Signal anti-interference method and device for liquid crystal phased-array antenna

Abstract

The invention discloses a signal anti-interference method and device for a liquid crystal phased-array antenna, and relates to the technical field of signal anti-interference of the liquid crystal phased-array antenna, and the method comprises the steps: carrying out the collection and processing of the data of the liquid crystal phased-array antenna, and obtaining the preprocessing data; constructing an interference detection network model based on a convolutional neural network and a recurrent neural network; inputting the preprocessed data into an interference detection network model to discriminate and position interference signals; and performing anti-interference adjustment according to the determined interference signal. According to the method, the interference detection network model is constructed by introducing the convolutional neural network and the recurrent neural network, so that the interference signals are accurately identified and classified, and the anti-interference capability of the liquid crystal phased-array antenna signals is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid crystal phased array antenna signal anti-interference, and in particular to a signal anti-interference method and device for a liquid crystal phased array antenna. Background Art

[0002] In recent years, advances in high-performance electromagnetic liquid crystal material technology have provided an effective solution for the design of low-cost, low-power phased array antennas. As a revolutionary technological innovation, liquid crystal phased array antenna technology has become a focus of research and development for many manufacturers. Liquid crystal phased array antennas utilize the dielectric anisotropy of liquid crystals to provide deflection voltages to the upper and lower sides of the liquid crystal layer through transmission lines. This control of the liquid crystal deflection direction changes the phase shift of the phase shifter, thereby adjusting the alignment of the phased array antenna.

[0003] However, despite the many advantages of liquid crystal phased array antenna technology, it still has some technical defects and challenges in signal anti-interference. Since the anti-interference method of liquid crystal phased array antenna relies on the effective identification and processing of interference signals, the interference signal identification in the existing technology still has limitations. In particular, when the characteristics of the interference signal are close to the target signal, it is easy to be misjudged when judging based on traditional signal characteristics (such as signal strength, phase, etc.). For example, the noise level and signal strength of the liquid crystal phased array antenna signal vary greatly, resulting in a small difference between the interference signal and the target signal, which increases the difficulty of identifying the interference signal. Such complex interference situations cannot be handled by a simple threshold judgment method. Especially in high-noise, complex background environments, the interference signal may be mistakenly regarded as the target signal, thereby affecting the accuracy of the anti-interference processing.

[0004] Existing technologies usually rely on statistical characteristics of signals (such as autocorrelation function) and traditional signal processing methods (such as spectrum analysis, time-frequency analysis, etc.), and determine whether a signal is an interference signal by the degree of match with a preset interference pattern. Specifically, the autocorrelation function threshold is set according to the characteristics of the signal and the noise level, and the received signal is compared with the preset interference pattern. When the match exceeds the threshold, the signal is determined to be an interference signal. It relies more on preset, static interference patterns and is therefore less flexible.

[0005] Therefore, developing a signal anti-interference method for liquid crystal phased array antennas has important practical significance. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to address the deficiencies in the prior art and to design a signal anti-interference method and device for a liquid crystal phased array antenna. By combining the construction of an interference detection network model and adopting a machine learning algorithm, it is possible to intelligently identify new interference signals in complex environments, thereby solving the problems existing in the prior art.

[0007] The technical solution adopted by the present invention to solve its technical problem is:

[0008] In a first aspect, the present invention provides a signal anti-interference method for a liquid crystal phased array antenna, comprising:

[0009] Collecting and processing data from the liquid crystal phased array antenna to obtain pre-processed data;

[0010] Based on convolutional neural networks and recurrent neural networks, an interference detection network model is constructed;

[0011] Input the pre-processed data into the interference detection network model to identify and locate the interference signal;

[0012] Perform anti-interference adjustments based on the determined interference signal.

[0013] As a further technical solution of the present invention, the data of the liquid crystal phased array antenna is collected and processed to obtain preprocessed data; specifically, the method includes: integrating an adaptive sampling mechanism in a signal acquisition device to obtain signal data of the liquid crystal phased array antenna, and then processing the signal data to obtain preprocessed data; wherein the signal data includes signal strength, phase value and frequency parameters.

[0014] As a further technical solution of the present invention, the signal acquisition device includes an oscilloscope, a signal analyzer and a spectrum analyzer, and the signal acquisition device is provided with an initial sampling frequency;

[0015] The adaptive adoption mechanism is implemented as follows:

[0016] The noise energy monitoring method is used to detect the intensity of environmental noise. In a high-noise environment, the sampling frequency of the signal acquisition device is increased, while in a low-noise environment, the sampling frequency of the signal acquisition device is reduced.

