Multi-target unmanned aerial vehicle countering system based on multi-beam array antenna

Abstract

The invention discloses a multi-target unmanned aerial vehicle countering system based on a multi-beam array antenna. Real-time communication is carried out through a multi-beam array antenna, communication data of the unmanned aerial vehicle are obtained, positioning, speed evaluation and trajectory tracking are carried out, and multi-dimensional flight characteristic data are generated. And in one analysis period, dividing the unmanned aerial vehicle group by using K-means clustering analysis, constructing an isolated forest model to classify the feature set, identifying abnormal data points, and screening out the unmanned aerial vehicle group to be detected based on the highest frequency. And then, marking the to-be-detected group of unmanned aerial vehicles, obtaining real-time feature data of the unmanned aerial vehicles, and judging and marking abnormal unmanned aerial vehicles. And finally, multi-beam antenna communication resources are regulated and controlled according to the abnormal unmanned aerial vehicle data, an unmanned aerial vehicle countering strategy is formulated, and accurate and rapid abnormal evaluation and efficient countering management and control of the unmanned aerial vehicle are realized.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle data analysis, and more specifically, to a multi-target unmanned aerial vehicle 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 capabilities. However, in existing technologies, there is a lack of accurate abnormal state analysis and efficient counterattacks for multi-target drones, which makes it difficult to improve drone control capabilities. Therefore, how to use multi-beam array antennas to analyze drone communications and achieve high-precision counter-control is an important issue that needs to be solved urgently. 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] A first aspect of the present invention provides a multi-target UAV countermeasure method based on a multi-beam array antenna, comprising: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight characteristic data is generated; In one analysis cycle, the flight characteristic data of multiple target UAVs are used as sample data for K-means-based cluster analysis, and multiple UAV groups are divided according to the clustering results; Taking drone groups as analysis units, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency; Mark all target drones in the drone group to be tested and obtain real-time feature data of the drone group to be tested through real-time communication, judge drone anomalies based on the real-time feature data and mark abnormal drones; According to the real-time characteristic data of abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to transmit high-quality data to the abnormal UAVs. At the same time, countermeasure mode analysis and strategy evaluation are carried out based on abnormal UAVs to formulate a UAV countermeasure strategy.

[0005] In this solution, a multi-beam array antenna is set in a preset airspace, and real-time communication with the target UAV is performed through the multi-beam array antenna, specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAV, the communication frequency band, antenna polarization mode, gain, and directivity parameters are determined, and the multi-beam array antenna layout is set; Real-time communication with the target UAV is achieved through a multi-beam array antenna, and communication data of the target UAV is collected through the central platform.

[0006] In this solution, in one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data are generated, specifically: In one analysis cycle, the communication data of multiple target UAVs are obtained through real-time communication, and the communication data shown includes GPS positioning information, flight status information, and flight trajectory information of the UAVs; Based on the communication data, the drone is positioned, analyzed, and its speed is evaluated and its trajectory is tracked, and flight characteristic data based on three dimensions, namely position, speed, and path, is generated.

[0007] In this solution, in one analysis cycle, the flight characteristic data of multiple target drones are used as sample data for K-means-based cluster analysis, and multiple drone groups are divided according to the clustering results, specifically: Construct a clustering model based on K-means; In one analysis cycle, the flight characteristic data of multiple target UAVs are imported into the clustering model as sample data; In the clustering model, K cluster centers are randomly set, and the distance from the sample data point to the cluster center is calculated based on the Euclidean distance, and the sample data is clustered based on the closest distance; Recalculate whether the center points in multiple cluster groups coincide with the original cluster center. If not, reset the center point and perform clustering in a loop until the new center point in the cluster group coincides with the center point in the previous clustering process. Record the clustering data grouping results at this time to obtain the clustering results. Based on the clustering results, multiple target drones are mapped into corresponding groups and divided into multiple drone groups.

[0008] In this solution, the drone group is used as the analysis unit, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency, specifically: Taking drone groups as analysis units, the flight characteristic data of each drone group is integrated to form multiple feature sets; Construct an isolation forest model and initialize model parameters, including the number of trees, the estimated value of the proportion of abnormal data, and the random number seed; Perform data standardization preprocessing on multiple feature sets and import them as whole samples into the isolation forest model to predict abnormal data points, and return a list of abnormal data points; According to the list of abnormal data points, the frequency of occurrence of abnormal data points in each feature set is counted, and the corresponding drone group is marked based on the highest frequency and marked as the drone group to be tested.

