Gnss spoofing jamming detection method, device and equipment and storage medium

Abstract

The application discloses a GNSS spoofing interference detection method, device and equipment and a storage medium. The method comprises the following steps: receiving a frequency band signal from a radio frequency front end through a GNSS receiver, and capturing a plurality of visible satellites from the frequency band signal; extracting the observation quantity and the frequency deviation of each visible satellite from the frequency band signal; performing normalization preprocessing on the frequency deviation of each visible satellite after merging, obtaining feature data, training an integrated learning classifier through the feature data, and obtaining an intermediate integrated model; using the intermediate integrated model to determine whether there is a spoofing signal in the frequency band signal, adjusting the intermediate integrated model according to a predicted label and a real label, and obtaining an optimized integrated model; and using the optimized integrated model to detect the frequency band signal, and determining whether the detected signal is a spoofing signal or a real signal. The application reduces data redundancy and operation time, is easy to implement and has low complexity, greatly reduces the equipment cost of the receiver, and has a wider application scenario.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of satellite navigation technology, and in particular to a GNSS spoofing interference detection method, device, equipment and storage medium. BACKGROUND

[0002] After the global positioning system enters the commercial and civilian market, many components of the key infrastructure and widely used applications begin to rely on the continuous availability of PVT (Position, Velocity, Time) information. Once the global navigation satellite system is suddenly closed or interfered to provide false time position information, it will have a significant impact on various industries around the world and even a devastating blow. In the civil GNSS system (Global Navigation Satellite System), the navigation signal is very weak after long distance transmission, and because the signal structure is open, it is easy to be subjected to spoofing interference. With the development of science and technology, the development of integrated electronic technology, sensor technology and radio technology, spoofing interference becomes easier to achieve, and the cost is lower and the operation is more flexible, so spoofing must be detected, weakened or eliminated. Among them, spoofing detection is the key. Only the satellite navigation spoofing is correctly detected, can further weaken or eliminate, or further determine the location of the spoofing source, so as to eliminate the spoofing source.

[0003] In recent years, many solutions have been proposed for GNSS spoofing detection, including absolute power monitoring, relative power monitoring, multiple correlation peak detection method, signal angle of arrival detection method, time consistency detection, autonomous integrity detection, navigation and time information fusion detection and other methods. The above methods and technologies obtain good detection performance by arranging additional hardware devices, but increase the economic cost or implementation difficulty, which is completely unachievable for small and medium-sized enterprises, so it is difficult to popularize. SUMMARY

[0004] Therefore, the purpose of the present application is to overcome the deficiencies in the prior art and provide a GNSS spoofing interference detection method, device, equipment and storage medium.

[0005] The present application provides the following technical solutions:

[0006] In a first aspect, the present application provides a GNSS spoofing interference detection method, which comprises:

[0007] The GNSS receiver receives a frequency band signal from the radio frequency front end, and captures multiple visible satellites from the frequency band signal, wherein the frequency band signal includes a first frequency band signal and a second frequency band signal;

[0008] extracting observation quantities of each of the visible satellites from the frequency band signals, the observation quantities comprising first observation quantities extracted from the first frequency band signals and second observation quantities extracted from the second frequency band signals, and calculating an inter-frequency bias of each of the visible satellites according to the first observation quantities and the second observation quantities;

[0009] combining the inter-frequency biases of each of the visible satellites, and performing mean-variance normalization preprocessing on the combined inter-frequency biases to obtain feature data, training an ensemble learning classifier through the feature data to obtain an intermediate ensemble model;

[0010] judging whether there is a spoofing signal in the frequency band signals by using the intermediate ensemble model, outputting a prediction label, adjusting the intermediate ensemble model according to the prediction label and a true label to obtain an optimized ensemble model;

[0011] detecting the frequency band signals using the optimized ensemble model, determining that a detected signal is a spoofing signal when the output prediction label is 1, and determining that the detected signal is a true signal when the output prediction label is -1.

[0012] Further, the observation quantities include carrier-to-noise ratio, and the extracting of the observation quantities of each of the visible satellites from the frequency band signals comprises:

[0013] calculating the carrier-to-noise ratio according to the GNSS receiver and the frequency band signals by using a carrier-to-noise ratio calculation formula, wherein the carrier-to-noise ratio calculation formula is:

[0014]

[0015] wherein, is the carrier-to-noise ratio of the i-th visible satellite at time t, is the power density of the frequency band signal of the i-th visible satellite at time t, N d (t) is the noise power density of the GNSS receiver at time t, P (i) (t) is the power of the frequency band signal of the i-th visible satellite at time t, B I is the bandwidth of the GNSS receiver, n(t) is the noise power of the GNSS receiver at time t, S (i) (t) is the signal power transmitted by the i-th visible satellite at time t, and L(t) is the transmission path loss at time t.

[0016] Further, the observation quantities include carrier phase, and the extracting of the observation quantities of each of the visible satellites from the frequency band signals further comprises:

[0017] The carrier phase is calculated according to the GNSS receiver and the frequency band signal by using a carrier phase calculation formula, wherein the carrier phase calculation formula is:

[0018] φ (i) (t) = λ -1 (r(t) + c(δt u -δt (s) )-I(t) + T(t)) + N + ε φ

[0019] In the formula, φ (i) (t) is the carrier phase of the i th visible satellite at time t, λ is the wavelength of the visible satellite, r(t) is the geometric distance between the visible satellite and the GNSS receiver at time t, c is the speed of light, δt u is the clock error of the GNSS receiver, δt (s) is the clock error of the visible satellite, I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, N is the total number of the visible satellites, and ε φ is the sum of all carrier phase errors that cannot be accurately represented.