[0017] The specific method of processing the signal data to obtain the preprocessed data is: filtering and denoising the collected signal data, and then extracting the target information data as the preprocessed data.

[0018] As a further technical solution of the present invention, the interference detection network model is constructed based on the convolutional neural network and the recurrent neural network; specifically including:

[0019] Collect historical interference signal data of liquid crystal phased array antennas and annotate them;

[0020] Performing data enhancement on the collected interference signal data to obtain an interference signal data set;

[0021] The interference detection network model is trained using the interference signal dataset;

[0022] During the training process, the cross-entropy loss function is used to measure the difference between the model's prediction results and the actual labels, and the SGD optimizer is used to minimize the loss function. Finally, ten-fold cross validation is performed to ensure the stability and generalization ability of the model.

[0023] As a further technical solution of the present invention, the pre-processed data is input into the interference detection network model to distinguish and locate the interference signal; specifically:

[0024] The pre-processed data is input into the interference detection network model to obtain the discrimination result of the interference signal data. If there is no interference signal, no processing is required. If it is an interference signal, the source direction of the interference signal is estimated by the arrival angle estimation method, and then the direction of the interference source is determined by the triangulation method.

[0025] As a further technical solution of the present invention, the discrimination results are divided into one type of results and two types of results. The one type of results corresponds to whether it is an interference signal, and the second type of results corresponds to the interference type; the interference types include narrowband interference, broadband noise and pulse interference.

[0026] As a further technical solution of the present invention, the specific implementation of the arrival angle estimation method is as follows:

[0027] For narrowband interference types, the MUSIC algorithm is used to estimate the signal direction;

[0028] For broadband noise types, the MVDR beamforming method is used to estimate the signal direction;

[0029] For pulse interference types, the signal direction is estimated using time-frequency analysis methods.

[0030] As a further technical solution of the present invention, the anti-interference adjustment according to the determined interference signal specifically includes:

[0031] According to the determined direction of the interference source, dynamic multi-beam technology is used to form multiple beam zero points in the direction of the interference signal to suppress interference. At the same time, the signal quality is monitored in real time, and the beam shape and direction are continuously optimized according to the dynamic changes of the interference to ensure the quality of signal reception and realize the anti-interference of the liquid crystal phased control antenna.

[0032] As a further technical solution of the present invention, the specific steps of optimizing the beam shape and direction are:

[0033] Real-time acquisition of received signal quality, including signal-to-noise ratio and bit error rate;

[0034] Adaptive adjustment of beam shape through LMS algorithm;

[0035] Combined with spatial diversity technology to enhance target signal reception;

[0036] Adjust the sub-beam to complete the optimization.

[0037] In a second aspect, the present invention further provides a signal anti-interference device for a liquid crystal phased array antenna, comprising:

[0038] A data acquisition and processing unit collects and processes data from the liquid crystal phased array antenna to obtain pre-processed data;

[0039] Interference detection network model unit, based on convolutional neural network and recurrent neural network, builds interference detection network model;

[0040] The interference signal identification and positioning unit inputs the pre-processed data into the interference detection network model to identify and locate the interference signal;

[0041] The anti-interference adjustment unit performs anti-interference adjustment according to the determined interference signal.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention introduces convolutional neural networks and recurrent neural networks to construct an interference detection network model, thereby accurately identifying and classifying interference signals. It no longer relies on traditional threshold judgment methods and is more flexible and adaptive. Therefore, the present invention can adapt to various interference types, thereby significantly improving the anti-interference ability of liquid crystal phased array antenna signals.

[0044] 2. The present invention adopts an adaptive sampling mechanism to automatically adjust the sampling frequency of the signal acquisition device according to the intensity of the environmental noise. In a high-noise environment, the system can increase the sampling frequency to capture more signal details. In a low-noise environment, it automatically reduces the sampling frequency to save resources.

[0045] 3. The present invention adopts an interference detection network model, which can more accurately extract useful features from complex signals and can adapt to and expand new interference types. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a flow chart of a signal anti-interference method for a liquid crystal phased array antenna proposed by the present invention;

[0047] Figure 2 This is a schematic diagram of the process of training the interference detection network model proposed by the present invention;

[0048] Figure 3 This is a structural diagram of a signal anti-interference device for a liquid crystal phased array antenna proposed by the present invention. DETAILED DESCRIPTION

[0049] The specific implementation of the present invention is described below with reference to the accompanying drawings and embodiments:

[0050] It should be noted that the structures, colors, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in the present invention without affecting the efficacy and purpose that can be achieved by the present invention.

