77 results about "Signal averaging" patented technology

The invention belongs to the technical field of blood pressure monitoring, and particularly discloses an ECG and SCG combined continuous blood pressure monitoring method and system.The method comprises the following steps that an ECG signal and an SCG signal of the chest of a person to be detected are collected through an ECG electrode and an SCG sensor; carrying out signal averaging on the ECG signal and the SCG signal by adopting an averaging method; after average ECG signal and SCG signal segments are obtained, automatically identifying ECG and SCG signal feature points; according to the feature points of the ECG and SCG signals, feature parameters of the ECG and SCG signals are extracted; and constructing a blood pressure estimation model based on the ECG and SCG signal characteristic parameters, and outputting a blood pressure estimation result. By adopting the technical scheme, based on the synchronous ECG and SCG time domain characteristic parameters, the degree of dependence on the amplitude type parameters with large individual difference is reduced, the universality is higher, and the measurement precision is higher.

The invention provides a cardiac autonomic neurodynamics quantitative evaluation method based on a phase ordering signal averaging technology. The cardiac autonomic neurodynamics quantitative evaluation method comprises an ECG signal preprocessing step, a QRS wave detection and processing step, a phase ordering signal averaging step and an autonomic neurodynamics quantitative analysis step. According to the cardiac autonomic neurodynamics quantitative evaluation method based on the phase ordering signal averaging technology, on the basis of inhibiting aperiodic interference and improving index stability in a complex physiological environment, continuous analysis of cardiac sympathetic nerve activity and cardiac parasympathetic nerve activity is carried out; time-varying CSI and CPI indexes are extracted to realize quantification of cardiac autonomic neurodynamics, and a lightweight algorithm framework is designed to adapt to real-time monitoring requirements of portable equipment.

The invention relates to the technical field of V2I communication, and provides an OTFS signal blind frequency offset estimation method and device, and a medium, and the method comprises the steps: obtaining an OTFS baseband time domain receiving signal; based on the OTFS baseband time domain receiving signal, obtaining a time delay domain receiving signal; calculating the average power of the time delay domain received signals based on the time delay domain received signals; acquiring a time delay-Doppler domain signal based on the time delay domain receiving signal; estimating frequency offset through a cost function based on the time delay domain receiving signal average power and the time delay-Doppler domain signal; and performing frequency offset compensation on the received signal by using the estimated frequency offset. According to the method, the problem that the reliability of the system is reduced due to the fact that the vehicle runs at a higher speed in a V2I communication scene is solved, the robustness of the OTFS system to Doppler frequency shift can be further improved, and the communication quality of the vehicle during high-speed movement is guaranteed.

The invention provides a phase error correction method for an inductive position sensor. The device is characterized by consisting of a first group of multipliers (1), a sliding window integrator (2) for solving a signal average value in a period of time, a second group of multipliers (3) and an adder group (4). The method can be used for correcting and eliminating the phase error in the inductive position sensor chip circuit, and can be widely applied to the fields of industrial robots, automobile manufacturing, industrial automation and the like.

The present application discloses an information transmission method, device, network equipment, terminal and storage medium. The method includes: the network equipment sends first information to the terminal; the first information indicates a first reference signal used to determine at least one of the following parameters: average delay; delay spread.

The embodiment of the present application provides a high-frequency communication terminal performance detection system and related methods. By introducing two independently operable signal test paths, a base station simulator, a carrier coupler, a directional coupler and a first power meter form a signal test path; a base station simulator, a 5G millimeter wave coupler, a 5G millimeter wave receiving antenna and a first power meter form another signal test path. The two test paths can independently perform signal tests, and the upper host control machine summarizes and analyzes the real-time power measurement results of the 5G millimeter wave uplink signal and the real-time power measurement results of the LTE uplink signal, and generates a relevant performance test report. The performance test report records the average time power of the millimeter wave uplink signal and the average time power of the LTE uplink signal corresponding to the high-frequency communication terminal under test. The above architecture has high scalability and configuration flexibility, and can be used to effectively and reliably detect the high-frequency time average power of the uplink signal of the communication terminal.