[0020] Further, the observation quantity includes Doppler frequency shift, and the observation quantity of each visible satellite is extracted from the frequency band signal, and the method further comprises:

[0021] The Doppler frequency shift is calculated according to the GNSS receiver and the frequency band signal by using a Doppler frequency shift calculation formula, wherein the Doppler frequency shift calculation formula is:

[0022]

[0023] In the formula, f d (i) is the Doppler frequency shift of the i th visible satellite, f r (i) is the receiving frequency of the i th visible satellite, f (i) is the transmitting frequency of the i th visible satellite, v is the running speed of the GNSS receiver, λ (i) is the wavelength of the i th visible satellite, β is the incident angle of the frequency band signal, and c is the speed of light.

[0024] Further, the observation quantity includes pseudo-range, and the observation quantity of each visible satellite is extracted from the frequency band signal, and the method further comprises:

[0025] The pseudo-range is calculated according to the GNSS receiver and the frequency band signal by using a pseudo-range calculation formula, wherein the pseudo-range calculation formula is:

[0026] ρ (i) (t) = r(t - τ, t) + c · (δt u (t) - δt (s) (t - τ)) + cI(t) + cT(t) + ε ρ

[0027] wherein ρ (i) (t) is the pseudo-range of the i-th visible satellite at time t, τ is the actual propagation time of the frequency band signal, r(t - τ, t) is the geometric distance between the visible satellite at time t - τ and the GNSS receiver at time t, c is the speed of light, δt u (t) is the clock error of the GNSS receiver at time t, δt (s) (t - τ) is the clock error of the visible satellite at time (t - τ), I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, and ε ρ is the sum of all pseudo-range errors that cannot be accurately represented.

[0028] Further, the calculation of the inter-frequency bias of each visible satellite according to the first observation and the second observation comprises:

[0029] calculating the inter-frequency bias of the carrier-to-noise ratio, the carrier phase, the Doppler shift and the pseudo-range in the first frequency band signal and the second frequency band signal according to an inter-frequency bias calculation formula, wherein the inter-frequency bias calculation formula is:

[0030]

[0031] wherein is the inter-frequency bias of the carrier-to-noise ratio of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, is the carrier-to-noise ratio of the i-th visible satellite in the first frequency band signal L1 at time t, is the carrier-to-noise ratio of the i-th visible satellite in the second frequency band signal L2 at time t, is the inter-frequency bias of the carrier phase of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, φ (i) L1 is the carrier phase of the i-th visible satellite in the first frequency band signal L1 at time t, (i) L2 is the carrier phase of the i-th visible satellite in the second frequency band signal L2 at time t, is the inter-frequency bias of the Doppler shift of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, a Doppler shift of the i th visible satellite in the first frequency band signal L1 at time t, a Doppler shift of the i th visible satellite in the second frequency band signal L2 at time t, an inter-frequency bias of a pseudo-range of the i th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, a pseudo-range of the i th visible satellite in the first frequency band signal L1 at time t, a pseudo-range of the i th visible satellite in the second frequency band signal L2 at time t.

[0032] Further, the detecting the frequency band signal using the optimized integrated model comprises:

[0033] detecting the first frequency band signal and the second frequency band signal using the optimized integrated model, and outputting a predicted label, the predicted label comprising a first binary hypothesis and a second binary hypothesis, the first binary hypothesis representing -1, and the second binary hypothesis representing 1;

[0034] wherein the first binary hypothesis is:

[0035]

[0036] wherein H0 is the first binary hypothesis, T i [n] is a detection statistic of the i th visible satellite in the n th detected signal, is a real signal of the i th visible satellite in the n th detected signal, and ζ[n] is channel noise of the n th detected signal;

[0037] wherein the second binary hypothesis is:

[0038]

[0039] wherein H1 is the second binary hypothesis, is a spoofing signal of the i th visible satellite in the n th detected signal.

[0040] In a second aspect, the disclosure provides a GNSS spoofing jamming detection device, the device comprising:

[0041] a receiving module configured to receive a frequency band signal from a radio frequency front end through a GNSS receiver, and capture a plurality of visible satellites from the frequency band signal, wherein the frequency band signal comprises a first frequency band signal and a second frequency band signal;

[0042] an extraction module configured to extract observations of each of the visible satellites from the frequency band signals, the observations comprising first observations extracted from the first frequency band signals and second observations extracted from the second frequency band signals, and to calculate an inter-frequency bias of each of the visible satellites according to the first observations and the second observations;

[0043] a training module configured to combine the inter-frequency biases of each of the visible satellites, and to perform mean-variance normalization preprocessing on the combined inter-frequency biases to obtain feature data, to train an ensemble learning classifier using the feature data, and to obtain an intermediate ensemble model;

[0044] a judging module configured to judge whether a spoofing signal exists in the frequency band signals using the intermediate ensemble model, to output a predicted label, and to adjust the intermediate ensemble model according to the predicted label and a true label to obtain an optimized ensemble model;

[0045] a detecting module configured to detect the frequency band signals using the optimized ensemble model, to determine that a detected signal is a spoofing signal when the output predicted label is 1, and to determine that the detected signal is a true signal when the output predicted label is -1.

[0046] In a third aspect, a computer device is provided in the embodiments of the present disclosure, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the GNSS spoofing interference detection method in the first aspect when executing the computer program.

