Multi-target UAV countermeasure system based on multi-beam array antenna

Abstract

The present invention discloses a multi-target UAV countermeasure system based on a multi-beam array antenna. Through real-time communication with the multi-beam array antenna, UAV communication data is obtained, positioning, speed evaluation and trajectory tracking are carried out, and multi-dimensional flight feature data is generated. Within an analysis period, the UAV groups are divided by using K-means clustering analysis, an isolation forest model is constructed to classify the feature set, abnormal data points are identified, and the UAV groups to be measured are selected based on the highest frequency. Subsequently, the UAVs in the group to be measured are marked and their real-time feature data is obtained, and the abnormal UAVs are judged and marked. Finally, according to the data of the abnormal UAVs, the communication resources of the multi-beam antenna are regulated, and a UAV countermeasure strategy is formulated to achieve accurate, rapid abnormal evaluation and efficient countermeasure control of the UAVs.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) data analysis, and more particularly, to a multi-target UAV countermeasure system based on a multi-beam array antenna. Background Art

[0002] A multi-beam array antenna is an antenna that can generate multiple concurrent and independent directional beams. Through beamforming technology, it can enhance signal gain and improve anti-interference ability. However, in the prior art, there is a lack of accurate abnormal state analysis and efficient countermeasure strikes against multi-target UAVs, resulting in difficulty in improving UAV control capabilities. Therefore, how to use a multi-beam array antenna to conduct communication analysis on UAVs and achieve highly accurate countermeasure control is an important problem that needs to be solved urgently at present. Summary of the Invention

[0003] The present invention overcomes the defects of the prior art and proposes a multi-target UAV countermeasure system based on a multi-beam array antenna.

[0004] The first aspect of the present invention provides a multi-target UAV countermeasure method based on a multi-beam array antenna, including:

[0005] In a preset airspace, set a multi-beam array antenna to conduct real-time communication with target UAVs through the multi-beam array antenna;

[0006] Within an analysis period, obtain communication data of multiple target UAVs through real-time communication, perform positioning analysis, speed evaluation, and trajectory tracking based on the communication data, and generate multi-dimensional flight feature data;

[0007] Within an analysis period, use the flight feature data of multiple target UAVs as sample data for clustering analysis based on K-means, and divide multiple groups of UAVs through the clustering results;

[0008] Taking the groups of UAVs as analysis units, integrate the flight feature data of each group of UAVs to form multiple feature sets, construct and initialize an isolation forest model, preprocess the multiple feature sets and import them into the isolation forest model for data classification, analyze abnormal data points, analyze the occurrence frequency of abnormal data points in multiple groups of UAVs, and screen out the groups of UAVs to be tested based on the highest frequency;

[0009] Mark all target UAVs in the groups of UAVs to be tested and obtain real-time feature data of the groups of UAVs to be tested through real-time communication, and judge UAV anomalies through the real-time feature data and mark the abnormal UAVs;

[0010] According to the real-time characteristic data of the abnormal UAV, regulate the communication resource allocation of the multi-beam array antenna to perform high-quality data transmission for the abnormal UAV. At the same time, based on the abnormal UAV, analyze the countermeasure mode and evaluate the strategy, and formulate a UAV countermeasure strategy.

[0011] In this solution, in the preset airspace, a multi-beam array antenna is set, and real-time communication is performed on the target UAV through the multi-beam array antenna. Specifically:

[0012] According to the preset airspace range, altitude information and the attribute parameters of the target UAV, determine the communication frequency band, polarization mode, gain, and directivity parameters of the antenna, and set the layout of the multi-beam array antenna;

[0013] Realize real-time communication with the target UAV through the multi-beam array antenna, and collect the communication data of the target UAV through the central platform.

[0014] In this solution, within an analysis period, through real-time communication, obtain the communication data of multiple target UAVs, and perform positioning analysis, speed evaluation, and trajectory tracking based on the communication data, and generate multi-dimensional flight characteristic data. Specifically:

[0015] Within an analysis period, through real-time communication, obtain the communication data of multiple target UAVs. The shown communication data includes the GPS positioning information, flight status information, and flight trajectory information of the UAV;

[0016] According to the communication data, perform positioning analysis, speed evaluation, and trajectory tracking on the UAV, and generate flight characteristic data based on three dimensions of position, speed, and path.

[0017] In this solution, within an analysis period, use the flight characteristic data of multiple target UAVs as sample data for clustering analysis based on K-means. Through the clustering results, divide multiple UAV groups. Specifically:

[0018] Construct a clustering model based on K-means;

[0019] Within an analysis period, import the flight characteristic data of multiple target UAVs into the clustering model as sample data;

[0020] In the clustering model, randomly set K clustering centers, calculate the distance from the sample data points to the clustering centers based on the Euclidean distance, and cluster the sample data based on the nearest distance;

[0021] Recalculate whether the center points in multiple clustering groups coincide with the original clustering centers. If not, reset the center points and perform clustering in a loop until the new center points in the clustering group coincide with the center points in the previous clustering process. Record the clustering data grouping result at this time to obtain the clustering result;

[0022] Based on the clustering results, perform corresponding grouping mapping on multiple target UAVs to divide them into multiple UAV groups.

