Transient electromagnetic pulse signal identification method and device, medium and equipment

Abstract

The invention discloses a transient electromagnetic pulse signal identification method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring pulse data containing time information and an actual pulse amplitude value; defining a pulse model function, and initializing model parameters of the pulse model function; inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; on the basis of the predicted value and the actual pulse amplitude value, updating model parameters of the pulse model function through a Kalman filtering algorithm fused with gradient calculation; and updating the pulse model function based on the updated model parameters to obtain an updated pulse model function, and inputting the collected pulse data into the updated pulse model function for identification to obtain an identification result of the pulse data. The pulse data can be accurately judged, and the calculation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of nuclear explosion pulse identification, and in particular to a transient electromagnetic pulse signal identification method, device, storage medium and electronic equipment. Background Art

[0002] Nuclear electromagnetic pulse (NEMP) is the electromagnetic radiation generated by the interaction between gamma rays generated by the explosion of a nuclear weapon and the surrounding air. NEMP has the characteristics of fast propagation speed, large impact range and long detection distance, which meets the timeliness requirements of remote nuclear explosion detection and occupies an important position in nuclear explosion detection.

[0003] Traditional nuclear explosion identification methods mostly use a relatively primitive method of combining manual experience judgment with the detector trigger time window to judge nuclear explosion events (this can be attributed to the template matching method in pattern recognition). Currently popular recognition technologies mostly belong to statistical pattern recognition methods, which require certain prior knowledge of the NEMP to be identified, such as the signal generation mechanism, physical properties, etc. Existing research results mostly focus on the two key steps of "feature extraction" and "classification decision". For example: feature extraction based on Hilbert-Huang (HHT) or wavelet transform, and signal classification and recognition based on BP neural network, support vector machine (SVM) or KNN. These algorithms have been popularized and applied to a certain extent at present, but they also have the problem of overly complex calculations. Summary of the invention

[0004] The embodiments of the present application provide a transient electromagnetic pulse signal recognition method, device, storage medium and electronic device, which can accurately judge pulse data and improve computing efficiency.

[0005] The present application provides a method for signal recognition of transient electromagnetic pulses, including: Obtain pulse data including time information and actual pulse amplitude value; defining a pulse model function, and initializing model parameters of the pulse model function; Inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; Based on the predicted value and the actual pulse amplitude value, the model parameters of the pulse model function are updated by a Kalman filter algorithm incorporating gradient calculation; The pulse model function is updated based on the updated model parameters to obtain an updated pulse model function, and the collected pulse data is input into the updated pulse model function for recognition to obtain a recognition result of the pulse data.

[0006] Furthermore, in the above transient electromagnetic pulse signal recognition method, the pulse model function is defined, including: The impulse model function is expressed by a double exponential function:

[0007] in, is the instantaneous value of the pulse, is the elapsed time, is the correction factor, and They are the mathematical parameters of the pulse leading edge and the mathematical parameters of the pulse trailing edge respectively.

[0008] Furthermore, in the above transient electromagnetic pulse signal recognition method, the model parameters of the pulse model function are updated based on the predicted value and the actual pulse amplitude value by a Kalman filter algorithm integrated with gradient calculation, including: Calculating an amplitude error based on the predicted value and the actual pulse amplitude value; Calculating the gradient of the model parameters based on the latest pulse time in the time information; Calculating a Kalman gain matrix based on the gradient; Model parameters of the pulse model function are updated based on the amplitude error, the Kalman gain matrix and a preset scalar learning rate.

[0009] Furthermore, in the above transient electromagnetic pulse signal recognition method, the model parameters include a correction factor , mathematical parameters of the pulse front Mathematical parameters of the pulse trailing edge ; The step of calculating the gradient of the model parameters based on the latest pulse time in the time information includes: Based on the time information, the latest pulse time x is obtained, and the gradient of the model parameters is calculated by the first formula , and , the first formula is: .

