An adaptive navigation jamming optimization method based on time sequence convolution neural network

Abstract

The application provides an adaptive navigation jamming optimization method based on a time sequence convolution neural network, and relates to the field of communication, and the method comprises the following steps: collecting navigation signals transmitted by a target satellite to a target receiver in real time, and performing feature analysis to obtain feature information of the navigation signals; when the navigation signals are locked by the target receiver, a first jamming signal is generated until the target receiver loses the lock on the navigation signals; when the navigation signals are not locked by the target receiver, a second jamming signal is generated; the feature information is input into a preset signal parameter prediction model to predict signal parameters of the navigation signals; the signal parameters of the jamming signals are adjusted based on the prediction result, and then the jamming signals are sent to the target receiver. Through the above method, the whole process from cutting off communication to misleading the target is realized, the flexibility and adaptability of the jamming are enhanced, the success rate and comprehensive efficiency of the jamming are improved, and the redundant consumption of the jamming resources is significantly reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a navigation interference optimization method based on a time sequence convolutional neural network. BACKGROUND

[0002] With the development of navigation technology, navigation interference technology has been widely used. Interference systems are deployed near key civilian places such as airports and nuclear power plants to prevent unauthorized drones from invading or malicious attacks. In large-scale activities such as concerts and sports events, drones cannot fly normally under navigation interference, which can prevent illegal photography or disrupt the order of activities. With the continuous development of navigation positioning, diversified anti-interference means and enhanced mobile connection technologies, the demand for navigation interference optimization technology is increasing.

[0003] However, the existing interference optimization method mainly interferes with specific signals, and has problems such as single interference dimension, poor real-time parameter setting, and slow convergence speed of interference optimization algorithm. Especially with low-orbit satellites gradually becoming the main force of positioning, navigation and timing services, their strong anti-interference ability due to strong signal power, narrow beam and wide coverage, etc. This leads to a significant decline in the effectiveness of traditional interference optimization methods. SUMMARY

[0004] In order to solve the problems of single interference mode, poor real-time parameter setting and other problems in the prior art, and improve the interference effect, the present application proposes a navigation interference optimization method based on a time sequence convolutional neural network, the method comprising:

[0005] Step 1, real-time collection of navigation signals transmitted by a target satellite to a target receiver, and feature analysis to obtain feature information of the navigation signals;

[0006] Step 2, determining whether the navigation signals are locked by the target receiver;

[0007] Step 3, when the navigation signals are locked by the target receiver, generating a first interference signal until the target receiver loses lock on the navigation signals; wherein the first interference signal is used to construct a navigation signal denial environment;

[0008] Step 4, when the navigation signals are not locked by the target receiver, generating a second interference signal; wherein the second interference signal is used to cause the target receiver to produce an erroneous positioning;

[0009] Step 5, inputting the feature information into a preset signal parameter prediction model to predict the signal parameters of the navigation signals, and obtaining a parameter prediction result of the navigation signals; wherein the signal parameter prediction model is built based on a time domain convolutional neural network;

[0010] Step 6, based on the parameter prediction result, adjusting the signal parameter of the first interference signal or the second interference signal, and then sending the adjusted first interference signal or the second interference signal to the target receiver.

[0011] Optionally, the second interference signal includes a retransmission interference signal, and the step 4 includes:

[0012] Step 41, when the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal belongs to an unknown state, performing signal transformation processing on the navigation signal to obtain a retransmission interference signal.

[0013] Optionally, the retransmission interference signal includes a direct retransmission signal; and the step 41 includes:

[0014] When the navigation signal is not locked by the target receiver and both the structure of the pseudo-random code included in the navigation signal and the modulation mode of the navigation signal belong to an unknown state, performing delay processing on the navigation signal to obtain a direct retransmission signal.

[0015] Optionally, the retransmission interference signal includes a partial reconstruction retransmission signal; and the step 41 includes:

[0016] When the navigation signal is not locked by the target receiver, the structure of the pseudo-random code included in the navigation signal belongs to an unknown state, and the modulation mode of the navigation signal belongs to a known state, performing symbol domain-based processing on the navigation signal to obtain a partial reconstruction retransmission signal.

[0017] Optionally, the symbol domain-based processing includes at least one of superposition processing, replacement processing, and phase flip processing.

