Method and apparatus for detecting interfering signals

Abstract

The embodiment of the present application provides a kind of method and device for detecting interference signal, comprising: the one-dimensional signal energy data of the signal to be detected is handled, and the two-dimensional image data of the signal to be detected is obtained;The two-dimensional image data of the signal to be detected is reconstructed, and the reconstructed image data of the signal to be detected is obtained;According to the two-dimensional image data of the signal to be detected and the reconstructed image data of the signal to be detected, whether the signal to be detected is interference signal is determined.The present application solves the problem that the accuracy of detecting interference signal is low, and thus improves the accuracy of detecting interference signal.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communications, and in particular, to a method and device for detecting an interference signal. BACKGROUND

[0002] With the rapid development of satellite network technology, a large constellation satellite network with extensive coverage and high communication rate is being deployed on a large scale. At present, tens of thousands of satellites are competing for limited orbital resources and spectrum resources. However, the wireless communication spectrum resources are limited and scarce, and a large number of non-geostationary orbit (NGSO) systems and geostationary orbit (GSO) systems use the same frequency band for communication. As the number of NGSO satellites continues to increase, the downlink communication interference problem between the NGSO and the GSO system is increasingly prominent.

[0003] At present, the interference signal between the NGSO and the GSO is detected by relying on artificial experience, which is highly subjective and heavily dependent on experience, and the accuracy of detecting the interference signal is low.

[0004] At present, there is no effective solution to the above problems. SUMMARY

[0005] Embodiments of the present application provide a method and device for detecting an interference signal to at least solve the problem of low accuracy of the interference signal in the related art.

[0006] According to an embodiment of the present application, a method for detecting an interference signal is provided, which is applied to detecting an interference signal in a satellite network, and includes: processing one-dimensional signal energy data of a to-be-detected signal to obtain two-dimensional image data of the to-be-detected signal; reconstructing the two-dimensional image data of the to-be-detected signal to obtain reconstructed image data of the to-be-detected signal; and determining whether the to-be-detected signal is an interference signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal.

[0007] In one exemplary embodiment, determining whether the to-be-detected signal is an interference signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal includes: determining a reconstruction error of the to-be-detected signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal; and determining whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold.

[0008] In an example embodiment, before determining whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold, the method further comprises: determining reconstruction errors between two-dimensional image data of N first normal signals and reconstructed image data of the first normal signals, to obtain N first reconstruction errors, wherein the first normal signals are normal communication signals of the NGSO or normal communication signals of the GSO, and N is an integer; and determining the target reconstruction error threshold according to the N first reconstruction errors.

[0009] In an example embodiment, determining the target reconstruction error threshold according to the N first reconstruction errors comprises: determining the target reconstruction error threshold according to a mean of the N first reconstruction errors and a variance of the N first reconstruction errors.

[0010] In an example embodiment, determining the reconstruction errors between the two-dimensional image data of the N first normal signals and the reconstructed image data of the first normal signals comprises: inputting two-dimensional image data of a first target normal signal into a target autoencoder, encoding the two-dimensional image data of the first target normal signal through an encoding layer of the target autoencoder to obtain an encoded feature map of the first target normal signal, wherein the N first normal signals include the first target normal signal; decoding the encoded feature map of the first target normal signal through a decoding layer of the target autoencoder to obtain reconstructed image data of the first target normal signal; and determining a reconstruction error of the first target normal signal according to the two-dimensional image data of the first target normal signal and the reconstructed image data of the first target normal signal.

[0011] In an example embodiment, reconstructing the two-dimensional image data of the to-be-detected signal to obtain reconstructed image data of the to-be-detected signal comprises: inputting the two-dimensional image data of the to-be-detected signal into a target autoencoder, encoding the two-dimensional image data of the to-be-detected signal through an encoding layer of the target autoencoder to obtain an encoded feature map of the to-be-detected signal; and decoding the encoded feature map of the to-be-detected signal through a decoding layer of the target autoencoder to obtain the reconstructed image data of the to-be-detected signal.

[0012] In an example embodiment, the method further comprises: training the autoencoder using a training sample dataset, wherein the training sample dataset comprises: a training sample dataset and a test sample dataset, the training sample dataset comprises a plurality of training sample data, the training sample data comprises: two-dimensional image data of normal signal training samples, the test sample dataset comprises a plurality of test sample data, the test sample data comprises: two-dimensional image data of interference signal test samples of the first system and the second system at different angles; and ending the training to obtain the target autoencoder in a case where a test result of the autoencoder on the test sample dataset meets a preset condition.

[0013] In an example embodiment, the method further comprises: inputting target test sample data into the autoencoder trained in the i th round to obtain reconstructed image data of the target test sample data, the test sample dataset comprises the target test sample data, wherein i is an integer; determining a reconstruction error between the target test sample data and the reconstructed image data of the target test sample data to obtain a reconstruction error of the target test sample; and determining a test result of the target test sample data according to a relationship between the reconstruction error of the target test sample and a reconstruction error threshold value obtained in the i th round.

