Radio signal unique identity identification method based on I / Q component weight characteristics

Abstract

The invention provides a radio signal unique identity identification method based on I / Q component weight features. The method comprises the following steps: S11, carrying out I / Q data acquisition on a monitoring frequency band of target radio equipment of each detection node; s12, processing the I / Q data to obtain a to-be-evaluated value; s13, judging whether the target radio equipment has a signal or not through the to-be-evaluated value, if yes, executing the step S14, and if not, executing the step S11 again; s14, performing secondary processing on the I / Q data to obtain a radio frequency fingerprint characteristic value, matching the radio frequency fingerprint characteristic value with a pre-stored radio frequency fingerprint characteristic value in a radio frequency fingerprint characteristic database, and identifying a signal; and S15, if the signal identification in the step S14 fails, storing the radio frequency fingerprint characteristic value into a radio frequency fingerprint characteristic database. According to the method, the features are directly extracted from the I / Q data, and the phase and amplitude information of the signal can be fully utilized, so that the signal can be identified more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of fingerprint feature extraction, and in particular to a radio signal unique identity recognition method based on I / Q component weight features. Background Art

[0002] Traditional signal recognition methods include spectrum analysis, time domain analysis, matched filter detection, energy detection and recognition methods based on deep learning.

[0003] Spectral analysis is a technique that decomposes complex signals into simpler signals. Its principle is to find out the information of these signals at different frequencies, such as amplitude, power, intensity or phase. Spectrum refers to the representation of a time domain signal in the frequency domain, which can be obtained by Fourier transforming the signal. The result will be two graphs with amplitude and phase as the vertical axis and frequency as the horizontal axis. By performing spectral analysis on the signal, the distribution of the signal in the frequency domain can be obtained. However, the disadvantage of spectral analysis is that its processing process is complicated, and for certain types of signals (such as non-stationary signals or transient signals), the accuracy of spectral analysis may be affected.

[0004] Time domain analysis refers to the analysis of the stability, transient and steady-state performance of the control system based on the time domain expression of the output under certain input. The filtering, amplification, statistical feature calculation, correlation analysis and other processing of the signal in the time domain are collectively referred to as the time domain analysis of the signal. Through the time domain analysis method, the signal-to-noise ratio can be effectively improved, and the similarity and correlation of the signal waveform at different times can be obtained. The disadvantage of the time domain analysis method is that it cannot directly provide the frequency information of the signal, and it is difficult to extract the timing features of complex signals. The matched filter is a signal processing technology. Its working principle is to convolve the received signal with the complex conjugate (time reversal) of the signal, and then integrate the result to achieve signal enhancement and noise suppression. Its disadvantages are that it has a large amount of calculation and requires accurate prior information of the authorized user signal, which leads to certain difficulties in its practical application.

[0005] Energy detection is a non-coherent signal detection method, which is applicable to the case where the signal detection party does not know the prior information of the authorized user signal. Its disadvantage is that it is difficult to set the threshold value. In an environment with low signal-to-noise ratio, the energy detection method is easy to identify interference noise with very large energy as a useful signal, and exclude weak signals with small energy, resulting in reduced detection accuracy.

[0006] The recognition method based on deep learning is an advanced signal recognition technology developed in recent years. It mainly extracts and classifies signals through deep learning models such as convolutional neural networks (CNN). This recognition method has high complexity and computing resource requirements, and requires a large amount of training data to optimize the model. Summary of the invention

[0007] The purpose of the present invention is to provide a method for uniquely identifying a radio signal based on I / Q component weight characteristics, which can fully utilize the phase and amplitude information of the signal by directly extracting features from I / Q data, thereby achieving more accurate identification of the signal.

[0008] To achieve the above object, the present invention provides a method for uniquely identifying a radio signal based on I / Q component weight characteristics, the method comprising:

[0009] S11, collecting I / Q data for the monitoring frequency band of the target radio equipment of each detection node;

[0010] S12, processing the I / Q data to obtain a value to be evaluated;

[0011] S13, judging whether the target radio device has a signal by the value to be evaluated, if yes, executing step S14, if no, re-executing step S11;

[0012] S14, performing secondary processing on the I / Q data to obtain a radio frequency fingerprint characteristic value, matching the radio frequency fingerprint characteristic value with a pre-stored radio frequency fingerprint characteristic value in a radio frequency fingerprint characteristic database, and identifying the signal;

[0013] S15. If the signal recognition fails in step S14, the radio frequency fingerprint feature value is stored in the radio frequency fingerprint feature database.