[0047] In a fourth aspect, a computer readable storage medium is provided in the embodiments of the present disclosure, the computer readable storage medium stores a computer program, and the computer program implements the steps of the GNSS spoofing interference detection method in the first aspect when executed by a processor.

[0048] The embodiments of the present disclosure have the following advantages:

[0049] The GNSS spoofing interference detection method provided by the embodiment of the application, the method comprises: receiving a frequency band signal from a radio frequency front end by a GNSS receiver, and capturing a plurality of visible satellites from the frequency band signal, wherein the frequency band signal comprises a first frequency band signal and a second frequency band signal; extracting an observation quantity of each of the visible satellites from the frequency band signal, the observation quantity comprising a first observation quantity extracted from the first frequency band signal and a second observation quantity extracted from the second frequency band signal, and calculating a frequency deviation of each of the visible satellites according to the first observation quantity and the second observation quantity; combining the frequency deviations of each of the visible satellites, and performing mean-variance normalization preprocessing on the combined frequency deviation to obtain feature data, training an integrated learning classifier through the feature data to obtain an intermediate integrated model; determining whether there is a spoofing signal in the frequency band signal by using the intermediate integrated model, outputting a prediction label, adjusting the intermediate integrated model according to the prediction label and a true label to obtain an optimized integrated model; and detecting the frequency band signal by using the optimized integrated model, determining that the detected signal is a spoofing signal when the output prediction label is 1, and determining that the detected signal is a real signal when the output prediction label is -1. The application reduces data redundancy and operation time, is easy to implement and has low complexity, has low requirements on the receiver, greatly reduces the equipment cost of the receiver, and has a wider application scenario.

[0050] In order to make the above objectives, features and advantages of the present application more apparent and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are referred to, and the detailed description is as follows. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor. In each drawing, similar components are marked with similar reference numerals.

[0052] Figure 1 A flowchart of a GNSS spoofing interference detection method provided by an embodiment of the application is shown;

[0053] Figure 2 A schematic diagram of carrier-to-noise ratio and frequency deviation provided by an embodiment of the application is shown;

[0054] Figure 3 A schematic diagram of carrier phase and frequency deviation provided by an embodiment of the application is shown;

[0055] Figure 4A Doppler frequency shift and frequency deviation diagram provided by an embodiment of the application is shown.

[0056] Figure 5 A pseudo-range and frequency deviation diagram provided by an embodiment of the application is shown.

[0057] Figure 6 A structure diagram of a GNSS spoofing interference detection device provided by an embodiment of the application is shown. DETAILED DESCRIPTION

[0058] Embodiments of the present application are described in detail below with reference to examples illustrated in the accompanying drawings, in which the same or similar components have the same or similar designations throughout the various figures. The embodiments described below are examples of the present application, and are not intended to limit the present application.

[0059] It should be noted that when an element is referred to as being "on" another element, it can be directly on the other element or intervening elements can also be present. In contrast, when an element is referred to as being "directly on" another element, there are no intervening elements present. The terms "over," "under," "right," "left," and "sides" are used herein only to describe the relative position of one element to another as the drawings are viewed.

[0060] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "fixing" and the like should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0061] In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise explicitly specified and limited.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the templates herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0063] Embodiment 1

[0064] As Figure 1 shown, a flow chart of a GNSS spoofing jamming detection method in the embodiments of the present application, the GNSS spoofing jamming detection method provided by the embodiments of the present application includes the following steps:

[0065] Step S110, receiving a frequency band signal from a radio frequency front end by a GNSS receiver, and capturing a plurality of visible satellites from the frequency band signal, wherein the frequency band signal includes a first frequency band signal and a second frequency band signal.

[0066] First, a frequency band signal is received from a radio frequency front end by a GNSS receiver, including a first frequency band signal L1 and a second frequency band signal L2, a plurality of visible satellites are captured from the frequency band signal, and the captured visible satellites are tracked.

[0067] Step S120, extracting an observation quantity of each of the visible satellites from the frequency band signal, the observation quantity including a first observation quantity extracted from the first frequency band signal and a second observation quantity extracted from the second frequency band signal, and calculating an inter-frequency bias of each of the visible satellites according to the first observation quantity and the second observation quantity.

[0068] Further, the observation quantity of each visible satellite is extracted from the frequency band signal, including carrier-to-noise ratio, carrier phase, Doppler shift and pseudo-range. The carrier-to-noise ratio, carrier phase, Doppler shift and pseudo-range can reflect the state of the GNSS receiver and the health status of the visible satellite. When the receiving environment of the GNSS receiver changes or is interfered, the above observation quantities will deviate from the original observation level value and change to different degrees.

[0069] The carrier-to-noise ratio refers to the ratio of the frequency band signal power to the noise power of the GNSS receiver. Specifically, the carrier-to-noise ratio is calculated according to the GNSS receiver and the frequency band signal by using a carrier-to-noise ratio calculation formula, wherein the carrier-to-noise ratio calculation formula is:

[0070]

[0071] In the formula, is the carrier-to-noise ratio of the i-th visible satellite at time t, is the power density of the frequency band signal of the i-th visible satellite at time t, Nd (t) is the noise power density of the GNSS receiver at time t, P (i) (t) is the power of the band signal of the i-th visible satellite at time t, B I is the bandwidth of the GNSS receiver, n(t) is the noise power of the GNSS receiver at time t, S (i) (t) is the signal power transmitted by the i-th visible satellite at time t, L(t) is the transmission path loss at time t.

