High-speed moving object deception detection method of Beidou satellite navigation system

Abstract

The invention relates to a high-speed moving object deception detection method for a Beidou satellite navigation system, which comprises the following steps of: acquiring a navigation signal sent by the Beidou satellite navigation system, and preprocessing the navigation signal; receiving signal data from various sensors, including an inertial measurement unit, a Doppler radar, a visual sensor and a magnetic field sensor, are collected, and data fusion is performed on the receiving signal data; extracting signal features in the preprocessed navigation signals and the sensor receiving signal data after data fusion based on a Gaussian mixture model algorithm of time sequence prediction; and presetting a signal feature dynamic threshold, and judging whether the navigation signal corresponding to the current signal feature is a deception signal or not according to the signal feature dynamic threshold.

Description

Technical Field

[0001] The invention relates to a high-speed moving object deception detection method for a Beidou satellite navigation system, belonging to the technical field of navigation and positioning. Background Art

[0002] With the advancement of science and technology, satellite navigation systems are increasingly used in military and civilian fields. However, due to the susceptibility of satellite signals to interference, forged satellite signals may mislead the receiver, resulting in navigation errors. Especially for high-speed moving objects, such as missiles and aircraft, any navigation error may lead to serious consequences due to their extremely fast movement speed; however, the security issues of navigation signals are gradually emerging, especially the risk of signal deception faced by high-speed moving objects during navigation, which urgently requires targeted solutions.

[0003] The first is that existing navigation signal deception detection technology mainly relies on traditional signal verification and anomaly detection methods, which are usually unable to effectively deal with deception signals under high-speed motion conditions. First, traditional signal verification mechanisms often make judgments based on the characteristics of a single signal source and lack the ability to comprehensively analyze multi-source data. When a high-speed moving object encounters signal deception, a single signal source is easily interfered by fake signals, resulting in misjudgment and failure to identify the true signal characteristics in a timely manner.

[0004] Second, existing technologies often face the problem of insufficient data fusion accuracy when processing multi-sensor data. Although multi-sensor fusion can improve navigation accuracy and reliability, in actual applications, due to differences in data characteristics between different sensors, the fused data may be biased, thus affecting the accuracy of the overall judgment. In the case of high-speed movement, the signal changes rapidly, and any small error may lead to major consequences.

[0005] Third, existing spoof signal detection systems usually lack adaptive learning capabilities. Traditional detection algorithms are mostly based on fixed models and rules and cannot be dynamically adjusted according to environmental changes. This means that under new environmental conditions, the effectiveness and accuracy of the system are greatly reduced, especially in complex electromagnetic environments, where the detection of counterfeit signals becomes more difficult. Systems that lack self-learning capabilities are prone to reduced detection accuracy when dealing with a constantly changing signal environment, increasing safety risks for navigation systems. Summary of the invention

[0006] In order to solve the above problems existing in the prior art, the present invention proposes a high-speed moving object deception detection method for the Beidou satellite navigation system.

[0007] The technical solution of the present invention is as follows:

[0008] On the one hand, the present invention provides a method for detecting high-speed moving object spoofing in a Beidou satellite navigation system, comprising the following steps:

[0009] Collect navigation signals sent by the Beidou satellite navigation system and pre-process the navigation signals;

[0010] Collect received signal data from multiple sensors, including inertial measurement units, Doppler radars, visual sensors, and magnetic field sensors, and perform data fusion on the received signal data;

[0011] The mixed Gaussian model algorithm based on time series prediction extracts the signal features from the pre-processed navigation signal and the sensor receiving signal data after data fusion;

[0012] A signal feature dynamic threshold is preset, and the signal feature dynamic threshold is used to determine whether the navigation signal corresponding to the current signal feature is a spoofing signal.

[0013] As a preferred embodiment of the present invention, the step of extracting the signal features is:

[0014] Perform preliminary feature extraction on the preprocessed navigation signal and the sensor receiving signal data after data fusion to obtain a signal feature set. At the same time, assign weights to each type of feature in the signal feature set to obtain a weight vector set, and construct a feature weighting function to calculate the weighted feature value of the signal feature set.