[0018] Optionally, the second interference signal includes a pseudo-low-orbit satellite signal.

[0019] The step 4 includes:

[0020] When the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal belongs to a known state, performing analysis on the navigation signal to obtain an analysis result.

[0021] Generating a pseudo-low-orbit satellite signal according to the analysis result and the structure of the pseudo-random code; the pseudo-low-orbit satellite signal is used to be locked by the target receiver in a case where the target receiver does not lock the navigation signal, and further used to send error position information to the target receiver.

[0022] Optionally, the type of the first interference signal includes at least one of narrow-band interference, wide-band noise interference, and sweep-frequency interference.

[0023] Optionally, the number of jamming machines for generating the jamming signals is at least two, and the jamming signal received by the target receiver is a superposition signal of jamming signals respectively emitted by the at least two jamming machines.

[0024] Optionally, the parameter prediction result comprises a predicted power and a predicted frequency.

[0025] The step 6 comprises:

[0026] When the jamming signal is the first jamming signal, the power of the first jamming signal is adjusted so that the power of the adjusted first jamming signal is greater than the predicted power, and then the adjusted first jamming signal is sent to the target receiver.

[0027] When the jamming signal is the second jamming signal, the frequency of the second jamming signal is adjusted to the predicted frequency, and then the adjusted second jamming signal is sent to the target receiver.

[0028] Optionally, the signal parameter prediction model is trained based on signal parameter residual data, wherein the signal parameter residual data is represented as the difference between the real signal parameter and the predicted signal parameter based on polynomial regression.

[0029] The present application has the following advantages:

[0030] The present application provides an adaptive navigation jamming optimization method based on a time sequence convolutional neural network. The navigation signal is collected in real time, and the feature information of the navigation signal is obtained through feature analysis. Then, it is judged whether the navigation signal is locked by the target receiver. When the navigation signal is locked by the target receiver, a first jamming signal for constructing a navigation signal denial environment is generated until the target receiver loses the lock on the navigation signal. When the navigation signal is not locked by the target receiver, a second jamming signal for making the target receiver produce an error positioning is generated. Then, the jamming signal is adjusted, the feature information is input into a preset signal parameter prediction model based on a time sequence convolutional neural network to predict the signal parameters of the navigation signal, and the signal parameters of the jamming signal are adjusted according to the parameter prediction result, and then the adjusted jamming signal is sent.

[0031] Therefore, at the level of interference method, the application completes the whole process from cutting off communication to deceiving the target by constructing a navigation signal denial environment by suppression jamming and misleading the flexible switching of the target receiver by deception jamming, which breaks through the limitation of traditional single mode, enhances the flexibility and adaptability of jamming, and improves the success rate and comprehensive effectiveness of jamming through the cooperation of different jamming modes; at the level of parameter regulation, the parameter prediction model built by the time sequence convolutional neural network realizes the fine dynamic regulation and real-time regulation of the parameters of the jamming signal, which improves the success rate of jamming while significantly reduces the redundant consumption of interference resources. BRIEF DESCRIPTION OF DRAWINGS

[0032] The above and / or additional aspects and advantages of the application will become apparent and be readily understood from the following description, taken in conjunction with the following drawings, in which:

[0033] Figure 1 A step flow chart of an adaptive navigation jamming optimization method based on a time sequence convolutional neural network provided for an embodiment of the application is shown in Figure 1.

[0034] Figure 2 A step flow chart of another adaptive navigation jamming optimization method based on a time sequence convolutional neural network provided for an embodiment of the application is shown in Figure 2.

[0035] Figure 3 A structural schematic diagram of a residual block of a time sequence convolutional neural network provided for an embodiment of the application is shown in Figure 3. DETAILED DESCRIPTION

[0036] Embodiments of the application are described in detail below, examples of which are shown in the accompanying drawings, in which the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are exemplary and are intended to explain the application, and cannot be understood as a limitation of the application.

[0037] Referring to Figure 1 A step flow chart of an adaptive navigation jamming optimization method based on a time sequence convolutional neural network provided for an embodiment of the application is shown in Figure 1, the method comprising:

[0038] Step 1, real-time acquisition of the navigation signal transmitted by the target satellite to the target receiver is performed, and feature analysis is performed to obtain the feature information of the navigation signal.

