Multi-band unmanned aerial vehicle signal intelligent detection device

Abstract

The application discloses a multi-band unmanned aerial vehicle signal intelligent detection device, and relates to the technical field of signal detection.The device comprises a data acquisition module, a detection device setting module, a signal detection module, a signal output module and a database.When the unmanned aerial vehicle signal intelligent detection device is detecting, the power self-adaptive adjustment mechanism of the unmanned aerial vehicle is used to adjust the parameter values of the unmanned aerial vehicle signal intelligent detection device in real time, and based on the detection signal of the unmanned aerial vehicle and its behavior, it is determined whether there is a false signal in the detection signal of the unmanned aerial vehicle.If there is, the unmanned aerial vehicle signal is divided into unforgeable signals and forgeable signals, the detection information of the unforgeable signals is adjusted, the detection information of the forgeable signals is reconstructed according to the detection information of the unforgeable signals after adjustment, and the effectiveness of the unmanned aerial vehicle signal detection is ensured, and the authenticity and accuracy of the unmanned aerial vehicle signal output are ensured.

Description

Technical Field

[0001] This invention relates to the field of signal detection technology, and specifically to a multi-band unmanned aerial vehicle (UAV) signal intelligent detection device. Background Technology

[0002] In recent years, drone technology has become widespread across consumer, industrial, and sectoral levels due to its miniaturization, low cost, high mobility, and multifunctionality. It is widely used in civilian fields such as aerial surveying and mapping, logistics and distribution, agricultural plant protection, and power line inspection, becoming an important carrier for the integration of the digital economy and the real economy.

[0003] Traditional multi-band drone signal intelligent detection devices require setting parameters before detection, then detecting the drone, acquiring its signal, and finally performing noise reduction processing to obtain the actual drone signal. Clearly, this type of multi-band drone signal intelligent detection device has at least the following shortcomings: 1. Most drones now have a power adaptive adjustment mechanism that can adjust the power in real time. Different power levels of drones require different parameters from the drone signal detection device. However, traditional multi-band drone signal intelligent detection devices keep the parameters of the drone signal detection device unchanged during the detection process, so they cannot guarantee that the drone signal can be effectively detected.

[0004] 2. Some drones may be equipped with GAN modules to generate false signals to mask the drone's real signal. Traditional multi-band drone signal intelligent detection devices lack processing for false drone signals, and cannot guarantee the authenticity and accuracy of the drone signals output by the drone signal intelligent detection device. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to provide a multi-band unmanned aerial vehicle (UAV) signal intelligent detection device.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a multi-band UAV signal intelligent detection device, including: a data acquisition module, a detection device setting module, a signal detection module, a signal output module, and a database.

[0007] The data acquisition module is used to acquire the RFID tag of the drone and obtain information about the drone from it.

[0008] The detection device setting module is used to obtain the drone's power adaptive adjustment mechanism from the drone's information and adjust the parameter values ​​of the drone signal intelligent detection device in real time to detect the drone.

[0009] The signal detection module is used to acquire the drone signals detected by the drone signal intelligent detection device and refer to them as drone detection signals. It distinguishes the drone detection signals and extracts the drone's real signals from them.

[0010] The signal output module is used to output the actual signals of the UAV.

[0011] The database is used to store information from each historical detection and the hardware physical fingerprint of the drone.

[0012] The beneficial effects of this invention are as follows: 1. This invention provides a multi-band intelligent detection device for drone signals. When the intelligent detection device is performing detection, it adjusts the parameter values ​​of the device in real time according to the drone's power adaptive adjustment mechanism. Based on the drone's detected signals and behavior, it determines whether there are false signals in the detected signals. If so, the drone signals are divided into unforgeable signals and forgeable signals. The detection information of the unforgeable signals is adjusted, and the detection information of the forgeable signals is reconstructed based on the adjusted detection information of the unforgeable signals. This ensures the effectiveness of drone signal detection and the authenticity and accuracy of the drone signal output.

[0013] 2. This invention obtains the environment in which the UAV signal intelligent detection device is located, which is called the marked environment. The marked environment is matched with the power adaptive adjustment mechanism of the UAV to obtain the power adaptive adjustment mechanism of the UAV in the marked environment, which is called the marked power adaptive adjustment mechanism. The correlation between the marked power adaptive adjustment mechanism and the parameters of the UAV signal intelligent detection device is analyzed, and a marked power adaptive adjustment mechanism-parameter matching table is constructed. The required values ​​of the parameters of the UAV signal intelligent detection device are obtained from the matching table and set, thus ensuring the effectiveness of UAV signal detection.