[0015] The final features of the signal are output through a mixed Gaussian model based on time series and the weighted eigenvalues ​​of the signal feature set, as shown in the following formula:

[0016]

[0017] Where: H is the weighted eigenvalue of the signal feature corresponding to the current signal; K represents the total number of Gaussian components; k represents the kth Gaussian component; π k represents the weight of the kth Gaussian component; μ represents the mean of the Gaussian component; ∑ represents the covariance matrix of the Gaussian component.

[0018] As a preferred embodiment of the present invention, the steps of determining the fraudulent signal are as follows:

[0019] Compare the predicted probability with the preset signal feature dynamic threshold and output the judgment result, as shown in the following formula:

[0020]

[0021] Where: R ′ Indicates the judgment result; T ′ Represents the dynamic threshold of signal characteristics, which is adjusted according to real-time data; R ′When it is 1, it means the signal is a real navigation signal. ′ When it is 0, it means the signal is a spoof signal.

[0022] As a preferred embodiment of the present invention, when a fraudulent signal is detected, if it is greater than an alarm threshold, a fraudulent signal alarm message is issued and the alarm message is recorded;

[0023] Perform adaptive fuzzy reasoning on the alarm information to determine the alarm level corresponding to the current alarm information;

[0024] Based on the alarm level, the alarm threshold is dynamically adjusted as the alarm threshold for the next deception signal, as shown in the following formula:

[0025] G′=G base +σ·L;

[0026] Where: G′ is the alarm threshold; G base is the basic threshold; σ is the dynamic adjustment coefficient; L is the alarm level of the current alarm information.

[0027] As a preferred embodiment of the present invention, the alarm level calculation step of the alarm information is:

[0028] Extract signal features from alarm events to construct input variable set F a ={f amplitude , f stability , f frequency}, where f amplitude is the amplitude of the signal change, f stability is the historical stability of the signal, f frequency is the abnormal detection frequency of the signal;

[0029] Define fuzzy sets A and B, where A represents the fuzzy level of the feature and B represents the fuzzy level of the alarm, and build a fuzzy rule base based on fuzzy sets A and B;

[0030] Based on the fuzzy rule base, the input variables are converted into fuzzy values ​​to obtain the fuzzy input variable set

[0031] Based on the fuzzy rule base, fuzzy reasoning is performed on the fuzzy input variable set, and the fuzzy reasoning result Z is output, as shown in the following formula:

[0032]

[0033] Where: I represents the total number of variables in the fuzzy input variable set; i represents the i-th variable; w i represents the weight of the i-th variable; represents the fuzzy value of the i-th variable;

[0034] The output reasoning result Z is defuzzified to obtain the alarm level, as shown in the following formula:

[0035]

[0036] Where: L is the alarm level; M is the length of the deceptive signal; j is the fuzzy inference result of the jth deceptive signal; μ output (z j ) represents the alarm level membership of the jth segment deception signal.

[0037] As a preferred embodiment of the present invention, the deception signal detection is optimized by using historical deception signals, and the specific steps are as follows:

[0038] Collect historical deception signals and construct a historical deception signal set D, as shown in the following formula:

[0039] D={(F i , R i )|i=1,2,...,N};

[0040] Among them: signal feature set of the i-th detection; R i is the corresponding judgment result;

[0041] The historical data set is analyzed by anomaly detection algorithm to extract the importance index V of key features, as shown in the following formula:

[0042]

[0043] Where: J represents the total number of signal feature sets; j represents the jth signal feature set; w j represents the weight of the jth signal feature set; Var(F j ) is the variance of the jth signal feature set; MaxVar represents the maximum variance of all signal feature sets;

[0044] Based on the importance index V, the weight vector set corresponding to the signal feature set is updated.