[0023] In this solution, taking the UAV group as the analysis unit, integrate the flight characteristic data of each UAV group to form multiple feature sets, construct an isolation forest model and initialize it, preprocess the multiple feature sets and import them into the isolation forest model for data classification, analyze the abnormal data points, analyze the occurrence frequency of the abnormal data points in multiple UAV groups, and screen out the UAV groups to be tested based on the highest frequency. Specifically:

[0024] Taking the UAV group as the analysis unit, integrate the flight characteristic data of each UAV group to form multiple feature sets;

[0025] Construct an isolation forest model and initialize the model parameters. The model parameters include the number of trees, the estimated value of the proportion of abnormal data, and the random number seed;

[0026] Perform data standardization preprocessing on the multiple feature sets and import them as a whole sample into the isolation forest model for predicting abnormal data points, and return a list of abnormal data points;

[0027] According to the list of abnormal data points, count the occurrence frequency of abnormal data points in each feature set, mark the corresponding UAV group based on the highest frequency, and mark it as the UAV group to be tested.

[0028] In this solution, mark all the target UAVs in the UAV group to be tested and obtain the real-time characteristic data of the UAV group to be tested through real-time communication. Perform UAV anomaly judgment through the real-time characteristic data and mark the abnormal UAVs. Specifically:

[0029] Through real-time communication, obtain the real-time characteristic data of all the target UAVs in the UAV group to be tested;

[0030] The real-time characteristic data includes GPS positioning information, flight status information, and flight trajectory information;

[0031] Perform abnormal state judgment on the real-time characteristic data for the UAVs and mark the abnormal UAVs.

[0032] In this solution, according to the real-time characteristic data of the abnormal UAVs, adjust the communication resource allocation of the multi-beam array antenna to perform high-quality data transmission for the abnormal UAVs. At the same time, based on the abnormal UAVs, perform anti-aircraft mode analysis and strategy evaluation to formulate UAV anti-aircraft strategies. Specifically:

[0033] According to the real-time characteristic data of the abnormal UAVs, perform coordinate positioning analysis and flight status evaluation on the abnormal UAVs to form abnormal UAV status information;

[0034] Based on the abnormal UAV status information, set the priority communication requirements, and within a preset short period, dynamically adjust the multi-beam array antenna configuration, regulate the communication resource allocation, so as to meet the priority communication requirements;

[0035] The dynamic adjustment of the multi-beam array antenna configuration includes frequency, bandwidth, power, and frequency band parameters;

[0036] Through the abnormal UAV status information, conduct anti-aircraft mode analysis and strategy evaluation, and formulate UAV countermeasure strategies.

[0037] The second aspect of the present invention also provides a multi-target UAV countermeasure system based on a multi-beam array antenna. The system includes: a memory and a processor. The memory includes a multi-target UAV countermeasure program based on a multi-beam array antenna. When the multi-target UAV countermeasure program based on a multi-beam array antenna is executed by the processor, the following steps are implemented:

[0038] In a preset airspace, set a multi-beam array antenna, and conduct real-time communication with the target UAV through the multi-beam array antenna;

[0039] Within an analysis period, through real-time communication, obtain the communication data of multiple target UAVs, conduct positioning analysis, speed evaluation, and trajectory tracking based on the communication data, and generate multi-dimensional flight feature data;

[0040] Within an analysis period, use the flight feature data of multiple target UAVs as sample data for clustering analysis based on K-means. Through the clustering results, divide multiple groups of UAVs;

[0041] Taking the group of UAVs as the analysis unit, integrate the flight feature data of each group of UAVs to form multiple feature sets, construct an isolation forest model and initialize it, preprocess the multiple feature sets and import them into the isolation forest model for data classification, analyze the abnormal data points, analyze the occurrence frequency of the abnormal data points in multiple groups of UAVs, and screen out the group of UAVs to be tested based on the highest frequency;

[0042] Mark all the target UAVs in the group of UAVs to be tested and obtain the real-time feature data of the group of UAVs to be tested through real-time communication. Conduct UAV abnormality judgment through the real-time feature data and mark the abnormal UAVs;

[0043] According to the real-time feature data of the abnormal UAVs, regulate the communication resource allocation of the multi-beam array antenna, conduct high-quality data transmission for the abnormal UAVs. At the same time, conduct anti-aircraft mode analysis and strategy evaluation based on the abnormal UAVs, and formulate UAV countermeasure strategies.

[0044] The third aspect of the present invention further provides a computer-readable storage medium, which includes a multi-target UAV countermeasure program based on a multi-beam array antenna. When the multi-target UAV countermeasure program based on the multi-beam array antenna is executed by a processor, the steps of the multi-target UAV countermeasure method based on the multi-beam array antenna as described in any one of the above are implemented.

[0045] The present invention discloses a multi-target UAV countermeasure system based on a multi-beam array antenna. Through real-time communication by the multi-beam array antenna, UAV communication data is acquired, positioning, speed evaluation and trajectory tracking are performed, and multi-dimensional flight feature data is generated. Within an analysis period, the UAV group is divided by using K-means clustering analysis, an isolation forest model is constructed to classify the feature set, abnormal data points are identified, and the UAV group to be measured is selected based on the highest frequency. Subsequently, the UAVs in the group to be measured are marked and their real-time feature data is acquired, and the abnormal UAVs are judged and marked. Finally, according to the abnormal UAV data, the communication resources of the multi-beam antenna are regulated, and a UAV countermeasure strategy is formulated to achieve accurate, rapid abnormal evaluation and efficient countermeasure control of the UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The flowchart of a multi-target UAV countermeasure method based on a multi-beam array antenna according to the present invention is shown;

[0047] Figure 2 The block diagram of a multi-target UAV countermeasure system based on a multi-beam array antenna according to the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0049] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0050] Figure 1 The flowchart of a multi-target UAV countermeasure method based on a multi-beam array antenna according to the present invention is shown.

[0051] As Figure 1 shown, the first aspect of the present invention provides a multi-target UAV countermeasure method based on a multi-beam array antenna, including:

[0052] In a preset airspace, a multi-beam array antenna is set up to conduct real-time communication with target UAVs through the multi-beam array antenna.

[0053] S102, within an analysis period, through real-time communication, obtain the communication data of multiple target UAVs, conduct positioning analysis, speed assessment, and trajectory tracking based on the communication data, and generate multi-dimensional flight feature data.

[0054] S104, within an analysis period, use the flight feature data of multiple target UAVs as sample data for clustering analysis based on K-means. Through the clustering results, divide multiple UAV groups.

[0055] S106, taking the UAV groups as the analysis units, integrate the flight feature data of each UAV group to form multiple feature sets, construct and initialize an isolation forest model, preprocess the multiple feature sets and import them into the isolation forest model for data classification, analyze the abnormal data points, analyze the occurrence frequency of the abnormal data points in multiple UAV groups, and screen out the UAV groups to be tested based on the highest frequency.

[0056] S108, mark all the target UAVs in the UAV groups to be tested and obtain the real-time feature data of the UAV groups to be tested through real-time communication. Conduct UAV anomaly judgment through the real-time feature data and mark the abnormal UAVs.

[0057] S110, according to the real-time feature data of the abnormal UAVs, adjust the communication resource allocation of the multi-beam array antenna to conduct high-quality data transmission for the abnormal UAVs. At the same time, conduct anti-aircraft UAV countermeasure mode analysis and strategy evaluation based on the abnormal UAVs, and formulate UAV countermeasure strategies.

[0058] According to the embodiments of the present invention, the step of setting up a multi-beam array antenna in a preset airspace to conduct real-time communication with target UAVs through the multi-beam array antenna is specifically as follows:

[0059] According to the preset airspace range, altitude information, and attribute parameters of the target UAVs, determine the communication frequency band, polarization mode, gain, and directivity parameters of the antenna, and set the layout of the multi-beam array antenna.

[0060] Realize real-time communication with the target UAVs through the multi-beam array antenna, and collect the communication data of the target UAVs through the central platform.

[0061] It should be noted that in the process of multi-UAV data collection and analysis, it is necessary to use a multi-beam array antenna for communication enhancement to obtain high-quality communication data.

[0062] According to an embodiment of the present invention, within an analysis period, communication data of multiple target unmanned aerial vehicles (UAVs) is obtained through real-time communication, and positioning analysis, speed evaluation, and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data is generated. Specifically:

[0063] Within an analysis period, communication data of multiple target UAVs is obtained through real-time communication. The communication data includes GPS positioning information, flight status information, and flight trajectory information of the UAVs.

[0064] Based on the communication data, positioning analysis, speed evaluation, and trajectory tracking are performed on the UAVs, and flight feature data based on three dimensions of position, speed, and path is generated.

[0065] It should be noted that the position dimension analysis is generally performed based on the three-dimensional coordinates of a preset airspace.

[0066] According to an embodiment of the present invention, within an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means based clustering analysis, and through the clustering results, multiple groups of UAVs are divided. Specifically:

[0067] Construct a K-means based clustering model;

[0068] Within an analysis period, the flight feature data of multiple target UAVs is imported into the clustering model as sample data;

[0069] In the clustering model, K clustering centers are randomly set, the distances from the sample data points to the clustering centers are calculated based on the Euclidean distance, and the sample data is clustered based on the nearest distance;

[0070] Recalculate whether the central points in multiple clustering groups coincide with the original clustering centers. If not, reset the central points and perform clustering in a loop until the new central points in the clustering groups coincide with the central points in the previous clustering process, and record the clustering data grouping results at this time to obtain the clustering results;

[0071] Through the clustering results, corresponding grouping mappings are performed on multiple target UAVs, and multiple groups of UAVs are divided.

[0072] It should be noted that the analysis period is a time period set by the user. Each group of UAVs includes one or more target UAVs.

[0073] According to an embodiment of the present invention, taking the unmanned aircraft group as the analysis unit, integrating the flight characteristic data of each unmanned aircraft group to form multiple feature sets, constructing an isolation forest model and initializing it, preprocessing the multiple feature sets and importing them into the isolation forest model for data classification, analyzing the abnormal data points, analyzing the occurrence frequency of the abnormal data points in multiple unmanned aircraft groups, and screening out the unmanned aircraft groups to be tested based on the highest frequency, specifically:

[0074] Taking the unmanned aircraft group as the analysis unit, integrating the flight characteristic data of each unmanned aircraft group to form multiple feature sets;

[0075] Constructing an isolation forest model and initializing the model parameters, where the model parameters include the number of trees, the estimated value of the proportion of abnormal data, and the random number seed;

[0076] Performing data standardization preprocessing on the multiple feature sets and importing them as a whole sample into the isolation forest model for predicting abnormal data points, and returning a list of abnormal data points;

[0077] According to the list of abnormal data points, counting the occurrence frequency of abnormal data points in each feature set, and marking the corresponding unmanned aircraft group based on the highest frequency, and marking it as the unmanned aircraft group to be tested.

[0078] It should be noted that the list of abnormal data points includes information such as the location of abnormal data, the dataset to which it belongs, and the abnormal value. The isolation forest model can perform abnormal prediction training based on historical feature sets. Each feature set corresponds to each unmanned aircraft group one by one.

[0079] According to an embodiment of the present invention, marking all target unmanned aircraft in the unmanned aircraft group to be tested and obtaining the real-time feature data of the unmanned aircraft group to be tested through real-time communication, and performing unmanned aircraft abnormal judgment through the real-time feature data and marking the abnormal unmanned aircraft, specifically:

[0080] Obtaining the real-time feature data of all target unmanned aircraft in the unmanned aircraft group to be tested through real-time communication;

[0081] The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information;

[0082] Performing abnormal state judgment on the real-time feature data for the unmanned aircraft and marking the abnormal unmanned aircraft.

[0083] It should be noted that the abnormal state judgment can be evaluated based on preset flight standard state data.

[0084] It is worth mentioning here that for the analysis of multi-target drones, especially large-scale drone data, accurately identifying and countering some or a small number of abnormal drones among them is a complex control task. Traditional drone analysis systems often analyze and identify drones one by one based on single drones, which is inefficient and difficult to quickly screen out abnormal situations. Based on this, the present invention obtains multi-dimensional flight feature data through the communication of multiple drones (multi-beam array antennas), imports the feature data into a clustering model for feature analysis and clustering, divides the clustering groups, and conducts the first screening and grouping of the drone groups that may be abnormal. The clustering results can analyze the characteristics of drones on a large scale, quickly aggregate abnormal data. Further, the frequency analysis of abnormal data points is carried out for each clustering group (i.e., each feature set), which is completed through the isolation forest algorithm, further predicting and screening out the drone groups with abnormalities and marking them as the groups to be tested, and further accurately screening the drone groups with abnormalities and marking the abnormal drones, so as to achieve accurate and rapid abnormal evaluation and screening of large-scale drones, and this process can effectively conduct rapid data mining and effective data screening for flight feature data. In addition, the isolation forest algorithm has the characteristics of fast abnormal detection and less required computing resources, and is suitable for the process of the present invention.

[0085] According to an embodiment of the present invention, based on the real-time feature data of the abnormal drone, the communication resource allocation of the multi-beam array antenna is adjusted to perform high-quality data transmission for the abnormal drone. At the same time, based on the abnormal drone, anti-interference mode analysis and strategy evaluation are carried out to formulate a drone anti-interference strategy, specifically:

[0086] Based on the real-time feature data of the abnormal drone, coordinate positioning analysis and flight state evaluation are carried out on the abnormal drone to form abnormal drone state information;

[0087] According to the abnormal drone state information, set the priority communication requirements, and within a preset short period, dynamically adjust the multi-beam array antenna configuration to regulate the communication resource allocation to meet the priority communication requirements;

[0088] Dynamically adjusting the multi-beam array antenna configuration includes frequency, bandwidth, power, and frequency band parameters;

[0089] Through the abnormal drone state information, anti-interference mode analysis and strategy evaluation are carried out to formulate a drone anti-interference strategy.

[0090] It should be noted that the preset short period is a relatively short time period set by the user. The multi-beam array antenna is dynamically adjusted within the short period to adapt to the communication of the abnormal drone in the short term, improve the communication quality and communication effect of the abnormal drone, and appropriately suspend the communication of other non-abnormal drones to improve the utilization rate of communication resources.

[0091] According to an embodiment of the present invention, it further includes:

[0092] Obtain the flight characteristic data of the target UAV in multiple analysis periods, and mark it as multi-period characteristic data;

[0093] The multiple analysis periods are consecutive periods;

[0094] Perform feature vectorization on the multi-period characteristic data to form a multi-dimensional feature vector dataset;

[0095] Based on the time dimension, order the feature vector dataset and serialize the feature vector dataset to form feature sequence data;

[0096] Perform data standardization and outlier removal on the flight characteristic data;

[0097] Construct a prediction model based on LSTM, import the feature sequence data into the prediction model, set the prediction period as one analysis period, and output a prediction sequence;

[0098] Parse the prediction sequence to form the predicted flight characteristic data of the UAV;

[0099] Mark the UAV countermeasure strategy as the first strategy;

[0100] Perform countermeasure mode analysis and strategy evaluation according to the predicted flight characteristic data to generate a second strategy;

[0101] Perform a joint feasibility evaluation of the countermeasure mode according to the first strategy and the second strategy. The feasibility evaluation includes countermeasure resource limitation analysis and countermeasure mode matching analysis, and perform a solution fusion of the countermeasure mode for the first strategy and the second strategy to generate an optimized countermeasure plan.

[0102] It should be noted that during the UAV countermeasure process, different countermeasure modes and strategies can be adopted for UAVs in different flight states to achieve an efficient countermeasure effect. The countermeasure modes include signal interference, laser strike, acoustic wave interference, navigation deception, etc. Here, they are dynamically selected and matched based on the flight state, UAV type, etc., and an optimized plan is generated through joint analysis based on the first and second strategies.