[0009] In this solution, all target drones in the drone group to be tested are marked and real-time feature data of the drone group to be tested is obtained through real-time communication, and drone abnormality is judged and abnormal drones are marked based on the real-time feature data. Specifically, Through real-time communication, obtain the real-time characteristic data of all target drones in the drone group to be tested; The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information; The real-time feature data is used to determine the abnormal status of the drone and mark the abnormal drone.

[0010] In this scheme, the communication resource allocation of the multi-beam array antenna is adjusted according to the real-time characteristic data of the abnormal drone, and high-quality data transmission is performed on the abnormal drone. At the same time, the counter-attack mode analysis and strategy evaluation are performed based on the abnormal drone, and the drone counter-attack strategy is formulated, which is specifically: According to the real-time characteristic data of abnormal UAVs, coordinate positioning analysis and flight status evaluation of abnormal UAVs are performed to form abnormal UAV status information; According to abnormal drone status information, priority communication needs are set, and within a preset short period, the multi-beam array antenna configuration is dynamically adjusted to regulate communication resource allocation to meet priority communication needs; Dynamically adjust multi-beam array antenna configuration including frequency, bandwidth, power, and band parameters; Through abnormal drone status information, countermeasure mode analysis and strategy evaluation are carried out to formulate drone countermeasure strategies.

[0011] The second aspect of the present invention further provides a multi-target UAV countermeasure system based on a multi-beam array antenna, the system comprising: a memory, a processor, the memory comprising a multi-target UAV countermeasure program based on a multi-beam array antenna, and the multi-target UAV countermeasure program based on a multi-beam array antenna is executed by the processor to implement the following steps: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight characteristic data is generated; In one analysis cycle, the flight characteristic data of multiple target UAVs are used as sample data for K-means-based cluster analysis, and multiple UAV groups are divided according to the clustering results; Taking drone groups as analysis units, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency; Mark all target drones in the drone group to be tested and obtain real-time feature data of the drone group to be tested through real-time communication, judge drone anomalies based on the real-time feature data and mark abnormal drones; According to the real-time characteristic data of abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to transmit high-quality data to the abnormal UAVs. At the same time, countermeasure mode analysis and strategy evaluation are carried out based on abnormal UAVs to formulate a UAV countermeasure strategy.

[0012] The third aspect of the present invention also 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 a multi-beam array antenna is executed by a processor, the steps of the multi-target UAV countermeasure method based on a multi-beam array antenna as described in any one of the above items are implemented.

[0013] The present invention discloses a multi-target UAV countermeasure system based on a multi-beam array antenna. Real-time communication is carried out through a multi-beam array antenna to obtain UAV communication data, perform positioning, speed evaluation and trajectory tracking, and generate multi-dimensional flight feature data. Within an analysis cycle, the UAV group is divided by K-means clustering analysis, and an isolated forest model is constructed to classify the feature set, identify abnormal data points, and screen out the UAV group 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 are obtained, and abnormal UAVs are judged and marked. Finally, the multi-beam antenna communication resources are adjusted according to the abnormal UAV data, and a UAV countermeasure strategy is formulated to achieve accurate and rapid abnormal evaluation and efficient countermeasure control of UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1A flowchart of a multi-target UAV countermeasure method based on a multi-beam array antenna of the present invention is shown; Figure 2 A block diagram of a multi-target UAV countermeasure system based on a multi-beam array antenna of the present invention is shown. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1 A flow chart of a multi-target UAV countermeasure method based on a multi-beam array antenna of the present invention is shown.

[0018] like Figure 1 As shown, the first aspect of the present invention provides a multi-target UAV countermeasure method based on a multi-beam array antenna, comprising: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; S102, within one analysis cycle, obtaining communication data of multiple target UAVs through real-time communication, performing positioning analysis, speed evaluation and trajectory tracking based on the communication data, and generating multi-dimensional flight characteristic data; S104, within an analysis cycle, performing a K-means based cluster analysis on the flight characteristic data of the multiple target UAVs as sample data, and dividing the multiple UAV groups according to the clustering results; S106, taking the drone group as the analysis unit, integrating the flight feature data of each drone group to form multiple feature sets, constructing and initializing an isolation forest model, preprocessing the multiple feature sets and importing the isolation forest model to perform data classification, analyzing abnormal data points, analyzing the frequency of occurrence of abnormal data points in multiple drone groups, and screening out the drone group to be tested based on the highest frequency; S108, marking all target drones in the drone group to be tested and obtaining real-time feature data of the drone group to be tested through real-time communication, judging drone abnormalities based on the real-time feature data and marking abnormal drones; S110, according to the real-time characteristic data of the abnormal UAV, adjusts the communication resource allocation of the multi-beam array antenna to transmit high-quality data to the abnormal UAV. At the same time, based on the counter-attack mode analysis and strategy evaluation of the abnormal UAV, a UAV counter-attack strategy is formulated.

[0019] According to an embodiment of the present invention, in the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna, specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAV, the communication frequency band, antenna polarization mode, gain, and directivity parameters are determined, and the multi-beam array antenna layout is set; Real-time communication with the target UAV is achieved through a multi-beam array antenna, and communication data of the target UAV is collected through the central platform.

[0020] It should be noted that in the process of multi-UAV data collection and analysis, multi-beam array antennas are required for communication enhancement to obtain high-quality communication data.

[0021] According to an embodiment of the present invention, in one analysis cycle, communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data is generated, specifically: In one analysis cycle, the communication data of multiple target UAVs are obtained through real-time communication, and the communication data shown includes GPS positioning information, flight status information, and flight trajectory information of the UAVs; Based on the communication data, the drone is positioned, analyzed, and its speed is evaluated and its trajectory is tracked, and flight characteristic data based on three dimensions, namely position, speed, and path, is generated.

[0022] It should be noted that the position dimension analysis is generally performed based on the three-dimensional coordinates of a preset airspace.

[0023] According to an embodiment of the present invention, in one analysis cycle, the flight characteristic data of multiple target drones are used as sample data for cluster analysis based on K-means, and multiple drone groups are divided according to the clustering results, specifically: Construct a clustering model based on K-means; In one analysis cycle, the flight characteristic data of multiple target UAVs are imported into the clustering model as sample data; In the clustering model, K cluster centers are randomly set, and the distance from the sample data point to the cluster center is calculated based on the Euclidean distance, and the sample data is clustered based on the closest distance; Recalculate whether the center points in multiple cluster groups coincide with the original cluster center. If not, reset the center point and perform clustering in a loop until the new center point in the cluster group coincides with the center point in the previous clustering process. Record the clustering data grouping results at this time to obtain the clustering results. Based on the clustering results, multiple target drones are mapped into corresponding groups and divided into multiple drone groups.

[0024] It should be noted that the analysis period is a time period set by the user. Each drone group includes one or more target drones.

[0025] According to an embodiment of the present invention, the drone group is used as an analysis unit, the flight feature data of each drone 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 frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency, specifically: Taking drone groups as analysis units, the flight characteristic data of each drone group is integrated to form multiple feature sets; Construct an isolation forest model and initialize model parameters, including the number of trees, the estimated value of the proportion of abnormal data, and the random number seed; Perform data standardization preprocessing on multiple feature sets and import them as whole samples into the isolation forest model to predict abnormal data points, and return a list of abnormal data points; According to the list of abnormal data points, the frequency of occurrence of abnormal data points in each feature set is counted, and the corresponding drone group is marked based on the highest frequency and marked as the drone group to be tested.

[0026] It should be noted that the list of abnormal data points includes the location of the abnormal data, the data set to which it belongs, the abnormal value, and other information. The isolation forest model can be trained for abnormal prediction based on the historical feature set. Each feature set corresponds to each drone group.

[0027] According to an embodiment of the present invention, marking all target drones in the drone group to be tested and obtaining real-time feature data of the drone group to be tested through real-time communication, judging drone anomalies through real-time feature data and marking abnormal drones are specifically as follows: Through real-time communication, obtain the real-time characteristic data of all target drones in the drone group to be tested; The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information; The real-time feature data is used to determine the abnormal status of the drone and mark the abnormal drone.

[0028] It should be noted that the abnormal state judgment can be made based on preset flight standard state data.