[0072] The carrier phase refers to the measurement value of the phase of the visible satellite signal received by the reference station at the same receiving time relative to the phase of the carrier signal generated by the GNSS receiver. Specifically, the carrier phase is calculated according to the GNSS receiver and the band signal by using the carrier phase calculation formula, wherein the carrier phase calculation formula is:

[0073] φ (i) (t) = λ -1 (r(t) + c(δt u - δt (s) )- I(t) + T(t)) + N + ε φ

[0074] In the formula, φ (i) (t) is the carrier phase of the i-th visible satellite at time t, λ is the wavelength of the visible satellite, r(t) is the geometric distance between the visible satellite and the GNSS receiver at time t, c is the speed of light, δt u is the GNSS receiver clock error, δt (s) is the visible satellite clock error, I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, N is the total number of visible satellites, ε φ is the sum of all carrier phase errors that cannot be accurately represented.

[0075] The Doppler shift refers to the relative motion between the visible satellite and the earth (GNSS receiver) resulting in the shift of the received frequency. If the transmission frequency of the visible satellite is f, and the GNSS receiver moves at a speed v, then the received signal frequency f r of the GNSS receiver is no longer the transmission frequency f of the visible satellite, but f + f d . The change of the received frequency f r with the relative motion between the signal transmission source and the GNSS receiver is called the Doppler effect. Specifically, the Doppler shift is calculated according to the GNSS receiver and the band signal by using the Doppler shift calculation formula, wherein the Doppler shift calculation formula is:

[0076]

[0077] wherein f d (i) is the Doppler shift of the i-th visible satellite, f r (i) is the receiving frequency of the i-th visible satellite, f (i) is the transmitting frequency of the i-th visible satellite, v is the running speed of the GNSS receiver, and λ (i) is the wavelength of the i-th visible satellite, and β is the incidence angle of the band signals, i.e. the included angle between the incidence direction of the band signals and the moving direction of the GNSS receiver.

[0078] The pseudo-range refers to the product of the time difference between the time when the visible satellite transmits the signal and the time when the user receives the signal and the speed of light. Specifically, the pseudo-range is calculated according to the GNSS receiver and the band signals by using a pseudo-range calculation formula, wherein the pseudo-range calculation formula is:

[0079] ρ (i) (t) = r(t-τ, t) + c·(δt u (t) - δt (s) (t-τ)) + cI(t) + cT(t) + ε ρ

[0080] wherein ρ (i) (t) is the pseudo-range of the i-th visible satellite at time t, τ is the actual propagation time of the band signals, r(t-τ, t) is the geometric distance between the position of the visible satellite at time t-τ and the GNSS receiver at time t, c is the speed of light, δt u (t) is the clock error of the GNSS receiver at time t, δt (s) (t-τ) is the clock error of the visible satellite at time (t-τ), I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, and ε ρ is the sum of all pseudo-range errors that cannot be accurately represented.

[0081] Further, the inter-frequency deviation of the carrier-to-noise ratio, the carrier phase, the Doppler shift and the pseudo-range in the first band signal and the second band signal is calculated according to an inter-frequency deviation calculation formula, wherein the inter-frequency deviation calculation formula is:

[0082]

[0083] wherein is the inter-frequency deviation of the carrier-to-noise ratio of the i-th visible satellite in the first band signal L1 and the second band signal L2 at time t, a carrier-to-noise ratio of the i-th visible satellite at time t in the first frequency band signal L1, a carrier-to-noise ratio of the i-th visible satellite at time t in the second frequency band signal L2, a frequency interval deviation of a carrier phase of the i-th visible satellite at time t in the first frequency band signal L1 and the second frequency band signal L2, φ (i) L1 a carrier phase of the i-th visible satellite at time t in the first frequency band signal L1, φ (i) L2 a carrier phase of the i-th visible satellite at time t in the second frequency band signal L2, a frequency interval deviation of a Doppler shift of the i-th visible satellite at time t in the first frequency band signal L1 and the second frequency band signal L2, a Doppler shift of the i-th visible satellite at time t in the first frequency band signal L1, a Doppler shift of the i-th visible satellite at time t in the second frequency band signal L2, a frequency interval deviation of a pseudo-range of the i-th visible satellite at time t in the first frequency band signal L1 and the second frequency band signal L2, a pseudo-range of the i-th visible satellite at time t in the first frequency band signal L1, a pseudo-range of the i-th visible satellite at time t in the second frequency band signal L2.

[0084] It should be noted that the GNSS signal is only affected in one frequency band signal, such as the L1 frequency band signal is subjected to spoofing interference, while the L2 frequency band signal works normally, at this time the frequency interval deviation will have a large fluctuation.

[0085] The frequency interval deviations of the carrier-to-noise ratio, the carrier phase, the Doppler shift and the pseudo-range are combined with the machine learning algorithm and applied to the GNSS spoofing detection. When the spoofing device targets a certain frequency band, the frequency interval deviation will deviate from the normal value, so the above method can greatly improve the spoofing detection rate.

[0086] In step S130, the frequency interval deviations of each visible satellite are combined, and the combined frequency interval deviations are subjected to mean-variance normalization preprocessing to obtain feature data. The integrated learning classifier is trained through the feature data to obtain an intermediate integrated model.

[0087] Then, the frequency interval deviations of each visible satellite in step S120 are combined and subjected to mean-variance normalization preprocessing. The processed data is used as new feature data. The mean-variance normalization method is as follows:

[0088]

[0089] wherein, and are the k-th eigenvalue, eigenmean and standard deviation of the i-th satellite, respectively, is the normalized feature data.

