind of digital signal modulated sorting technique based on convolutional neural networks |
| CN108832982A (en) * | 2018-05-30 | 2018-11-16 | 毛述春 | A kind of time-frequency distributions modulator approach for base station signal |
| CN109361471A (en) * | 2018-11-22 | 2019-02-19 | 汤文宇 | A kind of optic communication format modulation signal recognition methods based on amplitude error analysis |
| CN109981517A (en) * | 2019-01-22 | 2019-07-05 | 西安电子科技大学 | A kind of QPSK neural network demodulation device and its control method based on FPGA |
| WO2020104465A2 (en) * | 2018-11-19 | 2020-05-28 | Resmed Sensor Technologies Limited | Methods and apparatus for detection of disordered breathing |
| CN111238814A (en) * | 2019-09-30 | 2020-06-05 | 杭州安脉盛智能技术有限公司 | Rolling bearing fault diagnosis method based on short-time Hilbert transform |
-
2020
- 2020-07-29 CN CN202010743782.3A patent/CN111884967B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2375663A1 (en) * | 2010-04-01 | 2011-10-12 | Rohde & Schwarz GmbH & Co. KG | Method for classifying signals according to the modulation type used |
| CN105162434A (en) * | 2015-09-22 | 2015-12-16 | 哈尔滨工业大学 | Time-variant filtering parameter generating and realizing system and method based on time frequency analysis |
| CN107147600A (en) * | 2017-04-28 | 2017-09-08 | 电子科技大学 | A kind of digital modulation signals demodulator and its demodulation method based on neutral net |
| CN108764077A (en) * | 2018-05-15 | 2018-11-06 | 重庆邮电大学 | A kind of digital signal modulated sorting technique based on convolutional neural networks |
| CN108832982A (en) * | 2018-05-30 | 2018-11-16 | 毛述春 | A kind of time-frequency distributions modulator approach for base station signal |
| WO2020104465A2 (en) * | 2018-11-19 | 2020-05-28 | Resmed Sensor Technologies Limited | Methods and apparatus for detection of disordered breathing |
| CN109361471A (en) * | 2018-11-22 | 2019-02-19 | 汤文宇 | A kind of optic communication format modulation signal recognition methods based on amplitude error analysis |
| CN109981517A (en) * | 2019-01-22 | 2019-07-05 | 西安电子科技大学 | A kind of QPSK neural network demodulation device and its control method based on FPGA |
| CN111238814A (en) * | 2019-09-30 | 2020-06-05 | 杭州安脉盛智能技术有限公司 | Rolling bearing fault diagnosis method based on short-time Hilbert transform |
Non-Patent Citations (1)
| Title |
|---|
| 黄震宇: ""基于深度学习的无线电信号识别方法研究"", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116260547A (en) * | 2023-05-11 | 2023-06-13 | 武汉能钠智能装备技术股份有限公司四川省成都市分公司 | System and method for inhibiting same-frequency interference |
| CN116260547B (en) * | 2023-05-11 | 2023-09-22 | 武汉能钠智能装备技术股份有限公司四川省成都市分公司 | System and method for inhibiting same-frequency interference |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111884967B (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Automatic modulation classification using CNN-LSTM based dual-stream structure | |
| CN108764077B (en) | Digital signal modulation classification method based on convolutional neural network | |
| CN107124381B (en) | Automatic identification method for digital communication signal modulation mode | |
| CN101124800B (en) | Coarse timing estimation system and methodology for wireless symbols | |
| O'Shea et al. | Learning approximate neural estimators for wireless channel state information | |
| CN110011942B (en) | Morse message intelligent detection and identification method based on deep learning | |
| Yang et al. | A sequential Monte Carlo blind receiver for OFDM systems in frequency-selective fading channels | |
| CN101764786B (en) | MQAM signal recognition method based on clustering algorithm | |
| CN109861932B (en) | Short wave Morse message automatic identification method based on intelligent image analysis | |
| CN111935046B (en) | Low-complexity frequency shift keying signal symbol rate estimation method | |
| Kharbech et al. | Blind digital modulation identification for MIMO systems in railway environments with high-speed channels and impulsive noise | |
| CN111884967B (en) | QPSK signal demodulation method based on time-frequency analysis and convolutional neural network | |
| CN104378320A (en) | Anti-interference communication method and receiving device based on single-channel blind source separation | |
| Gong et al. | A generative adversarial network based framework for specific emitter characterization and identification | |
| CN107276932B (en) | Blind source signal separation method and device | |
| Li et al. | Intelligent blind source separation technology based on OTFS modulation for LEO satellite communication | |
| CN109076038B (en) | Method for estimating parameters of a signal contained in a frequency band | |
| CN110113273B (en) | Time-frequency overlapping signal blind separation method based on frequency spectrum symmetry | |
| CN104270328B (en) | A kind of signal to noise ratio real-time estimation method | |
| CN116015484A (en) | SCA interference suppression method based on data driving | |
| CN112232120B (en) | Radar radiation source signal classification system and method based on software radio | |
| Li et al. | Blind separation for wireless communication convolutive mixtures based on denoising iva | |
| CN111814703B (en) | HB-based signal joint feature extraction method under non-reconstruction condition | |
| CN110190920B (en) | Reference signal extraction method and system based on minimum mean square error cancellation algorithm | |
| Weng et al. | Message structure aided attentional convolution network for rf device fingerprinting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |