373 results about "Time frequency transform" patented technology

The invention discloses a turbofan engine operation monitoring method and system based on digital twinning, belongs to the technical field of turbofan engine monitoring, and aims to solve the problems that weak fault signals such as early cracks and abrasion are difficult to extract and the prediction precision of a multi-source fault propagation path is low under a strong noise background. An original operation signal is collected through a sensing array, and is processed by an adaptive resonance demodulation chain to generate a demodulation signal. The method comprises the following steps: carrying out time-frequency transformation on a demodulation signal, constructing an initial candidate feature set by combining feature frequency prior matching actual measurement and theoretical feature frequency, and generating an independent feature set by fusing multi-scale decoupling network separation features of digital twin constraints; for independent features, effective causal pairs are screened by adopting a physical coupling relationship combining Granger causal analysis and digital twinborn simulation, a dynamic Bayesian network is constructed to simulate fault propagation, a posterior probability is calculated through digital twinborn verification and Monte Carlo simulation, early warning is triggered, and a maintenance decision is generated. And weak signal extraction and accurate fault prediction under strong noise are realized.

The invention discloses a self-adaptive frequency spectrum monitoring and interference suppression method for a railway power transformer. The method comprises the following steps: S1, collecting original multi-source signal data; s2, performing high-order filtering and Z-score normalization processing on the original multi-source signal; s3, inputting the original multi-source signal into a multi-scale residual fusion time-frequency transformation network, and extracting a time-frequency feature tensor; s4, inputting the time-frequency feature tensor into the interference identification network fused with the attention mechanism; s5, dynamically activating an interference suppression module according to an identification result; s6, constructing a multi-dimensional tensor data structure, extracting sparse dictionary morphological features and spectral domain statistics, and generating a composite feature vector set; s7, inputting the composite feature vector into a health state evaluation module; and S8, uploading the diagnosis result to a remote monitoring platform through the embedded communication module. According to the invention, multi-dimensional perception and adaptive modeling are fused, and intelligent identification and remote monitoring of railway transformer faults are realized.

The invention relates to an audio noise reduction method, device and system based on deep learning, and the method comprises the steps: obtaining an input audio signal with noise, and carrying out the multi-scale time-frequency decomposition, and obtaining a mixed time-frequency feature and a noise fingerprint spectrum; performing parameter parallel processing on the noise fingerprint spectrum through a preset dynamic kernel generation network, and performing preliminary noise reduction processing on the mixed time-frequency characteristics to obtain noise-reduced mixed data; performing dual-path processing structure construction on the noise reduction mixed data to obtain amplitude optimization data and phase optimization data; performing dynamic time-frequency domain cross fusion on the amplitude optimization data and the phase optimization data to obtain fused audio data; and carrying out differentiable acoustic equation constraint adversarial training on the fused audio data, and carrying out inverse time-frequency transformation processing to obtain a target noise-reduced audio signal. According to the invention, the overall efficiency and effect of audio signal processing can be effectively improved.

The invention relates to a millimeter wave radar vital sign modeling method based on time-frequency characteristic decoupling. According to the method, a millimeter wave radar array is arranged, reflection echo signals are collected, and pure initial signal data are obtained; performing time-frequency transformation on the initial signal data based on a multi-scale sliding window to generate a time-frequency energy distribution map; according to the energy concentration degree and stability difference of different frequency components in the time-frequency spectrum, frequency components which are high in energy concentration degree and have continuous, stable and periodic changes on a time axis are extracted and serve as effective signal components corresponding to human respiration and heartbeat characteristics; extracting a corresponding frequency change trajectory according to the effective signal components, establishing a vital sign signal trajectory model based on a time-frequency characteristic change trend, and determining an optimal vital sign trajectory path according to the stability and continuity of the trajectory on a time axis; and establishing a vital sign monitoring model by using the optimal vital sign track path to realize high-precision monitoring of human respiration and heart rate.