[0014] In an example embodiment, before determining the test result of the target test sample data according to the relationship between the reconstruction error of the target test sample and the reconstruction error threshold value obtained in the i th round, the method further comprises: inputting two-dimensional image data of M second normal signals into the autoencoder trained in the i th round to obtain reconstructed image data of the M second normal signals, wherein the second normal signal is a normal communication signal, and M is an integer; determining a reconstruction error between the two-dimensional image data of the M second normal signals and the reconstructed image data of the second normal signals to obtain M second reconstruction errors; and determining the reconstruction error threshold value obtained in the i th round according to the M second reconstruction errors, wherein the reconstruction error threshold value obtained in the i th round is the target reconstruction error threshold value if the i th round of training is the last round of training on the autoencoder.

[0015] In an example embodiment, the first system is a non-geostationary satellite NGSO system, the second system is a geostationary satellite GSO system, and the interference signal is an interference signal between the non-geostationary satellite NGSO system and the geostationary satellite GSO system.

[0016] According to another embodiment of the present application, there is provided a device for detecting an interference signal, applied to detecting an interference signal in a satellite network, comprising: a processing module configured to process one-dimensional signal energy data of a to-be-detected signal to obtain two-dimensional image data of the to-be-detected signal; a reconstruction module configured to reconstruct the two-dimensional image data of the to-be-detected signal to obtain reconstructed image data of the to-be-detected signal; and a determination module configured to determine whether the to-be-detected signal is an interference signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal.

[0017] According to still another embodiment of the present application, there is also provided a computer readable storage medium having a computer program stored therein, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of the preceding embodiments.

[0018] According to still another embodiment of the present application, there is also provided an electronic device comprising a memory and a processor, wherein the memory has a computer program stored therein, and the processor is configured to execute the computer program to perform the steps of the method according to any one of the preceding embodiments.

[0019] According to still another embodiment of the present application, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of the preceding embodiments.

[0020] According to the present application, the one-dimensional signal energy data of a to-be-detected signal is processed to obtain two-dimensional image data of the to-be-detected signal, the two-dimensional image data of the to-be-detected signal is reconstructed to obtain reconstructed image data of the to-be-detected signal, and whether the to-be-detected signal is an interference signal is determined according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal. Therefore, the problem of low accuracy in detecting an interference signal in the related art can be solved, and the accuracy in detecting an interference signal is improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 is a hardware structure block diagram of a mobile terminal of a method for detecting an interference signal according to an embodiment of the present application;

[0022] Figure 2 is a flowchart of a method for detecting an interference signal according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of time series data imaging according to an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of a core module according to an embodiment of the present application;

[0025] Figure 5is a schematic diagram of a satellite constellation interference scenario according to an embodiment of the present application;

[0026] Figure 6 is an experimental result of different angles between GSO and ground station antenna pointing according to an embodiment of the present application;

[0027] Figure 7 is a structural block diagram of a device for detecting interference signals according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings and in conjunction with embodiments.

[0029] It should be noted that the terms "first", "second", and the like in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking the case of running on a mobile terminal, Figure 1 is a hardware structural block diagram of a mobile terminal of a method for detecting interference signals according to an embodiment of the present application. As shown in Figure 1 , the mobile terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned mobile terminal can further include a transmission device 106 for communication function and an input / output device 108. Those skilled in the art can understand that Figure 1 the structure shown is only for illustration, which does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal can further include more or less components than those shown in Figure 1 , or have a different configuration from that shown in Figure 1 .

[0031] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the method for detecting interference signals in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the above method, by running the computer programs stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories remotely arranged with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0032] The transmission device 106 is configured to receive or send data via a network. Specific examples of the above network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to be able to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is configured to communicate with the Internet in a wireless manner.

[0033] In the present embodiment, a method for detecting interference signals running on the above mobile terminal is provided, which is applied to detecting interference signals in a satellite network. Figure 2 is a flowchart of the method for detecting interference signals according to the embodiments of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0034] In step S202, one-dimensional signal energy data of a to-be-detected signal is processed to obtain two-dimensional image data of the to-be-detected signal.

[0035] The to-be-detected signal can be a normal signal of an NGSO, or a normal signal of a GSO, or an interference signal between the NGSO and the GSO.

[0036] The signal preprocessing module converts the received I / Q data of the to-be-detected signal into one-dimensional energy data by the following formula:

[0037] ;

[0038] wherein, is the I / Q data of the to-be-detected signal, is the one-dimensional signal energy data of the to-be-detected signal.

[0039] The data imaging module converts one-dimensional energy data of the to-be-detected signal into an image form in a manner such as Figure 3 By converting the time-series one-dimensional energy data into two-dimensional image data, the spatiotemporal distribution characteristics of the signal energy can be increased. The processed two-dimensional image has one channel, similar to a grayscale image.

[0040] In step S204, the two-dimensional image data of the to-be-detected signal is reconstructed to obtain reconstructed image data of the to-be-detected signal.

[0041] Specifically, the two-dimensional image data of the to-be-detected signal is input into a target autoencoder, the two-dimensional image data of the to-be-detected signal is encoded by an encoding layer of the target autoencoder to obtain an encoded feature map of the to-be-detected signal, and the encoded feature map of the to-be-detected signal is decoded by a decoding layer of the target autoencoder to obtain the reconstructed image data of the to-be-detected signal.

[0042] The target autoencoder is a two-dimensional convolutional autoencoder, and the target autoencoder is a trained two-dimensional convolutional autoencoder.

[0043] In step S206, it is determined whether the to-be-detected signal is an interference signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal.

[0044] The interference signal is an interference signal between a non-geostationary satellite NGSO and a geostationary satellite GSO.

[0045] Specifically, a reconstruction error of the to-be-detected signal is determined according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal, and it is determined whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold.

[0046] The calculation formula of the reconstruction error is as follows:

[0047] ;

[0048] wherein, is the two-dimensional image data of the to-be-detected signal, is the reconstruction error of the to-be-detected signal.

[0049] When the reconstruction error of the to-be-detected signal is greater than or equal to the target reconstruction error threshold, the to-be-detected signal is an interference signal, and when the reconstruction error of the to-be-detected signal is less than the target reconstruction error threshold, the to-be-detected signal is a normal signal.

[0050] Optionally, the execution subject of the above steps can be a background processor, or other devices with similar processing capabilities, and can also be a machine integrated with at least an image acquisition device and a data processing device, wherein the image acquisition device can include a camera and other image acquisition modules, and the data processing device can include a computer, a mobile phone and other terminals, but is not limited thereto.

[0051] Through the above steps, the to-be-detected signal is first converted into one-dimensional signal energy data by the signal preprocessing module, and then the one-dimensional signal energy data is converted into two-dimensional image data by the data imaging module. Then the two-dimensional image data passes through the encoding layer and the decoding layer of the two-dimensional convolutional autoencoder to obtain the reconstructed image data of the to-be-detected signal, and the reconstruction error between the two-dimensional image data of the to-be-detected signal and the reconstructed image restored by the two-dimensional convolutional autoencoder is calculated. The reconstruction error is compared with the target reconstruction error threshold, and when the reconstruction error is greater than or equal to the target reconstruction error threshold, the to-be-detected signal is an interference signal, and when the reconstruction error is less than the target reconstruction error threshold, the to-be-detected signal is a normal signal. Since the two-dimensional convolutional autoencoder can autonomously learn the difference between the normal signal and the interference signal, and automatically learn the reconstruction error threshold, it is more in line with the change rule of the normal signal and the signal, and the accuracy of detecting the interference signal is higher.

[0052] In one exemplary embodiment, before determining whether the to-be-detected signal is the interference signal according to the relationship between the reconstruction error of the to-be-detected signal and the target reconstruction error threshold, the method further comprises:

[0053] determining the reconstruction error between the two-dimensional image data of N first normal signals and the reconstructed image data of the first normal signal, to obtain N first reconstruction errors, wherein the first normal signal is a normal communication signal, and N is an integer; and determining the target reconstruction error threshold according to the N first reconstruction errors.

[0054] The first normal signal is a normal communication signal of the NGSO or a normal communication signal of the GSO.

[0055] Taking the first normal signal as an example, the specific value of N can be determined according to actual conditions.

[0056] The reconstruction error of any signal in the N first normal signals (the first target normal signal is any signal in the N first normal signals) can be obtained in the following way:

[0057] inputting the two-dimensional image data of the first target normal signal into the target autoencoder, encoding the two-dimensional image data of the first target normal signal through an encoding layer of the target autoencoder to obtain an encoded feature map of the first target normal signal, wherein the N first normal signals include the first target normal signal; decoding the encoded feature map of the first target normal signal through a decoding layer of the target autoencoder to obtain reconstructed image data of the first target normal signal; and determining a reconstruction error of the first target normal signal according to the two-dimensional image data of the first target normal signal and the reconstructed image data of the first target normal signal.

[0058] In one example embodiment, the target reconstruction error threshold is determined according to the N first reconstruction errors, including: determining the target reconstruction error threshold according to a mean of the N first reconstruction errors and a variance of the N first reconstruction errors.

[0059] ;

[0060] wherein, is the jth first reconstruction error, k is a preset weight value, and the value of k can be adjusted according to actual conditions, for example, adjusted according to the distribution of the interference signal.

[0061] The target autoencoder is obtained by training an autoencoder. Specifically, the autoencoder is trained using a training sample data set, wherein the training sample data set includes a training sample data set and a test sample data set, the training sample data set includes a plurality of training sample data, and the training sample data includes two-dimensional image data of a normal signal training sample. The test sample data set includes a plurality of test sample data, and the test sample data includes two-dimensional image data of an interference signal test sample of the first system and the second system at different angles. The training is ended to obtain the target autoencoder when the test result of the test sample data set by the autoencoder meets a preset condition.

[0062] The first system is a non-geostationary satellite NGSO system, and the second system is a geostationary satellite GSO system.

[0063] The preset condition includes, but is not limited to, that in the test result of the test sample data set, more than a preset proportion (which can be determined according to actual conditions, for example, 50%) of the test sample data is accurate. For example, it is assumed that the test sample data set includes two-dimensional image data of 200 interference signal test samples. If the result output by the trained autoencoder indicates that more than 100 interference signal test samples are accurate, the training is ended to obtain the target autoencoder.