[0090] Further, the ensemble learning classifier is trained by the feature data, and after the training, a trained intermediate ensemble model is obtained.

[0091] It can be understood that in the embodiment, the ensemble learning classifier refers to an Adaboost model, and the working mechanism thereof is that a weak learner Model-1 is trained from a training set with an initial weight, the weight of the training sample is updated according to the error rate of the weak learning, so that the weight of the training sample point with a high error rate of Model-1 learning is high, and these points with a high error rate are paid more attention in Model-2. Then Model-2 is trained based on the training set with the adjusted weight. This is repeated until the number of weak learners reaches a specified number T, and finally the T weak learners are integrated through a set strategy to obtain a final strong learner. The Adaboost model uses an exponential loss function to evaluate the model:

[0092]

[0093] The intermediate ensemble learning model avoids the problem that the model has a high error rate on some samples, and through the reassignment of the weight and the retraining of the weak learner, a strong learner with a higher detection rate is finally obtained by integrating the weak learners through a set strategy.

[0094] In step S140, it is judged whether there is a spoofing signal in the frequency band signal by using the intermediate ensemble model, a prediction label is output, the intermediate ensemble model is adjusted according to the prediction label and the true label, and an optimized ensemble model is obtained.

[0095] Further, it is judged whether there is a spoofing signal in the frequency band signal by using the intermediate ensemble model, if there is a spoofing signal, the intermediate ensemble learning model outputs a prediction label of 1, otherwise outputs a prediction label of -1, and the feature data set is divided according to a ratio of 70% training and 30% testing, so that the constructed feature data set is:

[0096] Tr={(x1, y1), (x2, y2),..., (x m , y m )}

[0097]

[0098] Further, the prediction labels are compared with the real labels, each evaluation index is calculated, and the parameters are adjusted to optimize the performance of the intermediate integrated model to obtain an optimized integrated model. The evaluation indexes are shown in Table 1.

[0099] Table 1

[0100]

[0101] The application uses an algorithm to analyze and process the data obtained by the GNSS receiver for judgment, without changing the satellite navigation signal system and installing additional equipment, and has a wider application scenario.

[0102] In step S150, the frequency band signal is detected using the optimized integrated model. When the output prediction label is 1, it is determined that the detected signal is a spoofing signal, and when the output prediction label is -1, it is determined that the detected signal is a real signal.

[0103] Finally, the optimized integrated model is used to detect spoofing of the frequency band signal. During detection, the output prediction label of the optimized integrated model is 1, indicating the second binary hypothesis H1, i.e., the detected signal is a spoofing signal; and the output prediction label of the optimized integrated model is -1, indicating the first binary hypothesis H0, i.e., the detected signal is a normal signal, i.e., not subjected to GNSS spoofing attack.

[0104] The first binary hypothesis is:

[0105]

[0106] In the formula, H0 is the first binary hypothesis, T i [n] is the detection statistic of the ith visible satellite in the nth detected signal, is the real signal of the ith visible satellite in the nth detected signal, and ζ[n] is the channel noise of the nth detected signal.

[0107] The second binary hypothesis is:

[0108]

[0109] In the formula, H1 is the second binary hypothesis, is the spoofing signal of the ith visible satellite in the nth detected signal.

[0110] In an optional embodiment, as Figures 2 to 5As shown, the GNSS receiver and GPS (Global Positioning System) antenna were used to collect GPS satellite navigation data from 12:00 to 14:00 on July 18 and 19, 2023, with a sampling frequency of 1 Hz (once per second) and an observation frequency band of GPS L1 (1575.42 MHz) and L2 (1227.60 MHz). During the collection period on July 18, GPS spoofing was performed using the GPS-SIM-SDR open source package and the Hack RF One software-defined radio module, and the signals in the L1 frequency band were spoofed. The GNSS receiver observed 8 visible satellites, PRN (Pseudo Random Noise code) 3, 6, 7, 13, 16, 19, 20, and 23. The observation quantities of each visible satellite in the L1 and L2 frequency bands were obtained, including carrier-to-noise ratio (C / N0), carrier phase (φ), Doppler shift (fd), and pseudo-range (ρ). Figure 2 Figure 3 Figure 4 Figure 5

[0111] The GNSS spoofing interference detection method provided by the embodiments of the present application receives a frequency band signal from a radio frequency front end through a GNSS receiver, captures a plurality of visible satellites from the frequency band signal, wherein the frequency band signal includes a first frequency band signal and a second frequency band signal; extracts observation quantities of each of the visible satellites from the frequency band signal, the observation quantities including first observation quantities extracted from the first frequency band signal and second observation quantities extracted from the second frequency band signal, and calculates the inter-frequency bias of each of the visible satellites according to the first observation quantities and the second observation quantities; combines the inter-frequency biases of each of the visible satellites, and performs mean-variance normalization preprocessing on the combined inter-frequency bias to obtain feature data, trains an integrated learning classifier through the feature data to obtain an intermediate integrated model; determines whether there is a spoofing signal in the frequency band signal by using the intermediate integrated model, outputs a prediction label, adjusts the intermediate integrated model according to the prediction label and a true label to obtain an optimized integrated model; and uses the optimized integrated model to detect the frequency band signal, determines that the detected signal is a spoofing signal when the output prediction label is 1, and determines that the detected signal is a true signal when the output prediction label is -1. The present application reduces data redundancy and computation time, is easy to implement and has low complexity, has low requirements for the receiver, greatly reduces the equipment cost of the receiver, and has a wider application scenario.