[0045] On the other hand, the present invention also provides a high-speed moving object deception detection system for the Beidou satellite navigation system, including a signal receiving module, a multi-sensor data acquisition module, a signal feature extraction module, and a deception signal detection module;

[0046] The signal receiving module is used to receive the navigation signals sent by Beidou satellites in real time and perform preliminary processing on the received signals;

[0047] Multi-sensor data acquisition module, used to collect data from multiple sensors, including inertial measurement unit, Doppler radar, visual sensor and magnetic field sensor, and perform data fusion processing;

[0048] A signal feature extraction module extracts signal features based on the processed sensor data and the received navigation signal;

[0049] The spoofing signal detection module determines whether the navigation signal corresponding to the current signal feature is a spoofing signal through the signal feature dynamic threshold.

[0050] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0051] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0052] The present invention has the following beneficial effects:

[0053] 1. The present invention adopts a mixed Gaussian model algorithm based on time series prediction to analyze signal characteristics, which has good adaptive ability. The algorithm can judge in real time whether the received navigation signal conforms to the characteristics of the real signal and quickly identify the forged signal. Compared with the traditional method, the present invention can more effectively deal with signal deception in complex electromagnetic environments and ensure navigation safety.

[0054] 2. The present invention dynamically adjusts the alarm threshold through an adaptive fuzzy inference system, thereby improving the response speed and accuracy of the system. When it is detected that the signal characteristics do not conform to the real navigation signal, the system can issue an alarm in time to prevent potential risks caused by signal deception. In a high-speed motion environment, the real-time monitoring and response capabilities of the present invention significantly improve the safety of navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be understood that the step numbers used in this article are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0058] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0059] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0060] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0061] Embodiment 1:

[0062] See also Figure 1 , a high-speed moving object deception detection method for Beidou satellite navigation system, comprising the following steps:

[0063] Collect navigation signals sent by the Beidou satellite navigation system and pre-process the navigation signals;

[0064] Collect received signal data from multiple sensors, including inertial measurement units, Doppler radars, visual sensors, and magnetic field sensors, and perform data fusion on the received signal data;

[0065] The mixed Gaussian model algorithm based on time series prediction extracts the signal features from the pre-processed navigation signal and the sensor receiving signal data after data fusion;

[0066] A signal feature dynamic threshold is preset, and the signal feature dynamic threshold is used to determine whether the navigation signal corresponding to the current signal feature is a spoofing signal.

[0067] As a preferred implementation of this embodiment, the steps of extracting the signal features are:

[0068] Perform preliminary feature extraction on the preprocessed navigation signal and the sensor receiving signal data after data fusion to obtain the signal feature set F = {f1, f2, f3}, where f1 represents the position of the object in space, f2 represents the speed of the object, and f3 represents the acceleration of the object. At the same time, assign weights to each type of feature in the signal feature set to obtain a weight vector set W = {w1, w2, w3}, where w1 is the weight of the position feature, w2 is the weight of the speed feature, and w3 is the weight of the acceleration feature. Construct a feature weighting function H(F) = w1·f1+w2·f2+w3·f3 and calculate the weighted feature value H(F) of the signal feature set.

[0069] The final features of the signal are output through a mixed Gaussian model based on time series and the weighted eigenvalues ​​of the signal feature set, as shown in the following formula:

[0070]

[0071] Where: H is the weighted eigenvalue of the signal feature corresponding to the current signal; K represents the total number of Gaussian components; k represents the kth Gaussian component; π k represents the weight of the kth Gaussian component; μ represents the mean of the Gaussian component; ∑ represents the covariance matrix of the Gaussian component.

[0072] As a preferred implementation of this embodiment, the steps of determining the fraudulent signal are:

[0073] Compare the predicted probability with the preset signal feature dynamic threshold and output the judgment result, as shown in the following formula:

[0074]

[0075] Wherein: R′ represents the judgment result; T′ represents the dynamic threshold of the signal feature, which is adjusted according to the real-time data; when R′ is 1, it indicates that the signal is a real navigation signal, and when R′ is 0, it indicates that the signal is a deceptive signal.