[0064] Taking the i-th training in the training process of the autoencoder as an example (the i-th training can be any training), the 0-th training is the initial autoencoder which is not trained, and the last training obtains the target autoencoder. The target test sample data is any test sample data in the test sample data set.

[0065] The target test sample data is input into the autoencoder obtained by the i-th training to obtain reconstructed image data of the target test sample data, the test sample data set includes the target test sample data, wherein i is an integer; a reconstruction error between the target test sample data and the reconstructed image data of the target test sample data is determined to obtain a reconstruction error of the target test sample; and a test result of the target test sample data is determined according to a relationship between the reconstruction error of the target test sample and a reconstruction error threshold obtained by the i-th training.

[0066] In an example embodiment, the reconstruction error threshold obtained by the i-th training is obtained in the following manner:

[0067] Two-dimensional image data of M second normal signals is input into the autoencoder obtained by the i-th training to obtain reconstructed image data of the M second normal signals, wherein the second normal signals are normal communication signals, and M is an integer; reconstruction errors between the two-dimensional image data of the M second normal signals and the reconstructed image data of the second normal signals are determined to obtain M second reconstruction errors; and the reconstruction error threshold obtained by the i-th training is determined according to the M second reconstruction errors, wherein if the i-th training is the last training of the autoencoder, the reconstruction error threshold obtained by the i-th training is the target reconstruction error threshold.

[0068] The second normal signals are normal communication signals of the NGSO or normal communication signals of the GSO.

[0069] The determination of the reconstruction error threshold obtained by the i-th training according to the M second reconstruction errors includes determining the reconstruction error threshold obtained by the i-th training according to a mean value of the M second reconstruction errors and a variance of the M second reconstruction errors. The second normal signals can be normal signals of the NGSO or the GSO. The first normal signals and the second normal signals can be the same normal signals or different normal signals.

[0070] In the above embodiment, by converting the time sequence energy data of the signal (including the to-be-detected signal and the training sample signal) into two-dimensional image data, the spatiotemporal distribution law of the signal energy is highlighted, and the two-dimensional convolutional autoencoder is designed to learn the spatiotemporal correlation characteristics of the signal energy fluctuation. The reconstruction error threshold is defined based on the reconstruction error of the two-dimensional autoencoder for the normal signal, and the effective detection of the interference signal in multiple scenarios is realized.

[0071] As shown in Figure 4 is a core module schematic diagram, including a signal preprocessing module, a data imaging module, a feature learning module and an interference detection module.

[0072] Firstly, the I / Q data of the received signal (including the to-be-detected signal or the training sample signal, the signal in the training process is the training sample signal, and the signal in the detection process is the to-be-detected signal) is converted into one-dimensional energy data by the following formula through the signal preprocessing module. Through the conversion, the energy change of the signal can be highlighted.

[0073] ;

[0074] The data imaging module converts the one-dimensional energy data into the form of an image in the manner as shown in Figure 3 . The time sequence one-dimensional energy data is converted into two-dimensional image data, which can increase the spatiotemporal distribution characteristics of the signal energy, and then the two-dimensional convolutional autoencoder extracts the spatiotemporal high-dimensional features of the signal energy data. The processed two-dimensional image has one channel, which is similar to a grayscale image, and is input into the two-dimensional convolutional autoencoder for feature learning.

[0075] The feature learning module mainly includes a two-dimensional convolutional autoencoder, and the structure thereof is shown in Table 1.

[0076] Table 1

[0077]

[0078] The feature learning of the two-dimensional convolutional autoencoder is the training phase, and mainly includes three steps to realize feature learning, which are an input signal encoding process, a feature decoding process and a reconstruction loss calculation process.

[0079] Firstly, the two-dimensional image data (the two-dimensional image data of the training sample signal, i.e. the two-dimensional image data of the normal signal training sample) processed by the data imaging module is input into the encoding layer of the two-dimensional convolutional autoencoder, and the encoding layer is composed of multiple convolutional layers, activation function layers and maximum pooling layers. Through the processing of the encoding layer, the dimension reduction and spatiotemporal feature mapping of the two-dimensional image data can be realized, and the features include the spatiotemporal fluctuation law of the signal energy. The encoding layer of the two-dimensional convolutional autoencoder learns the input two-dimensional image data The feature mapping is performed as shown in the following formula:

[0080] ;

[0081] wherein, is a feature vector learned by the encoding layer, is an activation function for realizing a nonlinear transformation, W1 is a weight of a convolutional neuron of the encoding layer, and b1 is a bias of the convolutional neuron of the encoding layer.

[0082] For example, in the encoding process, two-dimensional image data is first input into a first convolutional layer to obtain an intermediate feature with a size of (8, 28, 28), wherein 8 is a channel number, and 28 is a length and a width of the intermediate feature map. The first convolutional layer performs preliminary feature extraction and data dimension reduction on spatial information in the two-dimensional image. Then, the intermediate feature is further input into a ReLU activation function layer, and the ReLU activation function layer can map a nonlinear factor for the feature mapping, so that the model can fit a nonlinear problem of signal energy feature extraction. Next, the nonlinear feature map is input into a max-pooling layer for feature screening and dimension reduction to obtain an intermediate feature map with a size of (8, 14, 14). Further, the intermediate feature map with the size of (8, 14, 14) is input into a second convolutional layer to further extract the feature map, and an intermediate feature map with a size of (16, 14, 14) is obtained, which is then input into a ReLU activation function layer and a max-pooling layer to obtain an intermediate feature map with a size of (16, 7, 7). The intermediate feature map is further input into a third convolutional layer and a ReLU activation function layer to further extract high-dimensional spatial and temporal features. Finally, the intermediate feature map with the size of (16, 7, 7) is input into a fourth convolutional layer, a ReLU activation function layer and a max-pooling layer to obtain a high-dimensional feature map with a size of (16, 3, 3) containing signal spatial and temporal attributes.