A method of estimating local oscillator leakage (LOL) for a radio frequency (RF) signal transmitter. The method comprises generating a transmitter wideband baseband signal (s(t)) with a direct current (DC) voltage element of the transmitter wideband baseband signal (s(t)) removed or blocked and an average of the transmitter wideband baseband signal (s(t)) set to zero. The method includes processing said transmitter wideband baseband signal (s(t)) to form a RF signal; processing the RF signal to obtain a receiver baseband signal (y(t)); and determining a magnitude of an average of the receiver baseband signal (y(t)) as comprising a magnitude of the transmitter DC offset.

A method of estimating local oscillator leakage (LOL) for a radio frequency (RF) signal transmitter. The method comprises generating a transmitter wideband baseband signal (s(t)) with a direct current (DC) voltage element of the transmitter wideband baseband signal (s(t)) removed or blocked and an average of the transmitter wideband baseband signal (s(t)) set to zero. The method includes processing said transmitter wideband baseband signal (s(t)) to form a RF signal; processing the RF signal to obtain a receiver baseband signal (y(t)); and determining a magnitude of an average of the receiver baseband signal (y(t)) as comprising a magnitude of the transmitter DC offset.

The invention relates to a method for measuring soil moisture content based on coupling of a ground penetrating radar early signal average amplitude envelope (AEA) method and an autoregressive moving average power spectrum (ARMA) method, and belongs to the field of soil moisture content measurement, and the method comprises the following implementation steps: (1) researching the relationship between the early signal average amplitude envelope and the soil moisture content; (2) researching the relationship between a radar signal power spectrum below an early signal time window and the soil moisture content, and exploring the effective detection depth of the AEA method for inverting the soil moisture content; (3) calculating a radar signal power spectrum by adopting ARMA (autoregressive moving average), and preferably selecting attributes which are closely related to the soil moisture content and are mutually independent according to a fitting relation between each attribute of the power spectrum and the soil moisture content and a cross-correlation relation among the attributes; (4) combining the effective detection depth of the AEA method, and selecting a proper Gaussian window to divide the radar signal to obtain power spectrums of different depths; and (5) inverting the soil moisture content according to the relationship between each power spectrum attribute and the soil moisture content obtained by BP neural network training. According to the method provided by the invention, nondestructive detection of the field scale soil moisture content can be realized, detection of the soil moisture content in the whole detection range of the ground penetrating radar can be realized, and the error of the moisture content is less than 1%.

A yarn monitoring system for textile machines uses sensors to indicate yarn over-tensioning and breakage. The sensors within eyelets monitor the passage of the yarn and send new signals to the controller. The eyelets, each with a sensor, are within a body containing a circuit board which is in constant communication with the sensors and software contained within a controller. The controller is in constant communication with the textile machine. The software contains an acceptable operational zone for new signal data and control limits establishing the lowest new signal data reading permitted for the yarn. The user establishes set points for the control limits, and reaching these set points is an indication of over-tension or yarn breakage. To prevent unnecessary shut down of the machine, the software averages the new signal data and, when the new signal average remains out of the established set points, initiates communication to the textile machine.

A method of estimating local oscillator leakage (LOL) for a radio frequency (RF) signal transmitter. The method comprises generating a transmitter wideband baseband signal (s(t)) with a direct current (DC) voltage element of the transmitter wideband baseband signal (s(t)) removed or blocked and an average of the transmitter wideband baseband signal (s(t)) set to zero. The method includes processing said transmitter wideband baseband signal (s(t)) to form a RF signal; processing the RF signal to obtain a receiver baseband signal (y(t)); and determining a magnitude of an average of the receiver baseband signal (y(t)) as comprising a magnitude of the transmitter DC offset.

The embodiment of the present application provides a method for evaluating fine cracks in cement-based materials based on digital image processing. The technical key points are: stretching a target specimen of a high-toughness cement-based composite material ECC, collecting a crack image once at a fixed interval through a camera, and obtaining a background-corrected crack image by performing signal averaging conversion, median filter filtering and other operations on the crack image; obtaining qualified binary images that accurately contain information on fine cracks and wide cracks in sequence through an edge recognition algorithm or a dual threshold algorithm; denoising and enhancing each of the qualified binary images in reverse and forward order according to the time sequence axis of shooting, obtaining the pixel area and boundary coordinates of each crack region through each of the denoised images, identifying the crack width as the projection length of the crack in the loading direction, and obtaining the average width of the crack by dividing the pixel area of ​​the crack region by the crack length, accumulating the crack length and dividing it by the entire width of the specimen to obtain the number of cracks.