[0029] It is worth mentioning here that for multi-target drones, especially large-scale drone data analysis, accurate identification and countermeasures of some or a small number of abnormal drones are a complex control task. Traditional drone analysis systems are often based on the analysis and identification of single drones one by one, which is inefficient and difficult to quickly screen out abnormal conditions. Based on this, the present invention obtains multi-dimensional flight feature data through the (multi-beam array antenna) communication of multiple drones, imports the feature data into a clustering model for feature analysis and clustering, and divides the cluster groups to perform the first screening and grouping of drone groups with abnormalities. The clustering results can analyze the characteristics of drones on a large scale and quickly aggregate the abnormal data. Further, each cluster group (i.e., each feature set) is analyzed for the frequency of abnormal data points, which is completed here by the isolation forest algorithm, and further predicts and screens the drone groups with abnormalities and marks them as the test group. Further, the drone groups with abnormalities are accurately screened and abnormal drones are marked, thereby realizing accurate and rapid abnormal evaluation and screening of large-scale drones, and the process can effectively perform rapid data mining and effective data screening on flight feature data. In addition, the isolation forest algorithm has the characteristics of fast anomaly detection and less required computing resources, and is suitable for the process of the present invention.

[0030] According to an embodiment of the present invention, the communication resource allocation of the multi-beam array antenna is adjusted according to the real-time characteristic data of the abnormal drone, and high-quality data transmission is performed on the abnormal drone. At the same time, the counter-measure mode analysis and strategy evaluation are performed based on the abnormal drone, and a drone counter-measure strategy is formulated, which is specifically: According to the real-time characteristic data of abnormal UAVs, coordinate positioning analysis and flight status evaluation of abnormal UAVs are performed to form abnormal UAV status information; According to abnormal drone status information, priority communication needs are set, and within a preset short period, the multi-beam array antenna configuration is dynamically adjusted to regulate communication resource allocation to meet priority communication needs; Dynamically adjust multi-beam array antenna configuration including frequency, bandwidth, power, and band parameters; Through abnormal drone status information, countermeasure mode analysis and strategy evaluation are carried out to formulate drone countermeasure strategies.

[0031] It should be noted that the preset short cycle is a shorter time period set by a user. The multi-beam array antenna is dynamically adjusted within the short cycle to adapt to the communication of abnormal drones in a short period of time, improve the communication quality and communication effect of abnormal drones, appropriately terminate the communication of other non-abnormal drones, and improve the utilization rate of communication resources.

[0032] According to an embodiment of the present invention, it also includes: Obtain flight characteristic data of the target UAV under multiple analysis cycles and mark them as multi-cycle characteristic data; The multiple analysis cycles are continuous cycles; Performing feature vectorization on the multi-period feature data to form a multi-dimensional feature vector data set; Based on the time dimension, the feature vector data set is ordered and the feature vector data set is serialized to form feature sequence data; Standardize flight characteristics data and remove outliers; Build a prediction model based on LSTM, import feature sequence data into the prediction model, set the prediction period as one analysis period, and output the prediction sequence; Perform data analysis on the predicted sequence to form the predicted flight characteristic data of the UAV; Mark the drone countermeasure strategy as the first strategy; Perform countermeasure mode analysis and strategy evaluation based on the predicted flight characteristic data to generate a second strategy; A joint feasibility assessment of the countermeasure mode is performed based on the first strategy and the second strategy. The feasibility assessment includes countermeasure resource limitation analysis and countermeasure mode matching analysis. The countermeasure mode solutions of the first strategy and the second strategy are integrated to generate a countermeasure optimization solution.

[0033] It should be noted that in the process of countering drones, different counter modes and strategies can be used for drones in different flight states to achieve efficient counter effects. Counter modes include signal interference, laser strikes, sound wave interference, navigation deception, etc. Here, dynamic selection and matching are performed based on flight status, drone type, etc., and a joint analysis is performed based on the first and second strategies to generate an optimization solution.

[0034] Furthermore, the present invention serializes the flight characteristics, uses the LSTM model to perform flight prediction, learns and predicts the feature data, and finally generates a first strategy based on the real-time characteristics, generates a second strategy based on the predicted characteristics, analyzes the difference between the first and second strategies, and performs feasibility fusion of the counter-strategies to obtain the corresponding optimization scheme, so that the counter-strategy has a wide range of applicability, improves the counter-control management and control capabilities, and realizes efficient and precise control of the entire drone swarm.