[0039] The characteristic information of the navigation signal includes, but is not limited to, spectrum characteristic information, Doppler shift information, and power baseline and the like environmental characteristics. Specifically, the satellite downlink signal, i.e., the navigation signal transmitted by the target satellite to the target receiver, can be collected by the environmental perception device, and characteristic analysis is performed to realize environmental characteristic monitoring of the navigation signal. Different interference modes are determined according to different navigation signals and environmental characteristics, different interference signals are generated, and then multi-dimensional intelligent interference of the navigation signal is realized.

[0040] Step 2, determining whether the navigation signal is locked by the target receiver.

[0041] The receiver locking the navigation signal means that the receiver successfully establishes a stable connection with the signal of the target navigation satellite, can continuously decode the navigation information, and thus calculates the position, speed and time information. By determining whether the navigation signal is locked by the target receiver, the targeted interference mode under different conditions is determined, the success rate of interference is ensured to be improved, the redundant consumption of interference resources is significantly reduced, and the interference effect is improved.

[0042] In the embodiment of the application, whether the navigation signal is locked by the target receiver can be determined by electronic reconnaissance, for example, by collecting data output by the target receiver and signals transmitted by the radio frequency front end; or by judging the behavior of the device to which the target receiver belongs. For example, if the receiver in the unmanned aerial vehicle loses the lock on the navigation signal, the unmanned aerial vehicle may stop moving or force landing.

[0043] Step 3, when the navigation signal is locked by the target receiver, a first interference signal is generated until the target receiver loses the lock on the navigation signal; wherein the first interference signal is used to construct a navigation signal denial environment.

[0044] When the navigation signal is locked by the target receiver, the interference mode is determined to be a blanking interference mode, and a blanking interference signal, i.e., a first interference signal, is generated. The type of the first interference signal includes at least one of narrowband interference, wideband noise interference and sweep frequency interference. The blanking interference mode constructs a navigation signal denial environment by interference of multiple different signals, so that the target receiver gradually loses the lock on the navigation signal.

[0045] As an example, the first interference signal can be expressed as follows:

[0046] , (1)

[0047] wherein, is the number of jammers; represents the The noise envelope of the first interference signal of the nth type generated by the jammer obeys the Rayleigh distribution; Indicates the The interference carrier frequency of each jammer can be adjusted in real time according to environmental observation data, and can cover multiple frequency bands at the same time; Indicates the The random phase of the jammer; Re ( ) represents a function for extracting the real part of a complex number; is the imaginary number symbol;

[0048] Step 4: When the navigation signal is not locked by the target receiver, generate a second interference signal; wherein the second interference signal is used to cause the target receiver to generate an erroneous positioning.

[0049] When the target receiver loses lock on to the navigation signal, a second jamming signal containing erroneous position information is generated, deceiving the target receiver into mispositioning. For example, the second jamming signal can be generated by delaying, symbol flipping, or overlaying the navigation signal. Alternatively, the second jamming signal can be generated by analyzing the navigation signal, forcing the target receiver to lock onto the second jamming signal even when it is not locked on to the navigation signal. The jamming signal then continues to send erroneous position information to the target receiver, achieving navigation interference control.

[0050] By flexibly switching between suppressive jamming to create a navigation signal denial environment and deceptive jamming to mislead the target receiver, the entire process from communication interruption to target deception is achieved. This breaks through the limitations of traditional single-mode jamming, avoiding the blind spots of single-scale effects, enhancing the flexibility and adaptability of jamming, and synergizing different jamming methods to improve the success rate and overall effectiveness of jamming.

[0051] Step 5: Input the characteristic information into a preset signal parameter prediction model to predict the signal parameters of the navigation signal to obtain a parameter prediction result of the navigation signal; wherein the signal parameter prediction model is built based on a time domain convolutional neural network.

[0052] Signal parameters include, but are not limited to, power, frequency, Doppler shift, code phase, and other information. The signal parameter prediction model built on a time-domain convolutional neural network combines causal convolution with dilated convolution, enabling full-sequence parallel computing in modeling. This allows for efficient processing of navigation signal time series data and accurately captures the time-varying patterns of signal parameters.