A detector circuit for a measurement instrument is described. The detector circuit includes a first signal input, a second signal input, and an averaging sub-circuit. The first signal input is configured to receive a first complex-valued measurement signal associated with an input signal received from a device under test. The second signal input is configured to receive a second complex-valued measurement signal associated with the input signal received from the device under test. The averaging sub-circuit is configured to determine an average of the first complex-valued measurement signal and of a complex conjugate of the second complex-valued measurement signal over a predetermined number of samples, thereby obtaining a complex-valued average signal. The averaging sub-circuit is configured to generate an output signal based on the complex-valued average signal. Further, a signal processing circuit and a measurement instrument are described.

A kind of depth camera module with dirt detection function, including laser emitter, for switchably emitting structured light or floodlight;Receiver, for receiving the reflection signal of the structured light or the floodlight;Controller, for controlling the laser emitter emits structured light and floodlight in a certain proportion, the receiver receives the first signal of adjacent structured light and the second signal of the floodlight, respectively generates first depth map and second depth map, obtains first area N1 with depth value less than N on the first depth map, obtains second area N2 with depth value less than N on the second depth map, according to the ratio of signal average intensity on the first area N1, the second area N2 judges whether there is dirt on lens or not.The present application does not need additional device, can carry out dirt detection at any time, and does not affect data acquisition, with very high efficiency and convenience.

This invention relates to a method and system for monitoring and enhancing the power of GPS P(Y) signals based on civilian signal tracking. The method employs a carrier tracking loop to stably track civilian satellite navigation signals, generating a local carrier with the same frequency and phase as the GPS satellite navigation digital signal. The GPS satellite navigation digital signal is then orthogonally mixed with the local carrier to output the in-phase branch signal u. I (n) and the orthogonal branch signal u Q (n); the in-phase branch signal u I (n), Orthogonal branch signal u Q (n) Perform low-pass filtering and incoherent integration respectively to obtain the average power P of the baseband signal in the in-phase branch. IB Average power P of baseband signal in orthogonal branch QB The average power P of the baseband signal in the same phase branch IB Average power P of baseband signal in orthogonal branch QB The power enhancement state of the current P(Y) signal is determined by comparing it with the weak-state power threshold of the in-phase branch, the strong-state power threshold of the in-phase branch, the strong-state power threshold of the quadrature branch, and the weak-state power threshold of the quadrature branch.

This invention discloses a remote, non-contact heart rate estimation method, system, and device based on sparse structure representation, belonging to the field of physiological sign research applications. It addresses the problem of inaccurate heart rate signal detection in existing methods, including: Step 1: Inputting a face video and segmenting the face into multiple sub-regions; Step 2: Constructing the average RGB pulse signal for each sub-region, performing motion compensation, and calculating the chromaticity signal S using linear combinations of different RGB channels, and calculating the signal-to-noise ratio; Step 3: Solving for the coefficient matrix using a structure dictionary composed of cosine bases of different frequencies and wavelet bases of different scales, and reconstructing the heart rate signal using the structure dictionary and coefficient matrix; Step 4: Averaging the reconstructed sub-region heart rate signals and performing power spectral analysis to calculate the heart rate HR. Finding the optimal sparse representation based on the dictionary, reconstructing the heart rate signal using the dictionary and sparse coding, and representing the most realistic heart rate signal with as few dictionary atoms as possible helps improve the accuracy of the algorithm.

This invention discloses a variable-step automatic gain control method based on an adaptive window, applicable to signal automatic gain control in data acquisition systems. The method preprocesses the input signal and samples it using an ADC to obtain a digital signal, which is then fed into an FPGA. A zero-crossing detection method based on a hysteresis comparator is used to estimate the signal frequency, and the window length is calculated based on this adaptive amplitude matching. The average signal amplitude within the window is then calculated and compared with a preset automatic gain threshold range. The gain step value is dynamically matched and updated to the variable gain amplifier to complete closed-loop control. Finally, the gain value is used to perform an amplitude inverse calculation to restore the signal. This invention improves the detection accuracy and dynamic response speed of the system over a wide bandwidth and dynamic range, eliminates the hardware resource consumption of floating-point division operations, and accurately outputs a distortion-free original proportional signal stream.