The invention relates to the technical field of mechanical vibration testing, in particular to a method for testing dynamic rigidity and damping characteristics of an engine support, which comprises the following steps of: 1, simulating a boundary; step 2, double-source excitation loading is carried out; step 3, dynamic response acquisition: arranging vibration measurement points in the main shaft direction of the rigidity of the support to acquire acceleration signals in three directions, synchronously acquiring excitation force signals, and recording all the signals at a set sampling rate after anti-aliasing filtering; 4, constructing a frequency response matrix: performing time-frequency transformation on the exciting force signal and the acceleration signal, and calculating a cross-point frequency response function matrix; 5, parameter decoupling calculation is carried out, wherein parameter decoupling is achieved through cross iterative optimization; and 6, outputting parameters. Through the decoupling calculation of the low frequency band and the high frequency band, the cross iteration optimization method can effectively reduce the calculation error, improves the parameter decoupling precision, and guarantees the reliability of the test result under different frequency bands.

The invention discloses a high-low voltage switch cabinet feeder fault positioning method and system based on transient traveling waves, and belongs to the technical field of power system fault detection and positioning, and the method comprises the steps: synchronously collecting electric and acoustic multi-mode signals, and generating a weighted transient synchronization feature matrix; performing time-frequency transformation and feedback optimization on the matrix, and outputting a multi-scale time-frequency feature set; analyzing the feature set by using an integrated learning network, and outputting a layered preliminary positioning result; convergence to an accurate fault section is carried out through iteration calibration; and finally, fusing multi-model calculation and outputting a comprehensive fault positioning report. According to the method, a technical path of combining multi-modal signal fusion and a physical model is adopted, convergence from fuzzy region division to an accurate position can be realized in stages, and the accuracy, the speed and the anti-interference capability of switch cabinet feeder line fault positioning are remarkably improved.

The invention discloses a hydroelectric generating set operation fault data enhancement method and device, and the method comprises the steps: firstly collecting a set vibration signal, selecting a time-frequency transformation method to convert a one-dimensional vibration signal into a two-dimensional time-frequency image, enhancing the feature dimension of the signal, constructing a diffusion feature migration model, gradually disturbing the data distribution to Gaussian noise through forward diffusion, and carrying out the recognition of the Gaussian noise. The method comprises the following steps of: performing inverse denoising to generate simulation data highly similar to a real fault sample, realizing relevance learning and migration sharing of fault features among different working conditions in combination with an adversarial feature migration architecture, and finally evaluating an enhancement effect by calculating similarity among samples, and inputting enhanced data into a fault diagnosis model to verify precision improvement. Through the combination of time-frequency transformation and a diffusion model, sample scarcity and working condition barriers are broken through, a remarkable effect is shown in the aspects of expanding the fault sample scale and enriching the sample dimension, the similarity of generated data and a real sample is improved, the diagnosis precision is improved, and the model generalization ability is remarkably enhanced.

The invention discloses an intelligent gearbox state monitoring method based on a Transform network, and the method comprises the following steps: collecting vibration and rotating speed signals, and generating a standardized sequence through synchronization and resampling; performing time-frequency transformation on the sequence, extracting order, transient energy and cyclostationary characteristics, and forming a tensor; inputting the tensor into a time sequence Transform network to obtain a coding feature and attention distribution; constructing a weighted graph based on attention and executing persistent coherence to generate a barcode set; establishing a hierarchical structure and calculating barcodes of different dimensions to form cross-scale description; mapping the description into a persistent image, and outputting topological features through constraint optimization; and fusing topological features and coding features, inputting the fused features into a classification and regression module, and outputting a health state, an abnormal score and degradation evaluation. According to the method, the Transform and the persistent coherence are combined, so that high-precision diagnosis of the gearbox signal under the complex working condition is realized.