[0083] The high-dimensional feature map with the size of (16, 3, 3) is a signal feature map learned by the two-dimensional convolutional autoencoder. A larger feature map can obtain more abundant features of the signal, but can also cause redundancy of the features. A smaller feature map can obtain more accurate features of the signal, but can cause the independence of different features to be weakened. In the process of detecting downlink interference of a low-orbit communication satellite, the feature map is set to (16, 3, 3), which can effectively learn the energy features of the signal.

[0084] Further, the feature map containing high-dimensional spatial and temporal key attributes is input into a decoding layer of the two-dimensional convolutional autoencoder. The decoding layer includes multiple deconvolutional layers and activation function layers. The key role of the decoding layer is to accurately restore the signal high-dimensional feature map to two-dimensional image data consistent with the input data, and therefore, the structure of the decoding layer is almost completely opposite to that of the encoding layer. The decoding layer of the two-dimensional convolutional autoencoder restores the feature vector by a nonlinear function G() as shown in the following formula:

[0085] ;

[0086] wherein, is the two-dimensional reconstructed image data output by the decoding layer, Z is the feature vector learned by the encoding layer, The activation function of the decoding layer realizes a nonlinear transformation, W2 is the weight of the convolutional neuron of the decoding layer, and b2 is the bias of the convolutional neuron of the decoding layer.

[0087] In the decoding process, the high-dimensional feature map with a size of (16, 3, 3) is input into the first deconvolutional layer, and through the deconvolutional operation, the decoding layer restores the feature map with a size of (16, 3, 3) to an intermediate image with a size of (8, 6, 6) according to the spatio-temporal correlation in the high-dimensional feature map. Then, the intermediate image is also input into the ReLU activation function layer, and a nonlinear transformation is introduced in the decoding process to restore the nonlinear change between the data and the feature map. Then, through the second deconvolutional layer and the third deconvolutional layer, the spatio-temporal correlation between the image data is further restored to obtain image data with a size of (4, 24, 24). Finally, the image data with a size of (4, 24, 24) is input into the fourth deconvolutional layer for the final data restoration, and the channel of the image is restored to 1, and the length and width are restored to 28, to obtain a reconstructed image consistent with the input image. In the transformation process of the fourth deconvolutional layer, the activation function layer is not included, and the purpose is to complete the linear mapping from the feature vector to the input two-dimensional image data to approximate the input data as much as possible.

[0088] Finally, the reconstruction error calculation process uses the reconstruction error between the input two-dimensional image data and the two-dimensional reconstructed image restored by the two-dimensional convolutional autoencoder through the encoding layer and the decoding layer as the loss function of the two-dimensional convolutional autoencoder, and uses gradient random descent and back propagation to drive the two-dimensional convolutional autoencoder for training, so that the two-dimensional convolutional autoencoder learns the mapping process from the input data to the feature map and the restoration process from the feature map to the two-dimensional image data, thereby obtaining the learning ability of the spatio-temporal characteristics of the signal energy in the two-dimensional image data. In the reconstruction error calculation process, the mean square error (MSE) is used for calculation, and the MSE calculates the mean value of the square sum of the difference between the input two-dimensional image data and the two-dimensional reconstructed image restored by the two-dimensional convolutional autoencoder, to measure the encoding and decoding ability of the two-dimensional convolutional autoencoder. The calculation formula of the reconstruction error is as follows:

[0089] ;

[0090] The interference detection module is based on a trained two-dimensional convolutional autoencoder to detect interference data. Since only normal communication signals without interference are used for model training in the feature learning training process of the two-dimensional convolutional autoencoder, the two-dimensional convolutional autoencoder can learn the energy space fluctuation characteristics of the normal communication signals well and accurately restore the two-dimensional image data of the normal communication signals. However, when the interference signal is input into the two-dimensional convolutional autoencoder, the signal feature vector extracted by the two-dimensional convolutional autoencoder is different from that of the normal communication signal, so the two-dimensional image data of the interference signal cannot be accurately restored in the decoding process, resulting in a large reconstruction error. Therefore, the normal communication signal has a small reconstruction error, and the interference signal has a large reconstruction error. Therefore, in the interference detection module, a decision threshold is calculated based on the reconstruction error of the normal communication signal to determine whether there is an interference signal, as shown in the following formula:

[0091] ;

[0092] wherein, is the jth first reconstruction error, k is a preset weight value, and the value of k can be adjusted according to actual conditions, for example, adjusted according to the distribution of the interference signal.

