Intelligent electromagnetic environment assessment method, equipment and medium

Abstract

The invention discloses an intelligent electromagnetic environment assessment method and device and a medium, and the method comprises the steps: S1, obtaining a PDW of any frequency band and azimuth range, and carrying out the normalization processing of the pulse density and center frequency of the PDW; s2, a histogram interval is set, and histogram statistics is carried out on RF, PRI, PW and PA of the PDW; s3, carrying out normalization processing on a histogram statistical result; s4, performing length alignment on a normalization processing result; s5, performing feature extraction on a result after length completion by using a one-dimensional convolutional network; s6, fusing the normalized pulse density, the normalized center frequency and the extracted features; and S7, carrying out background signal identification on the fusion features by adopting a full-connection network, and judging whether the PDW has an electromagnetic background signal or not. According to the method, an accurate electromagnetic background recognition result is obtained in combination with artificial cognition and deep network features, background suppression is further carried out, and the accuracy of electronic reconnaissance is improved.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to an intelligent electromagnetic environment assessment method, device and medium. Background Art

[0002] Electronic reconnaissance is a special military reconnaissance method for obtaining enemy military intelligence. It does not obtain intelligence through direct observation by scouts, but uses electronic equipment to observe the activities of enemy electronic equipment. The equipment used for reconnaissance is called a reconnaissance receiver, which can collect weak electromagnetic signals in space, amplify and process them, and identify the characteristics of these signals. Therefore, within the detection range of the reconnaissance receiver, if the enemy's electronic equipment emits electromagnetic waves due to the need to perform tasks, its signals may be intercepted by the reconnaissance equipment, thereby obtaining the enemy's electromagnetic information, and further analyzing to obtain valuable military intelligence such as the enemy's military deployment and action intentions. Radar and radio communication equipment rely on radiating electromagnetic waves to work. They are the source of electromagnetic waves, so these devices are called radiation sources.

[0003] Electronic reconnaissance plays a very important role in the electromagnetic situation on today's battlefield. However, there are a large number of background radiation sources in complex electromagnetic environments, which can directly affect the performance of electronic reconnaissance. Summary of the invention

[0004] To solve the above problems, the present invention provides an intelligent electromagnetic environment assessment method, device and medium. The method combines artificial cognition and deep network features to obtain more accurate electromagnetic background recognition results, and can further perform background suppression, thereby improving the accuracy of electronic reconnaissance.

[0005] The present invention provides an intelligent electromagnetic environment assessment method, and the specific technical solution is as follows:

[0006] S1: Obtain PDW in any frequency band and azimuth range, and normalize the pulse density and center frequency of PDW;

[0007] S2: Set the histogram intervals of RF, PRI, PW, and PA, perform histogram statistics on RF, PRI, PW, and PA of PDW, and obtain corresponding statistical results;

[0008] S3: performing normalization processing on the histogram statistical results to obtain a normalized processing result;

[0009] S4: perform length alignment on the normalized processing results;

[0010] S5: After the length is padded, a one-dimensional convolutional network is used to extract features;

[0011] S6: Fusion of normalized pulse density, normalized center frequency, and features extracted by one-dimensional convolutional network based on RF, PRI, PW, and PA histograms;

[0012] S7: Use a fully connected network to identify the background signal based on the fusion features to determine whether there is an electromagnetic background signal in the PDW.

[0013] Furthermore, in step S1, the specific process of normalization is as follows:

[0014] Set the pulse threshold to Thres Num , then the normalized pulse density is Where, Num is the number of pulses of PDW;

[0015] Set the center frequency threshold to Thres RF , get the center frequency RF based on PDW statistics center , then the normalized center frequency is

[0016] Furthermore, in step S3, the normalization process of the histogram statistical results is as follows:

[0017] Obtain the statistical results of the histograms of RF, PRI, PW, and PA of PDW, and obtain the maximum value of the corresponding statistical results;

[0018] Calculate the ratio of each histogram statistical result to the corresponding maximum value.

[0019] Furthermore, in step S4, the length alignment is performed, and the specific process is as follows:

[0020] Obtain the length of each normalized processing result of the histogram statistical result, and obtain the maximum length thereof;

[0021] The maximum length is used as the reference length, and zeros are added before and after the result sequence.

