A foil jamming recognition method based on improved support vector machine

Abstract

This invention discloses an improved support vector machine (SVM) method for identifying chaff interference, comprising: acquiring target echo signals and chaff interference echo signals; down-converting the target echo signal to obtain a first down-converted signal; down-converting the chaff interference echo signal to obtain a second down-converted signal; performing pulse compression processing on the first and second down-converted signals respectively to obtain a first pulse compressed signal and a second pulse compressed signal; performing dimensionality reduction processing on the first and second pulse compressed signals using uniform manifold approximation and projection methods to obtain a first dimensionality-reduced signal and a second dimensionality-reduced signal; and inputting the first and second dimensionality-reduced signals as input signals to the SVM identification method for identification. This invention overcomes the low identification efficiency problem of traditional SVM methods and improves the overall identification performance of radar targets in chaff interference backgrounds.

Description

Technical Field

[0001] This invention relates to the field of radar signal processing, and in particular to an improved support vector machine-based method for identifying chaff interference. Background Technology

[0002] When a radar detects a target, it radiates electromagnetic waves into the air in a specific direction through a transmitting antenna, and then detects the target by receiving the echo. The radar target echo information mainly includes: motion information such as the target's distance, speed, and angle; and target scattering information such as radar cross-section, high-resolution one-dimensional image, two-dimensional time spectrum, and polarization characteristics.

[0003] Chaff, as an important passive electronic countermeasure, can suppress or deceive radars of different frequencies, directions, and systems, causing them to fail to detect targets. Chaff is usually made of very thin metal wires or metal-plated glass fibers, nylon fibers, etc. When the length of the chaff is close to half the wavelength of the radar being jammed, it will produce a strong resonant reflection of the radar waves.

[0004] A large number of chaff strips form a cloud-like distribution in space. When radar waves illuminate the chaff cloud, the chaff cloud reflects the radar waves like a real target, thus creating numerous false target echoes on the radar screen and interfering with the radar's detection and tracking of real targets.

[0005] Due to its advantages such as low cost, wide jamming range, significant jamming effect, and simple operation, chaff jamming technology has been widely used in passive radar countermeasures systems. Therefore, research on chaff jamming identification technology is of great practical significance. Summary of the Invention

[0006] The purpose of this invention is to provide an improved support vector machine-based method for identifying foil interference, which has the advantage of high recognition rate.

[0007] To achieve the above objectives, the present invention provides a method for identifying foil interference based on an improved support vector machine, comprising:

[0008] S10. Acquire the target echo signal and the chaff interference echo signal;

[0009] S20. The target echo signal is down-converted to obtain a first down-converted signal; the foil interference echo signal is down-converted to obtain a second down-converted signal.

[0010] S30. Perform pulse compression processing on the first down-converted signal and the second down-converted signal respectively to obtain a first pulse compressed signal and a second pulse compressed signal;

[0011] S40. The first pulse compression signal and the second pulse compression signal are reduced in dimension using the uniform manifold approximation and projection method to obtain the first dimension-reduced signal and the second dimension-reduced signal.

[0012] S50. The first dimensionality reduction signal and the second dimensionality reduction signal are used as input signals to the support vector machine recognition method for recognition.

[0013] Optionally, the first down-conversion signal is represented as:

[0014] S rTarget (t)=A(t)exp[-j2πf c τ+jπk(t-τ) 2 In the formula, A(t) represents the target echo amplitude; Indicates the target echo delay; c = 3 × 10 8 m / s is the speed of light, R0 is the initial radial distance of the target, and v is the target's velocity.

[0015] Optionally, the second down-conversion signal can be represented as: Where N is the total number of foil strips, a represents the Doppler frequency shift of the i-th foil strip. i (t), and v i These represent the echo amplitude, radial velocity, and radial distance of the i-th foil strip, respectively.

[0016] Optionally, the total radar echo signal is the sum of the first down-converted signal and the second down-converted signal, and the total echo signal can be expressed as: S r (t)=S rTarget (t)+S sChaff (t).

[0017] Optionally, after step S50, the method further includes step S60, which involves inputting the first pulse compression signal and the second pulse compression signal as input signals to the K-nearest neighbor method, the random forest method, and the traditional support vector machine method for identification, and comparing the identification obtained by the K-nearest neighbor method, the random forest method, and the traditional support vector machine method with the result obtained in step S50.

[0018] Optionally, comparing the identifications obtained by the K-nearest neighbor method, the random forest method, and the traditional support vector machine with the results obtained in step S50 includes comparing the AUC values ​​under the ROC curve.

[0019] In summary, compared with the prior art, the improved support vector machine-based foil interference identification method provided by this invention has the following beneficial effects:

[0020] The present invention provides an improved support vector machine-based chaff interference identification method. This method down-converts the echo signal, performs pulse compression on the down-converted signal, reduces the dimensionality of the pulse-compressed signal, and then uses the support vector machine identification method for identification. The identification method of the present invention overcomes the problem of low identification efficiency of traditional support vector machine methods and improves the overall identification performance of radar targets with chaff interference background. Attached Figure Description

[0021] Figure 1 This is a flowchart of the improved support vector machine-based foil interference identification method of the present invention.