[0014] 3. This invention analyzes the correlation between the UAV's detection signal and its behavior during the current detection based on information from previous detections. Based on this correlation, it determines whether false signals exist in the UAV's detection signal. When no false signals are present, the detected signal is considered the UAV's true signal. When false signals are present, the UAV's detection signal is divided into forgerable and non-forgerable signals. The detection information of the non-forgerable signal is adjusted to obtain its actual information. Based on this actual information, the forgerable signal is reconstructed to obtain its actual information. Therefore, the actual information of both the non-forgerable and forgerable signals constitutes the UAV's true signal, ensuring the authenticity and accuracy of the UAV signal output. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0017] Figure 2 This is a schematic diagram showing the connections between units in the signal detection module of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1 As shown, the present invention provides a multi-band UAV signal intelligent detection device, including: a data acquisition module, a detection device setting module, a signal detection module, a signal output module, and a database.

[0020] The data acquisition module is connected to the detection device setting module, the detection device setting module is connected to the signal detection module, the signal detection module is connected to the signal output module, and the database is connected to the detection device setting module and the signal detection module.

[0021] The data acquisition module is used to acquire the RFID tag of the drone and obtain information about the drone from it.

[0022] It should be noted that the drone signal intelligent detection device is equipped with an RFID reader / writer, which acquires the drone's RFID tag.

[0023] It should also be noted that the RFID tag of the drone stores information about the drone, including its power adaptive adjustment mechanism, model, and manufacturer.

[0024] The detection device setting module is used to obtain the drone's power adaptive adjustment mechanism from the drone's information and adjust the parameter values ​​of the drone signal intelligent detection device in real time to detect the drone.

[0025] It should be noted that the power adaptive adjustment mechanism of a drone is set by the drone manufacturer. The power adaptive adjustment mechanism of a drone will vary depending on the environment, and different environments correspond to different power adaptive adjustment mechanisms.

[0026] Among them, the power adaptive adjustment mechanism of the UAV refers to the UAV automatically and accurately adjusting the transmission power of the radio frequency signal through hardware modules according to the real-time changes of flight status, communication link quality, external electromagnetic environment and physical flight scenario.

[0027] It should also be noted that the parameters of the drone signal intelligent detection device include the detection coverage frequency band, radio frequency receiving bandwidth, and number of effective channels.

[0028] In a specific embodiment, the detection device setting module performs the following process: acquiring the environment where the UAV signal intelligent detection device is located and calling it the marked environment; matching the marked environment with the UAV's power adaptive adjustment mechanism; acquiring the UAV's power adaptive adjustment mechanism in the marked environment and calling it the marked power adaptive adjustment mechanism.

[0029] It should be noted that the environment in which the drone signal intelligent detection device is located refers to the external electromagnetic environment and the scene of the area where the drone signal intelligent detection device is located.

[0030] The external electromagnetic environment is obtained through an industrial-grade real-time spectrum analyzer, field strength meter, and vector signal analyzer, while the scene of the area is captured by a camera.

[0031] It should also be noted that the environment in which the drone signal intelligent detection device is located is matched with the environment corresponding to the different power adaptive adjustment mechanisms of the drone, and the power adaptive adjustment mechanism of the drone in the marked environment is selected.

[0032] The correlation between the adaptive adjustment mechanism of the marker power and the parameters of the intelligent detection device for UAV signals is analyzed, and a parameter matching table of the adaptive adjustment mechanism of the marker power is constructed. The required values ​​of the parameters of the intelligent detection device for UAV signals are obtained from the matching table and then set.

[0033] It should be noted that the marker power adaptive adjustment mechanism - parameter matching table is used to store the effective parameter values ​​of the UAV signal intelligent detection device under different radio frequency signal transmission powers.

[0034] It should be noted that the detection device's setting module operates in real time, monitoring the drone's radio frequency signal transmission power and matching it with the marker power adaptive adjustment mechanism - parameter matching table to adjust the parameter values ​​of the drone signal intelligent detection device.