[0103] Furthermore, the present invention serializes the flight characteristics, uses the LSTM model for flight prediction, learns and predicts the characteristic data. Finally, based on the real-time characteristics, a first strategy is generated, based on the predicted characteristics, a second strategy is generated, the differences between the first and second strategies are analyzed, and the feasibility fusion of the countermeasure strategies is performed to obtain the corresponding optimized plan, making the countermeasure strategy have wide applicability, improving the countermeasure control ability, and achieving efficient and accurate control of the overall UAV group.

[0104] The feature sequence data includes sequences under multiple periods.

[0105] According to an embodiment of the present invention, the prediction model further includes:

[0106] Based on a preset number of analysis periods, obtain a feature set corresponding to each unmanned aircraft group;

[0107] Based on the time dimension, serialize the feature set and import it into the prediction model for sequence prediction to obtain a feature prediction sequence;

[0108] Each feature set corresponds to a feature prediction sequence;

[0109] Parse the feature prediction sequence to form multi-dimensional real-time prediction features;

[0110] Based on an autoencoder network, map the real-time prediction features as input data to low-dimensional hidden representation data, and the mapping process is performed based on a multi-layer perceptron;

[0111] Through a multi-layer perceptron, reconstruct the low-dimensional hidden representation data and obtain output features;

[0112] Evaluate the difference between the output features and the input data through cross-entropy loss and optimize the training of the autoencoder network until the cross-entropy loss converges within a preset range, and obtain the corresponding output features marked as reconstructed prediction features;

[0113] Based on the reconstructed prediction features, perform flight anomaly evaluation and countermeasure warning analysis on multiple unmanned aircraft groups, and combine the flight prediction states of multiple unmanned aircraft groups to generate countermeasure warning information.

[0114] It should be noted that each unmanned aircraft group corresponds to independent reconstructed prediction features. In the present invention, based on the prediction model, flight prediction is performed on multiple unmanned aircraft groups, and the autoencoder network is used for dimensionality reduction analysis of high-dimensional real-time flight features, which helps to reduce useless prediction information, extract core prediction information, and achieve accurate, fast, and efficient flight warning and countermeasure warning for multiple unmanned aircraft groups, improving the countermeasure control ability of the system.

[0115] Figure 2 Shows a block diagram of a multi-target unmanned aircraft countermeasure system based on a multi-beam array antenna according to the present invention.

[0116] The second aspect of the present invention also provides a multi-target unmanned aircraft countermeasure system based on a multi-beam array antenna. The system includes: a memory 21 and a processor 22. The memory 21 includes a multi-target unmanned aircraft countermeasure program based on a multi-beam array antenna. When the multi-target unmanned aircraft countermeasure program based on a multi-beam array antenna is executed by the processor 22, the following steps are implemented:

[0117] In a preset airspace, a multi-beam array antenna is set, and real-time communication is carried out with target unmanned aerial vehicles (UAVs) through the multi-beam array antenna.

[0118] Within an analysis period, through real-time communication, communication data of multiple target UAVs is obtained, and positioning analysis, speed evaluation, and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data is generated.

[0119] Within an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means-based clustering analysis, and through the clustering results, multiple groups of UAVs are divided.

[0120] Taking the groups of UAVs as analysis units, the flight feature data of each group of UAVs is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, the multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the occurrence frequency of the abnormal data points in multiple groups of UAVs is analyzed, and the groups of UAVs to be tested are screened based on the highest frequency.

[0121] All target UAVs in the groups of UAVs to be tested are marked, and real-time feature data of the groups of UAVs to be tested is obtained through real-time communication. UAV abnormality judgment is performed through the real-time feature data, and the abnormal UAVs are marked.

[0122] According to the real-time feature data of the abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to perform high-quality data transmission for the abnormal UAVs. At the same time, anti-interference mode analysis and strategy evaluation are performed based on the abnormal UAVs, and a UAV anti-interference strategy is formulated.

[0123] According to an embodiment of the present invention, the step of setting a multi-beam array antenna in a preset airspace and performing real-time communication with target UAVs through the multi-beam array antenna is specifically as follows:

[0124] According to the preset airspace range, altitude information, and attribute parameters of the target UAVs, the communication frequency band, polarization mode, gain, and directivity parameters of the antenna are determined, and the layout of the multi-beam array antenna is set.

[0125] Real-time communication with the target UAVs is achieved through the multi-beam array antenna, and the communication data of the target UAVs is collected by the central platform.

[0126] It should be noted that in the process of multi-UAV data collection and analysis, a multi-beam array antenna needs to be used for communication enhancement to obtain high-quality communication data.

[0127] According to an embodiment of the present invention, the step of obtaining communication data of multiple target UAVs through real-time communication within an analysis period, performing positioning analysis, speed evaluation, and trajectory tracking based on the communication data, and generating multi-dimensional flight feature data is specifically as follows:

[0128] During an analysis period, communication data of multiple target unmanned aerial vehicles (UAVs) is obtained through real-time communication. The communication data includes GPS positioning information, flight status information, and flight trajectory information of the UAVs.

[0129] Based on the communication data, positioning analysis, speed assessment, and trajectory tracking of the UAVs are performed, and flight feature data in three dimensions of position, speed, and path is generated.