[0014] Furthermore, in step S11, each detection node is composed of a main control module and a software radio module, the software radio module is used to collect I / Q data, the software radio module is used to receive and preprocess the I / Q data, and the main control module is signal-connected to the software radio module.

[0015] Further, in step S12, the I / Q data is processed, specifically including:

[0016] The Q values ​​in the collected I / Q data are subtracted from the back to the front, and the absolute values ​​of all the values ​​after the subtraction are summed to obtain the value to be evaluated.

[0017] Further, in step S13, determining whether there is a signal of the target radio device by the value to be evaluated specifically includes:

[0018] The value to be evaluated is compared with the preset threshold. When the value to be evaluated is less than the preset threshold, it is determined that no signal is detected and step S11 is executed again. When the value to be evaluated is greater than or equal to the preset threshold, step S14 is executed.

[0019] Furthermore, in step S14, the collected data is subjected to secondary processing, specifically including:

[0020] S21, statistically analyzing the count value of each I / Q data, and using the count value as the characteristic value corresponding to each I / Q data;

[0021] S22, setting the weight value of I / Q data;

[0022] S23, multiply each eigenvalue by its corresponding weight value and then sum them up to obtain the x value on the new coordinate axis;

[0023] S24, summing the absolute values ​​of the horizontal and vertical coordinates of all points that have appeared in the two-dimensional distribution feature as the y value on the new coordinate axis, wherein the two-dimensional distribution feature is composed of I and Q;

[0024] S25, processing all I / Q data sampled once through steps S21 to S24, filling in new coordinates, transforming to form a curve that approximates an 8th-order polynomial consisting of 9 parameters, and fitting the curve to obtain a characteristic distribution curve of the signal;

[0025] S26. Using the vertex coordinates and nine parameters of the characteristic distribution curve as the radio frequency fingerprint characteristic values ​​of the signal source.

[0026] Furthermore, the count value of each I / Q data is statistically analyzed, including:

[0027] S31, describing each I / Q component of the I / Q data in a complex form I+jQ, with I as the horizontal axis and Q as the vertical axis, to obtain a two-dimensional distribution of each I / Q component;

[0028] S32, taking the number of points with the same horizontal and vertical coordinates as the count value of the I / Q component;

[0029] S33. Use the count value as the characteristic value corresponding to each I / Q data.

[0030] Furthermore, when setting the weight value of I / Q data, the stronger the signal energy, the closer the I value and Q value of the I / Q data are to the four coordinate points of (1, -1), (-1, -1), (1, 1), and (-1, 1), and the smaller the weight value; the weaker the signal energy, the more concentrated the I value and Q value of the I / Q data are at the coordinate point of (0, 0), and the larger the weight value. The weight is set according to this rule.

[0031] Furthermore, the expression of the curve consisting of 9 parameters approximating the 8th-order polynomial is:

[0032] Curve=a+b*X+c*X 2 +d*X 3 +e*X 4

[0033] +f*X 5 +g*X 6 +h*X 7 +i*X 8

[0034] Among them, Curve is the curve of an 8th-order polynomial, a, b, c, d, e, f, g, h, and i are constant terms, that is, 9 parameters, and X is the independent variable.

[0035] Further, the radio frequency fingerprint feature value is matched with the radio frequency fingerprint feature value in the radio frequency fingerprint feature database to identify the signal, specifically including:

[0036] S41, firstly, compare the vertex coordinates of the radio frequency fingerprint feature value with the vertex coordinates in the radio frequency fingerprint feature database one by one;

[0037] S42, if the distance between the vertex coordinates of the radio frequency fingerprint feature value and the vertex coordinates in the radio frequency fingerprint feature database is greater than a preset threshold, the matching fails, and the radio frequency fingerprint feature value is stored in the radio frequency fingerprint feature database;