[0093] In the interference detection module, the signal to be detected is first converted into one-dimensional signal energy data by the signal preprocessing module, and then the one-dimensional signal energy data is converted into two-dimensional image data by the data imaging module. Then the two-dimensional image is sequentially input into the encoding layer and the decoding layer of the two-dimensional convolutional autoencoder in the feature learning module, and the MSE error between the input two-dimensional image data and the reconstructed image restored by the two-dimensional convolutional autoencoder is calculated. The MSE reconstruction error is compared with the threshold value, and when the MSE reconstruction error is greater than the threshold value, the input data is an interference signal, and when the MSE reconstruction error is less than the threshold value, the input data is a normal signal.

[0094] In the embodiment of the present application, a satellite constellation interference scenario is constructed using MATLAB, including one GSO satellite, 40 NGSO satellites and one NGSO ground station, as shown in Figure 5 Fig. 1, including an NGSO satellite 501, a GSO satellite 502 and an NGSO ground station. Among them, the GSO and NGSO satellites are enabled to run through two-line orbit data (Two-Line Element, TLE) files. The TLE file contains a set of orbital elements of the earth orbiting satellite, which can be used to calculate the real running state of the satellite. Both GSO and NGSO use Ku band 10.7-12.7 GHz for communication, so the interference between GSO and NGSO can be effectively simulated.

[0095] In the embodiment of the application, according to the above satellite constellation interference scenario, 1200 NGSO normal communication signal I / Q samples are generated, and 200 signal samples under the NGSO and GSO interference condition are generated. Among them, 1000 NGSO normal communication signals are used as the training set of the time series data imaging and two-dimensional convolutional autoencoder, 200 NGSO normal communication signals are used as the non-interference test set, and 200 NGSO and GSO interference signal samples are used as the interference test set.

[0096] Firstly, the I / Q samples of the 1000 NGSO normal communication signals are input into the signal preprocessing module, the 1000 NGSO one-dimensional signal energy data are obtained, and the one-dimensional signal energy data are input into the data imaging module to obtain two-dimensional image data with a size of (1, 28, 28), which are then input into the two-dimensional convolutional autoencoder for encoding, feature extraction of the feature map, and restoration of the decoding layer. The two-dimensional convolutional autoencoder output restored 1000 NGSO two-dimensional reconstruction image data are obtained, and the reconstruction error between the 1000 original NGSO two-dimensional image data and the restored 1000 NGSO two-dimensional reconstruction image data is calculated. After 50 rounds of training, the trained two-dimensional convolutional autoencoder is obtained, and the interference judgment threshold is calculated according to the reconstruction error. Finally, the non-interference test set of 200 NGSO normal communication signals and the interference test set of 200 NGSO and GSO are sequentially input into the signal preprocessing module, the data imaging module and the feature learning module, the reconstruction error is obtained, and compared with the interference judgment threshold to obtain the test result. In addition, when the angle between the GSO satellite and the NGSO ground station antenna pointing is different, the influence on the NGSO communication link is different. When the angle is small, the interference of GSO on NGSO is greater, and when the angle is large, the GSO signal received by the NGSO ground station is weak, and the interference of GSO on NGSO is small. In the embodiment of the application, the data of GSO as an interference signal under different angles is simulated as an interference test data set, and the angle range of the antenna of GSO and NGSO ground receiving station is 0-20°. Figure 6 The experimental results of the application and the prior art when the angle of the NGSO ground station antenna pointing is different show that the detection accuracy of the application when the interference signal is weak is significantly higher than that of the interference detection method based on the full connection autoencoder and the interference detection method based on the energy threshold.

[0097] The timing data imaging method is introduced in the application to transform one-dimensional signal energy data into two-dimensional image data, highlight the space-time characteristics of energy fluctuation, facilitate the convolutional autoencoder to extract effective features, and improve the interference detection accuracy. The two-dimensional convolutional autoencoder is introduced to autonomously learn the space-time high-dimensional features of energy through the input signal energy two-dimensional image data, and the image reconstruction error is used as the interference judgment threshold to improve the satellite downlink interference detection accuracy.

[0098] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software necessary for a general hardware platform, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device) to execute the method described in each embodiment of the present application.

[0099] In this embodiment, a device for detecting an interference signal is also provided, which is applied to detecting an interference signal in a satellite network. The device is used to implement the above embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0100] Figure 7 is a structural block diagram of the device for detecting an interference signal according to the embodiment of the present application, as shown in Figure 5 The device comprises:

[0101] A processing module 72 is configured to process one-dimensional signal energy data of a to-be-detected signal to obtain two-dimensional image data of the to-be-detected signal.

[0102] A reconstruction module 74 is configured to reconstruct the two-dimensional image data of the to-be-detected signal to obtain reconstructed image data of the to-be-detected signal.

[0103] A determination module 76 is configured to determine whether the to-be-detected signal is an interference signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal.

[0104] In one exemplary embodiment, the device is further configured to determine a reconstruction error of the to-be-detected signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal; and determine whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold.

[0105] In an example embodiment, the apparatus is further configured to determine reconstruction errors between two-dimensional image data of N first normal signals and reconstructed image data of the first normal signals, to obtain N first reconstruction errors, before determining whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold, wherein the first normal signals are normal communication signals, and N is an integer; and determine the target reconstruction error threshold according to the N first reconstruction errors.