[0010] Furthermore, in the above transient electromagnetic pulse signal recognition method, the step of calculating the Kalman gain matrix based on the gradient includes: Calculate the observation vector based on the gradient :

[0011] in, represents transpose; Calculate the Kalman gain matrix based on the observation vector:

[0012] in, is matrix multiplication, is the covariance matrix.

[0013] Furthermore, in the above transient electromagnetic pulse signal recognition method, the updating of the model parameters of the pulse model function based on the amplitude error, the Kalman gain matrix and a preset scalar learning rate comprises: The model parameters are updated by a second formula, wherein the second formula is: .

[0014] Furthermore, the signal recognition method of the transient electromagnetic pulse, after the step of updating the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value by a Kalman filter algorithm incorporating gradient calculation, comprises: Determine whether the updated correction factor is higher than a preset threshold, and if so, perform further testing; The further testing includes: According to the mathematical parameters of the current pulse front edge and the mathematical parameters of the pulse rear edge, a plurality of pulse data containing time information are obtained; downsampling the pulse data; The downsampled pulse data is input into the updated pulse model function to obtain the predicted value corresponding to the downsampled pulse data; Calculating a mean square error based on the predicted value, and filtering the mean square error; The mean square error after filtering is compared with the detection threshold. If the mean square error after filtering is less than the detection threshold, it is determined that a pulse that conforms to the pulse model function has been detected. If the mean square error after filtering is greater than or equal to the detection threshold, it is determined that no valid pulse has been detected.

[0015] The present application also provides a transient electromagnetic pulse signal recognition device, including: An acquisition module, used for acquiring pulse data including time information and actual pulse amplitude value; A construction module is used to define a pulse model function and initialize model parameters of the pulse model function; An initial prediction module, used for inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; An updating module, configured to update the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value and by a Kalman filter algorithm incorporating gradient calculation; The recognition module is used to update the pulse model function based on the updated model parameters to obtain an updated pulse model function, input the collected pulse data into the updated pulse model function for recognition, and obtain a recognition result of the pulse data.

[0016] An embodiment of the present application further provides a computer-readable storage medium, wherein a plurality of instructions are stored in the computer-readable storage medium, and wherein the instructions are suitable for being loaded by a processor to execute any of the above-mentioned transient electromagnetic pulse signal identification methods.

[0017] An embodiment of the present application also provides an electronic device, including a processor and a memory, wherein the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used to perform the steps in the transient electromagnetic pulse signal identification method described in any one of the above items.

[0018] The transient electromagnetic pulse signal recognition method, device, storage medium and electronic device provided by the present application define a pulse model function, predict the pulse data through the pulse model function, update the model parameters of the pulse model function based on the predicted value and the Kalman filter algorithm integrated with gradient calculation, and identify the collected pulse data through the updated pulse model function. The present application achieves rapid detection of typical nuclear explosion pulses by fitting nonlinear time series model parameters using a recursive Kalman filter algorithm integrated with gradient descent. It can also dynamically update model parameters as new data arrives, accurately judge pulse data in real time, and there is no need to recalculate the entire model, thereby improving computational efficiency and obtaining more accurate detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The technical solution and other beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.

[0020] Figure 1 A flow chart of a transient electromagnetic pulse signal recognition method provided in an embodiment of the present application.

[0021] Figure 2 A schematic diagram of the structure of a transient electromagnetic pulse signal identification device provided in an embodiment of the present application.

[0022] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0023] Figure 4 Another schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] Traditional nuclear explosion identification methods mostly use a relatively primitive method of combining manual experience judgment with the detector trigger time window to judge nuclear explosion events (this can be attributed to the template matching method in pattern recognition). Most of the current popular identification technologies belong to statistical pattern recognition methods, which require certain prior knowledge of the NEMP to be identified, such as the signal generation mechanism and physical characteristics. Most of the existing research results focus on the two key steps of "feature extraction" and "classification decision". For example: feature extraction based on Hilbert-Huang (HHT) or wavelet transform, and signal classification and recognition based on BP neural network, support vector machine (SVM) or KNN. Such algorithms have been popularized and applied to a certain extent at present, but they also have their own problems. The HHT transform algorithm faces problems such as modal aliasing and endpoint effect. The wavelet transform can resist the influence of modal aliasing, but the feature extraction has high computational complexity and poor real-time performance. Similarly, waveform classification methods such as BP neural network and KNN face problems such as small feature training data, difficult collection, high quality requirements, and poor persuasiveness of experimental accuracy. On the other hand, the connections between multi-step operations are complex, the model cannot be updated dynamically, and it is impossible to build an end-to-end recognition or detection method.