[0035] It should also be noted that a database is created in which the effective values ​​of the parameters of the UAV signal intelligent detection device under different radio frequency signal transmission powers and the transmission power of each radio frequency signal are stored one-to-one, forming a power adaptive adjustment mechanism - parameter matching table.

[0036] The above-mentioned analysis of the correlation between the adaptive adjustment mechanism of the marker power and the parameters of the UAV signal intelligent detection device is carried out in the following specific process: a simulation platform is built, and the marking environment is simulated on the simulation platform. At the same time, the power of the UAV is obtained from the UAV's adaptive adjustment mechanism of the marker power.

[0037] It should be noted that the simulation platform was built using FEKO, Wireless Insite, MATLAB, and Simulink software.

[0038] Several experimental groups were set up for each power level, and the parameter values ​​of the UAV signal intelligent detection device in each experimental group were different. At a certain power level, the real-time signal-to-noise ratio of the simulated UAV signal intelligent detection device in each experimental group during the detection process was obtained. The detection effectiveness coefficient of the UAV signal intelligent detection device in each simulation group was determined and compared. The parameter value of the UAV signal intelligent detection device in the simulation group with the largest detection effectiveness coefficient was taken as the effective parameter value of the UAV signal intelligent detection device under that power level.

[0039] It should be noted that the signal-to-noise ratio of the simulated drone signal intelligent detection device is monitored during the detection process using a dedicated integrated instrument for drone signal detection.

[0040] It should also be noted that, in a certain simulation group, the real-time signal-to-noise ratio of the UAV signal intelligent detection device in the simulation group is obtained during the detection process, and the minimum signal-to-noise ratio is obtained by comparison. The minimum signal-to-noise ratio is then normalized, and the normalized result is used as the detection effectiveness coefficient of the UAV signal intelligent detection device in the simulation group. The detection effectiveness coefficient of the UAV signal intelligent detection device in each simulation group is obtained by this method.

[0041] If the detection effectiveness coefficient of the UAV signal intelligent detection device is the maximum in multiple simulation groups, then one simulation group is randomly selected from the simulation groups with the maximum detection effectiveness coefficient of the UAV signal intelligent detection device, and the value used by the UAV signal intelligent detection device parameter in the simulation group is taken as the effective value of the UAV signal intelligent detection device parameter under that power.

[0042] This method is used to obtain the effective parameter values ​​of the UAV signal intelligent detection device under various power levels, and uses them as a marker to establish the correlation between the power adaptive adjustment mechanism and the parameters of the UAV signal intelligent detection device.

[0043] The signal detection module is used to acquire the drone signals detected by the drone signal intelligent detection device and refer to them as drone detection signals. It distinguishes the drone detection signals and extracts the drone's real signals from them.

[0044] It should be noted that drone signals include surface radio frequency parameter signals, radio frequency communication signals, physical fingerprint characteristics of the drone's radio frequency hardware, and flight signals, among which flight signals include speed, altitude, and attitude. These drone signals are monitored and acquired through intelligent drone signal detection devices.

[0045] Please see Figure 2 As shown, in a specific embodiment, the signal detection module includes a signal analysis unit and a signal reconstruction and completion unit.

[0046] The signal analysis unit is used to acquire the detection signals of the UAV and retrieve information from the database of each historical detection to determine whether there are false signals in the UAV's detection signals.

[0047] It should be noted that the information from each historical detection includes the drone's detection signal, the drone's actual signal, the drone's behavior, the type of impact of false signals on unforgeable signals, and the drone model, etc.

[0048] It should also be noted that the presence of false signals in the drone's detection signals refers to the fact that the false signals generated by the GAN module overlap the real signals of the drone.

[0049] In a specific embodiment, the signal analysis unit performs the following process: acquiring the detection signal and behavior of the UAV during the current detection, acquiring the detection signal, the actual signal, and the behavior of the UAV during each historical detection, and analyzing the correlation characteristics between the detection signal and the behavior of the UAV during the current detection.

[0050] It should be noted that the behavior of a drone refers to the quantifiable, regular, and dynamic response operations and execution strategies that a drone performs in response to external electromagnetic environment, communication link quality, physical flight status, and mission requirements, all driven uniformly by the flight control system. These strategies are set by the drone manufacturer. Drone behavior possesses four core characteristics: quantifiability, regularity, hardware-driven, and scene-linked. GANs can simulate its surface numerical patterns, but cannot replicate its true hardware-driven physical response logic.