[0053] As an example, the process of dilated causal convolution can be expressed as follows:

[0054] , (2)

[0055] in, represents the output of dilated causal convolution, d is a dilated factor used to control the sampling interval of the convolution kernel, is a convolution kernel weight, k is the size of the convolution kernel, is a convolution symbol; is a convolution input signal.

[0056] Step 6, based on the parameter prediction result, adjusting the signal parameters of the first interference signal or the second interference signal, and then sending the adjusted first interference signal or the second interference signal to the target receiver.

[0057] For different situations, different interference strategies are used to adjust the interference signal, which helps to improve the success rate of interference. Specifically, when the receiver locks the navigation signal, the interference signal generated by the jammer is the first interference signal, the purpose is to suppress the navigation signal through the covering interference, so that the target receiver loses the lock of the navigation signal, therefore, the power of the adjusted first interference signal is greater than the predicted power, for example, the difference between the power of the adjusted first interference signal and the predicted power is greater than 20dB, the specific value can be adjusted according to the actual situation; When the receiver loses the lock of the navigation signal, the interference signal generated by the jammer is the second interference signal, the purpose is to deliver false position information to the target receiver, and the target receiver must receive the second interference signal to deliver information, therefore, the frequency of the adjusted second interference signal is equal to the predicted frequency. Of course, in the actual interference process, only the frequency, power and other parameters may need to be adjusted, and other parameters can be determined according to the communication situation, which will not be described here.

[0058] The parameter prediction model built by the time sequence convolutional neural network is used to predict the parameters, and the interference signal is adjusted in real time based on the predicted parameters, realizing the transition of interference energy from static configuration to dynamic optimization, improving the interference success rate while significantly reducing the redundant consumption of interference resources.

[0059] In summary, the embodiment of the present application provides a self-adaptive navigation interference optimization method based on a time sequence convolutional neural network. The navigation signal is collected in real time, and the feature analysis is performed to obtain the feature information of the navigation signal, and then it is judged whether the navigation signal is locked by the target receiver. When the navigation signal is locked by the target receiver, the first interference signal for constructing the navigation signal rejection environment is generated until the target receiver loses the lock of the navigation signal, and when the navigation signal is not locked by the target receiver, the second interference signal for making the target receiver produce false positioning is generated. Then the interference signal is adjusted, the feature information is input into the signal parameter prediction model built based on the time sequence convolutional neural network, the signal parameters of the navigation signal are predicted, and the signal parameters of the interference signal are adjusted according to the parameter prediction result, and then the adjusted interference signal is sent.

[0060] Therefore, at the level of interference method, the embodiments of the present application complete the whole process from cutting off communication to deceiving the target by constructing a navigation signal denial environment by suppressing interference, misleading the flexible switching of the target receiver, breaking through the limitation of the traditional single mode, enhancing the flexibility and adaptability of interference, and improving the success rate and comprehensive effectiveness of interference through different interference modes.

[0061] Optionally, the second interference signal includes a repeating interference signal, and the step 4 includes:

[0062] Step 41, when the navigation signal is not locked by the target receiver, and the structure of the pseudo-random code included in the navigation signal belongs to an unknown state, performing signal transformation processing on the navigation signal to obtain a repeating interference signal.

[0063] Wherein, the pseudo-random code is a binary code sequence that looks like random noise but is actually determinable and repeatedly produced, which is used for synchronization of navigation signals and receivers, calculation of pseudo-range, etc. The signal transformation includes but is not limited to delay processing, symbol flipping, replacement, phase flipping, etc.

[0064] Referring to Figure 2 , another step flow chart of the adaptive navigation interference optimization method based on the time sequence convolutional neural network provided by the embodiments of the present application is given. Among them, whether the receiver locks the navigation signal and whether the structure of the pseudo-random code belongs to the known state are the intelligent judgment links, which realizes the whole process interference from suppressing interference to "deception" interference, and effectively improves the interference effect.

[0065] In order to determine whether the structure of the pseudo-random code included in the navigation belongs to the known state, it is mainly determined according to whether the structure of the pseudo-random code is public. If the pseudo-random code is public, it can be determined that the structure of the pseudo-random code included in the navigation signal belongs to the known state, otherwise it is unknown. Of course, the structure of the pseudo-random code can also be obtained in a legal way by analysis, such as teaching and experimental purposes, etc., which is not described herein.