[0106] In an example embodiment, the apparatus is further configured to determine the target reconstruction error threshold according to a mean of the N first reconstruction errors and a variance of the N first reconstruction errors.

[0107] In an example embodiment, the apparatus is further configured to input two-dimensional image data of a first target normal signal into a target autoencoder, encode the two-dimensional image data of the first target normal signal through an encoding layer of the target autoencoder to obtain an encoded feature map of the first target normal signal, wherein the N first normal signals include the first target normal signal; decode the encoded feature map of the first target normal signal through a decoding layer of the target autoencoder to obtain reconstructed image data of the first target normal signal; and determine a reconstruction error of the first target normal signal according to the two-dimensional image data of the first target normal signal and the reconstructed image data of the first target normal signal.

[0108] In an example embodiment, the apparatus is further configured to input two-dimensional image data of a first target normal signal into a target autoencoder, encode the two-dimensional image data of the first target normal signal through an encoding layer of the target autoencoder to obtain an encoded feature map of the first target normal signal, wherein the N first normal signals include the first target normal signal; decode the encoded feature map of the first target normal signal through a decoding layer of the target autoencoder to obtain reconstructed image data of the first target normal signal; and determine a reconstruction error of the first target normal signal according to the two-dimensional image data of the first target normal signal and the reconstructed image data of the first target normal signal.

[0109] In an example embodiment, the apparatus is further configured to train an autoencoder using a training sample data set, wherein the training sample data set includes a training sample data set and a test sample data set, the training sample data set includes a plurality of training sample data, and the training sample data includes two-dimensional image data of normal signal training samples; the test sample data set includes a plurality of test sample data, and the test sample data includes two-dimensional image data of interference signal test samples of the first system and the second system at different angles; and end the training to obtain the target autoencoder when a test result of the autoencoder on the test sample data set meets a preset condition.

[0110] In an example embodiment, the apparatus is further configured to input the target test sample data into the autoencoder trained in the i-th round to obtain reconstructed image data of the target test sample data, the test sample data set comprising the target test sample data, wherein i is an integer; determine a reconstruction error between the target test sample data and the reconstructed image data of the target test sample data to obtain a reconstruction error of the target test sample; and determine a test result of the target test sample data according to a relationship between the reconstruction error of the target test sample and a reconstruction error threshold value obtained in the i-th round.

[0111] In an example embodiment, the apparatus is further configured to, before determining the test result of the target test sample data according to the relationship between the reconstruction error of the target test sample and the reconstruction error threshold value obtained in the i-th round, input two-dimensional image data of M second normal signals into the autoencoder trained in the i-th round to obtain reconstructed image data of the M second normal signals, wherein the second normal signals are normal communication signals, and M is an integer; determine a reconstruction error between the two-dimensional image data of the M second normal signals and the reconstructed image data of the second normal signals to obtain M second reconstruction errors; and determine the reconstruction error threshold value obtained in the i-th round according to the M second reconstruction errors, wherein the reconstruction error threshold value obtained in the i-th round is the target reconstruction error threshold value if the i-th round is the last round of training of the autoencoder.

[0112] In an example embodiment, the first system is a non-geostationary satellite (NGSO) system, the second system is a geostationary satellite (GSO) system, and the interference signal is an interference signal between the non-geostationary satellite (NGSO) system and the geostationary satellite (GSO) system.

[0113] It should be noted that each of the above modules can be implemented by software or hardware, and for the latter, the following implementation manners can be used, but are not limited thereto: all of the above modules are located in the same processor; or the above modules are located in different processors in any combination.

[0114] Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, wherein the computer program, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0115] In an example embodiment, the computer readable storage medium described above can include, but is not limited to, a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media capable of storing computer programs.

[0116] Embodiments of the present application also provide an electronic device, comprising a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps of any of the method embodiments described above.

[0117] In an example embodiment, the electronic device described above can further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0118] The specific examples in the embodiments can refer to the examples described in the above embodiments and example implementations, and will not be described here again.

[0119] Embodiments of the present application also provide a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the methods described in various embodiments of the present application.

[0120] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be realized by general computing devices, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, which can be realized by program codes executable by computing devices, so that they can be stored in storage devices and executed by computing devices, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps can be manufactured into a single integrated circuit module. Thus, the present application is not limited to any particular combination of hardware and software.

[0121] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of detecting an interfering signal, characterized by, The method is applied to detecting an interference signal in a satellite network, and comprises the following steps: processing one-dimensional signal energy data of a to-be-detected signal to obtain two-dimensional image data of the to-be-detected signal; reconstructing the two-dimensional image data of the to-be-detected signal by using a target autoencoder to obtain reconstructed image data of the to-be-detected signal, wherein the target autoencoder is obtained by training an autoencoder by using a training sample data set and a test sample data set, and the training of the autoencoder is ended to obtain the target autoencoder when a test result of the autoencoder on the test sample data set meets a preset condition, the training sample data set comprises two-dimensional image data of a normal signal training sample, and the test sample data set comprises two-dimensional image data of an interference signal test sample in which a non-geostationary satellite (NGSO) system and a geostationary satellite (GSO) system are at different angles; determining a reconstruction error of the to-be-detected signal according to the two-dimensional image data of the to-be-detected signal and the reconstructed image data of the to-be-detected signal; determining whether the to-be-detected signal is the interference signal according to a relationship between the reconstruction error of the to-be-detected signal and a target reconstruction error threshold, wherein the target reconstruction error threshold is a reconstruction error threshold obtained by performing a last round of training on the autoencoder, and the interference signal is an interference signal between the non-geostationary satellite (NGSO) system and the geostationary satellite (GSO) system.