[0130] It should be noted that the position dimension analysis is generally performed based on the three-dimensional coordinates of a preset airspace.

[0131] According to an embodiment of the present invention, during an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means-based clustering analysis. Through the clustering result, multiple groups of UAVs are divided, specifically as follows:

[0132] Construct a K-means-based clustering model;

[0133] During an analysis period, the flight feature data of multiple target UAVs is imported into the clustering model as sample data;

[0134] In the clustering model, K clustering centers are randomly set. Based on the Euclidean distance, the distance from the sample data points to the clustering centers is calculated, and the sample data is clustered based on the nearest distance;

[0135] Recalculate whether the center points in multiple clustering groups coincide with the original clustering centers. If not, reset the center points and perform clustering in a loop until the new center points in the clustering group coincide with the center points in the previous clustering process. Record the clustering data grouping result at this time to obtain the clustering result;

[0136] Through the clustering result, corresponding group mapping is performed on multiple target UAVs to divide multiple groups of UAVs.

[0137] It should be noted that the analysis period is a time period set by the user. Each group of UAVs includes one or more target UAVs.

[0138] According to an embodiment of the present invention, taking the group of UAVs as the analysis unit, the flight feature data of each group of UAVs is integrated to form multiple feature sets. An isolation forest model is constructed and initialized. The multiple feature sets are preprocessed and imported into the isolation forest model for data classification to analyze abnormal data points. The occurrence frequency of the abnormal data points in multiple groups of UAVs is analyzed, and the group of UAVs to be tested is selected based on the highest frequency, specifically as follows:

[0139] Taking the group of UAVs as the analysis unit, the flight feature data of each group of UAVs is integrated to form multiple feature sets;

[0140] Construct an isolation forest model and initialize the model parameters, which include the number of trees, the estimated value of the proportion of abnormal data, and the random number seed;

[0141] Preprocess the data standardization of multiple feature sets and import them as a whole sample into the isolation forest model for abnormal data point prediction, and return a list of abnormal data points;

[0142] According to the list of abnormal data points, count the occurrence frequency of abnormal data points for each feature set, and mark the corresponding unmanned aircraft group based on the highest frequency, and mark it as the to-be-tested unmanned aircraft group.

[0143] It should be noted that the list of abnormal data points includes information such as the location of abnormal data, the dataset to which it belongs, and the abnormal value. The isolation forest model can perform abnormal prediction training based on historical feature sets. Each feature set corresponds to each unmanned aircraft group one by one.

[0144] According to an embodiment of the present invention, marking all target unmanned aircraft in the to-be-tested unmanned aircraft group and obtaining real-time feature data of the to-be-tested unmanned aircraft group through real-time communication, and performing unmanned aircraft abnormal judgment through the real-time feature data and marking the abnormal unmanned aircraft, specifically:

[0145] Obtain the real-time feature data of all target unmanned aircraft in the to-be-tested unmanned aircraft group through real-time communication;

[0146] The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information;

[0147] Perform abnormal state judgment on the real-time feature data and mark the abnormal unmanned aircraft.

[0148] It should be noted that the abnormal state judgment can be evaluated based on preset flight standard state data.

[0149] It is worth mentioning here that for the analysis of multi-target drones, especially large-scale drone data, accurately identifying and countering some or a small number of abnormal drones among them is a complex control task. Traditional drone analysis systems often analyze and identify drones one by one based on single drones, which is inefficient and difficult to quickly screen out abnormal situations. Based on this, the present invention obtains multi-dimensional flight feature data through the communication of multiple drones (multi-beam array antennas), imports the feature data into a clustering model for feature analysis and clustering, and divides the clustering groups to conduct the first screening and grouping of the drone groups that may be abnormal. The clustering results can analyze the feature situations of drones on a large scale, quickly aggregate abnormal data. Further, the frequency analysis of abnormal data points is performed on each clustering group (i.e., each feature set), which is completed through the isolation forest algorithm. Further, the drone groups with abnormalities are predicted and screened out and marked as the groups to be tested. Further, precise screening is carried out on the drone groups with abnormalities, and the abnormal drones are marked, so as to achieve accurate and rapid abnormal evaluation and screening of large-scale drones, and this process can effectively conduct rapid data mining and effective data screening of flight feature data. In addition, the isolation forest algorithm has the characteristics of fast abnormal detection and less required computing resources, and is suitable for the process of the present invention.

[0150] According to an embodiment of the present invention, based on the real-time feature data of abnormal drones, the communication resource allocation of the multi-beam array antenna is adjusted to perform high-quality data transmission on the abnormal drones. At the same time, based on the abnormal drones, anti-interference mode analysis and strategy evaluation are carried out to formulate a drone anti-interference strategy, specifically:

[0151] Based on the real-time feature data of abnormal drones, coordinate positioning analysis and flight state evaluation are carried out on the abnormal drones to form the state information of the abnormal drones;

[0152] According to the state information of the abnormal drones, the priority communication requirements are set, and within a preset short period, the configuration of the multi-beam array antenna is dynamically adjusted to regulate the communication resource allocation to meet the priority communication requirements;

[0153] Dynamically adjusting the configuration of the multi-beam array antenna includes frequency, bandwidth, power, and frequency band parameters;

[0154] Through the state information of the abnormal drones, anti-interference mode analysis and strategy evaluation are carried out to formulate a drone anti-interference strategy.