[0035] The characteristic sequence data includes sequences under multiple periods.

[0036] According to an embodiment of the present invention, the prediction model further includes: Based on a preset number of analysis cycles, a feature set corresponding to each drone group is obtained; Based on the time dimension, the feature set is serialized and imported into the prediction model for sequence prediction to obtain a feature prediction sequence; Each feature set corresponds to a feature prediction sequence; Perform data analysis on the feature prediction sequence to form multi-dimensional real-time prediction features; Based on the autoencoder network, the real-time prediction features are used as input data to map to low-dimensional hidden representation data. The mapping process is based on a multi-layer perceptron. Through the multi-layer perceptron, the low-dimensional hidden representation data is reconstructed and the output features are obtained; The difference between the output features and the input data is evaluated through the cross entropy loss and the autoencoder network is optimized and trained until the cross entropy loss converges to the preset range, and the corresponding output features are obtained and marked as reconstructed prediction features; Based on the reconstructed prediction features, flight anomaly assessment and counter-warning analysis are performed on multiple drone groups, and counter-warning information is generated by combining the flight prediction status of multiple drone groups.

[0037] It should be noted that each drone group corresponds to an independent reconstruction prediction feature. In the present invention, flight prediction is performed on multiple drone groups based on the prediction model, and the autoencoder network is used to perform dimensionality reduction analysis on high-dimensional real-time flight features, which helps to reduce useless prediction information, extract core prediction information, and realize accurate, fast and efficient flight warning and counter-warning for multiple drone groups, thereby improving the system's counter-control capability.

[0038] Figure 2 A block diagram of a multi-target UAV countermeasure system based on a multi-beam array antenna of the present invention is shown.

[0039] The second aspect of the present invention further provides a multi-target UAV countermeasure system based on a multi-beam array antenna, the system comprising: a memory 21, a processor 22, the memory 21 comprising a multi-target UAV countermeasure program based on a multi-beam array antenna, the multi-target UAV countermeasure program based on a multi-beam array antenna being executed by the processor 22 to implement the following steps: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight characteristic data is generated; In one analysis cycle, the flight characteristic data of multiple target UAVs are used as sample data for K-means-based cluster analysis, and multiple UAV groups are divided according to the clustering results; Taking drone groups as analysis units, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency; Mark all target drones in the drone group to be tested and obtain real-time feature data of the drone group to be tested through real-time communication, judge drone anomalies based on the real-time feature data and mark abnormal drones; According to the real-time characteristic data of abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to transmit high-quality data to the abnormal UAVs. At the same time, countermeasure mode analysis and strategy evaluation are carried out based on abnormal UAVs to formulate a UAV countermeasure strategy.

[0040] According to an embodiment of the present invention, in the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna, specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAV, the communication frequency band, antenna polarization mode, gain, and directivity parameters are determined, and the multi-beam array antenna layout is set; Real-time communication with the target UAV is achieved through a multi-beam array antenna, and communication data of the target UAV is collected through the central platform.

[0041] It should be noted that in the process of multi-UAV data collection and analysis, multi-beam array antennas are required for communication enhancement to obtain high-quality communication data.

[0042] According to an embodiment of the present invention, in one analysis cycle, communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data is generated, specifically: In one analysis cycle, the communication data of multiple target UAVs are obtained through real-time communication, and the communication data shown includes GPS positioning information, flight status information, and flight trajectory information of the UAVs; Based on the communication data, the drone is positioned, analyzed, and its speed is evaluated and its trajectory is tracked, and flight characteristic data based on three dimensions, namely position, speed, and path, is generated.

[0043] It should be noted that the position dimension analysis is generally performed based on the three-dimensional coordinates of a preset airspace.