[0051] When the detection signal and behavior of the drone during this detection match the correlation characteristics between the detection information of the drone signal and its behavior, it means that there are no false signals in the drone's detection signal; otherwise, it means that there are false signals in the drone's detection signal.

[0052] The above-mentioned analysis of the correlation between the drone's detection signal and drone behavior during this detection is specifically carried out as follows: based on the detection signals of drones during each historical detection, the drone's actual signals and drone behavior, and the drone's behavior during this detection, historical detection data for each marker is obtained.

[0053] It should be noted that the drone behavior during each historical detection is compared with the drone behavior during the current detection. The historical detections in which the drone behavior is the same as the drone behavior during the current detection are called the marked historical detections.

[0054] Based on the detection signals and drone behavior of the drones during the historical detection of each marker, the correlation features between the drone detection signals and drone behavior during the historical detection of each marker are obtained, and the return value of the correlation features is determined.

[0055] It should be noted that the correlation features between the UAV's detection signals and UAV behavior during the historical detection of each marker are obtained through the basic quantitative correlation analysis method of single behavior-single signal and the global correlation feature mining method of multi-behavior-multi-signal. Both the basic quantitative correlation analysis method of single behavior-single signal and the global correlation feature mining method of multi-behavior-multi-signal are existing technologies.

[0056] It should also be noted that the correlation features between the drone's detection signals and drone behavior during the historical detection of each marker are compared. If the correlation features between the drone's detection signals and drone behavior during the historical detection of each marker are the same, the return value of the correlation feature is 1; otherwise, the return value of the correlation feature is 0.

[0057] When the return value of the association feature is 1, the association feature between the drone's detection signal and drone behavior during the historical detection of each marker is used as the association feature between the drone's detection signal and drone behavior during the current detection. When the return value of the association feature is 0, the association features between the drone's detection signal and drone behavior during the historical detection of each marker are fused to obtain the association feature between the drone's detection signal and drone behavior during the current detection.

[0058] It should be noted that when the return value of the association feature is 0, the association feature between the drone's detection signal and drone behavior during the historical detection of each marker is called each marker feature. These features are compared, and the same marker features are grouped together. Each group is obtained in this way, and the proportion of marker features in each group is calculated. This proportion is used as the weight of the corresponding marker features in each group. Based on the weight of the corresponding marker features in each group and the corresponding marker features in each group, the corresponding marker features in each group are weighted and fused to obtain the association feature between the drone's detection signal and drone behavior during the current detection.

[0059] The signal reconstruction and completion unit is used to reconstruct the drone's detection signal to obtain the drone's true signal when there are no false signals in the drone's detection signal, and when there are false signals in the drone's detection signal.

[0060] In one specific embodiment, the signal reconstruction and completion unit performs the following process: dividing the detection signal of the UAV into spoofable signals and non-spoofable signals, obtaining the UAV model and manufacturer, obtaining the hardware physical fingerprint of the UAV from the database based on the UAV model and manufacturer, extracting the detection information of non-spoofable signals from the UAV's detection signal based on the UAV's hardware physical fingerprint, and simultaneously extracting the detection information of spoofable signals.

[0061] It should be noted that signals that cannot be forged in drone signals are classified as unforgeable signals, and signals that can be forged are classified as forgeable signals. Forgeable signals include surface radio frequency parameter signals and radio frequency communication signals, while unforgeable signals include the physical fingerprint characteristics of the drone's radio frequency hardware and flight signals. Unforgeable signals are determined by the physical fingerprint of the drone's hardware.

[0062] It should also be noted that the hardware physical fingerprint of a drone refers to the inherent, unique, and unforgeable set of physical characteristics attached to the radio frequency communication signal by the core hardware of the drone's radio frequency front-end during operation, due to factors such as its own physical characteristics, individual differences in manufacturing processes, and hardware aging. The hardware physical fingerprint of a drone is inherent, individually unique, physically unforgeable, and strongly bound to the radio frequency signal.

[0063] The detection information of the unforgeable signal is adjusted to obtain the actual information of the unforgeable signal. Based on the actual information of the unforgeable signal, the forgeable signal is reconstructed to obtain the actual information of the forgeable signal. Then, the actual information of the unforgeable signal and the forgeable signal are the real signals of the UAV.