[0051] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments to their relative relationships should be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0052] like Figure 1 As shown, the present invention provides a signal anti-interference method for a liquid crystal phased array antenna, comprising:

[0053] Step 101: collect and process data from the liquid crystal phased array antenna to obtain pre-processed data;

[0054] Step 102: construct an interference detection network model based on a convolutional neural network and a recurrent neural network;

[0055] Step 103: input the pre-processed data into the interference detection network model to identify and locate the interference signal;

[0056] Step 104: Perform anti-interference adjustment according to the determined interference signal.

[0057] In step 101, data from the liquid crystal phased array antenna is collected and processed to obtain preprocessed data. Specifically, the process includes integrating an adaptive sampling mechanism into a signal acquisition device to obtain signal data from the liquid crystal phased array antenna, and then processing the signal data to obtain preprocessed data. The signal data includes signal strength, phase value, and frequency parameters.

[0058] The purpose of this step is to achieve efficient signal data acquisition through the combination of signal acquisition equipment and adaptive sampling mechanism, laying a solid foundation for the subsequent anti-interference adjustment of the liquid crystal phased array antenna.

[0059] The signal acquisition equipment includes an oscilloscope, a signal analyzer and a spectrum analyzer. The oscilloscope is used to observe the antenna output signal in real time, obtain the signal amplitude change information, and calculate the signal strength. The signal analyzer combines spectrum analysis with time domain analysis to analyze the received signal waveform to calculate the phase information. The spectrum analyzer analyzes the spectrum of the antenna signal to obtain the signal's frequency distribution. The above-mentioned signal acquisition equipment has its own initial sampling frequency.

[0060] The adaptive sampling mechanism is implemented by using a noise energy monitoring method to monitor ambient noise intensity. This involves embedding a noise energy detection algorithm in the signal acquisition device to monitor the noise intensity in real time. This algorithm analyzes changes in the signal spectrum or energy density to calculate the noise level trend. Furthermore, the signal acquisition device pre-sets a reasonable initial sampling frequency value based on environmental assessments, device performance, and historical data.

[0061] Then, in a high-noise environment, the signal data acquisition frequency of the signal acquisition device is increased, while in a low-noise environment, the sampling frequency is reduced. Because in a high-noise environment, the signal acquisition device needs to respond quickly to noise changes, so the sampling frequency is increased. When the noise level is low, low-frequency sampling is sufficient to obtain the main characteristics of the signal and reduce the consumption of computing resources, so that the present invention can work stably for a long time without affecting performance.

[0062] For high noise and low noise, the comparison is made through the threshold comparison method. A standard value is pre-set for the noise energy and the comparison is made based on the detected noise. A higher sampling frequency helps to capture signal changes more finely, especially when the signal is interfered with by noise. A higher sampling frequency can obtain more details, which helps to better distinguish between interference signals and valid signals in subsequent processing.

[0063] Then, the signal data of the liquid crystal phased array antenna is obtained. The data includes signal strength, phase value and frequency parameters. The signal strength reflects the power level of the signal and helps to determine whether the signal has strong attenuation or loss. The phase value is used for interference source positioning and beamforming to achieve more accurate signal directionality. The frequency parameter helps to classify the signal and analyze the interference type.

[0064] The specific method of processing the signal data to obtain the preprocessed data is: filtering and denoising the collected signal data, and then extracting the target information data as the preprocessed data.

[0065] In step 102, an interference detection network model is constructed based on a convolutional neural network and a recurrent neural network. Specifically, the convolutional neural network is used to extract local features in the signal data, especially the local patterns in the frequency domain and time domain of the signal. By applying the convolution kernel to the signal data, it can automatically learn important features in the signal, such as frequency components, periodic fluctuations, time domain mutations, etc., and the recurrent neural network is used to process long-term dependencies in the time domain signal data and identify the evolution trend and periodicity of the interference signal. Therefore, in the present invention, the interference detection network model first uses a convolutional neural network to extract the spatial (spectral or time-frequency) features in the signal, and then inputs the extracted features into the recurrent neural network to capture the temporal dependency of the signal. Finally, the network will output the classification result of the interference type.