[0066] In the case that the structure of the pseudo-random code belongs to the unknown state, although the target receiver cannot directly lock the interference signal, the interference strategy can be adjusted to the retransmission interference mode, that is, the signal transformation is directly performed on the collected navigation signal to obtain the retransmission interference signal, so that the position information recorded in the navigation signal, such as the system time, the satellite orbit parameter and the code phase used for calculating the pseudo-range, is changed, so that the target receiver produces an error positioning based on the error position information, and the interference effect is achieved.

[0067] Optionally, the retransmission interference signal comprises a direct retransmission signal; and the step 41 comprises:

[0068] Step 411, when the navigation signal is not locked by the target receiver, and the structure of the pseudo-random code included in the navigation signal and the modulation mode of the navigation signal both belong to the unknown state, performing delay processing on the navigation signal to obtain a direct retransmission signal.

[0069] As shown in Figure 2 According to whether the modulation mode of the navigation signal is known, the retransmission interference mode can be divided into two interference strategies, that is, the direct retransmission mode and the partial reconstruction retransmission mode. The way of judging whether the modulation mode is known is the same as that of the pseudo-random code, which is not described herein.

[0070] Corresponding to step 411, that is, when the navigation signal is not locked by the target receiver, and the structure of the pseudo-random code included in the navigation signal and the modulation mode of the navigation signal both belong to the unknown state, only the delay processing is performed on the navigation signal to change the pseudo-range to produce a positioning error, so that the navigation interference effect is achieved.

[0071] Optionally, the retransmission interference signal comprises a partial reconstruction retransmission signal; and the step 41 comprises:

[0072] Step 412, when the navigation signal is not locked by the target receiver, the structure of the pseudo-random code included in the navigation signal belongs to the unknown state, and the modulation mode of the navigation signal belongs to the known state, performing symbol domain-based processing on the navigation signal to obtain a partial reconstruction retransmission signal.

[0073] Corresponding to step 412, when the navigation signal is not locked by the target receiver, the structure of the pseudo-random code included in the navigation signal belongs to the unknown state, and the modulation mode of the navigation signal belongs to the known state, as Figure 2As shown, the interference adjustment strategy is a partial reconstruction forwarding mode, the collected navigation signal is processed based on a symbol domain to generate an interference symbol set and reconstruct a time domain waveform. The partial reconstruction forwarding signal thus obtained changes the position information carried in the original navigation signal and produces a stronger interference effect compared with the direct forwarding signal. Of course, in the partial reconstruction forwarding mode, time delay processing can also be performed on the basis of the symbol domain-based processing of the signal to deepen the error degree of the position information received by the target receiver.

[0074] Optionally, the symbol domain-based processing includes at least one of superposition processing, replacement processing, and phase inversion processing.

[0075] Optionally, the second interference signal includes a pseudo low-orbit satellite signal.

[0076] The step 4 includes:

[0077] Step 421, when the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal belongs to a known state, the navigation signal is parsed to obtain a parsing result.

[0078] Step 422, generating a pseudo low-orbit satellite signal according to the parsing result and the structure of the pseudo-random code; the pseudo low-orbit satellite signal is used to be locked by the target receiver in the case that the target receiver does not lock the navigation signal, and further sends error position information to the target receiver.

[0079] It can be understood that the satellite signal contains a unique pseudo-random (PRN, Pseudo-Random Noise Code) code, and a receiver will generate a local PRN code copy identical to the target satellite. The receiver locks the signal by correlating the received signal with the locally generated PRN code. The cross-correlation operation is used to measure the similarity of two signals at different time offsets. When the local code is completely aligned with the pseudo-random code in the navigation signal, i.e. time synchronization, the correlation reaches a maximum value, producing a sharp peak, which is the correlation peak. The receiver searches for the correlation peak in the received signal by sliding the local code. Once a correlation peak exceeding a threshold is found, the receiver confirms that the satellite signal is successfully locked, i.e. synchronized with the satellite signal, and can continuously receive information in the satellite signal.