[0155] It should be noted that the preset short period is a relatively short time period set by the user. Within the short period, the multi-beam array antenna is dynamically adjusted to adapt to the communication of abnormal drones in the short term, improve the communication quality and communication effect of abnormal drones, and appropriately suspend the communication of other non-abnormal drones to improve the utilization rate of communication resources.

[0156] In a third aspect of the present invention, there is also provided a computer-readable storage medium, which includes a multi-target UAV countermeasure program based on a multi-beam array antenna. When the multi-target UAV countermeasure program based on the multi-beam array antenna is executed by a processor, the steps of the multi-target UAV countermeasure method based on the multi-beam array antenna as described in any one of the above are implemented.

[0157] The present invention discloses a multi-target UAV countermeasure system based on a multi-beam array antenna. Through real-time communication with the multi-beam array antenna, UAV communication data is obtained, and positioning, speed evaluation, and trajectory tracking are performed to generate multi-dimensional flight feature data. Within an analysis period, the K-means clustering analysis is used to divide UAV groups, and an isolation forest model is constructed to classify the feature set, identify abnormal data points, and screen out the UAV groups to be tested based on the highest frequency. Subsequently, the UAVs in the group to be tested are marked and their real-time feature data is obtained to judge and mark abnormal UAVs. Finally, based on the abnormal UAV data, the communication resources of the multi-beam antenna are regulated, and a UAV countermeasure strategy is formulated to achieve accurate, rapid abnormal evaluation and efficient countermeasure control of UAVs.

[0158] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0159] The units described as separate components above may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in the embodiments of the present invention can be all integrated in one processing unit, or each unit can be separately used as one unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of a hardware plus a software functional unit.

[0161] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the foregoing storage medium includes: various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0162] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, 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 causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0163] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. A multi-target UAV countermeasure method based on a multi-beam array antenna, characterized in that Including: In a preset airspace, a multi-beam array antenna is set up to conduct real-time communication with target UAVs through the multi-beam array antenna; Within an analysis period, through real-time communication, communication data of multiple target UAVs is obtained, and positioning analysis, speed evaluation and trajectory tracking are carried out based on the communication data, and multi-dimensional flight feature data is generated; Within an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means-based clustering analysis, and through the clustering results, multiple UAV groups are divided; Taking the UAV group as the analysis unit, the flight feature data of each UAV group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, the multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the occurrence frequency of the abnormal data points in multiple UAV groups is analyzed, and the UAV groups to be tested are selected based on the highest frequency; All target UAVs in the UAV groups to be tested are marked and the real-time feature data of the UAV groups to be tested is obtained through real-time communication, and UAV anomaly judgment is carried out through the real-time feature data and the abnormal UAVs are marked; According to the real-time feature data of the abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to conduct high-quality data transmission to the abnormal UAVs. At the same time, based on the abnormal UAVs, anti-countermeasure mode analysis and strategy evaluation are carried out, and a UAV anti-countermeasure strategy is formulated; Among them, within an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means-based clustering analysis, and through the clustering results, multiple UAV groups are divided. Specifically: Construct a K-means-based clustering model; Within an analysis period, the flight feature data of multiple target UAVs is imported into the clustering model as sample data; In the clustering model, K clustering centers are randomly set, the distance from the sample data points to the clustering centers is calculated based on the Euclidean distance, and the sample data is clustered based on the nearest distance; Recalculate whether the central points in multiple clustering groups coincide with the original clustering centers. If not, reset the central points and perform clustering in a loop until the new central points in the clustering groups coincide with the central points in the previous clustering process, record the clustering data grouping results at this time to obtain the clustering results; Through the clustering results, corresponding grouping mapping is carried out on multiple target UAVs to divide multiple UAV groups.

2. The multi-target UAV countermeasure method based on a multi-beam array antenna according to claim 1, wherein, In the preset airspace, a multi-beam array antenna is set up to conduct real-time communication with target UAVs through the multi-beam array antenna. Specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAVs, determine the communication frequency band, polarization mode, gain and directivity parameters of the antenna, and set the layout of the multi-beam array antenna; Realize real-time communication with target UAVs through the multi-beam array antenna, and collect target UAV communication data through the central platform.

3. A multi-target UAV countermeasure method based on a multi-beam array antenna according to claim 1, characterized in that Within an analysis period, through real-time communication, communication data of multiple target UAVs is obtained, and positioning analysis, speed evaluation and trajectory tracking are carried out based on the communication data, and multi-dimensional flight feature data is generated. Specifically: During an analysis period, communication data of multiple target UAVs is obtained through real-time communication. The communication data includes GPS positioning information, flight status information, and flight trajectory information of the UAVs. Based on the communication data, positioning analysis, speed assessment, and trajectory tracking of the UAVs are performed, and flight feature data based on three dimensions of position, speed, and path is generated.