[0022] Furthermore, during the length padding process, if the number of zeros to be padded is an even number, symmetrical zero padding is performed before and after the structure sequence;

[0023] If the number of zeros to be padded is an odd number, add one more zero after the result sequence.

[0024] Furthermore, in step S5, the structure of the one-dimensional convolutional network is a multi-layer stacked structure of convolutional layers, activation layers and pooling layers, and the output feature dimension is 1*N, where N represents the set feature dimension.

[0025] Furthermore, in step S7, the fully connected network uses a stack of fully connected layers, activation layers and Dropout layers, and the loss function uses a cross entropy loss function.

[0026] The present invention also provides an intelligent electromagnetic environment assessment device, which includes: a memory, a processor, and an intelligent electromagnetic environment assessment program stored in the memory and executable on the processor. When the intelligent electromagnetic environment assessment program is executed by the processor, the steps of the above-mentioned intelligent electromagnetic environment assessment method are implemented.

[0027] The present invention also provides a computer storage medium, on which an intelligent electromagnetic environment assessment program is stored. When the intelligent electromagnetic environment assessment program is executed by a processor, the steps of the intelligent electromagnetic environment assessment method described above are implemented.

[0028] The beneficial effects of the present invention are as follows:

[0029] The present invention targets a PDW (Pulse Description Word, which includes information such as frequency, azimuth, pulse width, amplitude, repetition rate, etc.) of a certain frequency band and azimuth range of an input signal. Firstly, the pulse density and the center frequency are normalized. Then, histogram statistics, histogram normalization processing and length alignment are performed on RF, PRI, PW and PA respectively. Feature extraction is performed through a one-dimensional convolutional neural network respectively. Then, the features extracted by the convolutional neural network and the normalized density and the normalized center frequency are feature fused. A fully connected neural network is adopted with cross entropy as the loss function to identify whether the PDW has a background signal. A more accurate electromagnetic background recognition result is obtained by combining artificial cognition and deep network features. Background suppression is further performed to improve the accuracy of electronic reconnaissance. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the framework structure of the method process of the present invention. DETAILED DESCRIPTION

[0031] The following description clearly and completely describes the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In the description of the embodiments of the present invention, it should be noted that the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the invention product is usually placed when in use, or the orientation or positional relationship commonly understood by those skilled in the art, or the orientation or positional relationship in which the invention product is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first" and "second" are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0033] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] Example 1

[0035] Embodiment 1 of the present invention discloses an intelligent electromagnetic environment assessment method, such as Figure 1 As shown, the specific steps are as follows:

[0036] S1: Obtain PDW in any frequency band and azimuth range, and normalize the pulse density and center frequency of PDW;

[0037] As a preferred embodiment, the specific process of normalization is as follows:

[0038] Set the pulse threshold to Thres Num , then the normalized pulse density is Where, Num is the number of pulses of PDW;

[0039] Set the center frequency threshold to Thres RF , get the center frequency RF based on PDW statistics center , then the normalized center frequency is

[0040] S2: Set the histogram interval of carrier frequency RF, pulse width PW, pulse repetition period PRI and pulse amplitude PA. The histogram intervals are Gap RF , Gap PRI , Gap PW and Gap PA ; Perform histogram statistics on RF, PRI, PW, and PA of PDW respectively to obtain the corresponding statistical results HistRF 、Hist PRI 、Hist PW and Hist PA .

[0041] S3: Histogram statistics results Hist RF 、Hist PRI 、Hist PW 、Hist PA Perform normalization processing to obtain the normalized processing result Hist' RF 、Hist' PRI 、Hist' PW 、Hist' PA ;

[0042] As a preferred embodiment, the normalization process of the histogram statistical results is as follows:

[0043] Obtain the statistical results of the histograms of RF, PRI, PW, and PA of PDW, and obtain the maximum value of the corresponding statistical results;

[0044] Calculate the ratio of each histogram statistical result to the corresponding maximum value.