[0080] Based on the above principle of receiver locking satellite signal, as shown in FIG. 2, the interference adjustment strategy is a partial reconstruction forwarding mode. Figure 2When the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal belongs to a known state, the interference strategy can be adjusted to a generated interference mode, i.e. an interference signal, i.e. a pseudo-low-orbit satellite signal, which can be locked by the target receiver is generated by using the known structure of the pseudo-random code and the analyzed parameter information of the navigation signal. After the target receiver locks the pseudo-low-orbit satellite signal, the jammer can continuously send error information, so that the target receiver continuously solves errors and produces error positioning, effectively enhancing the interference effect.

[0081] As an example, the pseudo-low-orbit satellite signal can be expressed according to the following formula:

[0082] , (3)

[0083] wherein, represents the number of target satellites, represents the amplitude of the pseudo-low-orbit satellite signal generated by the i th jammer, represents the code phase of the pseudo-low-orbit satellite signal generated by the i th jammer.

[0084] represents the bit stream of the pseudo-low-orbit satellite signal generated by the i th jammer according to the analysis result of the navigation signal emitted by the k th target satellite; represents the pseudo-random code of the pseudo-low-orbit satellite signal generated by the i th jammer according to the structure of the pseudo-random code in the navigation signal emitted by the k th target satellite; represents the signal frequency of the pseudo-low-orbit satellite signal generated by the i th jammer according to the analysis result of the navigation signal emitted by the k th target satellite; represents the initial phase of the pseudo-low-orbit satellite signal generated by the i th jammer according to the analysis result of the navigation signal emitted by the k th target satellite.

[0085] Before the target receiver locks the pseudo-low-orbit satellite signal, it is ensured that the pseudo-low-orbit satellite signal generated by the jammer is the same as the signal structure, modulation mode, pseudo-random code and code phase of the navigation signal, so that when the receiver slides to search for the correlation peak, the receiver will preferentially lock the correlation peak generated by the pseudo-low-orbit satellite signal and the local code of the receiver, and then lock the pseudo-low-orbit satellite signal. After the pseudo-low-orbit satellite signal is locked by the target receiver, the code phase, carrier phase, part of the navigation text, bit stream and other information of the pseudo-low-orbit satellite signal can be gradually changed, so that the target receiver continuously produces error positioning.

[0086] Optionally, the number of jammers for generating the interference signal is at least two, and the interference signal received by the target receiver is a superimposed signal of the interference signals emitted by the at least two jammers.

[0087] Taking the retransmission interference signal as an example, the interference signal received by the target receiver can be expressed as:

[0088] , (4)

[0089] wherein, represents the amplitude of the retransmission interference signal transmitted by the i th jammer, represents the retransmission signal obtained after the navigation signal is delayed for a time delay, represents the retransmission signal obtained after the navigation signal is delayed for a time delay, represents the time delay when the i th jammer delays the navigation signal.

[0090] Optionally, the parameter prediction result includes a predicted power and a predicted frequency.

[0091] The step 6 includes:

[0092] When the interference signal is a first interference signal, the power of the first interference signal is adjusted so that the power of the adjusted first interference signal is greater than the predicted power, and then the adjusted first interference signal is sent to the target receiver.

[0093] When the interference signal is a second interference signal, the frequency of the second interference signal is adjusted to the predicted frequency, and then the adjusted second interference signal is sent to the target receiver.

[0094] Specifically, as shown in Figure 2 , when the interference signal is a first interference signal, i.e., the interference strategy is a suppression interference mode, after generating different types of interference signals, the power of the first interference signal is adjusted so that the power of the adjusted first interference signal is greater than the predicted power, and the frequency can also be adjusted according to the actual situation of the communication environment, equipment, etc., and then the adjusted first interference signal is sent to the target receiver until the target receiver loses the lock on the navigation signal.

[0095] When the interference signal is a second interference signal, taking a pseudo-low-orbit satellite signal as an example, the frequency of the pseudo-low-orbit satellite signal is adjusted to the predicted frequency, and the power of the pseudo-low-orbit satellite signal can also be adjusted so that the power of the adjusted pseudo-low-orbit satellite signal is greater than the predicted power, so that the receiver will first lock the larger correlation peak generated by the pseudo-low-orbit satellite signal when slidingly searching for the correlation peak, thereby improving the lock rate of the target receiver on the pseudo-low-orbit satellite signal.