[0038] S43. If the distance between the vertex coordinates of the RF fingerprint feature value and the vertex coordinates in the RF fingerprint feature database is less than or equal to the preset threshold, continue to match the curve consisting of an approximate 8th-order polynomial consisting of 9 parameters, with an average error between 210,000 and 500,000 on the horizontal axis. If the average error is greater than the preset threshold, the matching fails. The RF fingerprint feature value is stored in the RF fingerprint feature database. If the average error is less than or equal to the preset threshold, the matching is successful.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention provides a unique identification method for radio signals based on I / Q component weight features, which only uses original I / Q data but not energy data. The characteristic curve extracted based on I / Q data will not change due to environmental changes and center frequency changes, and has good stability. Compared with the electromagnetic spectrum energy detection method, it has a better recognition rate. Compared with the signal recognition method based on deep learning, this method has lower computing power requirements and lower complexity. Compared with the method of using other signal features as radio frequency fingerprints, directly extracting features from I / Q data plays a key role in identifying information such as the modulation mode and emission source of the signal.

[0041] Compared with traditional signal recognition methods, the feature extraction of the present invention is more direct and efficient, and can make full use of the phase and amplitude information of the signal to achieve more accurate signal recognition, especially in complex communication environments, such as in the presence of multipath interference, noise interference, etc., it can still maintain a high degree of accuracy. The radio measurement task requires improving the capabilities of each electromagnetic spectrum monitoring terminal device. The I / Q data distribution feature proposed in the present invention is a baseband signal, and the radio frequency hardware features of the radio equipment can be effectively extracted from it, which is suitable for the establishment of a distributed electromagnetic spectrum monitoring terminal with radio equipment as the monitoring object. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0043] Figure 1 A schematic flow chart of a method for uniquely identifying a radio signal based on I / Q component weight characteristics provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0045] Reference Figure 1 This embodiment provides a method for uniquely identifying a radio signal based on I / Q component weight characteristics, the method comprising:

[0046] S11, collect I / Q data for the monitoring frequency band of the target radio equipment of each detection node. In step S11, each detection node is composed of a main control module and a software radio module, the software radio module is used to collect I / Q data, the software radio module is used to receive and pre-process the I / Q data, and the main control module is connected to the software radio module signal.

[0047] In this embodiment, each detection node is composed of a main control module and a software radio module. The main control module can be a Windows platform or an embedded hardware platform, and the software radio module can be various software radio products. The software radio module is mainly responsible for the collection of I / Q data, and the main control module is responsible for controlling the software radio module, which can receive and preprocess I / Q data. In this embodiment, multiple monitoring nodes can be combined to collaboratively collect and process RF I / Q data.

[0048] S12, processing the I / Q data to obtain the value to be evaluated. In step S12, processing the I / Q data specifically includes:

[0049] The Q values ​​in the collected I / Q data are subtracted from the back to the front, and the absolute values ​​of all the values ​​after the subtraction are summed to obtain the value to be evaluated.

[0050] In this embodiment, the value to be evaluated increases with the increase of signal energy intensity. When the signal-to-noise ratio is 0 dB, this value is still different from the value obtained by pure noise. The signal and noise are distinguished by setting a threshold.

[0051] S13, judging whether the target radio device has a signal by the value to be evaluated, if yes, executing step S14, if no, re-executing step S11. In step S13, judging whether the target radio device has a signal by the value to be evaluated specifically includes:

[0052] The value to be evaluated is compared with the preset threshold. When the value to be evaluated is less than the preset threshold, it is determined that no signal is detected and step S11 is executed again. When the value to be evaluated is greater than or equal to the preset threshold, step S14 is executed.

[0053] In this embodiment, if no signal is detected, the signal of the target radio device continues to be collected until it is determined that a signal exists in the monitoring frequency band, and the signal is identified.

[0054] S14, perform secondary processing on the I / Q data to obtain a radio frequency fingerprint feature value, match the radio frequency fingerprint feature value with the pre-stored radio frequency fingerprint feature value in the radio frequency fingerprint feature database, and identify the signal. In step S14, perform secondary processing on the collected data, specifically including:

[0055] S21. Statistically analyze the count value of each I / Q data, and use the count value as the eigenvalue corresponding to each I / Q data. Extract the I / Q data collected by the software radio module, and statistically analyze the count value of each I / Q data. In the I / Q data of the RF baseband signal, each I / Q component is described in the complex form I+jQ. With I as the horizontal axis and Q as the vertical axis, a two-dimensional distribution of each I / Q component can be obtained (all I and Q values ​​are between -1 and 1). An I / Q data contains 131072 I / Q components. In the coordinate system composed of I and Q, the number of points with the same horizontal and vertical coordinates is used as the count value of the I / Q component. The count value is used as the eigenvalue of the I / Q component under the same horizontal and vertical coordinates. By setting the count value, an I / Q data can be converted into N eigenvalues.