[0045] Hist RF Take an example to illustrate. Specifically, assume Hist RF The maximum value of max(Hist RF ), the normalized result is

[0046] S4: Normalization result Hist' RF 、Hist' PRI 、Hist' PW and Hist' PA Perform length alignment to obtain

[0047] As a preferred embodiment, the specific process is as follows:

[0048] Get the length of each normalized result of the histogram statistics, record it as Hist' RF 、Hist' PRI 、Hist' PW 、Hist' PA The lengths are M1, M2, M3, and M4 respectively, and the maximum length M=max(M1,M2,M3,M4) is obtained;

[0049] Taking the maximum length M as the reference length, the leading and trailing zeros are padded to the result sequence.

[0050] During the length padding process, if the number of zeros to be padded is an even number, zero padding is performed symmetrically before and after the structure sequence;

[0051] If the number of zeros to be padded is an odd number, add one more zero after the result sequence.

[0052] Specifically, Hist' RF Take the length M1 as an example, the number of zeros to be padded is M-M1, if M-M1 is an even number;

[0053] Then fill in the result

[0054] If M-M1 is an odd number;

[0055] Then fill in the result

[0056] S5: Result after padding the length and One-dimensional convolutional networks are used for feature extraction respectively;

[0057] As a preferred embodiment, the structure of the one-dimensional convolutional network is a multi-layer stacked structure of convolutional layers, activation layers and pooling layers, and the output feature dimension is 1*N, where N represents the set feature dimension.

[0058] Specifically, in this embodiment, M is 128, N is 16; the activation function in the one-dimensional convolutional neural network is Relu, and the pooling function is maxpool;

[0059] The size of each convolution unit after processing in the one-dimensional convolution processing is: 1*128->8*64->32*64->32*32->8*32->1*16.

[0060] S6: Fuse the normalized pulse density, the normalized center frequency, and the features extracted by the one-dimensional convolutional network based on the RF, PRI, PW, and PA histograms to obtain a fused feature with a dimension of 1*(4*16+2)=1*66;

[0061] S7: Use a fully connected network to identify the background signal based on the fusion features to determine whether there is an electromagnetic background signal in the PDW.

[0062] As a preferred embodiment, the fully connected network uses a stack of fully connected layers, activation layers and Dropout layers, and the loss function uses a cross entropy loss function.

[0063] Specifically, in this embodiment, the activation layer of the fully connected network selects the sigmoid function, and the Dropout parameter is set to 0.5; the size of the fully connected layer after processing is: 1*66->1*16->1*1.

[0064] Example 2

[0065] Embodiment 2 of the present invention discloses an intelligent electromagnetic environment assessment device, which may be a user equipment (UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing device connected to a wireless modem, a mobile station (MS), etc. for executing an intelligent electromagnetic environment assessment method. The device may be called a user terminal, a portable terminal, a desktop terminal, etc.

[0066] Typically, the device includes: at least one processor, a memory, and an intelligent electromagnetic environment assessment program stored in the memory and executable on the processor, wherein the intelligent electromagnetic environment assessment program is configured to implement the steps of the intelligent electromagnetic environment assessment method as described in Example 1.

[0067] The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. The processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to the intelligent electromagnetic environment assessment program, so that the intelligent electromagnetic environment assessment method can be trained and learned autonomously to improve efficiency and accuracy.

[0068] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one instruction, which is used to be executed by the processor to implement the intelligent electromagnetic environment assessment method described in the above embodiment 1.

[0069] In some embodiments, the terminal may also optionally include: a communication interface and at least one peripheral device. The processor, the memory and the communication interface may be connected via a bus or a signal line. Each peripheral device may be connected to the communication interface via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit, a display screen and a power supply.

[0070] The communication interface can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor and the memory. The communication interface is used to receive the movement trajectories and other data of multiple mobile terminals uploaded by users through the peripheral device. In some embodiments, the processor, memory and communication interface are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor, memory and communication interface can be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0071] The radio frequency circuit is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit communicates with the communication network and other communication devices through electromagnetic signals, so that the movement trajectory and other data of multiple mobile terminals can be obtained. The radio frequency circuit converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit may also include circuits related to NFC (Near Field Communication), which is not limited in this embodiment.