[0096] In addition, as shown in Figure 2As shown, for the second interference signal including the forwarding interference signal and the pseudo low-orbit satellite signal, the parameter prediction result can be adjusted, and the present application does not repeat here. Moreover, the parameter prediction result includes but is not limited to predicted power, predicted frequency, predicted code phase, predicted Doppler shift and other signal parameters. According to the parameter prediction result and the type of the interference signal, the adjusted interference signal is sent to the target receiver to make the receiver solve the error and produce the error positioning.

[0097] Optionally, the signal parameter prediction model is trained based on signal parameter residual data; wherein the signal parameter residual data is represented as the difference between the real signal parameter and the predicted signal parameter based on polynomial regression.

[0098] Reference Figure 3 A structural diagram of a residual block of a time sequence convolutional neural network provided by an embodiment of the present application is given. Wherein, represents the output of the i-th residual block, represents the input of the i-1-th residual block, is the input of the model, representing a group of sequences composed of the difference between the real signal parameter and the predicted signal parameter based on polynomial regression. represents a group of discrete sequences from 1 to T, 1 The signal parameter residual data includes but is not limited to power residual data and frequency residual data.

[0099] In the residual block structure shown, Figure 3 The first layer uses an expanded causal convolution to expand the time sequence receptive field, and captures long-range dependencies through an interval sampling mechanism. Under the premise of keeping the convolution kernel size and network depth constant, increasing the expansion factor can expand the input interval covered by the top layer of neurons, so that the limited level network can capture a larger range of historical information. In this way, without expanding the size of the convolution kernel or increasing the network depth, the problems of gradient dispersion and parameter redundancy in deep networks can be effectively avoided. The second layer further deepens the feature abstraction using an expanded causal convolution, and weight normalization is embedded between the two layers to decompose the convolution weight vector, accelerating the convergence of the model.

[0100] After each layer of convolution and weight normalization, a nonlinear activation function is sequentially connected to introduce nonlinear representation capability. After the activation layer, a channel-level regularization strategy is implemented: during the training process, the complete channel of the feature map is randomly set to zero, forcing the network to build robust feature redundancy. To solve the problem of input and output tensor dimension mismatch, the module introduces a 1x1 convolution to map the channel dimension of the original input, ensuring that the tensor addition operation in the residual connection can be executed.

[0101] In the signal parameter prediction model training process, the time series convolutional neural network parameters can be updated through back propagation to minimize the residual prediction error. The Adam optimizer is used to make the training converge quickly through momentum and adaptive learning rate, reduce the training time, improve the generalization ability, avoid overfitting, and at the same time, can alleviate the problem of gradient vanishing and explosion.

[0102] Specifically, taking the power residual data as an example, the power data of the real satellite signal on the continuous time sequence is taken as the training set. The long-term trend of the sequence is extracted by polynomial regression, and the residual is taken as the short-term fluctuation feature input into the time series convolutional neural network.

[0103] The small range window data is obtained from the training set, and the following formula is defined:

[0104] , (5)

[0105] wherein, represents the starting position of the window, is the window length, represents the power of the time series at time. By sliding window to construct the feature and the target value, a large number of training samples are generated, the data diversity is increased, the risk of overfitting is reduced, and batch parallel operation is facilitated, improving the operation efficiency.

[0106] Using the window data, an n-order function is fitted, and the polynomial regression function is represented as:

[0107] , (6)

[0108] , (7)

[0109] wherein, represents the predicted power of the time series at t, represents the coefficient of n power; represents the Vandermonde matrix, each row corresponds to the time point of the sliding window, and each column corresponds to the power of the polynomial basis function. Trend fitting is a pre-processing of data, which can reduce the data complexity, reduce the model burden, and improve the robustness of the model to abnormal values.

[0110] Based on formulas (5)-(7), the difference between the predicted value and the real value of the polynomial regression function is obtained, and the power residual is:

[0111] , (8)

[0112] wherein, represents the next time real value at the end of the window, represents the power prediction value at the next time at the end of the window. The power residual data is constituted by a set of discrete power residual data from 1 to T.