[0112] Embodiment 2

[0113] As shown in Figure 6 , it is a structure schematic diagram of a GNSS spoofing interference detection device 600 in the embodiments of the present application, and the device comprises:​​​​

[0114] The receiving module 610 is configured to receive a frequency band signal from a radio frequency front end by a GNSS receiver, and capture a plurality of visible satellites from the frequency band signal, wherein the frequency band signal includes a first frequency band signal and a second frequency band signal.

[0115] The extracting module 620 is configured to extract an observation quantity of each of the visible satellites from the frequency band signal, wherein the observation quantity includes a first observation quantity extracted from the first frequency band signal and a second observation quantity extracted from the second frequency band signal, and calculate an inter-frequency bias of each of the visible satellites according to the first observation quantity and the second observation quantity.

[0116] The training module 630 is configured to combine the inter-frequency biases of the visible satellites, and perform mean-variance normalization preprocessing on the combined inter-frequency biases to obtain feature data, train an ensemble learning classifier by using the feature data to obtain an intermediate ensemble model.

[0117] The judging module 640 is configured to judge whether there is a spoofing signal in the frequency band signal by using the intermediate ensemble model, output a prediction label, and adjust the intermediate ensemble model according to the prediction label and a true label to obtain an optimized ensemble model.

[0118] The detecting module 650 is configured to detect the frequency band signal by using the optimized ensemble model, determine that a detected signal is a spoofing signal when the output prediction label is 1, and determine that the detected signal is a real signal when the output prediction label is -1.

[0119] Optionally, the GNSS spoofing interference detection device further includes:

[0120] The first extracting sub-module is configured to calculate the carrier-to-noise ratio according to the GNSS receiver and the frequency band signal by using a carrier-to-noise ratio calculation formula, wherein the carrier-to-noise ratio calculation formula is as follows:

[0121]

[0122] wherein, is a carrier-to-noise ratio of the i th visible satellite at time t, is a power density of the frequency band signal of the i th visible satellite at time t, N d is a noise power density of the GNSS receiver at time t, P (i) is a power of the frequency band signal of the i th visible satellite at time t, B I is a bandwidth of the GNSS receiver, n(t) is a noise power of the GNSS receiver at time t, S (i)(t) is the signal power of the i-th visible satellite at time t, and L(t) is the transmission path loss at time t.

[0123] Optionally, the GNSS spoofing jamming detection device further comprises:

[0124] The second extraction submodule is configured to calculate the carrier phase of the GNSS receiver and the frequency band signal according to a carrier phase calculation formula, wherein the carrier phase calculation formula is:

[0125] φ (i) (t) = λ -1 (r(t) + c(δt u - δt (s) )-I(t) + T(t)) + N + ε φ

[0126] In the formula, φ (i) (t) is the carrier phase of the i-th visible satellite at time t, λ is the wavelength of the visible satellite, r(t) is the geometric distance between the visible satellite and the GNSS receiver at time t, c is the speed of light, δt u is the clock error of the GNSS receiver, δt (s) is the clock error of the visible satellite, I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, N is the total number of visible satellites, and ε φ is the sum of all carrier phase errors that cannot be accurately represented.

[0127] Optionally, the GNSS spoofing jamming detection device further comprises:

[0128] The third extraction submodule is configured to calculate the Doppler shift of the GNSS receiver and the frequency band signal according to a Doppler shift calculation formula, wherein the Doppler shift calculation formula is:

[0129]

[0130] In the formula, f d (i) is the Doppler shift of the i-th visible satellite, f r (i) is the receiving frequency of the i-th visible satellite, f (i) is the transmitting frequency of the i-th visible satellite, v is the running speed of the GNSS receiver, λ (i) is the wavelength of the i-th visible satellite, β is the incident angle of the frequency band signal, and c is the speed of light.

[0131] Optionally, the GNSS spoofing jamming detection device further comprises:

[0132] a fourth extracting sub-module, configured to calculate the pseudo-range between the GNSS receiver and the frequency band signal according to a pseudo-range calculation formula, wherein the pseudo-range calculation formula is:

[0133] ρ (i) (t) = r(t - τ, t) + c · (δt u (t) - δt (s) (t - τ)) + cI(t) + cT(t) + ε ρ

[0134] wherein μ (i) (t) is the pseudo-range of the ith visible satellite at time t, τ is the actual propagation time of the frequency band signal, r(t - τ, t) is the geometric distance between the visible satellite at time t - τ and the GNSS receiver at time t, c is the speed of light, δt u (t) is the clock error of the GNSS receiver at time t, δt (s) (t - τ) is the clock error of the visible satellite at time (t - τ), I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, and ε ρ is the sum of all pseudo-range errors that cannot be accurately represented.

[0135] Optionally, the GNSS spoofing jamming detection device further comprises:

[0136] a fifth extracting sub-module, configured to calculate the inter-frequency deviation of the carrier-to-noise ratio, the carrier phase, the Doppler shift and the pseudo-range in the first frequency band signal and the second frequency band signal according to an inter-frequency deviation calculation formula, wherein the inter-frequency deviation calculation formula is:

[0137]

[0138] wherein, is the inter-frequency deviation of the carrier-to-noise ratio of the ith visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, is the carrier-to-noise ratio of the ith visible satellite in the first frequency band signal L1 at time t, is the carrier-to-noise ratio of the ith visible satellite in the second frequency band signal L2 at time t, is the inter-frequency deviation of the carrier phase of the ith visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, φ (i)L1 (t) is the carrier phase of the ith visible satellite in the first frequency band signal L1 at time t, (i) L2 (t) is the carrier phase of the ith visible satellite in the second frequency band signal L2 at time t, a frequency interval deviation of a Doppler frequency shift of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at the t moment, a Doppler frequency shift of the i-th visible satellite in the first frequency band signal L1 at the t moment, a Doppler frequency shift of the i-th visible satellite in the second frequency band signal L2 at the t moment, a frequency interval deviation of a pseudo-range of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at the t moment, a pseudo-range of the i-th visible satellite in the first frequency band signal L1 at the t moment, a pseudo-range of the i-th visible satellite in the second frequency band signal L2 at the t moment.