[0076] As a preferred implementation of this embodiment, when a fraudulent signal is detected, if it is greater than the alarm threshold, a fraudulent signal alarm message is issued, and the alarm message E={t, R′, F} is recorded, where t is the timestamp of the alarm occurrence;

[0077] Perform adaptive fuzzy reasoning on the alarm information to determine the alarm level corresponding to the current alarm information;

[0078] Based on the alarm level, the alarm threshold is dynamically adjusted as the alarm threshold for the next deception signal, as shown in the following formula:

[0079] G′=G base +σ·L;

[0080] Where: G′ is the alarm threshold; G base is the basic threshold; σ is the dynamic adjustment coefficient, which is used to reflect the impact of the alarm level on the threshold; L is the alarm level of the current alarm information.

[0081] As a preferred implementation of this embodiment, the alarm level calculation step of the alarm information is:

[0082] Extract signal features from alarm events to construct input variable set F a ={f amplitude , f stability , f frequency}, where famplitude is the amplitude of the signal change, f stability is the historical stability of the signal, f frequency is the abnormal detection frequency of the signal;

[0083] Define fuzzy sets A and B, where A represents the fuzzy level of the feature and B represents the fuzzy level of the alarm, and build a fuzzy rule base based on fuzzy sets A and B;

[0084] Based on the fuzzy rule base, the input variables are converted into fuzzy values ​​to obtain the fuzzy input variable set

[0085] Based on the fuzzy rule base, fuzzy reasoning is performed on the fuzzy input variable set, and the fuzzy reasoning result Z is output, as shown in the following formula:

[0086]

[0087] Where: I represents the total number of variables in the fuzzy input variable set; i represents the i-th variable; w i represents the weight of the i-th variable; represents the fuzzy value of the i-th variable;

[0088] The output reasoning result Z is defuzzified to obtain the alarm level, as shown in the following formula:

[0089]

[0090] Where: L is the alarm level; M is the length of the deceptive signal; j is the fuzzy inference result of the jth deceptive signal; μ output (z j ) represents the alarm level membership of the jth segment deception signal.

[0091] As a preferred implementation of this embodiment, the deception signal detection is optimized by using historical deception signals, and the specific steps are as follows:

[0092] Collect historical deception signals and construct a historical deception signal set D, as shown in the following formula:

[0093] D={(F i , R i )|i=1,2,...,N};

[0094] Among them: the signal feature set of the i-th detection; R i is the corresponding judgment result;

[0095] The historical data set is analyzed by anomaly detection algorithm to extract the importance index V of key features, as shown in the following formula:

[0096]

[0097] Where: J represents the total number of signal feature sets; j represents the jth signal feature set; w j represents the weight of the jth signal feature set; Var(F j ) is the variance of the jth signal feature set; MaxVar represents the maximum variance of all signal feature sets;

[0098] Based on the importance index V, the weight vector set corresponding to the signal feature set is updated.

[0099] Embodiment 2:

[0100] A high-speed moving object deception detection system for a Beidou satellite navigation system, comprising a signal receiving module, a multi-sensor data acquisition module, a signal feature extraction module, and a deception signal detection module;

[0101] The signal receiving module is used to receive the navigation signals sent by Beidou satellites in real time and perform preliminary processing on the received signals;

[0102] Multi-sensor data acquisition module, used to collect data from multiple sensors, including inertial measurement unit, Doppler radar, visual sensor and magnetic field sensor, and perform data fusion processing;

[0103] A signal feature extraction module extracts signal features based on the processed sensor data and the received navigation signal;

[0104] The spoofing signal detection module determines whether the navigation signal corresponding to the current signal feature is a spoofing signal through the signal feature dynamic threshold.

[0105] The alarm module, when a deceptive signal is detected, dynamically adjusts the alarm threshold using an adaptive fuzzy inference system and issues an alarm signal;

[0106] The historical data analysis module uses anomaly detection algorithms to analyze and learn historical data and optimize the deception signal detection model;

[0107] The data storage module is used to store received signals and detection results.

[0108] The system is used to implement the method in Example 1, which will not be described in detail here.

[0109] Embodiment three:

[0110] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0111] Embodiment 4:

[0112] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0113] Embodiment five:

[0114] The high-speed moving object deception detection system based on the Beidou satellite navigation system of the present invention was implemented in a highway transportation scenario. This highway connects multiple logistics centers. Transport vehicles travel at high speeds on this road, and safe navigation is essential. However, the traditional navigation signal detection system shows obvious deficiencies in such an environment, mainly because of its poor ability to prevent signal deception and susceptibility to external interference, resulting in insufficient reliability of the navigation signal.