[0044] According to an embodiment of the present invention, in one analysis cycle, the flight characteristic data of multiple target drones are used as sample data for cluster analysis based on K-means, and multiple drone groups are divided according to the clustering results, specifically: Construct a clustering model based on K-means; In one analysis cycle, the flight characteristic data of multiple target UAVs are imported into the clustering model as sample data; In the clustering model, K cluster centers are randomly set, and the distance from the sample data point to the cluster center is calculated based on the Euclidean distance, and the sample data is clustered based on the closest distance; Recalculate whether the center points in multiple cluster groups coincide with the original cluster center. If not, reset the center point and perform clustering in a loop until the new center point in the cluster group coincides with the center point in the previous clustering process. Record the clustering data grouping results at this time to obtain the clustering results. Based on the clustering results, multiple target drones are mapped into corresponding groups and divided into multiple drone groups.

[0045] It should be noted that the analysis period is a time period set by the user. Each drone group includes one or more target drones.

[0046] According to an embodiment of the present invention, the drone group is used as an analysis unit, the flight feature data of each drone 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 frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency, specifically: Taking drone groups as analysis units, the flight characteristic data of each drone group is integrated to form multiple feature sets; Construct an isolation forest model and initialize model parameters, including the number of trees, the estimated value of the proportion of abnormal data, and the random number seed; Perform data standardization preprocessing on multiple feature sets and import them as whole samples into the isolation forest model to predict abnormal data points, and return a list of abnormal data points; According to the list of abnormal data points, the frequency of occurrence of abnormal data points in each feature set is counted, and the corresponding drone group is marked based on the highest frequency and marked as the drone group to be tested.

[0047] It should be noted that the list of abnormal data points includes the location of the abnormal data, the data set to which it belongs, the abnormal value, and other information. The isolation forest model can be trained for abnormal prediction based on the historical feature set. Each feature set corresponds to each drone group.

[0048] According to an embodiment of the present invention, marking all target drones in the drone group to be tested and obtaining real-time feature data of the drone group to be tested through real-time communication, judging drone anomalies through real-time feature data and marking abnormal drones are specifically as follows: Through real-time communication, obtain the real-time characteristic data of all target drones in the drone group to be tested; The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information; The real-time feature data is used to determine the abnormal status of the drone and mark the abnormal drone.

[0049] It should be noted that the abnormal state judgment can be made based on preset flight standard state data.

[0050] It is worth mentioning here that for multi-target drones, especially large-scale drone data analysis, accurate identification and countermeasures of some or a small number of abnormal drones are a complex control task. Traditional drone analysis systems are often based on the analysis and identification of single drones one by one, which is inefficient and difficult to quickly screen out abnormal conditions. Based on this, the present invention obtains multi-dimensional flight feature data through the (multi-beam array antenna) communication of multiple drones, imports the feature data into a clustering model for feature analysis and clustering, and divides the cluster groups to perform the first screening and grouping of drone groups with abnormalities. The clustering results can analyze the characteristics of drones on a large scale and quickly aggregate the abnormal data. Further, each cluster group (i.e., each feature set) is analyzed for the frequency of abnormal data points, which is completed here by the isolation forest algorithm, and further predicts and screens the drone groups with abnormalities and marks them as the test group. Further, the drone groups with abnormalities are accurately screened and abnormal drones are marked, thereby realizing accurate and rapid abnormal evaluation and screening of large-scale drones, and the process can effectively perform rapid data mining and effective data screening on flight feature data. In addition, the isolation forest algorithm has the characteristics of fast anomaly detection and less required computing resources, and is suitable for the process of the present invention.

[0051] According to an embodiment of the present invention, the communication resource allocation of the multi-beam array antenna is adjusted according to the real-time characteristic data of the abnormal drone, and high-quality data transmission is performed on the abnormal drone. At the same time, the counter-measure mode analysis and strategy evaluation are performed based on the abnormal drone, and a drone counter-measure strategy is formulated, which is specifically: According to the real-time characteristic data of abnormal UAVs, coordinate positioning analysis and flight status evaluation of abnormal UAVs are performed to form abnormal UAV status information; According to abnormal drone status information, priority communication needs are set, and within a preset short period, the multi-beam array antenna configuration is dynamically adjusted to regulate communication resource allocation to meet priority communication needs; Dynamically adjust multi-beam array antenna configuration including frequency, bandwidth, power, and band parameters; Through abnormal drone status information, countermeasure mode analysis and strategy evaluation are carried out to formulate drone countermeasure strategies.