[0139] Optionally, the GNSS spoofing interference detection device further comprises:

[0140] a detection sub-module, configured to detect the first frequency band signal and the second frequency band signal by using the optimized integrated model, and output a prediction label, wherein the prediction label comprises a first binary hypothesis and a second binary hypothesis, the first binary hypothesis represents -1, and the second binary hypothesis represents 1;

[0141] wherein the first binary hypothesis is:

[0142]

[0143] wherein H0 represents the first binary hypothesis, T i [n] is a detection statistic of the i-th visible satellite in the n-th detected signal, is a real signal of the i-th visible satellite in the n-th detected signal, and ζ[n] is channel noise of the n-th detected signal;

[0144] wherein the second binary hypothesis is:

[0145]

[0146] wherein H1 represents the second binary hypothesis, is a spoofing signal of the i-th visible satellite in the n-th detected signal.

[0147] The GNSS spoofing interference detection device provided by the embodiment reduces data redundancy and operation time, is easy to implement and has low complexity, has low requirements on the receiver, greatly reduces the equipment cost of the receiver, and has a wider application scenario.

[0148] The embodiment of the present disclosure further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the GNSS spoofing interference detection method described in the embodiment 1 when executing the computer program, which will not be repeated here.

[0149] The embodiment of the present disclosure further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the GNSS spoofing interference detection method described in the embodiment 1, which will not be repeated here.

[0150] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are only schematic, for example, the flow charts and structural diagrams in the drawings show the possible implementation architectures, functions and operations of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flow charts or structural diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that, in alternative implementation manners, the functions noted in the blocks can also occur in different orders from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flow chart, and the combination of blocks in the structural diagram and / or flow chart, can be implemented by a dedicated hardware-based system for executing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0151] In addition, each functional module or unit in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0152] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0153] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method of GNSS spoofing jamming detection, characterized in that, The method comprises: receiving a frequency band signal from a radio frequency front end by a GNSS receiver, and capturing a plurality of visible satellites from the frequency band signal, wherein the frequency band signal comprises a first frequency band signal and a second frequency band signal; extracting observation quantities of each of the visible satellites from the frequency band signal, the observation quantities comprising first observation quantities extracted from the first frequency band signal and second observation quantities extracted from the second frequency band signal, and calculating inter-frequency biases of each of the visible satellites according to the first observation quantities and the second observation quantities, the inter-frequency biases comprising carrier-to-noise ratios, carrier phases, Doppler shifts and pseudo ranges; combining the inter-frequency biases of each of the visible satellites, and performing mean-variance normalization preprocessing on the combined inter-frequency biases to obtain feature data, training an ensemble learning classifier through the feature data to obtain an intermediate ensemble model; judging whether a spoofing signal exists in the frequency band signal by using the intermediate ensemble model, outputting a prediction label, adjusting the intermediate ensemble model according to the prediction label and a true label to obtain an optimized ensemble model; detecting the frequency band signal by using the optimized ensemble model, determining that a detected signal is a spoofing signal when the output prediction label is 1, and determining that the detected signal is a true signal when the output prediction label is -1.

2. The GNSS spoofing jamming detection method of claim 1, wherein, The observation quantities comprise carrier-to-noise ratios, and the extracting of the observation quantities of each of the visible satellites from the frequency band signal comprises: calculating the carrier-to-noise ratios according to the GNSS receiver and the frequency band signal by using a carrier-to-noise ratio calculation formula, wherein the carrier-to-noise ratio calculation formula is: wherein is the carrier-to-noise ratio of the i-th visible satellite at time t, is the power density of the i-th visible satellite's band at time t, N d (t) is the noise power density of the GNSS receiver at time t, P (i) (t) is the power of the i-th visible satellite's band at time t, B I is the bandwidth of the GNSS receiver, n(t) is the noise power of the GNSS receiver at time t, S (i) (t) is the signal power transmitted by the i-th visible satellite at time t, L(t) is the transmission path loss at time t.

3. The GNSS spoofing jamming detection method of claim 2, wherein, The observation quantities comprise carrier phases, and the extracting of the observation quantities of each of the visible satellites from the frequency band signal further comprises: calculating the carrier phases according to the GNSS receiver and the frequency band signal by using a carrier phase calculation formula, wherein the carrier phase calculation formula is: φ (i) (t) = λ -1 (r(t) + c(δt u - δt (s) )- I(t) + T(t)) + N + ε φ wherein φ (i) (t) is the carrier phase of the i-th visible satellite at time t, λ is the wavelength of the visible satellite, r(t) is the geometric distance between the visible satellite and the GNSS receiver at time t, c is the speed of light, δt u is the clock error of the GNSS receiver, δt (s) is the clock error of the visible satellite, I(t) is the ionosphere delay of the atmospheric propagation delay at time t, T(t) is the troposphere delay of the atmospheric propagation delay at time t, N is the total number of visible satellites, ε φ is the sum of all carrier phase errors that cannot be accurately represented.