[0064] The process of adjusting the detection information of the unforgeable signal to obtain the actual information of the unforgeable signal described above is as follows: obtaining the type of influence of the false signal on the unforgeable signal and the drone model during the current detection, obtaining the type of influence of the false signal on the unforgeable signal and the drone model during each historical detection, and obtaining each similar historical detection.

[0065] It should be noted that when acquiring the time-domain spectrum of the detected signal, if the waveform amplitude decreases in the time-domain spectrum, the type of influence of the false signal on the unforgeable signal is heterogeneous and same-frequency superposition; if irregular spikes and waveform distortion appear in the time-domain spectrum, the type of influence of the false signal on the unforgeable signal is same-source superposition; if local defects appear in the time-domain spectrum, the type of influence of the false signal on the unforgeable signal is partial masking.

[0066] It should also be noted that previous detections using the same drone model as the one used in this detection are referred to as similar historical detections.

[0067] Obtain the detection information and actual information of the unforgeable signal during each similar historical detection, determine the functional relationship between the detection information and actual information of the unforgeable signal, and obtain the actual information of the unforgeable signal during this detection based on the functional relationship between the detection information and actual information of the unforgeable signal and the frame measurement information of the unforgeable signal during this detection.

[0068] It should be noted that an unforgeable signal curve is constructed, in which the x-axis represents the detection information of the unforgeable signal and the y-axis represents the actual information of the unforgeable signal. The curve function in this curve is obtained and used as the functional relationship between the detection information and the actual information of the unforgeable signal.

[0069] It should also be noted that the specific process of obtaining the curve function in the graph is as follows: First, the 32-bit floating-point model is quantized into INT8 using TensorRT, redundant CNN convolutional kernels and LSTM neurons are removed, and a lightweight CNN-GRU is trained using a trained large model distillation, and then converted into an edge-deployable format. Then, a lightweight inference engine is built, and finally, the spoofable signal graph is input, and the curve function in the graph is output.

[0070] The process of reconstructing the forgerable signal and obtaining its actual information is as follows: The correlation features between the UAV's detection signal and its behavior during the current detection, and the actual information of the unforgeable signal are obtained. The functional relationship between the unforgeable signal and the forgerable signal is obtained from the correlation features between the UAV's detection information and its behavior during the current detection. Based on the actual information of the unforgeable signal and the functional relationship between the unforgeable signal and the forgerable signal, the marking information of the forgerable signal is determined.

[0071] Determine whether the actual information of the unforgeable signal and the marking information of the forgeable signal conform to the hard constraints of the communication protocol. If they do, the marking information of the forgeable signal is used as the actual information of the forgeable signal. If they do not conform, the marking information of the forgeable signal and the actual information of the unforgeable signal that do not conform to the hard constraints of the communication protocol are adjusted to obtain the actual information of the forgeable signal, and the actual information of the unforgeable signal is updated.

[0072] It should be noted that hard constraints on communication protocols refer to the underlying rules in the dedicated communication protocols for drone flight control, image transmission, and data transmission, which are fixed by the manufacturer's dedicated hardware chips, have no software modification access, and are enforced to be followed.

[0073] The process of adjusting the marking information of forgerable signals that do not conform to the hard constraints of the communication protocol and the actual information of non-forgerable signals is as follows: Forgerable signals and non-forgerable signals that do not conform to the hard constraints of the communication protocol are called marked forgerable signals and marked non-forgerable signals, and non-forgerable signals that conform to the hard constraints of the communication protocol are called unmarked non-forgerable signals.

[0074] Obtain the correlation between unlabeled and unforgeable signals and labeled and unforgeable signals. Based on the correlation between the unlabeled and unforgeable signals and the actual information of the unlabeled and unforgeable signals, update the actual information of the labeled and unforgeable signals.

[0075] It should be noted that the correlation between unlabeled and labeled non-forgeable signals is determined using nonlinear regression, a technique that is currently in use. The correlation between the unlabeled and labeled non-forgeable signals refers to their functional relationship.

[0076] Based on the updated actual information of the unforgeable signal and the functional relationship between the unforgeable and forgeable signals, the marking information of the forgeable signal is adjusted to obtain the actual information of the forgeable signal.

[0077] The signal output module is used to output the actual signals of the UAV.

[0078] The database is used to store information from each historical detection and the hardware physical fingerprint of the drone.