[0066] See also Figure 2 ,Correspondingly, the interference detection network model needs to be trained. The specific steps for training the interference detection network model are:

[0067] Step 121: collecting historical interference signal data of the liquid crystal phased array antenna and marking it;

[0068] It is necessary to collect historical signal data received by the liquid crystal phased array antenna under different environmental conditions, including interference signals and normal signals. The collected data should include various types of interference (such as narrowband interference, broadband interference, pulse interference, etc.) and be labeled. The labeling work includes assigning the interference type to each signal segment or marking it as interference-free.

[0069] Step 122: performing data enhancement on the collected interference signal data to obtain an interference signal data set;

[0070] Perform data enhancement on the collected interference signal data, such as randomly changing the frequency, amplitude, and phase of the signal, randomly shifting or scaling the signal in time and frequency, simulating different signal environments, etc., to obtain an interference signal dataset;

[0071] Step 123, training the interference detection network model using the interference signal dataset;

[0072] The interference signal dataset is divided into a training set, a validation set, and a test set with a ratio of 8:1:1. The interference detection network model is trained using the interference signal dataset through the back propagation algorithm.

[0073] In step 124, during the training process, a cross-entropy loss function is used to measure the difference between the model's prediction results and the actual labels, and the loss function is minimized by the SGD optimizer. Finally, a ten-fold cross validation is performed to ensure the stability and generalization ability of the model.

[0074] In step 103, the pre-processed data is input into the interference detection network model to identify and locate the interference signal; specifically:

[0075] The pre-processed data is input into the interference detection network model to obtain the discrimination result of the interference signal data. If there is no interference signal, no processing is required. If it is an interference signal, the source direction of the interference signal is estimated by the arrival angle estimation method, and then the direction of the interference source is determined by the triangulation method.

[0076] Among them, the discrimination results are divided into one type of results and two types of results. The one type of results corresponds to whether it is an interference signal, and the second type of results corresponds to the type of interference;

[0077] The interference detection network model first judges the first type of result and determines that it is an interference signal, then performs a second type of judgment to classify it into which type of interference it is. Specifically, the interference type includes narrowband interference, broadband noise, and pulse interference.

[0078] The interference signal of narrowband interference has a narrow frequency band, which is usually characterized by a concentrated spectrum and less frequency distribution. The interference signal of broadband noise has a wide frequency band and a wider spectrum, which may contain multiple frequency components. The interference signal of pulse interference usually manifests as a short burst with high energy and a wide spectrum. Then, according to the classification category, the source direction of the interference signal is estimated by the corresponding arrival angle estimation method. Specifically:

[0079] Narrowband interference type: Use the MUSIC (Multiple Signal Classification) algorithm for DOA estimation. The MUSIC algorithm is based on the eigenvalue decomposition of the covariance matrix and is suitable for high-precision direction estimation of narrowband signals. It can achieve good angular resolution in the presence of multiple interference sources.

[0080] Broadband Noise: Minimum Variance Distortionless Response (MVDR) beamforming is used for DOA estimation. MVDR beamforming effectively reduces noise interference in broadband noise environments, ensuring accurate direction estimation. This method improves positioning accuracy by minimizing noise while maintaining an undistorted response to the target signal.

[0081] Pulse interference: Time-frequency analysis is used for DOA estimation. Because pulse interference is instantaneous and has a broad spectrum, time-frequency analysis methods (such as short-time Fourier transform (STFT) and wavelet transform) can capture the time and frequency domain characteristics of the interference signal in the time-frequency domain, thereby providing accurate angle estimation.

[0082] Once the angle of arrival (DOA) of the interference signal is determined, the interference source can be located using multiple known receiving points (such as multiple antenna arrays or receiving nodes). Taking three groups of receiving points as an example, the angle of arrival of the interference signal received by each receiving unit is measured through the angle of arrival estimation method. By utilizing geometric principles, based on the estimated value of the angle of arrival of each receiving unit and combined with the position of the receiving unit, the source of the interference source is solved.

[0083] In step 104, anti-interference adjustment is performed according to the determined interference signal, specifically including:

[0084] According to the determined direction of the interference source, dynamic multi-beam technology is used to form multiple beam zero points in the direction of the interference signal to suppress interference. At the same time, the signal quality is monitored in real time, and the beam shape and direction are continuously optimized according to the dynamic changes of the interference to ensure the quality of signal reception and realize the anti-interference of the liquid crystal phased control antenna.