[0022] Figure 2 This is the target echo image after pulse compression processing.

[0023] Figure 3 An echo image of the initial diffusion stage of the foil release.

[0024] Figure 4 This is an echo image of the foil during the stable diffusion period.

[0025] Figure 5 This is a schematic diagram showing the distribution of the original dataset.

[0026] Figure 6 This is a schematic diagram showing the distribution of the dataset after dimensionality reduction.

[0027] Figure 7 This is a schematic diagram comparing the ROC curves of the method of the present invention with those of other methods. Detailed Implementation

[0028] The following will be combined with the appendix in the embodiments of the present invention. Figure 1 ~Attached Figure 7 The technical solutions, structural features, objectives and effects achieved in the embodiments of the present invention will be described in detail.

[0029] It should be noted that the accompanying drawings are in a very simplified form and use non-precise proportions. They are only used to facilitate and clarify the purpose of illustrating the embodiments of the present invention, and are not intended to limit the implementation conditions of the present invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationship, or adjustments to the size should still fall within the scope of the technical content disclosed in the present invention, provided that they do not affect the effects and objectives that the present invention can produce.

[0030] It should be noted that, in this invention, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only the expressly listed elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0031] like Figure 1 As shown, this invention provides a method for identifying foil interference based on an improved support vector machine, comprising the following steps:

[0032] S10. Acquire the target echo signal and the chaff interference echo signal; assuming the radar transmits a linear frequency modulated signal, the radar's transmitted signal can be expressed as: s(t)=u(t)exp(j2πf c t+jπkt 2 In the formula, u(t) represents the complex envelope of the transmitted signal, k represents the frequency modulation slope, and f c Indicates the radar's operating center frequency.

[0033] S20. Down-convert the target echo signal to obtain the first down-converted signal; down-convert the chaff interference echo signal to obtain the second down-converted signal.

[0034] In this embodiment, the first down-conversion signal is represented as: s rTarget (t)=A(t)exp[-j2πf c τ+jπk(t-τ) 2 In the formula, A(t) represents the target echo amplitude; Indicates the target echo delay; c = 3 × 10 8 m / s is the speed of light, R0 is the initial radial distance of the target, and v is the target's velocity.

[0035] The second down-conversion signal can be represented as:

[0036] Where N is the total number of foil strips, a represents the Doppler frequency shift of the i-th foil strip. i (t), v i and r i These represent the echo amplitude, radial velocity, and radial distance of the i-th foil strip, respectively.

[0037] The total radar echo signal is the sum of the first down-conversion signal and the second down-conversion signal, and the total echo signal can be expressed as: S r(t)=S rTarget (t)+S sChaff (t).

[0038] S30. The first down-conversion signal and the second down-conversion signal are subjected to pulse compression processing to obtain a first pulse compressed signal and a second pulse compressed signal, respectively. In this embodiment, the parameters used for simulation are shown in Table 1, and the target echo after pulse compression processing is as follows: Figure 2 As shown, the interference effect of the foil cloud is as follows: Figure 3 and Figure 4 As shown, where Figure 3 This is an echo image of the initial diffusion stage of the foil release. Figure 4 This is an echo image from the stable diffusion period of the foil strip. (Comparison is needed.) Figure 2 , Figure 3 and Figure 4 It is known that before interference, the radar echo, after pulse compression, clearly shows the target. However, in the initial stage of chaff deployment, the target signal is overwhelmed by the interference signal, leading to target detection failure. Specifically, from Figure 3 It can be seen that the foil cloud echo has multiple strong scattering centers, and the one-dimensional distance image is sparsity. Figure 4 This is a mixed echo signal from the stable phase of a chaff cloud. At this point, the chaff cloud is in a stable phase, its radius of diffusion in the air is nearing its maximum, its density is relatively low, and the target is still overwhelmed by chaff interference. (Comparison) Figure 2 , Figure 3 and Figure 4 As shown, the one-dimensional range image of the chaff interference has a higher density of strong scattering points compared to the target echo.

[0039] S40. The first pulse compression signal and the second pulse compression signal are reduced in dimension using the uniform manifold approximation and projection method to obtain the first dimension-reduced signal and the second dimension-reduced signal. The interference identification dataset is constructed using the first dimension-reduced signal and the second dimension-reduced signal.

[0040] S50. Input the first and second dimension-reduced signals as input signals into the support vector machine recognition method for recognition. Figure 5 This is a schematic diagram illustrating the distribution of the original dataset. Figure 6 This is a schematic diagram illustrating the distribution of the dataset after dimensionality reduction. For example... Figure 5 and Figure 6 As shown in the comparison, the echo data distribution of the first and second dimension-reduced signals is more concentrated, and the number of discrete points is greatly reduced.