[0079] In this embodiment of the invention, when the UAV signal intelligent detection device is performing detection, the parameter values ​​of the UAV signal intelligent detection device are adjusted in real time according to the power adaptive adjustment mechanism of the UAV. Based on the UAV's detection signal and its behavior, it is determined whether there are false signals in the UAV's detection signal. If so, the UAV signal is divided into unforgeable signals and forgeable signals. The detection information of the unforgeable signals is adjusted, and the detection information of the forgeable signals is reconstructed based on the adjusted detection information of the unforgeable signals. This ensures the effectiveness of UAV signal detection and also ensures the authenticity and accuracy of the UAV signal output.

[0080] The examples described in this invention are not limited to the specific embodiments listed above. The examples are merely illustrative to facilitate understanding of the invention and do not constitute a limitation on the scope of protection of this invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of this invention should be included within the scope of protection.

[0081] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A multi-band unmanned aerial vehicle (UAV) signal intelligent detection device, characterized in that, include: The data acquisition module is used to acquire the RFID tags of the drone and obtain information about the drone from them; The detection device setting module is used to obtain the drone's power adaptive adjustment mechanism from the drone's information and adjust the parameter values ​​of the drone signal intelligent detection device in real time to detect the drone. The signal detection module is used to acquire the drone signals detected by the drone signal intelligent detection device and refer to them as the drone's detection signals. It distinguishes the drone's detection signals and extracts the drone's real signals from them. The signal output module is used to output the actual signals from the drone; The database is used to store information from each historical detection and the hardware physical fingerprint of the drone.

2. The intelligent detection device for multi-band UAV signals according to claim 1, characterized in that, The detection device setting module is configured as follows: The environment in which the UAV signal intelligent detection device is located is obtained and referred to as the marked environment. The marked environment is matched with the power adaptive adjustment mechanism of the UAV to obtain the power adaptive adjustment mechanism of the UAV in the marked environment and referred to as the marked power adaptive adjustment mechanism. The correlation between the adaptive adjustment mechanism of the marker power and the parameters of the intelligent detection device for UAV signals is analyzed, and a parameter matching table of the adaptive adjustment mechanism of the marker power is constructed. The required values ​​of the parameters of the intelligent detection device for UAV signals are obtained from the matching table and then set.

3. The intelligent detection device for multi-band UAV signals according to claim 2, characterized in that, The specific process of the correlation between the analysis marker power adaptive adjustment mechanism and the parameters of the UAV signal intelligent detection device is as follows: A simulation platform was built, and the marking environment was simulated on the platform. At the same time, the power of the UAV was obtained from the UAV's marking power adaptive adjustment mechanism. Several experimental groups were set up for each power level, and the parameter values ​​of the UAV signal intelligent detection device in each experimental group were different. At a certain power level, the real-time signal-to-noise ratio of the simulated UAV signal intelligent detection device in each experimental group during the detection process was obtained. The detection effectiveness coefficient of the UAV signal intelligent detection device in each simulation group was determined and compared. The parameter value of the UAV signal intelligent detection device in the simulation group with the largest detection effectiveness coefficient was taken as the effective parameter value of the UAV signal intelligent detection device under that power level. This method is used to obtain the effective parameter values ​​of the UAV signal intelligent detection device under various power levels, and uses them as a marker to establish the correlation between the power adaptive adjustment mechanism and the parameters of the UAV signal intelligent detection device.

4. The intelligent detection device for multi-band UAV signals according to claim 1, characterized in that, The signal detection module includes a signal analysis unit and a signal reconstruction and completion unit; The signal analysis unit is used to acquire the detection signals of the UAV and retrieve information from the database of each historical detection to determine whether there are false signals in the UAV's detection signals. The signal reconstruction and completion unit is used to reconstruct the drone's detection signal to obtain the drone's true signal when there are no false signals in the drone's detection signal, and when there are false signals in the drone's detection signal.

5. The intelligent detection device for multi-band UAV signals according to claim 4, characterized in that, The signal analysis unit operates as follows: Acquire the detection signal and behavior of the drone during this detection, and acquire the detection signal, real signal and behavior of the drone during each historical detection, and analyze the correlation characteristics between the detection signal and behavior of the drone during this detection. When the detection signal and behavior of the drone during this detection match the correlation characteristics between the detection information of the drone signal and its behavior, it means that there are no false signals in the drone's detection signal; otherwise, it means that there are false signals in the drone's detection signal.