2. The method of claim 1, wherein, Before determining whether the to-be-detected signal is the interference signal according to the relationship between the reconstruction error of the to-be-detected signal and the target reconstruction error threshold, the method further comprises the following steps: determining reconstruction errors between two-dimensional image data of N first normal signals and reconstructed image data of the first normal signals to obtain N first reconstruction errors, wherein the first normal signals are normal communication signals, and N is an integer; determining the target reconstruction error threshold according to the N first reconstruction errors.

3. The method of claim 2, wherein, Determining the target reconstruction error threshold according to the N first reconstruction errors comprises the following steps: determining the target reconstruction error threshold according to a mean value of the N first reconstruction errors and a variance of the N first reconstruction errors.

4. The method of claim 2, wherein, Determining the reconstruction errors between the two-dimensional image data of the N first normal signals and the reconstructed image data of the first normal signals comprises the following steps: inputting two-dimensional image data of a first target normal signal into a target autoencoder, encoding the two-dimensional image data of the first target normal signal by using an encoding layer of the target autoencoder to obtain an encoding feature map of the first target normal signal, wherein the N first normal signals comprise the first target normal signal; decoding the encoding feature map of the first target normal signal by using a decoding layer of the target autoencoder to obtain reconstructed image data of the first target normal signal; determining a reconstruction error of the first target normal signal according to the two-dimensional image data of the first target normal signal and the reconstructed image data of the first target normal signal.

5. The method of claim 1, wherein, Reconstructing the two-dimensional image data of the to-be-detected signal to obtain the reconstructed image data of the to-be-detected signal comprises the following steps: Input the two-dimensional image data of the signal to be detected into the target autoencoder, encode the two-dimensional image data of the signal to be detected through the encoding layer of the target autoencoder, and obtain the encoded feature map of the signal to be detected; Decode the encoded feature map of the signal to be detected through the decoding layer of the target autoencoder, and obtain the reconstructed image data of the signal to be detected.

6. The method of claim 1, wherein, The method further comprises: Input the target test sample data into the autoencoder obtained through the i-th round of training to obtain the reconstructed image data of the target test sample data, wherein the test sample data set comprises the target test sample data, and i is an integer; Determine the reconstruction error between the target test sample data and the reconstructed image data of the target test sample data to obtain the reconstruction error of the target test sample; Determine the test result of the target test sample data according to the relationship between the reconstruction error of the target test sample and the reconstruction error threshold obtained through the i-th round of training.

7. The method of claim 6, wherein, Before determining the test result of the target test sample data according to the relationship between the reconstruction error of the target test sample and the reconstruction error threshold obtained through the i-th round of training, the method further comprises: Input the two-dimensional image data of M second normal signals into the autoencoder obtained through the i-th round of training to obtain the reconstructed image data of the M second normal signals, wherein the second normal signals are normal communication signals, and M is an integer; Determine the reconstruction error between the two-dimensional image data of the M second normal signals and the reconstructed image data of the second normal signals to obtain M second reconstruction errors; Determine the reconstruction error threshold obtained through the i-th round of training according to the M second reconstruction errors.

8. An apparatus for detecting an interfering signal, the apparatus comprising: Applied to detecting an interference signal in a satellite network, comprising: A processing module configured to process one-dimensional signal energy data of a signal to be detected to obtain two-dimensional image data of the signal to be detected; A reconstruction module configured to reconstruct the two-dimensional image data of the signal to be detected through a target autoencoder to obtain reconstructed image data of the signal to be detected, wherein the target autoencoder is obtained by training an autoencoder using a training sample data set and a test sample data set, the training sample data set comprises two-dimensional image data of normal signal training samples, and the test sample data set comprises two-dimensional image data of interference signal test samples of a non-geostationary satellite NGSO system and a geostationary satellite GSO system at different angles; A determination module configured to determine a reconstruction error of the signal to be detected according to the two-dimensional image data of the signal to be detected and the reconstructed image data of the signal to be detected; Determine whether the signal to be detected is the interference signal according to the relationship between the reconstruction error of the signal to be detected and a target reconstruction error threshold, wherein the target reconstruction error threshold is a reconstruction error threshold obtained by performing a last round of training on the autoencoder, and the interference signal is an interference signal between the non-geostationary satellite NGSO system and the geostationary satellite GSO system.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method in any one of claims 1 to 7.

10. A chip comprising at least one of editable logic circuitry and executable instructions, the chip operating in an electronic device to implement the method in any one of claims 1 to 7. 11.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the computer program to perform the method in any one of claims 1 to 7.

12. A computer program product comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the method in any one of claims 1 to 7.

Images