[0026] In order to solve the above problems, the embodiments of the present application provide a transient electromagnetic pulse signal recognition method, device, storage medium and electronic device. The transient electromagnetic pulse signal recognition device provided in the embodiments of the present application can be integrated in an electronic device, which can be a terminal, a server and other devices, wherein the terminal can include a tablet computer, a laptop computer, a personal computer (PC), a micro processing box, or other devices.

[0027] See also Figure 1 , Figure 1 A flow chart of a transient electromagnetic pulse signal recognition method provided in an embodiment of the present application, which is applied in electronic equipment.

[0028] First of all, before collecting the electromagnetic pulse waveform, the preparations that need to be done are as follows: According to the actual situation, determine the characteristics of the electromagnetic pulse waveform. The following assumes that the input pulse waveform amplitude voltage range is: ±80mV~±10V, the single electromagnetic pulse waveform: the steepest rising front Tr(10%~90%)=10ns, and the maximum waveform duration is 500us. The noise includes low-frequency components that can be filtered out, and white noise with a standard deviation of 0.025V.

[0029] Design a signal sampling system: Consider using an ADC with a sampling rate of 250MHZ and an accuracy of 10bit to obtain the electromagnetic pulse waveform input signal.

[0030] Consider signal noise: The signal sampling system should take the DC and low-frequency components of the signal into consideration and set a reasonable detection threshold. If the residual noise after filtering is white noise and the standard deviation is 0.025V, 0.1V is used as the threshold for signal detection, which means that the probability of a noise signal exceeding 0.1V (4 times the standard deviation of noise) is 0.0063%.

[0031] Design waveform judgment conditions: When the mean square error between the predicted value and the sampled value within the interval is lower than the abnormal threshold, and the predicted correction factor k is higher than the expected value, the waveform is judged to meet the conditions.

[0032] Design the front-end signal processing solution of the signal sampling system. In order to reduce the spurious effect of active components (RF front-end with controllable gain) on the signal, a passive attenuator is used. And a reasonable detection threshold is set inside the FPGA.

[0033] Design a signal recording scheme. According to the requirements, use 1Mbyte SRAM as the onboard data storage to meet the storage requirements of 250MS / s sampling rate and the longest duration of the signal. To meet the need to record negative signals, take the absolute value of the input signal and store it for algorithm processing.

[0034] Design FPGA implementation scheme. FPGA realizes the functions of trigger level determination and signal acquisition, conversion and storage. In order to make full use of FPGA's high-speed signal processing capability, data preprocessing, sampling trigger, waveform detection and frequency domain conversion are realized inside FPGA through logic programming. Double buffer data storage method is adopted to ensure the reliability of detection. The transient electromagnetic pulse signal recognition method comprises the following steps: S1, obtain pulse data including time information and actual pulse amplitude value.

[0035] Among them, the pulse data containing time information and actual pulse amplitude value can be expressed as: several groups of pulse data (x, y) at time x and amplitude y.

[0036] Among them, the pulse data can be the nuclear explosion electromagnetic pulse generated at the moment of the nuclear explosion, or the electromagnetic pulse generated by lightning or microwave weapons.

[0037] S2, defining a pulse model function and initializing model parameters of the pulse model function.

[0038] Generally, the high-altitude transient electromagnetic pulse field strength can be expressed in the form of a double exponential function as follows:

[0039] In the formula, is the pulse peak value, is the correction factor, and They are the mathematical parameters of the pulse front edge and the pulse rear edge respectively. < It can be guaranteed that when t>0, the pulse is positive polarity. Controls the slower decay component, Controls the faster decay component.