The embodiment of the invention discloses a power amplification circuit and electronic equipment, and belongs to the technical field of power electronics. The power amplification circuit comprises a power amplifier, the input end of the power amplifier receives an input radio frequency signal, and the power amplifier is used for performing power amplification on the input radio frequency signal and outputting an amplified radio frequency signal; the input end of the bridge coupler is connected with the output end of the power amplifier, and the bridge coupler is used for averagely dividing the amplified radio frequency signal input by the power amplifier into two paths of output radio frequency signals and respectively outputting one path of output radio frequency signal through the two output ends; and one end of the matching load is connected with the isolation end of the bridge coupler, the other end of the matching load is grounded, and the matching load is used for assisting the bridge coupler in isolating the reflected radio frequency signal. According to the embodiment of the invention, the insertion loss introduced by the final-stage circulator is reduced, the size and cost of the power amplification circuit are reduced, and the final-stage output power and the final-stage efficiency are improved.

The present invention relates to the technical field of underwater acoustic signal processing, and provides a method for accurately directing underwater targets by synthesizing vector hydrophone array signals, comprising: obtaining vector hydrophone array signals of sound sources related to underwater targets; designing a conventional beamforming matrix; performing Kronecker product operations on the vector hydrophone array signals using the conventional beamforming matrix, thereby synthesizing the vector hydrophone array signals into new vector signals; and obtaining the azimuth information of underwater targets by using a single vector hydrophone directing method based on the new vector signals. The present invention synthesizes the vector hydrophone array signals into new vector signals by performing Kronecker product operations on the conventional beamforming matrix and the vector hydrophone array signals, and introduces spatial processing gain and array signal averaging operations, thereby improving the signal-to-noise ratio of the vector hydrophone array and the tolerance of array errors and array element errors.

Yaw drive monitoring method The invention describes a method of monitoring a wind turbine yaw system (2) comprising a plurality of yaw drives (D1, …, D8), which method comprises, for each yaw drive (D1): receiving encoder data (Eout) from a motor speed encoder (E) of that yaw drive (D1); computing a signal mean (10M) on the basis of the received encoder data (Eout); computing a collective signal mean (10Mcoll) from the signal means (10M) of the other yaw drives (D2, …, D8); comparing the signal mean (10M) to the collective signal mean (10Mcoll); and flagging that yaw drive (D1) as potentially faulty if the corresponding comparison result (10Δ) exceeds a predefined threshold (10T). The invention further describes a monitoring arrangement (1) for a wind turbine yaw system (20); and a 15 wind turbine (2) comprising such a monitoring arrangement (1).

Method for measuring the effective value (Ueff) of an alternating voltage, comprising the steps of: (a) applying the alternating voltage to a Pockels cell (12) of an alternating voltmeter (10), (b) guiding an incident light beam (24) linearly polarized in an input polarization direction through the Pockels cell (12) to produce a linearly polarized outgoing light beam (26) whose output polarization direction is rotated by a deflection angle relative to an input polarization direction of the incident light beam (24), (c) guiding the outgoing light beam (26) through a polarizer (16) to produce a polarization-filtered light beam (28), (d) measuring an alternating voltage-dependent intensity of the polarization-filtered light beam (28) to obtain an electrical measurement signal (Umess), and (e) determining the alternating voltage from the electrical measurement signal (Umess),(f) wherein determining the alternating voltage comprises low-pass filtering of the electrical measurement signal (Umess) so that a temporal measurement signal average (Aac(t)) is obtained, characterized in that (g) the effective value (Ueff) is determined from the temporal measurement signal average (Aac(t)) and characterized by the steps: (h) applying a positive feedback DC voltage to the Pockels cell (12), (i) guiding an incident light beam (24) linearly polarized in the input polarization direction through the Pockels cell (12) so that a linearly polarized outgoing light beam (26) is created, the output polarization direction of which is rotated by a deflection angle to an input polarization direction of the incident light beam (24), (j) guiding the outgoing light beam (26) through the polarizer (16) so that the polarization-filtered light beam (28) is created,(k) measuring a DC voltage-related positive voltage intensity of the polarization-filtered light beam (28), (l) applying a negative DC voltage feedback to the Pockels cell (12), (m) measuring a DC voltage-related negative voltage intensity of the polarization-filtered light beam (28), and (n) determining the AC voltage from the positive voltage intensity, the negative voltage intensity, and the AC voltage-related intensity.