[0052] It should be noted that the preset short cycle is a shorter time period set by a user. The multi-beam array antenna is dynamically adjusted within the short cycle to adapt to the communication of abnormal drones in a short period of time, improve the communication quality and communication effect of abnormal drones, appropriately terminate the communication of other non-abnormal drones, and improve the utilization rate of communication resources.

[0053] The third aspect of the present invention also 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 a multi-beam array antenna is executed by a processor, the steps of the multi-target UAV countermeasure method based on a multi-beam array antenna as described in any one of the above items are implemented.

[0054] The present invention discloses a multi-target UAV countermeasure system based on a multi-beam array antenna. Real-time communication is carried out through a multi-beam array antenna to obtain UAV communication data, perform positioning, speed evaluation and trajectory tracking, and generate multi-dimensional flight feature data. Within an analysis cycle, the UAV group is divided by K-means clustering analysis, and an isolated forest model is constructed to classify the feature set, identify abnormal data points, and screen out the UAV group 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 are obtained, and abnormal UAVs are judged and marked. Finally, the multi-beam antenna communication resources are adjusted according to the abnormal UAV data, and a UAV countermeasure strategy is formulated to achieve accurate and rapid abnormal evaluation and efficient countermeasure control of UAVs.

[0055] In the 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 schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: 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 can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0056] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0057] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0058] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0059] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0060] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A multi-target UAV countermeasure method based on multi-beam array antenna, characterized in that: include: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight characteristic data is generated; In one analysis cycle, the flight characteristic data of multiple target UAVs are used as sample data for K-means-based cluster analysis, and multiple UAV groups are divided according to the clustering results; Taking drone groups as analysis units, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency; Mark all target drones in the drone group to be tested and obtain real-time feature data of the drone group to be tested through real-time communication, judge drone anomalies based on the real-time feature data and mark abnormal drones; According to the real-time characteristic data of abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to transmit high-quality data to the abnormal UAVs. At the same time, countermeasure mode analysis and strategy evaluation are carried out based on abnormal UAVs to formulate a UAV countermeasure strategy.

2. According to claim 1, a multi-target UAV countermeasure method based on a multi-beam array antenna is characterized in that: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna, specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAV, the communication frequency band, antenna polarization mode, gain, and directivity parameters are determined, and the multi-beam array antenna layout is set; Real-time communication with the target UAV is achieved through a multi-beam array antenna, and communication data of the target UAV is collected through the central platform.

3. According to claim 1, a multi-target UAV countermeasure method based on a multi-beam array antenna is characterized in that: In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight feature data are generated, specifically: In one analysis cycle, the communication data of multiple target UAVs are obtained through real-time communication, and the communication data shown includes GPS positioning information, flight status information, and flight trajectory information of the UAVs; Based on the communication data, the drone is positioned, analyzed, and its speed is evaluated and its trajectory is tracked, and flight characteristic data based on three dimensions, namely position, speed, and path, is generated.

4. The multi-target UAV countermeasure method based on multi-beam array antenna according to claim 3 is characterized in that: In one analysis cycle, the flight characteristic data of multiple target drones are used as sample data for cluster analysis based on K-means, and multiple drone groups are divided according to the clustering results, specifically: Construct a clustering model based on K-means; In one analysis cycle, the flight characteristic data of multiple target UAVs are imported into the clustering model as sample data; In the clustering model, K cluster centers are randomly set, and the distance from the sample data point to the cluster center is calculated based on the Euclidean distance, and the sample data is clustered based on the closest distance; Recalculate whether the center points in multiple cluster groups coincide with the original cluster center. If not, reset the center point and perform clustering in a loop until the new center point in the cluster group coincides with the center point in the previous clustering process. Record the clustering data grouping results at this time to obtain the clustering results. Based on the clustering results, multiple target drones are mapped into corresponding groups and divided into multiple drone groups.