[0115] In order to improve the navigation security of high-speed moving objects, the deception signal detection system of the present invention is installed on multiple transport vehicles. Each vehicle is equipped with a Beidou satellite signal receiving module, a data acquisition module, a signal feature extraction module, a deception signal detection module and an alarm module. The antenna of the receiving module is installed on the roof to ensure good satellite signal reception. The data acquisition module collects relevant data of the vehicle's motion state in real time, including speed, acceleration and direction, and performs correlation analysis with the navigation signal through data fusion technology. In actual operation, the system was tested in a transport vehicle of a logistics center. When the vehicle is driving at high speed, the signal received by the Beidou satellite receiving module provides accurate location information for the navigation system. The data acquisition module is synchronized with the signal receiving module in real time to ensure that the acquired data is complete and accurate. Through the signal feature extraction module, the system can extract the key features of the navigation signal and compare it with historical data to identify potential deception signals.

[0116] In an actual application, when the vehicle was traveling at a speed of 120 kilometers per hour, the system detected that the characteristics of the received navigation signal were significantly different from the expected signal characteristics, and identified a possible fraudulent signal. The alarm module immediately sounded an alarm, reminding the driver to pay attention to the signal abnormality and recommending a temporary stop for inspection. After further analysis, the system identified the presence of interference sources in the area, resulting in signal falsification. The system has a real-time response time of 2 seconds, ensuring that the driver can respond in time and avoid potential traffic accidents.

[0117] Table 1 Performance comparison data before and after the implementation of the moving object high-speed motion deception detection system based on the Beidou satellite navigation system

[0118]

[0119]

[0120] As shown in Table 1, the traditional method has great deficiencies in signal detection delay and alarm response time, and the accuracy of deceptive signal recognition is only 70%, which poses a threat to the safety of high-speed vehicles. After installing the detection system of the present invention, the signal detection delay is significantly reduced to 50 milliseconds, the alarm response time is shortened to 2 seconds, and the accuracy of deceptive signal recognition is increased to 95%. These improvements show that the system of the present invention can effectively improve navigation safety in a high-speed motion environment.

[0121] Through practical application in this highway transportation scenario, the high-speed motion deception detection system of moving objects based on the Beidou satellite navigation system of the present invention effectively solves the signal deception detection problem of traditional navigation systems under high-speed driving conditions. The system not only significantly improves the accuracy and real-time performance of signal recognition, but also ensures the safety of drivers through a rapid response mechanism, ultimately improving overall transportation efficiency and safety.

[0122] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0123] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0125] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0126] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting high-speed moving object spoofing in Beidou satellite navigation system, characterized in that: The following steps are involved: Collect navigation signals sent by the Beidou satellite navigation system and pre-process the navigation signals; Collect received signal data from multiple sensors, including inertial measurement units, Doppler radars, visual sensors, and magnetic field sensors, and perform data fusion on the received signal data; The mixed Gaussian model algorithm based on time series prediction extracts the signal features from the pre-processed navigation signal and the sensor receiving signal data after data fusion; A signal feature dynamic threshold is preset, and the signal feature dynamic threshold is used to determine whether the navigation signal corresponding to the current signal feature is a spoofing signal.

2. The method for detecting high-speed moving objects spoofing in the Beidou satellite navigation system according to claim 1, characterized in that: The steps of extracting the signal features are: Perform preliminary feature extraction on the preprocessed navigation signal and the sensor receiving signal data after data fusion to obtain a signal feature set. At the same time, assign weights to each type of feature in the signal feature set to obtain a weight vector set, and construct a feature weighting function to calculate the weighted feature value of the signal feature set. The final features of the signal are output through a mixed Gaussian model based on time series and the weighted eigenvalues ​​of the signal feature set, as shown in the following formula: Where: H is the weighted eigenvalue of the signal feature corresponding to the current signal; K represents the total number of Gaussian components; k represents the kth Gaussian component; π k represents the weight of the kth Gaussian component; μ represents the mean of the Gaussian component; ∑ represents the covariance matrix of the Gaussian component.