[0085] The specific steps for optimizing beam shape and direction are as follows:

[0086] Real-time acquisition of received signal quality, which includes two parameters: signal-to-noise ratio (SNR) and bit error rate (BER). The SNR is used to assess the quality of the target signal and help determine the intensity and impact of interference. The BER is used to detect the impact of interference on signal transmission. A high BER indicates strong interference and requires beam optimization for suppression.

[0087] The LMS algorithm (least mean square error) adaptively adjusts the beam shape. Based on real-time signal quality feedback (such as SNR and BER), the LMS algorithm adaptively adjusts the phase and amplitude of the antenna array to optimize signal reception quality and maximize the gain of the target signal. Specifically, it points the beam in the direction of the target signal and ensures that the reception quality of the target signal is not interfered with by reducing the gain of interfering signals.

[0088] Incorporating spatial diversity technology to enhance target signal reception. Specifically, spatial diversity technology utilizes the spatial distribution of multiple receiving units in an antenna array to selectively enhance the reception quality of the target signal while reducing the impact of interfering signals.

[0089] Adjust the sub-beam to complete the optimization. Specifically, adjust the position and gain of the sub-beam according to the direction of the interference source. The main function of the sub-beam is to point to the interference source and eliminate the influence of the interference signal by forming a null point. When the position of the interference source changes, the sub-beam can be dynamically adjusted based on the real-time estimated interference source direction. This ensures that the sub-beam can effectively suppress the interference source while not affecting the reception of the target signal.

[0090] Ultimately, by continuously optimizing the beam shape and direction, high-quality reception of the target signal is ensured and interference is effectively resisted.

[0091] The present invention trains an interference detection network (based on deep learning) to identify and classify interference signals, so that the identification of interference patterns is not just based on a simple match of preset patterns, but can also automatically learn interference characteristics in different environments, thereby improving the adaptability to unknown or dynamic interference signals. That is, as time goes by, it is not limited to the initial three interference characteristics. Through the deep learning model, the present invention can more accurately extract useful features from complex signals and can adapt to and expand new types of interference.

[0092] The present invention introduces convolutional neural networks and recurrent neural networks to construct an interference detection network model, thereby accurately identifying and classifying interference signals. It no longer relies on traditional threshold judgment methods and is more flexible and adaptive. Therefore, the present invention can adapt to various interference types, thereby significantly improving the anti-interference ability of liquid crystal phased array antenna signals.

[0093] The present invention adopts an adaptive sampling mechanism to automatically adjust the sampling frequency of the signal acquisition device according to the intensity of the environmental noise. In a high-noise environment, the system can increase the sampling frequency to capture more signal details. In a low-noise environment, the sampling frequency is automatically reduced to save resources.

[0094] The present invention adopts an interference detection network model, which can more accurately extract useful features from complex signals and can adapt to and expand new interference types.

[0095] See also Figure 3 The present invention also provides a signal anti-interference device for a liquid crystal phased array antenna, comprising:

[0096] The data acquisition and processing unit 201 acquires and processes the data of the liquid crystal phased array antenna to obtain pre-processed data;

[0097] The interference detection network model unit 202 constructs an interference detection network model based on a convolutional neural network and a recurrent neural network;

[0098] The interference signal identification and positioning unit 203 inputs the pre-processed data into the interference detection network model to identify and locate the interference signal;

[0099] The anti-interference adjustment unit 204 performs anti-interference adjustment according to the determined interference signal.

[0100] The various variations and specific examples of the signal anti-interference method of a liquid crystal phased array antenna in the aforementioned embodiment are also applicable to a signal anti-interference device of a liquid crystal phased array antenna in this embodiment. Through the aforementioned detailed description of the signal anti-interference method of a liquid crystal phased array antenna, those skilled in the art can clearly understand the signal anti-interference device of a liquid crystal phased array antenna in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0101] The present invention adopts a convolutional neural network to construct and train the model. It should be pointed out that without changing the principle of the scheme, changing the model construction and training method should also be regarded as the scope of protection of the present invention.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0103] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0104] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0105] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A signal anti-interference method for a liquid crystal phased array antenna, characterized in that: include: Collecting and processing data from the liquid crystal phased array antenna to obtain pre-processed data; Based on convolutional neural networks and recurrent neural networks, an interference detection network model is constructed; Input the pre-processed data into the interference detection network model to identify and locate the interference signal; Perform anti-interference adjustments based on the determined interference signal.