[0040] Therefore, the fitted pulse model function can be defined as:

[0041] in, is the instantaneous value of the pulse, is the elapsed time.

[0042] Initializing the model parameters of the pulse model function includes: initializing the model parameters , and .in The initial value of is determined by the actual detected signal peak value. α and β The initial value of can be given in advance by prior knowledge of the waveform. For example, the standard in GB / T 18039.10-2018: Characteristics and evaluation methods of high altitude electromagnetic pulse (HEMP) environment can be referred to. For the early HEMP electric field waveform in free space, α=40000000 / s, β=600000000 / s (corresponding to 10%-90% rising front of 2.5ns and peak time of 4.8ns).

[0043] As an example, due to the expected The pulse amplitude should be gradually approached from low to high, and the pulse amplitude range is 0.1V to 10V. The initial value of k can be set according to 0.01V. Because the ADC accuracy is about 0.01V, the setting =0.01V / 0.01V = 1. and Corresponding to the rising and falling edges of the model signal. Approx. 40 times of the target signal waveform, and the rising edge duration is less than 2us. According to the calculation and simulation results, The lower limit is approximately , and because the ADC sampling rate is designed to be 250M SPS, it can be seen that The parameter value is not less than 0.004. Initial value 0.004, Initial value: 0.0001.

[0044] S3, inputting the pulse data into the initialized pulse model function to obtain the predicted value of the pulse data.

[0045] The predicted value of the pulse data is the predicted pulse amplitude value at the corresponding moment.

[0046] S4, based on the predicted value and the actual pulse amplitude value, the model parameters of the pulse model function are updated by a Kalman filter algorithm integrated with gradient calculation.

[0047] In one embodiment, step S4 may include the following steps: S41, calculate the amplitude error based on the predicted value and the actual pulse amplitude value:

[0048] in, is the actual pulse amplitude value, is the predicted value, is the amplitude error.

[0049] S42, calculating the gradient of the model parameters based on the latest pulse time in the time information.

[0050] Specifically, the latest pulse time x is obtained based on the time information, and the gradient of the model parameters is calculated by the first formula , and , the first formula is:

[0051] S43, calculating the Kalman gain matrix based on the gradient.

[0052] Specifically, the observation vector is calculated based on the gradient :

[0053] in, Indicates transpose.

[0054] Calculate the Kalman gain matrix based on the observation vector:

[0055] in, is matrix multiplication, is the covariance matrix. is a 3-section diagonal matrix, and its initial diagonal elements are all 100. The covariance matrix is ​​updated as follows:

[0056] S44, updating the model parameters of the pulse model function based on the amplitude error, the Kalman gain matrix and the preset scalar learning rate.

[0057] Specifically, the model parameters of the pulse model function are updated by the second formula, and the second formula is:

[0058] In one embodiment, after step S44, the model parameters may be modified according to other prior knowledge. , and range to avoid abnormal results. (For example: Limit the pulse amplitude to a preset range. and limited to a pre-set decay time constant).

[0059] In one embodiment, after step S4, the following steps are included: Determine the updated correction factor Is it higher than the preset threshold? If so, further testing is performed. If the correction factor If the value is not higher than a preset threshold, it is determined that the signal of the acquired pulse data is not similar to the pulse model function.

[0060] Further testing includes: S45, acquiring a plurality of pulse data including time information according to the mathematical parameters of the current pulse leading edge and the mathematical parameters of the pulse trailing edge.

[0061] Specifically, according to the current predicted values ​​of α and β, taking (ln(β) – ln(α)) / (β - α) sampling points before the peak point as the starting point, time series data with twice the length (pulse data containing time information) are extracted backward as the comparison object.