3. The method for detecting high-speed moving objects spoofing in the Beidou satellite navigation system according to claim 2, characterized in that: The steps of judging the deceptive signal are as follows: Compare the predicted probability with the preset signal feature dynamic threshold and output the judgment result, as shown in the following formula: Where: R ′ Indicates the judgment result; T ′ Represents the dynamic threshold of signal characteristics, which is adjusted according to real-time data; R ′ When it is 1, it means the signal is a real navigation signal. ′ When it is 0, it means the signal is a spoof signal.

4. The method for detecting high-speed moving objects spoofing in the Beidou satellite navigation system according to claim 1, characterized in that: When a deception signal is detected, if it is greater than the alarm threshold, a deception signal alarm message is issued and the alarm message is recorded; Perform adaptive fuzzy reasoning on the alarm information to determine the alarm level corresponding to the current alarm information; Based on the alarm level, the alarm threshold is dynamically adjusted as the alarm threshold for the next deception signal, as shown in the following formula: G′=G base +σ·L; Where: G ′ is the alarm threshold; G base is the basic threshold; σ is the dynamic adjustment coefficient; L is the alarm level of the current alarm information.

5. The method for detecting high-speed moving object spoofing in the Beidou satellite navigation system according to claim 4, characterized in that: The steps for calculating the alarm level of the alarm information are as follows: Extract signal features from alarm events to construct input variable set F a ={f amplitude ,f stability ,f frequency }, where f amplitude is the amplitude of the signal change, f stability is the historical stability of the signal, f frequency is the abnormal detection frequency of the signal; Define fuzzy sets A and B, where A represents the fuzzy level of the feature and B represents the fuzzy level of the alarm, and build a fuzzy rule base based on fuzzy sets A and B; Based on the fuzzy rule base, the input variables are converted into fuzzy values ​​to obtain the fuzzy input variable set Based on the fuzzy rule base, fuzzy reasoning is performed on the fuzzy input variable set, and the fuzzy reasoning result Z is output, as shown in the following formula: Where: I represents the total number of variables in the fuzzy input variable set; i represents the i-th variable; w i represents the weight of the i-th variable; represents the fuzzy value of the i-th variable; The output reasoning result Z is defuzzified to obtain the alarm level, as shown in the following formula: Where: L is the alarm level; M is the length of the deceptive signal; j is the fuzzy inference result of the jth deceptive signal; μ output (z j ) represents the alarm level membership of the jth segment deception signal.

6. The method for detecting high-speed moving object spoofing in Beidou satellite navigation system according to claim 2, characterized in that: Optimize the spoofing signal detection through historical spoofing signals. The specific steps are as follows: Collect historical deception signals and construct a historical deception signal set D, as shown in the following formula: D={(F i ,R i )|i=1,2,…,N}; Among them: signal feature set of the i-th detection; R i is the corresponding judgment result; The historical data set is analyzed by anomaly detection algorithm to extract the importance index V of key features, as shown in the following formula: Where: J represents the total number of signal feature sets; j represents the jth signal feature set; w j represents the weight of the jth signal feature set; Var(F j ) is the variance of the jth signal feature set; MaxVar represents the maximum variance of all signal feature sets; Based on the importance index V, the weight vector set corresponding to the signal feature set is updated.

7. A high-speed moving object deception detection system for the Beidou satellite navigation system, characterized in that: It includes a signal receiving module, a multi-sensor data acquisition module, a signal feature extraction module, and a deception signal detection module; The signal receiving module is used to receive the navigation signals sent by Beidou satellites in real time and perform preliminary processing on the received signals; Multi-sensor data acquisition module, used to collect data from multiple sensors, including inertial measurement unit, Doppler radar, visual sensor and magnetic field sensor, and perform data fusion processing; A signal feature extraction module extracts signal features based on the processed sensor data and the received navigation signal; The spoofing signal detection module determines whether the navigation signal corresponding to the current signal feature is a spoofing signal through the signal feature dynamic threshold.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images