[0041] In this embodiment, after step S50, step S60 is further included: inputting the first pulse compression signal and the second pulse compression signal as input signals to the K-Nearest Neighbors (KNN), Random Forest (RF), and traditional Support Vector Machine (SVM) methods for identification; and comparing the identification results obtained by the K-Nearest Neighbors, Random Forest, and traditional SVM methods with the results obtained in step S50. The identification method proposed in this invention, namely the Modified Support Vector Machine based on Uniform Manifold Approximation and Projection (MSVM-UMAP), is compared with the identification results of KNN, RF, and SVM methods. As shown in Tables 2 and 3, the identification accuracy and running time of each method under different interference-to-signal ratios are compared and analyzed.

[0042] The results obtained from the K-nearest neighbor method, random forest method, and traditional support vector machine are compared with those obtained in step S50, including comparing the AUC (Area Under the Curve) values ​​under the ROC (Receiver Operating Characteristic Curve). To evaluate the overall performance of each method, the ROC curves and AUC values ​​of each method are compared and analyzed. The evaluation results are as follows: Figure 7 As shown in Table 4, Tables 2 and 3 show that the interference identification accuracy of the MSVM-UMAP method proposed in this invention is similar to that of the traditional SVM method and is better than the other two methods. However, the interference identification efficiency of the MSVM-UMAP method proposed in this invention is better than that of the traditional SVM method.

[0043] Depend on Figure 7 As shown in Table 4, the ROC curve of the MSVM-UMAP method proposed in this invention is closest to the upper left and has the highest AUC value, indicating that the overall recognition performance of the method proposed in this invention is optimal.

[0044] The comparison results show that the interference identification method based on the improved support vector machine of the present invention improves the interference identification efficiency, retains the features of the original data to the greatest extent while significantly reducing the feature dimension, and uses the UMAP (the Modified Support Vector Machine) method to map the original echo data to a low-dimensional space, which reduces the computation time and helps to improve the overall interference identification performance of the algorithm.

[0045] Table 1 Main Simulation Parameters

[0046] name numerical values carrier frequency 17GHz bandwidth 4MHz Pulse width 20μs Pulse repetition frequency 1kHz Number of foil strips 1 million wind speed 10m / s Time step 0.005s

[0047] Table 2 Comparison of identification results using different methods (echo interference-to-signal ratio of 14.3 dB)

[0048] method accuracy Time consumed / s MSVM-UMAP 97.8％ 0.087 SVM 97.9％ 0.389 KNN 97.6％ 0.261 RF 96.4％ 0.869

[0049] Table 3 Comparison of identification results using different methods (echo interference-to-signal ratio of 17.6 dB)

[0050]

[0051]

[0052] Table 4. Comparison of AUC values ​​for each method (instance-to-information ratio: 14.3 dB)

[0053] method MSVM-UMAP SVM RF KNN AUC value 0.994 0.979 0.973 0.98

[0054] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Various modifications and substitutions to the present invention will be apparent to those skilled in the art after reading the above description. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. A method for identifying foil interference based on an improved support vector machine, characterized in that, The identification method includes: S10. Acquire the target echo signal and the chaff interference echo signal; S20. The target echo signal is down-converted to obtain a first down-converted signal; the foil interference echo signal is down-converted to obtain a second down-converted signal. S30. Perform pulse compression processing on the first down-converted signal and the second down-converted signal respectively to obtain a first pulse compressed signal and a second pulse compressed signal; S40. The first pulse compression signal and the second pulse compression signal are reduced in dimension using the uniform manifold approximation and projection method to obtain the first dimension-reduced signal and the second dimension-reduced signal. S50. The first dimensionality reduction signal and the second dimensionality reduction signal are used as input signals to the support vector machine recognition method for recognition.

2. The identification method as described in claim 1, characterized in that, The first down-conversion signal is represented as: s rTarget (t)=A(t)exp[-j2πf c τ+jπk(t-τ) 2 In the formula, A(t) represents the target echo amplitude; Indicates the target echo delay; c = 3 × 10 8 m / s is the speed of light, R0 is the initial radial distance of the target, and υ is the target's velocity.

3. The identification method as described in claim 2, characterized in that, The second down-conversion signal can be represented as: ， Where N is the total number of foil strips, a represents the Doppler frequency shift of the i-th foil strip. i (t), v i and r i These represent the echo amplitude, radial velocity, and radial distance of the i-th foil strip, respectively.

4. The identification method as described in claim 3, characterized in that, The total radar echo signal is the sum of the first down-converted signal and the second down-converted signal, and the total echo signal can be expressed as: S r (t)=S rTarget (t)+S sChaff (t)。 5. The identification method as described in claim 1, characterized in that, After step S50, the method further includes step S60, in which the first pulse compression signal and the second pulse compression signal are used as input signals to the K nearest neighbor method, the random forest method, and the traditional support vector machine method for identification, and the identification obtained by the K nearest neighbor method, the random forest method, and the traditional support vector machine method is compared with the result obtained in step S50.

6. The identification method as described in claim 5, characterized in that, The identifications obtained by the K-nearest neighbor method, the random forest method, and the traditional support vector machine are compared with the results obtained in step S50, including comparing the AUC values ​​under the ROC curve.

Images