[0062] For NEMP scenarios, the extraction range can be simplified based on the prior knowledge of the ratio of β and α. For example, when β=kα, k>10, the range can be set to ln(k) / β. If β=0.01, k=20, take 3 / 0.01 = 300 points before the peak point as the starting point, and accumulate 600 sampling points backward as sampling data.

[0063] S46, down-sampling the pulse data.

[0064] According to the computing capability of the signal sampling system, the signal time series data extracted in step S45 is downsampled to reduce the amount of calculation for calculating the root mean square error. For example, when the signal sampling system can support a processing capability of 60 points, for data containing 600 sampling points, sampling can be performed at intervals of 9 points to reduce the number of sample points to 60.

[0065] S47, inputting the down-sampled pulse data into the updated pulse model function to obtain a prediction value corresponding to the down-sampled pulse data.

[0066] S48, calculating a mean square error e based on the predicted value, and filtering the mean square error e.

[0067] Specifically, the mean square error e can be filtered by an exponentially weighted moving average method to obtain the filtered mean square error E.

[0068] S49, compare the filtered mean square error with the detection threshold. If the filtered mean square error is less than the detection threshold (for example, 2 times the noise variance), it is determined that a pulse that meets the pulse model function has been detected. If the filtered mean square error is greater than or equal to the detection threshold, it is determined that no valid pulse has been detected and the detection signal is cleared.

[0069] S4A, when the updated model parameter k is higher than the "abnormal threshold" (such as the upper limit of the ADC range, or a large positive number), it is considered that the model parameters diverge during training or use, and the model parameters need to be reinitialized.

[0070] Repeat steps S3-S4 to update the model parameters of the pulse model function multiple times.

[0071] As an example, the “detection threshold” is set to 4 times the standard deviation of the noise signal, and the “abnormal threshold” is set to 2 times the ADC range.

[0072] If the signal of the electromagnetic pulse is higher than 0.1V and continuously lower than 10V, the pulse is judged to be valid if the mean square error output by the algorithm model is lower than the "detection threshold"; if it is higher than the "detection threshold" but lower than the "abnormal threshold", the pulse is judged to be invalid; if it is higher than the "abnormal threshold" or other situations, the model parameters are reinitialized and the recorded data are re-initialized.

[0073] The pulse data is collected through the signal sampling system. The FPGA algorithm module port needs to be set to read the sampling value of the pulse data. The specific settings are as follows: Input port: The ADC sampling value after passing through the high-pass filter with a cutoff frequency of 1kHz is an integer in the range of -511 to 512, and the corresponding voltage range is -10.22V to 10.24V.

[0074] Output port: TTL level. When it is judged as a valid waveform, it outputs a low level pulse with a pulse width of 5ms; otherwise, it outputs a high level.

[0075] Specific execution process: The FPGA program reads the sample value every 4ns and iterates.

[0076] The key parameters of FPGA algorithm iteration are designed as follows: B1, in case the input dynamic range of the pulse is too large, when the FPGA recognizes that the sampling value is higher than 10V or lower than -10V, it directly outputs a valid signal.

[0077] B2, for possible negative pulses, take the absolute value of the input ADC sampling value.

[0078] B3, algorithm initial parameters, model parameters Set to 5 (corresponding to 0.1V sampling value), Set to 0.0001, Set to 0.004, the learning rate Set to 0.1.

[0079] B4, after the model parameter iteration is completed, additional constraints Greater than 5 and less than 500, Greater than 0.0001 and less than 0.01, Greater than 0.004 and less than 0.4 to avoid invalid parameters.

[0080] B5, when calculating the mean square error, based on the current , , forward and backward from the peak point Elements are used as the starting point and the end point. 40 sampling values ​​are sampled at equal intervals as the calculation object.

[0081] B6, when applying the exponentially weighted moving average method to the mean square error e, the smoothing factor is 0.2.

[0082] S5, updating the pulse model function based on the updated model parameters to obtain an updated pulse model function, inputting the collected pulse data into the updated pulse model function for recognition, and obtaining a recognition result of the pulse data.