[0113] Optionally, after step 6, the method further comprises:

[0114] The interference bit error rate is calculated based on the following formula to measure the reliability of the method described in the embodiments of the application:

[0115] , (9)

[0116] wherein, denotes the interference bit error rate, denotes the bit error rate function; denotes the amplitude of the true signal; denotes the noise power spectral density; denotes the amplitude of the interference signal;

[0117] The root mean square error and the mean absolute percentage error are calculated based on the following formula to quantify the performance of the signal parameter prediction model:

[0118] , (10)

[0119] , (11)

[0120] wherein, MAPE denotes the mean absolute percentage error, and RMSE denotes the root mean square error, denotes the true value of the navigation signal at time , and denotes the predicted value of the navigation signal at time .

[0121] In addition, the terms "first", "second" are only for the purpose of description, 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 application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified.

[0122] Although the embodiments of the application have been shown and described above, it should be understood that the above-described embodiments are exemplary and cannot be understood as limiting the application, and those of ordinary skill in the art can make changes, modifications, replacements and variations to the above-described embodiments without departing from the principles and purposes of the application within the scope of the application.

Claims

1. An adaptive navigation interference optimization method based on temporal convolutional neural network, characterized in that: The method comprises: Step 1: collecting the navigation signal transmitted by the target satellite to the target receiver in real time, and performing feature analysis to obtain feature information of the navigation signal; Step 2, determining whether the navigation signal is locked by the target receiver; Step 3: When the navigation signal is locked by the target receiver, generating a first interference signal until the target receiver loses the lock on the navigation signal; wherein the first interference signal is used to establish a navigation signal denial environment; Step 4: When the navigation signal is not locked by the target receiver, generating a second interference signal; wherein the second interference signal is used to cause the target receiver to generate an erroneous positioning; Step 5: Inputting the characteristic information into a preset signal parameter prediction model to predict the signal parameters of the navigation signal to obtain parameter prediction results of the navigation signal; the signal parameter prediction model is built based on a time-domain convolutional neural network and is trained using signal parameter residual data; the parameter prediction results include predicted power and predicted frequency; the signal parameter residual data is represented as the difference between the true signal parameters and the predicted signal parameters obtained based on polynomial regression; Step 6: Based on the parameter prediction result, adjust the signal parameters of the first interference signal or the second interference signal, and then send the adjusted first interference signal or the second interference signal to the target receiver. Specifically, when the interference signal is the first interference signal, adjust the power of the first interference signal so that the power of the adjusted first interference signal is greater than the predicted power, and then send the adjusted first interference signal to the target receiver; when the interference signal is the second interference signal, adjust the frequency of the second interference signal to the predicted frequency, and then send the adjusted second interference signal to the target receiver.

2. The method according to claim 1, characterized in that The second interference signal includes a forwarding interference signal, and step 4 includes: Step 41: When the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal is in an unknown state, performing signal conversion processing on the navigation signal to obtain a forwarding interference signal.

3. The method according to claim 2, characterized in that The forwarding interference signal includes a directly forwarded signal; and step 41 includes: When the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal and the modulation mode of the navigation signal are both in an unknown state, delay processing is performed on the navigation signal to obtain a directly forwarded signal.

4. The method according to claim 2, characterized in that The forwarding interference signal includes a partially reconstructed forwarding signal; the step 41 includes: When the navigation signal is not locked by the target receiver, the structure of the pseudo-random code included in the navigation signal is in an unknown state, and the modulation method of the navigation signal is in a known state, the navigation signal is processed based on the symbol domain to obtain a partially reconstructed forwarding signal.

5. The method according to claim 4, characterized in that The symbol domain-based processing includes at least one of a superposition process, a replacement process, and a phase flip process.

6. The method according to claim 1, characterized in that The second interference signal includes a pseudo low-orbit satellite signal; The step 4 comprises: When the navigation signal is not locked by the target receiver and the structure of the pseudo-random code included in the navigation signal is in a known state, parsing the navigation signal to obtain a parsing result; A pseudo low-orbit satellite signal is generated according to the analysis result and the structure of the pseudo-random code; the pseudo low-orbit satellite signal is used to be locked by the target receiver when the target receiver has not locked the navigation signal, and then send error position information to the target receiver.

7. The method according to claim 1, characterized in that The type of the first interference signal includes at least one of narrowband interference, broadband noise interference and swept frequency interference.

8. The method according to claim 1, characterized in that The number of jammers used to generate the interference signal is at least two, and the interference signal received by the target receiver is a superimposed signal of the interference signals respectively sent by the at least two jammers.

Images