[0072] The display screen is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. When the display screen is a touch screen, the display screen also has the ability to collect touch signals on the surface or above the surface of the display screen. The touch signal can be input to the processor as a control signal for processing. At this time, the display screen can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen can be one, the front panel of the electronic device; in other embodiments, the display screen can be at least two, respectively arranged on different surfaces of the electronic device or in a folding design; in some further embodiments, the display screen can be a flexible display screen, arranged on a curved surface or a folding surface of the electronic device. Even, the display screen can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode) and the like.

[0073] The power supply is used to power various components in the electronic device. The power supply can be AC, DC, a disposable battery or a rechargeable battery. When the power supply includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0074] Example 3

[0075] Embodiment 3 of the present invention discloses a computer storage medium, which is a readable storage medium. A computer program is stored on the readable storage medium. When the computer program is executed by a processor, the steps of the intelligent electromagnetic environment assessment method described in Embodiment 1 of the above method are implemented.

[0076] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0077] The present invention is not limited to the above-mentioned specific embodiments, but extends to any new features or any new combination disclosed in this specification, as well as any new method or process steps or any new combination disclosed.

Claims

1. An intelligent electromagnetic environment assessment method, characterized in that: include: S1: Obtain PDW in any frequency band and azimuth range, and normalize the pulse density and center frequency of PDW; S2: Set the histogram intervals of RF, PRI, PW, and PA, perform histogram statistics on RF, PRI, PW, and PA of PDW, and obtain corresponding statistical results; S3: performing normalization processing on the histogram statistical results to obtain a normalized processing result; S4: perform length alignment on the normalized processing results; S5: After the length is padded, a one-dimensional convolutional network is used to extract features; S6: Fusion of normalized pulse density, normalized center frequency, and features extracted by one-dimensional convolutional network based on RF, PRI, PW, and PA histograms; S7: Use a fully connected network to identify the background signal based on the fusion features to determine whether there is an electromagnetic background signal in the PDW.

2. The intelligent electromagnetic environment assessment method according to claim 1, characterized in that: In step S1, the specific process of normalization is as follows: Set the pulse threshold to Thres Num , then the normalized pulse density is Where, Num is the number of pulses of PDW; Set the center frequency threshold to Thres RF , get the center frequency RF based on PDW statistics center , then the normalized center frequency is 3. The intelligent electromagnetic environment assessment method according to claim 1, characterized in that: In step S3, the normalization process of the histogram statistical results is as follows: Obtain the statistical results of the histograms of RF, PRI, PW, and PA of PDW, and obtain the maximum value of the corresponding statistical results; Calculate the ratio of each histogram statistical result to the corresponding maximum value.

4. The intelligent electromagnetic environment assessment method according to claim 1, characterized in that: In step S4, the length is aligned, and the specific process is as follows: Obtain the length of each normalized processing result of the histogram statistical result, and obtain the maximum length thereof; The maximum length is used as the reference length, and zeros are added before and after the result sequence.

5. The intelligent electromagnetic environment assessment method according to claim 4, characterized in that: During the length padding process, if the number of zeros to be padded is an even number, zero padding is performed symmetrically before and after the structure sequence; If the number of zeros to be padded is an odd number, add one more zero after the result sequence.

6. The intelligent electromagnetic environment assessment method according to claim 1, characterized in that: In step S5, the structure of the one-dimensional convolutional network is a multi-layer stacked structure of convolutional layers, activation layers and pooling layers, and the output feature dimension is 1*N, where N represents the set feature dimension.

7. The intelligent electromagnetic environment assessment method according to claim 1, characterized in that: In step S7, the fully connected network uses a stack of fully connected layers, activation layers and Dropout layers, and the loss function uses a cross entropy loss function.

8. An intelligent electromagnetic environment assessment device, characterized in that: The intelligent electromagnetic environment assessment device includes: a memory, a processor, and an intelligent electromagnetic environment assessment program stored in the memory and executable on the processor. When the intelligent electromagnetic environment assessment program is executed by the processor, the steps of the intelligent electromagnetic environment assessment method described in any one of claims 1 to 7 are implemented.

9. A computer storage medium, characterized in that: The storage medium stores an intelligent electromagnetic environment assessment program, and when the intelligent electromagnetic environment assessment program is executed by the processor, the steps of the intelligent electromagnetic environment assessment method according to any one of claims 1 to 7 are implemented.

Images