[0083] The present invention achieves rapid detection of typical nuclear explosion pulses by fitting nonlinear time series model parameters using a recursive Kalman filter algorithm integrated with gradient descent. The calculation method and model processing steps adopted can dynamically update model parameters as new data arrives, accurately judge pulse data in real time, and there is no need to recalculate the entire model, thereby improving calculation efficiency and obtaining more accurate detection results. The present invention implements an end-to-end design model derivation and directly outputs results. No other configuration or subsequent secondary algorithm processing of data is required during work. Compared with other nuclear explosion pulse detection methods, the dependence on manual modification and parameter configuration is reduced, making pulse detection more automated and intelligent. In addition, by quantitatively comparing the similarity between the collected time series and the target pulse model, the method of the present invention can achieve a wider pulse detection range and higher reliability.

[0084] According to the method described in the above embodiment, this embodiment will be further described from the perspective of a transient electromagnetic pulse signal recognition device. The transient electromagnetic pulse signal recognition device can be implemented as an independent entity or integrated in an electronic device. The electronic device can be a terminal, a server, etc., wherein the terminal can include a tablet computer, a laptop computer, a personal computer (PC), a micro processing box, or other devices.

[0085] See also Figure 2 , Figure 2 The transient electromagnetic pulse signal recognition device provided in the embodiment of the present application is specifically described, and is applied to electronic equipment. The transient electromagnetic pulse signal recognition device may include: An acquisition module, used for acquiring pulse data including time information and actual pulse amplitude value; A construction module is used to define a pulse model function and initialize model parameters of the pulse model function; An initial prediction module is used to input the pulse data into the initialized pulse model function to obtain the predicted value of the pulse data; An updating module, used for updating the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value and by using a Kalman filter algorithm integrated with gradient calculation; The recognition module is used to update the pulse model function based on the updated model parameters to obtain an updated pulse model function, input the collected pulse data into the updated pulse model function for recognition, and obtain a recognition result of the pulse data.

[0086] During specific implementation, the above modules and / or units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above modules and / or units can refer to the previous method embodiments. The specific beneficial effects that can be achieved can also refer to the beneficial effects in the previous method embodiments, which will not be repeated here.

[0087] In addition, the embodiment of the present application also provides an electronic device, which may be a computer, a tablet computer, or other device. Figure 3 As shown, the electronic device 400 includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.

[0088] The processor 401 is the control center of the electronic device 400. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or loading applications stored in the memory 402 and calling data stored in the memory 402, thereby monitoring the electronic device as a whole.

[0089] In this embodiment, the processor 401 in the electronic device 400 loads instructions corresponding to the processes of one or more application programs into the memory 402 according to the following steps, and the processor 401 runs the application programs stored in the memory 402 to implement various functions: Obtain pulse data including time information and actual pulse amplitude value; defining a pulse model function, and initializing model parameters of the pulse model function; Inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; Based on the predicted value and the actual pulse amplitude value, the model parameters of the pulse model function are updated by a Kalman filter algorithm incorporating gradient calculation; The pulse model function is updated based on the updated model parameters to obtain an updated pulse model function, and the collected pulse data is input into the updated pulse model function for recognition to obtain a recognition result of the pulse data.

[0090] The electronic device can implement the steps in any embodiment of the transient electromagnetic pulse signal identification method provided in the embodiments of the present application. Therefore, it can achieve the beneficial effects that can be achieved by any transient electromagnetic pulse signal identification method provided in the embodiments of the present invention. Please refer to the previous embodiments for details and will not be repeated here.

[0091] Figure 4The specific structural block diagram of the electronic device provided in the embodiment of the present invention is shown, and the electronic device can be used to implement the signal recognition method of transient electromagnetic pulse provided in the above embodiment. The electronic device 500 can be a terminal, a server and other equipment, wherein the terminal can include a tablet computer, a laptop computer, a personal computer (PC, Personal Computer), a micro processing box, or other equipment.