4. The GNSS spoofing jamming detection method of claim 3, wherein, The observation quantities comprise Doppler shifts, and the extracting of the observation quantities of each of the visible satellites from the frequency band signal further comprises: calculating the Doppler shifts according to the GNSS receiver and the frequency band signal by using a Doppler shift calculation formula, wherein the Doppler shift calculation formula is: where f d (i) is the Doppler shift of the i-th visible satellite, f r (i) is the reception frequency of the i-th visible satellite, f (i) is the transmission frequency of the i-th visible satellite, v is the running speed of the GNSS receiver, λ (i) is the wavelength of the i-th visible satellite, β is the incidence angle of the frequency band signal, and c is the speed of light.

5. The GNSS spoofing jamming detection method of claim 4, wherein, The observation quantities comprise pseudo ranges, and the extracting of the observation quantities of each of the visible satellites from the frequency band signal further comprises: calculating the pseudo ranges according to the GNSS receiver and the frequency band signal by using a pseudo range calculation formula, wherein the pseudo range calculation formula is: p (i) (t) = r(t - τ, t) + c - (δt u (t) - δt (s) (t - τ)) + cI(t) + cT(t) + ε ρ wherein ρ (i) (t) is the pseudo-range of the i-th visible satellite at time t, τ is the actual propagation time of the signal in the frequency band, r(t-τ, t) is the geometric distance between the position of the visible satellite at time t-τ and the GNSS receiver at time t, c is the speed of light, δt u (t) is the clock bias of the GNSS receiver at time t, δt (s) (t-τ) is the clock bias of the visible satellite at time (t-τ), I(t) is the ionospheric delay of the atmospheric propagation delay at time t, T(t) is the tropospheric delay of the atmospheric propagation delay at time t, ε ρ is the sum of all pseudo-range errors that cannot be accurately represented.

6. The GNSS spoofing jamming detection method of claim 5, wherein, The calculating of the inter-frequency biases of each of the visible satellites according to the first observation quantities and the second observation quantities comprises: calculating inter-frequency biases of the carrier-to-noise ratios, the carrier phases, the Doppler shifts and the pseudo ranges in the first frequency band signal and the second frequency band signal according to an inter-frequency bias calculation formula, wherein the inter-frequency bias calculation formula is: In the formula, is the inter-frequency deviation of the carrier-to-noise ratio of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, is the carrier-to-noise ratio of the i-th visible satellite in the first frequency band signal L1 at time t, is the carrier-to-noise ratio of the i-th visible satellite in the second frequency band signal L2 at time t, is the inter-frequency deviation of the carrier phase of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, φ (i) L1 (t) is the carrier phase of the i-th visible satellite in the first frequency band signal L1 at time t, φ (i) L2 (t) is the carrier phase of the i-th visible satellite in the second frequency band signal L2 at time t, is the inter-frequency deviation of the Doppler frequency shift of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, is the Doppler frequency shift of the i-th visible satellite in the first frequency band signal L1 at time t, is the Doppler frequency shift of the i-th visible satellite in the second frequency band signal L2 at time t, is the inter-frequency deviation of the pseudo-range of the i-th visible satellite in the first frequency band signal L1 and the second frequency band signal L2 at time t, is the pseudo-range of the i-th visible satellite in the first frequency band signal L1 at time t, is the pseudo-range of the i-th visible satellite in the second frequency band signal L2 at time t.

7. The GNSS spoofing jamming detection method of claim 1, wherein, The detecting of the frequency band signal by using the optimized ensemble model comprises: The first frequency band signal and the second frequency band signal are detected using the optimized ensemble model, and a prediction label is output, the prediction label including a first binary hypothesis and a second binary hypothesis, the first binary hypothesis representing -1, and the second binary hypothesis representing 1. The first binary hypothesis is: wherein H0is the first binary hypothesis, T i [n] is the detection statistic of the i-th visible satellite in the n-th detected signal, is the true signal of the i-th visible satellite in the n-th detected signal, and ζ[n] is the channel noise of the n-th detected signal. The second binary hypothesis is: where H1 is the second binary hypothesis, is the spoofed signal for the i-th visible satellite in the n-th detected signal.

8. A GNSS spoofing jamming detection apparatus characterized by, The device includes: The receiving module receives frequency band signals from a radio frequency front end through a GNSS receiver and captures a plurality of visible satellites from the frequency band signals, wherein the frequency band signals include a first frequency band signal and a second frequency band signal; The extraction module extracts observations of each of the visible satellites from the frequency band signals, the observations including first observations extracted from the first frequency band signal and second observations extracted from the second frequency band signal, and calculates inter-frequency biases of each of the visible satellites according to the first observations and the second observations, the inter-frequency biases including carrier-to-noise ratio, carrier phase, Doppler shift, and pseudo-range; The training module combines the inter-frequency biases of each of the visible satellites, and performs mean-variance normalization preprocessing on the combined inter-frequency biases to obtain feature data, trains an ensemble learning classifier using the feature data to obtain an intermediate ensemble model; The judging module determines whether a spoofing signal exists in the frequency band signals using the intermediate ensemble model, outputs a prediction label, adjusts the intermediate ensemble model according to the prediction label and a true label to obtain an optimized ensemble model; The detection module detects the frequency band signals using the optimized ensemble model, determines that a detected signal is a spoofing signal when the output prediction label is 1, and determines that the detected signal is a true signal when the output prediction label is -1.

9. A computer device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the GNSS spoofing interference detection method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the GNSS spoofing interference detection method in any one of claims 1-7.

Images