[0056] S22, set the weight value of I / Q data. By analyzing the two-dimensional distribution of I / Q data, it is found that the stronger the signal energy intensity, the more divergent the two-dimensional distribution of I / Q data is, and finally concentrated on the four coordinate points of (1, -1), (-1, -1), (1, 1), (-1, 1). The weaker the signal energy intensity, the more concentrated the two-dimensional distribution of I / Q data is on the coordinate (0, 0). The closer to (0, 0), the larger the weight value is, and the closer to the four coordinate points of (1, -1), (-1, -1), (1, 1), (-1, 1), the smaller the weight value is, and the weight is set according to this rule.

[0057] S23, multiply each eigenvalue by its corresponding weight value and then sum it up to obtain the x value on the new coordinate axis. After an I / Q data is processed by S21, N eigenvalues ​​are obtained. Each eigenvalue is multiplied by its corresponding weight value and then summed up to obtain the x value on the new coordinate axis. The x value is used to describe the distribution characteristics of the I / Q data. The larger the x value, the weaker the signal strength.

[0058] S24, summing the absolute values ​​of the horizontal and vertical coordinates of all points that have appeared in the two-dimensional distribution feature as the y value on the new coordinate axis, wherein the two-dimensional distribution feature is composed of I and Q. After the I / Q data is transformed by S21, summing the absolute values ​​of the coordinates of all points that have appeared in the coordinate system composed of I and Q as the y value on the new coordinate axis, that is, the stronger the signal energy, the wider the distribution range, and the weaker the signal energy, the narrower the distribution range, and according to this rule, the range of signal distribution (that is, summing the absolute values ​​of the horizontal and vertical coordinates of the points that have appeared) is used as the y value in the new coordinate system.

[0059] S25. All I / Q data of a single sampling are processed through steps S21 to S24, and a new coordinate transformation is filled in to form a curve that is approximately an 8th-order polynomial composed of 9 parameters, and the curve is fitted to obtain the characteristic distribution curve of the signal. One I / Q data is converted into a point on the new coordinate axis. A single sampling includes multiple I / Q data. All I / Q data of a single sampling are processed through steps S21 to S24 to form a curve that is approximately an 8th-order polynomial composed of 9 parameters. The characteristic distribution curve of the signal is obtained by fitting the 8th-order polynomial.

[0060] S26, taking the vertex coordinates and 9 parameters of the characteristic distribution curve as the radio frequency fingerprint characteristic values ​​of the signal source. Taking the vertex coordinates and 9 parameters of the characteristic distribution curve obtained by fitting as the radio frequency fingerprint characteristic values ​​of the signal source.

[0061] Statistical analysis of the count value of each I / Q data, including:

[0062] S31. Describe each I / Q component of the I / Q data in the complex form I+jQ, with I as the horizontal axis and Q as the vertical axis, to obtain a two-dimensional distribution of each I / Q component.

[0063] S32. Use the number of points with the same horizontal and vertical coordinates as the count value of the I / Q component.

[0064] S33. Use the count value as the characteristic value corresponding to each I / Q data.

[0065] In this embodiment, the I / Q data collected by the software radio module is extracted, and the count value of each I / Q data is statistically analyzed. In the I / Q data of the radio frequency baseband signal, each I / Q component is described in the complex form I+jQ. With I as the horizontal axis and Q as the vertical axis, a two-dimensional distribution of each I / Q component can be obtained (all I and Q values ​​are between -1 and 1). One I / Q data contains 131072 I / Q components. In the coordinate system composed of I and Q, the number of points with the same horizontal and vertical coordinates is used as the count value of the I / Q component, and the count value is used as the eigenvalue of the I / Q component under the same horizontal and vertical coordinates. By setting the count value, one I / Q data can be converted into N eigenvalues.