[0092] The RF circuit 510 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, and thus communicate with a communication network or other devices. The RF circuit 510 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity module (SIM) cards, memories, etc. The RF circuit 510 can communicate with various networks such as the Internet, corporate intranets, wireless networks, or communicate with other devices through wireless networks. The above-mentioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. The above-mentioned wireless networks may use various communication standards, protocols and technologies, including but not limited to Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as Institute of Electrical and Electronics Engineers standards IEEE 802.11a, IEEE 802.11b, IEEE802.11g and / or IEEE802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging and short messages, and any other suitable communication protocols, even those that have not yet been developed.

[0093] The memory 520 can be used to store software programs and modules, such as the corresponding program instructions / modules in the above embodiments. The processor 580 executes various functional applications and data processing by running the software programs and modules stored in the memory 520, that is, realizing the functions of taking pictures with the front camera, processing the captured images, and switching the display color of the display content on the display screen. The memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 520 may further include a memory remotely arranged relative to the processor 580, and these remote memories may be connected to the electronic device 500 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0094] The input unit 530 may be used to receive input digital or character information, and generate a keyboard and a mouse related to user settings and function control. The display unit 540 may be used to display information input by the user or information provided to the user and various graphical user interfaces, which may be composed of graphics, text, icons, videos, and any combination thereof. The display unit 540 may include a display panel 541, which may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like.

[0095] The audio circuit 560, the speaker 561, and the microphone 562 can provide an audio interface between the user and the electronic device 500. The audio circuit 560 can transmit the electrical signal converted from the received audio data to the speaker 561, which is converted into a sound signal for output; on the other hand, the microphone 562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 560 and converted into audio data, and then the audio data is output to the processor 580 for processing, and then sent to another terminal through the RF circuit 510, or the audio data is output to the memory 520 for further processing. The audio circuit 560 may also include an earplug jack to provide communication between an external headset and the electronic device 500.

[0096] The electronic device 500 can help the user receive requests, send information, etc. through the transmission module 570 (such as a Wi-Fi module), which provides the user with wireless broadband Internet access. Although the transmission module 570 is shown in the figure, it can be understood that it is not a necessary component of the electronic device 500 and can be omitted as needed without changing the essence of the invention.

[0097] The processor 580 is the control center of the electronic device 500. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 520, and calling data stored in the memory 520, it executes various functions of the electronic device 500 and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 580 may include one or more processing cores; in some embodiments, the processor 580 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 580.

[0098] The electronic device 500 also includes a power supply 590 (such as a battery) for supplying power to various components. In some embodiments, the power supply can be logically connected to the processor 580 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 590 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0099] Although not shown, the electronic device 500 also includes a camera (such as a front camera, a rear camera), a Bluetooth module, etc., which will not be described in detail here. Specifically in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal also includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be executed by one or more processors. One or more programs include instructions for performing the following operations: Obtain pulse data including time information and actual pulse amplitude value; defining a pulse model function, and initializing model parameters of the pulse model function; Inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; Based on the predicted value and the actual pulse amplitude value, the model parameters of the pulse model function are updated by a Kalman filter algorithm incorporating gradient calculation; The pulse model function is updated based on the updated model parameters to obtain an updated pulse model function, and the collected pulse data is input into the updated pulse model function for recognition to obtain a recognition result of the pulse data.

[0100] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0101] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions, and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present invention provides a storage medium, which stores a plurality of instructions, and the instructions can be loaded by a processor to execute the steps of any embodiment of the transient electromagnetic pulse signal recognition method provided in the embodiment of the present invention.

[0102] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0103] Since the instructions stored in the storage medium can execute the steps in any embodiment of the transient electromagnetic pulse signal identification method provided in the embodiments of the present invention, the beneficial effects that can be achieved by any transient electromagnetic pulse signal identification method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0104] The above is a detailed introduction to a transient electromagnetic pulse signal recognition method, device, storage medium and electronic device provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for signal recognition of transient electromagnetic pulses, characterized in that: The method comprises: Obtain pulse data including time information and actual pulse amplitude value; defining a pulse model function, and initializing model parameters of the pulse model function; Inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; Based on the predicted value and the actual pulse amplitude value, the model parameters of the pulse model function are updated by a Kalman filter algorithm incorporating gradient calculation; The pulse model function is updated based on the updated model parameters to obtain an updated pulse model function, and the collected pulse data is input into the updated pulse model function for recognition to obtain a recognition result of the pulse data.