6. The intelligent detection device for multi-band UAV signals according to claim 5, characterized in that, The analysis of the correlation between the drone's detection signal and its behavior during this detection is as follows: Based on the detected signals, actual signals, and behavior of the drone during each historical detection, as well as the behavior of the drone during this current detection, historical detection data for each marker is obtained. Based on the detection signals and behaviors of drones during the historical detection of each marker, obtain the correlation features between the detection signals and behaviors of drones during the historical detection of each marker, and determine the return value of the correlation features; When the return value of the association feature is 1, the association feature between the drone's detection signal and drone behavior during the historical detection of each marker is used as the association feature between the drone's detection signal and drone behavior during the current detection. When the return value of the association feature is 0, the association features between the drone's detection signal and drone behavior during the historical detection of each marker are fused to obtain the association feature between the drone's detection signal and drone behavior during the current detection.

7. The intelligent detection device for multi-band UAV signals according to claim 4, characterized in that, The specific process of the signal reconstruction and completion unit is as follows: The detection signals of drones are divided into spoofable signals and non-spoofable signals. The model and manufacturer of the drone are obtained. Based on the model and manufacturer of the drone, the hardware physical fingerprint of the drone is obtained from the database. Based on the hardware physical fingerprint of the drone, the detection information of non-spoofable signals is extracted from the detection signals of the drone, and the detection information of spoofable signals is also extracted. The detection information of the unforgeable signal is adjusted to obtain the actual information of the unforgeable signal. Based on the actual information of the unforgeable signal, the forgeable signal is reconstructed to obtain the actual information of the forgeable signal. Then, the actual information of the unforgeable signal and the forgeable signal are the real signals of the UAV.

8. The intelligent detection device for multi-band UAV signals according to claim 7, characterized in that, The process of adjusting the detection information of the unforgeable signal to obtain the actual information of the unforgeable signal is as follows: Obtain the type of impact of false signals on unforgeable signals and the drone model during this detection, and obtain the type of impact of false signals on unforgeable signals and the drone model during each historical detection, and obtain each similar historical detection; Obtain the detection information and actual information of the unforgeable signal during each similar historical detection, determine the functional relationship between the detection information and actual information of the unforgeable signal, and obtain the actual information of the unforgeable signal during this detection based on the functional relationship between the detection information and actual information of the unforgeable signal and the frame measurement information of the unforgeable signal during this detection.

9. The intelligent detection device for multi-band UAV signals according to claim 7, characterized in that, The specific process of reconstructing the forgerable signal to obtain its actual information is as follows: Obtain the correlation characteristics between the UAV's detection signal and UAV behavior during this detection, as well as the actual information of the unforgeable signal. From the correlation characteristics between the UAV signal detection information and its behavior during this detection, obtain the functional relationship between the unforgeable signal and the forgeable signal. Based on the actual information of the unforgeable signal and the functional relationship between the unforgeable signal and the forgeable signal, determine the marking information of the forgeable signal. Determine whether the actual information of the unforgeable signal and the marking information of the forgeable signal conform to the hard constraints of the communication protocol. If they do, the marking information of the forgeable signal is used as the actual information of the forgeable signal. If they do not conform, the marking information of the forgeable signal and the actual information of the unforgeable signal that do not conform to the hard constraints of the communication protocol are adjusted to obtain the actual information of the forgeable signal, and the actual information of the unforgeable signal is updated.

10. The intelligent detection device for multi-band UAV signals according to claim 9, characterized in that, The process of adjusting the tagging information of spoofable signals that do not conform to the hard constraints of the communication protocol and the actual information of non-spoofable signals is as follows: Forgerable and non-forgerable signals that do not conform to the hard constraints of the communication protocol are called marked forgerable signals and marked non-forgerable signals, respectively, while non-forgerable signals that conform to the hard constraints of the communication protocol are called unmarked non-forgerable signals. Obtain the correlation between unlabeled and unforgeable signals and labeled and unforgeable signals, and update the actual information of labeled and unforgeable signals based on the correlation between the two signals and the actual information of the unlabeled and unforgeable signals; Based on the updated actual information of the unforgeable signal and the functional relationship between the unforgeable and forgeable signals, the marking information of the forgeable signal is adjusted to obtain the actual information of the forgeable signal.

Images