[0066] When setting the weight value of I / Q data, the stronger the signal energy, the closer the I value and Q value of the I / Q data are to the four coordinate points (1, -1), (-1, -1), (1, 1), and (-1, 1), and the smaller the weight value; the weaker the signal energy, the more concentrated the I value and Q value of the I / Q data are at the coordinate point (0, 0), and the larger the weight value. The weight is set according to this rule.

[0067] In this embodiment, by analyzing the two-dimensional distribution of I / Q data, it is found that the stronger the signal energy intensity, the more divergent the two-dimensional distribution of I / Q data is, and finally it is concentrated on the four coordinate points of (1, -1), (-1, -1), (1, 1), and (-1, 1). The weaker the signal energy intensity, the more concentrated the two-dimensional distribution of I / Q data is at the coordinate point (0, 0). The closer to (0, 0), the larger the weight value is, and the closer to (1, -1), (-1, -1), (1, 1), (-1 , 1) The smaller the weight values ​​of the four coordinate points, that is, in the coordinate system obtained with I as the horizontal axis and Q as the vertical axis, the stronger the signal energy, the closer the I and Q values ​​of the I / Q data are to 1 and -1, and the weaker the signal energy, the closer the I and Q values ​​of the I / Q data are to 0. The closer the point (I, Q) is to (0, 0), the larger the weight value of the coordinate point is, and the closer the point (I, Q) is to the four coordinate points (1, -1), (-1, -1), (1, 1), and (-1, 1), the smaller the weight value is. The weights are set according to this rule.

[0068] The expression of the curve consisting of 9 parameters approximating the 8th degree polynomial is:

[0069] Curve=a+b*X+c*X 2 +d*X 3 +e*X 4

[0070] +f*X 5 +g*X 6 +h*X 7 +i*X 8

[0071] Among them, Curve is the curve of an 8th-order polynomial, a, b, c, d, e, f, g, h, and i are constant terms, that is, 9 parameters, and X is the independent variable.

[0072] In this embodiment, the degree of the polynomial is directly related to the shape of the curve. By using an n-order polynomial to fit the new coordinate points, n+1 variables can be generated (in this embodiment, the 8th-order polynomial fitting obtains nine new parameters a, b, c, d, e, f, g, h, and i). These fitted variables are the eigenvalues. Through testing, it is found that the curve fitted with an octal polynomial has the highest similarity to the new coordinate points.

[0073] The radio frequency fingerprint characteristic value is matched with the radio frequency fingerprint characteristic value in the radio frequency fingerprint characteristic database to identify the signal, specifically including:

[0074] S41, firstly, compare the vertex coordinates of the radio frequency fingerprint feature value with the vertex coordinates in the radio frequency fingerprint feature database one by one;

[0075] S42, if the distance between the vertex coordinates of the radio frequency fingerprint feature value and the vertex coordinates in the radio frequency fingerprint feature database is greater than a preset threshold, the matching fails, and the radio frequency fingerprint feature value is stored in the radio frequency fingerprint feature database;

[0076] S43. If the distance between the vertex coordinates of the RF fingerprint feature value and the vertex coordinates in the RF fingerprint feature database is less than or equal to the preset threshold, continue to match the curve consisting of an approximate 8th-order polynomial consisting of 9 parameters, with an average error between 210,000 and 500,000 on the horizontal axis. If the average error is greater than the preset threshold, the matching fails. The RF fingerprint feature value is stored in the RF fingerprint feature database. If the average error is less than or equal to the preset threshold, the matching is successful.

[0077] S15. If the signal recognition fails in step S14, the RF fingerprint feature value is stored in the RF fingerprint feature database. In this embodiment, if the signal recognition fails, the recognition signal and its tag are stored in the RF fingerprint database, and the signal type in the database is updated.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for uniquely identifying a radio signal based on I / Q component weight characteristics, characterized in that: The method comprises: S11, collecting I / Q data for the monitoring frequency band of the target radio equipment of each detection node; S12, processing the I / Q data to obtain a value to be evaluated; S13, judging whether the target radio device has a signal by the value to be evaluated, if yes, executing step S14, if no, re-executing step S11; S14, performing secondary processing on the I / Q data to obtain a radio frequency fingerprint characteristic value, matching the radio frequency fingerprint characteristic value with a pre-stored radio frequency fingerprint characteristic value in a radio frequency fingerprint characteristic database, and identifying the signal; S15. If the signal recognition fails in step S14, the radio frequency fingerprint feature value is stored in the radio frequency fingerprint feature database.

2. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 1, characterized in that: In step S11, each detection node is composed of a main control module and a software radio module, the software radio module is used to collect I / Q data, the software radio module is used to receive and preprocess the I / Q data, and the main control module is signal-connected to the software radio module.

3. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 1, characterized in that: In step S12, the I / Q data is processed, specifically including: The Q values ​​in the collected I / Q data are subtracted from the back to the front, and the absolute values ​​of all the values ​​after the subtraction are summed to obtain the value to be evaluated.

4. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 1, characterized in that: In step S13, determining whether there is a signal on the target radio device by the value to be evaluated specifically includes: The value to be evaluated is compared with the preset threshold. When the value to be evaluated is less than the preset threshold, it is determined that no signal is detected and step S11 is executed again. When the value to be evaluated is greater than or equal to the preset threshold, step S14 is executed.

5. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 1, characterized in that: In step S14, the collected data is subjected to secondary processing, which specifically includes: S21, statistically analyzing the count value of each I / Q data, and using the count value as the characteristic value corresponding to each I / Q data; S22, setting the weight value of I / Q data; S23, multiply each eigenvalue by its corresponding weight value and then sum them up to obtain the x value on the new coordinate axis; S24, summing the absolute values ​​of the horizontal and vertical coordinates of all points that have appeared in the two-dimensional distribution feature as the y value on the new coordinate axis, wherein the two-dimensional distribution feature is composed of I and Q; S25, processing all I / Q data sampled once through steps S21 to S24, filling in new coordinates, transforming to form a curve that approximates an 8th-order polynomial consisting of 9 parameters, and fitting the curve to obtain a characteristic distribution curve of the signal; S26. Using the vertex coordinates and nine parameters of the characteristic distribution curve as the radio frequency fingerprint characteristic values ​​of the signal source.

6. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 5, characterized in that: Statistical analysis of the count value of each I / Q data, including: S31, describing each I / Q component of the I / Q data in a complex form I+jQ, with I as the horizontal axis and Q as the vertical axis, to obtain a two-dimensional distribution of each I / Q component; S32, taking the number of points with the same horizontal and vertical coordinates as the count value of the I / Q component; S33. Use the count value as the characteristic value corresponding to each I / Q data.

7. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 5, characterized in that: When setting the weight value of I / Q data, the stronger the signal energy, the closer the I value and Q value of the I / Q data are to the four coordinate points (1, -1), (-1, -1), (1, 1), and (-1, 1), and the smaller the weight value; the weaker the signal energy, the more concentrated the I value and Q value of the I / Q data are at the coordinate point (0, 0), and the larger the weight value. The weight is set according to this rule.

8. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 5, characterized in that: The expression of the curve consisting of 9 parameters approximating the 8th degree polynomial is: Curve=a+b*X+c*X 2 +d*X 3 +e*X 4 +f*X 5 +g*X 6 +h*X 7 +i*X 8 Among them, Curve is the curve of an 8th-order polynomial, a, b, c, d, e, f, g, h, and i are constant terms, that is, 9 parameters, and X is the independent variable.

9. The method for uniquely identifying a radio signal based on I / Q component weight characteristics according to claim 5, characterized in that: The radio frequency fingerprint characteristic value is matched with the radio frequency fingerprint characteristic value in the radio frequency fingerprint characteristic database to identify the signal, specifically including: S41, firstly, compare the vertex coordinates of the radio frequency fingerprint feature value with the vertex coordinates in the radio frequency fingerprint feature database one by one; S42, if the distance between the vertex coordinates of the radio frequency fingerprint feature value and the vertex coordinates in the radio frequency fingerprint feature database is greater than a preset threshold, the matching fails, and the radio frequency fingerprint feature value is stored in the radio frequency fingerprint feature database; S43. If the distance between the vertex coordinates of the RF fingerprint feature value and the vertex coordinates in the RF fingerprint feature database is less than or equal to the preset threshold, continue to match the curve consisting of an approximate 8th-order polynomial consisting of 9 parameters, with an average error between 210,000 and 500,000 on the horizontal axis. If the average error is greater than the preset threshold, the matching fails. The RF fingerprint feature value is stored in the RF fingerprint feature database. If the average error is less than or equal to the preset threshold, the matching is successful.

Images