4. A multi-target UAV countermeasure method based on a multi-beam array antenna according to claim 1, characterized in that, Taking the UAV group as the analysis unit, the flight feature data of each UAV group is integrated to form multiple feature sets. An isolation forest model is constructed and initialized. The multiple feature sets are preprocessed and imported into the isolation forest model for data classification to analyze abnormal data points. The occurrence frequency of the abnormal data points in multiple UAV groups is analyzed, and the UAV groups to be tested are selected based on the highest frequency. Specifically: Taking the UAV group as the analysis unit, the flight feature data of each UAV group is integrated to form multiple feature sets. An isolation forest model is constructed, and the model parameters are initialized. The model parameters include the number of trees, the estimated value of the proportion of abnormal data, and the random number seed. The multiple feature sets are preprocessed by data standardization and imported into the isolation forest model as a whole sample for predicting abnormal data points, and a list of abnormal data points is returned. According to the list of abnormal data points, the occurrence frequency of abnormal data points in each feature set is counted, and the corresponding UAV group is marked based on the highest frequency and marked as the UAV group to be tested.

5. The multi-target UAV countermeasure method based on a multi-beam array antenna according to claim 4, wherein All target UAVs in the UAV group to be tested are marked, and the real-time feature data of the UAV group to be tested is obtained through real-time communication. The abnormal state of the UAVs is judged through the real-time feature data, and the abnormal UAVs are marked. Specifically: Through real-time communication, the real-time feature data of all target UAVs in the UAV group to be tested is obtained. The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information. The abnormal state of the UAVs is judged based on the real-time feature data, and the abnormal UAVs are marked.

6. The multi-target UAV countermeasure method based on a multi-beam array antenna according to claim 5, characterized in that, According to the real-time feature data of the abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to perform high-quality data transmission for the abnormal UAVs. At the same time, based on the abnormal UAVs, anti-interference mode analysis and strategy evaluation are performed, and an UAV anti-interference strategy is formulated. Specifically: Based on the real-time feature data of the abnormal UAVs, coordinate positioning analysis and flight status evaluation of the abnormal UAVs are performed to form the status information of the abnormal UAVs. According to the status information of the abnormal UAVs, the priority communication requirements are set. Within a preset short period, the configuration of the multi-beam array antenna is dynamically adjusted to control the communication resource allocation to meet the priority communication requirements. The dynamic adjustment of the multi-beam array antenna configuration includes frequency, bandwidth, power, and frequency band parameters. Anti-interference mode analysis and strategy evaluation are performed through the status information of the abnormal UAVs, and an UAV anti-interference strategy is formulated.

7. A multi-target UAV countermeasure system based on a multi-beam array antenna, characterized in that, The system includes: a memory and a processor. The memory includes a multi-target UAV anti-interference program based on a multi-beam array antenna. When the multi-target UAV anti-interference program based on the multi-beam array antenna is executed by the processor, the following steps are implemented: In a preset airspace, a multi-beam array antenna is set, and real-time communication with the target UAVs is performed through the multi-beam array antenna. During an analysis period, communication data of multiple target UAVs is obtained through real-time communication, and positioning analysis, speed assessment, and trajectory tracking are performed based on the communication data to generate multi-dimensional flight feature data; During an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means based clustering analysis, and multiple UAV groups are divided based on the clustering results; Taking the UAV groups as the analysis units, the flight feature data of each UAV group is integrated to form multiple feature sets. An isolation forest model is constructed and initialized. The multiple feature sets are preprocessed and imported into the isolation forest model for data classification to analyze abnormal data points. The occurrence frequency of the abnormal data points in multiple UAV groups is analyzed, and the UAV groups to be tested are selected based on the highest frequency; All target UAVs in the UAV groups to be tested are marked, and the real-time feature data of the UAV groups to be tested is obtained through real-time communication. UAV abnormality judgment is performed based on the real-time feature data, and the abnormal UAVs are marked; According to the real-time feature data of the abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to perform high-quality data transmission for the abnormal UAVs. At the same time, anti-interference mode analysis and strategy evaluation are performed based on the abnormal UAVs, and a UAV anti-interference strategy is formulated; Among them, during an analysis period, the flight feature data of multiple target UAVs is used as sample data for K-means based clustering analysis, and multiple UAV groups are divided based on the clustering results. Specifically: Construct a clustering model based on K-means; During an analysis period, the flight feature data of multiple target UAVs is imported into the clustering model as sample data; In the clustering model, K clustering centers are randomly set. Based on the Euclidean distance, the distance from the sample data points to the clustering centers is calculated, and the sample data is clustered based on the nearest distance; Recalculate whether the center points in multiple clustering groups coincide with the original clustering centers. If not, reset the center points and perform clustering in a loop until the new center points in the clustering groups coincide with the center points in the previous clustering process. Record the clustering data grouping results at this time to obtain the clustering results; Based on the clustering results, corresponding grouping mapping is performed on multiple target UAVs to divide multiple UAV groups.

8. The multi-target UAV countermeasure system based on a multi-beam array antenna according to claim 7, wherein, In the preset airspace, a multi-beam array antenna is set, and real-time communication with the target UAVs is performed through the multi-beam array antenna. Specifically: According to the preset airspace range, altitude information, and attribute parameters of the target UAVs, determine the communication frequency band, polarization mode, gain, and directivity parameters of the antenna, and set the layout of the multi-beam array antenna; Realize real-time communication with the target UAVs through the multi-beam array antenna, and collect the communication data of the target UAVs through the central platform.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a multi-target UAV anti-interference program based on a multi-beam array antenna. When the multi-target UAV anti-interference program based on the multi-beam array antenna is executed by a processor, the steps of the multi-target UAV anti-interference method based on the multi-beam array antenna as described in any one of claims 1 to 6 are implemented.

Images