2. The method for identifying transient electromagnetic pulse signals according to claim 1, characterized in that: The pulse model function is defined, comprising: The impulse model function is expressed by a double exponential function: in, is the instantaneous value of the pulse, is the elapsed time, is the correction factor, and They are the mathematical parameters of the pulse leading edge and the mathematical parameters of the pulse trailing edge respectively.

3. The method for signal recognition of transient electromagnetic pulse according to claim 1, characterized in that: The updating of the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value by a Kalman filter algorithm integrated with gradient calculation includes: Calculating an amplitude error based on the predicted value and the actual pulse amplitude value; Calculating the gradient of the model parameters based on the latest pulse time in the time information; Calculating a Kalman gain matrix based on the gradient; Model parameters of the pulse model function are updated based on the amplitude error, the Kalman gain matrix and a preset scalar learning rate.

4. The method for identifying transient electromagnetic pulse signals according to claim 3, characterized in that: The model parameters include correction factors , mathematical parameters of the pulse front Mathematical parameters of the pulse trailing edge ; The step of calculating the gradient of the model parameters based on the latest pulse time in the time information includes: Based on the time information, the latest pulse time x is obtained, and the gradient of the model parameters is calculated by the first formula , and , the first formula is: 。 5. The method for identifying transient electromagnetic pulse signals according to claim 3, characterized in that: The calculating of the Kalman gain matrix based on the gradient comprises: Calculate the observation vector based on the gradient : in, represents transpose; Calculate the Kalman gain matrix based on the observation vector: in, is matrix multiplication, is the covariance matrix.

6. The method for signal recognition of transient electromagnetic pulse according to claim 5, characterized in that: The updating of the model parameters of the pulse model function based on the amplitude error, the Kalman gain matrix and a preset scalar learning rate comprises: The model parameters are updated by a second formula, wherein the second formula is: 。 7. The method for signal recognition of transient electromagnetic pulse according to claim 1, characterized in that: After the step of updating the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value by a Kalman filter algorithm integrated with gradient calculation, the method further comprises: Determine whether the updated correction factor is higher than a preset threshold, and if so, perform further testing; The further testing includes: According to the mathematical parameters of the current pulse front edge and the mathematical parameters of the pulse rear edge, a plurality of pulse data containing time information are obtained; downsampling the pulse data; The downsampled pulse data is input into the updated pulse model function to obtain the predicted value corresponding to the downsampled pulse data; Calculating a mean square error based on the predicted value, and filtering the mean square error; The mean square error after filtering is compared with the detection threshold. If the mean square error after filtering is less than the detection threshold, it is determined that a pulse that conforms to the pulse model function has been detected. If the mean square error after filtering is greater than or equal to the detection threshold, it is determined that no valid pulse has been detected.

8. A transient electromagnetic pulse signal recognition device, characterized in that: include: An acquisition module, used for acquiring pulse data including time information and actual pulse amplitude value; A construction module is used to define a pulse model function and initialize model parameters of the pulse model function; An initial prediction module, used for inputting the pulse data into the initialized pulse model function to obtain a predicted value of the pulse data; An updating module, configured to update the model parameters of the pulse model function based on the predicted value and the actual pulse amplitude value and by a Kalman filter algorithm incorporating gradient calculation; The recognition module is used to update the pulse model function based on the updated model parameters to obtain an updated pulse model function, input the collected pulse data into the updated pulse model function for recognition, and obtain a recognition result of the pulse data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the transient electromagnetic pulse signal identification method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used to execute the steps in the transient electromagnetic pulse signal identification method according to any one of claims 1 to 7.

Images