2. The signal anti-interference method of a liquid crystal phased array antenna according to claim 1, characterized in that: The data of the liquid crystal phased array antenna is collected and processed to obtain preprocessed data; specifically, the method includes: obtaining signal data of the liquid crystal phased array antenna by integrating an adaptive sampling mechanism in a signal acquisition device, and then processing the signal data to obtain preprocessed data; wherein the signal data includes signal strength, phase value and frequency parameters.

3. The signal anti-interference method of a liquid crystal phased array antenna according to claim 2, characterized in that: The signal acquisition device includes an oscilloscope, a signal analyzer and a spectrum analyzer, and the signal acquisition device is provided with an initial sampling frequency; The adaptive adoption mechanism is implemented by: using a noise energy monitoring method to detect the intensity of environmental noise, increasing the sampling frequency of the signal acquisition device in a high-noise environment, and reducing the sampling frequency of the signal acquisition device in a low-noise environment; The specific method of processing the signal data to obtain the pre-processed data is: filtering and denoising the collected signal data, and then extracting the target information data as the pre-processed data.

4. The signal anti-interference method of a liquid crystal phased array antenna according to claim 1, characterized in that: The interference detection network model is constructed based on the convolutional neural network and the recurrent neural network; specifically, it includes: Collect historical interference signal data of liquid crystal phased array antennas and annotate them; Performing data enhancement on the collected interference signal data to obtain an interference signal data set; The interference detection network model is trained using the interference signal dataset; During the training process, the cross-entropy loss function is used to measure the difference between the model's prediction results and the actual labels, and the SGD optimizer is used to minimize the loss function. Finally, ten-fold cross validation is performed to ensure the stability and generalization ability of the model.

5. The signal anti-interference method of a liquid crystal phased array antenna according to claim 1, characterized in that: The pre-processed data is input into the interference detection network model to identify and locate the interference signal; specifically: The pre-processed data is input into the interference detection network model to obtain the discrimination result of the interference signal data. If there is no interference signal, no processing is required. If it is an interference signal, the source direction of the interference signal is estimated by the arrival angle estimation method, and then the direction of the interference source is determined by the triangulation method.

6. The signal anti-interference method of a liquid crystal phased array antenna according to claim 5, characterized in that: The discrimination results are divided into one type of results and two types of results. The one type of results corresponds to whether it is an interference signal, and the second type of results corresponds to the interference type. The interference types include narrowband interference, broadband noise and pulse interference.

7. The signal anti-interference method for a liquid crystal phased array antenna according to claim 5, characterized in that: The specific implementation of the arrival angle estimation method is as follows: For narrowband interference types, the MUSIC algorithm is used to estimate the signal direction; For broadband noise types, the MVDR beamforming method is used to estimate the signal direction; For pulse interference types, the signal direction is estimated using time-frequency analysis methods.

8. The signal anti-interference method of a liquid crystal phased array antenna according to claim 1, characterized in that: The performing anti-interference adjustment according to the determined interference signal specifically includes: According to the determined direction of the interference source, dynamic multi-beam technology is used to form multiple beam zero points in the direction of the interference signal to suppress interference. At the same time, the signal quality is monitored in real time, and the beam shape and direction are continuously optimized according to the dynamic changes of the interference to ensure the quality of signal reception and realize the anti-interference of the liquid crystal phased control antenna.

9. The signal anti-interference method of a liquid crystal phased array antenna according to claim 8, characterized in that: The specific steps of optimizing the beam shape and direction are: Real-time acquisition of received signal quality, including signal-to-noise ratio and bit error rate; Adaptive adjustment of beam shape through LMS algorithm; Combined with spatial diversity technology to enhance target signal reception; Adjust the sub-beam to complete the optimization.

10. A signal anti-interference device for a liquid crystal phased array antenna, characterized in that: A signal anti-interference method using a liquid crystal phased array antenna as claimed in any one of claims 1 to 9, comprising: A data acquisition and processing unit collects and processes data from the liquid crystal phased array antenna to obtain pre-processed data; Interference detection network model unit, which builds an interference detection network model based on convolutional neural network and recurrent neural network; The interference signal identification and positioning unit inputs the pre-processed data into the interference detection network model to identify and locate the interference signal; The anti-interference adjustment unit performs anti-interference adjustment according to the determined interference signal.

Images