5. The multi-target UAV countermeasure method based on multi-beam array antenna according to claim 4 is characterized in that: The method takes the drone group as the analysis unit, integrates the flight feature data of each drone group, forms multiple feature sets, constructs and initializes the isolation forest model, pre-processes the multiple feature sets and imports the isolation forest model to perform data classification, analyzes abnormal data points, analyzes the frequency of occurrence of abnormal data points in multiple drone groups, and selects the drone group to be tested based on the highest frequency, specifically: Taking drone groups as analysis units, the flight characteristic data of each drone group is integrated to form multiple feature sets; Construct an isolation forest model and initialize model parameters, including the number of trees, the estimated value of the proportion of abnormal data, and the random number seed; Perform data standardization preprocessing on multiple feature sets and import them as whole samples into the isolation forest model to predict abnormal data points, and return a list of abnormal data points; According to the list of abnormal data points, the frequency of occurrence of abnormal data points in each feature set is counted, and the corresponding drone group is marked based on the highest frequency and marked as the drone group to be tested.

6. The multi-target UAV countermeasure method based on multi-beam array antenna according to claim 5 is characterized in that: The method of marking all target drones in the drone group to be tested and obtaining real-time feature data of the drone group to be tested through real-time communication, judging drone anomalies through the real-time feature data and marking abnormal drones is specifically as follows: Through real-time communication, obtain the real-time characteristic data of all target drones in the drone group to be tested; The real-time feature data includes GPS positioning information, flight status information, and flight trajectory information; The real-time feature data is used to determine the abnormal status of the drone and mark the abnormal drone.

7. The multi-target UAV countermeasure method based on multi-beam array antenna according to claim 6 is characterized in that: According to the real-time characteristic data of abnormal drones, the communication resource allocation of multi-beam array antennas is adjusted to transmit high-quality data to abnormal drones. At the same time, countermeasure mode analysis and strategy evaluation are performed based on abnormal drones to formulate drone countermeasure strategies, which are specifically: According to the real-time characteristic data of abnormal UAVs, coordinate positioning analysis and flight status evaluation of abnormal UAVs are performed to form abnormal UAV status information; According to abnormal drone status information, priority communication needs are set, and within a preset short period, the multi-beam array antenna configuration is dynamically adjusted to regulate communication resource allocation to meet priority communication needs; Dynamically adjust multi-beam array antenna configuration including frequency, bandwidth, power, and band parameters; Through abnormal drone status information, countermeasure mode analysis and strategy evaluation are carried out to formulate drone countermeasure strategies.

8. A multi-target UAV countermeasure system based on a multi-beam array antenna, characterized in that: The system includes: a memory and a processor, wherein the memory includes a multi-target UAV countermeasure program based on a multi-beam array antenna, and the multi-target UAV countermeasure program based on a multi-beam array antenna is executed by the processor to implement the following steps: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna; In one analysis cycle, the communication data of multiple target drones are obtained through real-time communication, positioning analysis, speed evaluation and trajectory tracking are performed based on the communication data, and multi-dimensional flight characteristic data is generated; In one analysis cycle, the flight characteristic data of multiple target UAVs are used as sample data for K-means-based cluster analysis, and multiple UAV groups are divided according to the clustering results; Taking drone groups as analysis units, the flight feature data of each drone group is integrated to form multiple feature sets, an isolation forest model is constructed and initialized, multiple feature sets are preprocessed and imported into the isolation forest model for data classification, abnormal data points are analyzed, the frequency of occurrence of abnormal data points in multiple drone groups is analyzed, and the drone group to be tested is screened out based on the highest frequency; Mark all target drones in the drone group to be tested and obtain real-time feature data of the drone group to be tested through real-time communication, judge drone anomalies based on the real-time feature data and mark abnormal drones; According to the real-time characteristic data of abnormal UAVs, the communication resource allocation of the multi-beam array antenna is adjusted to transmit high-quality data to the abnormal UAVs. At the same time, countermeasure mode analysis and strategy evaluation are carried out based on abnormal UAVs to formulate a UAV countermeasure strategy.

9. The multi-target UAV countermeasure system based on multi-beam array antenna according to claim 8, characterized in that: In the preset airspace, a multi-beam array antenna is set to communicate with the target UAV in real time through the multi-beam array antenna, specifically: According to the preset airspace range, altitude information and attribute parameters of the target UAV, the communication frequency band, antenna polarization mode, gain, and directivity parameters are determined, and the multi-beam array antenna layout is set; Real-time communication with the target UAV is achieved through a multi-beam array antenna, and communication data of the target UAV is collected through the central platform.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium 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 a processor, the steps of the multi-target UAV countermeasure method based on a multi-beam array antenna as described in any one of claims 1 to 7 are implemented.

Images