The present invention belongs to the field of speech processing and transmission technology, and specifically provides a joint source-channel coded speech wireless transmission method based on an adjusted autoencoder, which is used to adapt a single deep joint source-channel model to different channel conditions. The autoencoder of the present invention includes: a transmitter, a channel module, and a receiver. The transmitter includes: a joint encoder and an adjustment network. The channel module includes: a signal average transmit power limiter and a wireless channel. The receiver includes: a joint decoder and a demodulation network. The adjustment network and the demodulation network generate adjustment factors based solely on the signal-to-noise ratio (SNR) value of the wireless channel, and scale the speech feature vectors in the joint encoder and joint decoder to adjust the encoding and decoding processes, thereby achieving the ability to resist channel noise of varying intensities. Based on this, the present invention can provide robust speech wireless transmission performance within a given channel SNR range, surpassing existing deep joint source-channel methods.

The invention belongs to the technical field of integrated circuits, and provides a single-ended MEMS input-to-differential output circuit and an implementation method thereof. Through the CMFB circuit, effective signals of the CMEMS are averagely distributed to the VBIAS end and the VIN end, the maximum signal range which can be processed by the Pre-amplifier is doubled, meanwhile, a single-end-to-differential circuit is omitted, power consumption and noise are reduced, and circuit performance is improved. Compared with the prior art, according to the technical scheme, an impedance matching circuit or a capacitance compensation circuit is omitted, so that signal attenuation caused by parasitism is reduced, and performance is improved. Particularly, the stray capacitance of the VBIAS end can be ignored. The problem of performance deterioration under the condition that the stray capacitance of the VBIAS end is too large in the prior art is solved.

The invention relates to a control method and device for measuring and calculating the stability of a double-end flexible interconnection system, and the method comprises the steps: enabling a load converter to be equivalent to a constant-power load based on a large-signal averaging model of a three-phase PWM rectifier with a load, and estimating the stability boundary of the three-phase PWM rectifier with the constant-power load; applying a disturbance signal within the stable boundary, sampling the output side voltage and current of the three-phase PWM rectifier, and making a difference between the output side voltage and an output reference voltage, and taking the difference as a voltage drop on an output equivalent resistor of a Buck Boost system port; the voltage drop is sent to an impedance simulation link, and a Buck Boost system port output current reference instruction value is obtained; the difference value between the current reference instruction value and the output side current is sent to a current loop controller for closed-loop control, and the duty ratio change of the Buck Boost system is obtained; and the duty ratio change of the Buck Boost system is compared with the sawtooth wave of the modulation module, and a switching signal of the power device is generated according to the comparison result. According to the invention, a better stability measuring and calculating mode can be realized.

The present invention discloses a method for automatic control of the transmitting power of a monitoring interference system based on multi-parameter weighting. First, the target signal of the monitoring unmanned aerial vehicle is acquired; the average signal amplitude, signal duty cycle, and signal bandwidth ratio are calculated respectively based on the target signal of the monitoring unmanned aerial vehicle, and the modulation type of the signal is discriminated; the average signal amplitude, signal duty cycle, signal bandwidth ratio, and signal modulation type are weighted respectively to obtain the corresponding weighted values; according to the weighted value of the average signal amplitude, the weighted value of the signal duty cycle, the weighted value of the signal bandwidth ratio, and the weighted value of the signal modulation type, a multi-parameter weighted value is obtained; the decibel value for controlling the transmitting power is calculated through the multi-parameter weighted value, and the obtained decibel value is converted into the control quantity of the gain control circuit of the interference system in the monitoring interference system to realize the automatic control of the transmitting power; the cost-effectiveness of the interference signal is significantly improved, the cost expenditure is reduced and the benefit is increased, and the pollution of the surrounding electromagnetic environment is effectively reduced.

The present invention relates to the technical field of wireless communications. Disclosed in the present invention is a power amplifier. The power amplifier comprises a signal input end, a radio frequency amplifier and a signal output end which are electrically connected in sequence, and an average power tracking circuit. An input end of the average power tracking circuit is used for connecting a power supply and receiving an output signal of an external host computer, an output end of the average power tracking circuit is connected to an input end of a radio frequency amplifier, and the average power tracking circuit is used for converting, on the basis of a received target voltage value, a power supply voltage output by the power supply into a preset voltage to supply power to the radio frequency amplifier. The average power tracking circuit comprises a voltage conversion circuit, a comparator, a loop filter circuit, a PWM modulator, a voltage divider circuit, a pulse circuit, and a first inductor. By switching the characteristics of the loop filter, the present invention enables the power supply to achieve both fast establishment and high-precision output, thereby allowing a working voltage of the amplifier to be as low as possible, and further reducing power consumption of the power amplifier.

The invention discloses a classical Bluetooth adaptive frequency hopping optimization method and device, and relates to the field of Bluetooth transmission. The method comprises the following steps: counting the average power of received signals while Bluetooth master equipment receives a response data packet of slave equipment in odd time slots; the average background noise power is counted in the idle time before the odd number of time slots are finished; determining a real-time signal-to-noise ratio according to a ratio of the average power of the received signal to the average power of the background noise; judging whether the real-time signal to noise ratio is greater than a signal to noise ratio threshold value; if yes, the current channel is kept in an available state in the self-adaptive frequency hopping mapping table; if not, updating the adaptive frequency hopping mapping table, and marking the current channel as an unavailable state; and synchronizing the updated adaptive frequency hopping mapping table to the slave device, so that the master device and the slave device are switched to the updated adaptive frequency hopping mapping table for communication according to preset time. The technical problems that the real-time performance is poor and the transmission efficiency is affected when the frequency hopping mapping table is generated in the Bluetooth transmission process are solved.

The invention relates to the technical field of electrocardiosignal analysis, and discloses an autonomic nerve function evaluation method based on a phase whole sequence signal averaging technology, and the method comprises the steps: selecting a plurality of deceleration anchor points and / or acceleration anchor points from a plurality of sequence values of a heart beat interval sequence of a first to-be-detected object; for each deceleration anchor point / acceleration anchor point, selecting a deceleration sequence segment / acceleration sequence segment corresponding to each deceleration anchor point / acceleration anchor point from the heart beat interval sequence of the first to-be-tested object; averaging values with the same sequence in the plurality of deceleration sequence segments / acceleration sequence segments to obtain a deceleration signal sequence / acceleration signal sequence of the first to-be-detected object; performing power spectral density analysis on the deceleration signal sequence / acceleration signal sequence of the first to-be-detected object to obtain a deceleration index / acceleration index of the first to-be-detected object; and evaluating the autonomic nerve function of the first to-be-tested object according to the deceleration index and / or the acceleration index of the first to-be-tested object. The autonomic nerve function can be evaluated more accurately.

The application discloses a face video blood oxygen saturation detection method and system based on deep learning, and relates to the technical field of computer vision; the method comprises the following steps: shooting a face video; acquiring frame-by-frame pictures of segmented face key regions in the face video; extracting iPPG signals of the face key regions through the frame-by-frame pictures of the face key regions, and equally dividing the iPPG signals of each face key region into multiple segments; training a CNN-BiLSTM-GRU blood oxygen saturation prediction model; inputting the segmented iPPG signals into the CNN-BiLSTM-GRU blood oxygen saturation prediction model respectively, and obtaining multiple preliminary blood oxygen saturation prediction values for each face key region; inputting the multiple preliminary blood oxygen saturation prediction values of each face key region into discriminators respectively, and obtaining final blood oxygen saturation prediction values through signal screening; and the method can effectively and reliably predict oxygen saturation values from the face video, and can meet the long-term detection of blood oxygen saturation values in daily life.

The invention relates to the technical field of signal processing, in particular to a signal-to-noise ratio estimation algorithm based on an auto-encoder, which comprises the following steps of: firstly, selecting four groups of parameter signals with different code element rates and roll-off factors, each group containing 16 mainstream modulation type sub-signals, segmenting the sub-signals, adding Gaussian white noise to construct a data set, and performing data processing on the data set; dividing into a training set and a verification set according to the ratio of 7: 3, and calculating a noise adding signal and a power spectrum of corresponding noise by adopting a Welch method; secondly, constructing a stacked full-connection auto-encoder, taking a training set noise adding signal power spectrum as input, taking a noise power spectrum as a target, and introducing L2 regularization suppression over-fitting according to set batchsize and epoch training; and finally, inputting a test set noise adding signal into the trained model to obtain the noise average power, and calculating the signal average power and the signal-to-noise ratio by combining the noise adding signal power spectrum. The method can cover multiple signal parameters and modulation scenes, the low signal-to-noise ratio interval precision is better, the process is clear, engineering landing is easy, and the method is suitable for a multi-standard communication system.