The invention discloses a live detection method for insulation defects of high-voltage power equipment. The method comprises the following steps: firstly, synchronously arranging ultrahigh frequency sensors and acoustic emission sensors on a plurality of monitoring points on the surface of a gas insulated switchgear shell to form an array, and synchronously acquiring signals for filtering pretreatment; then, pulse events are extracted from the two types of signals respectively, and associated pulses in a time window are matched into matched pulse pairs representing the same discharge source; then, carrying out time-frequency transformation on the ultrahigh frequency and acoustic emission pulse waveform in each matched pulse pair, carrying out joint noise reduction by calculating a coherence coefficient between time-frequency distribution matrixes, and extracting a joint feature vector containing an energy ratio, a time parameter ratio and a frequency difference from the denoised time-frequency matrix; according to the invention, multi-source signals are fused, and high-sensitivity detection, high-precision positioning and high-accuracy identification of insulation defects are realized.

The invention discloses an emergency rescue real-time human body detection method and device based on time sequence motion feature enhancement, and the method comprises the steps: obtaining visible light and infrared image sequences of a rescue region and environment parameters (including smoke concentration and illumination intensity) in real time, and carrying out the spatial registration preprocessing; respectively carrying out frame difference processing on the two types of image sequences, generating a binary motion mask, calculating an optical flow amplitude, and carrying out adaptive fusion according to smoke concentration to obtain a multi-scale motion energy field; human body micro-motion frequency band energy is extracted through time-frequency transformation, a frequency domain dynamic attention mask is generated, and a saliency motion target area is extracted in combination with a multi-scale motion energy field; constructing a double-branch neural network, extracting time sequence motion features and multi-modal appearance features, dynamically distributing weights and fusing the weights, and outputting a human body bounding box and detection confidence; and calculating environment complexity according to the environment parameters, determining a dynamic confidence threshold, verifying a detection result by combining the average temperature of the human body bounding box region, and generating alarm information if a condition is met. The method aims at solving the problems that a traditional method is high in omission ratio and unstable in recognition in a complex environment.

The invention discloses a method for selecting and triggering gamma instant radiation pulse events, and belongs to the technical field of nuclear radiation detection. The method comprises the following steps: carrying out normalization preprocessing on an original gamma pulse radiation time spectrum; s time-frequency transformation is carried out on the preprocessed data, and time-frequency features are extracted; optimizing parameters of the frequency threshold and the amplitude threshold after S time-frequency transformation by adopting a deep reinforcement learning model to obtain an optimal frequency threshold and an optimal amplitude threshold; performing filtering processing on the signal of the S time-frequency conversion result, and separating noise from an effective signal; and searching a pulse radiation event for the filtered signal by applying a morphology-based peak searching method, and positioning the position and the characteristic of a real gamma instant radiation pulse event. According to the method, time-frequency analysis is carried out through S time-frequency transformation, the problem that the frequency of an analysis window cannot be adjusted through short-time window Fourier transformation is solved, the method has better frequency resolution and phase retention characteristics, and gamma pulse signal characteristics can be represented more accurately.

The invention provides an automatic equipment anomaly monitoring method and system based on image processing, and relates to the technical field of automatic equipment anomaly monitoring, and the method comprises the steps: converting an equipment operation video into a multi-dimensional physical field feature: in a motion field dimension, based on optical flow field analysis, extracting a full-period displacement statistical histogram and a space thermodynamic diagram, the motion instability characteristic of the mechanical transmission system is accurately quantified; in a vibration field dimension, an energy spectrum and a vibration thermodynamic diagram are generated innovatively through time-frequency transformation of a displacement signal of a frequency spectrum monitoring point, and frequency domain feature visualization of a hidden vibration fault is achieved; in the dimension of a structure field, edge gradient analysis and texture feature extraction technologies are fused, a time sequence structure thermodynamic diagram sequence is constructed to capture a progressive damage evolution rule, a three-field abnormal index dynamic weighting fusion mechanism overcomes the limitation of traditional single-point monitoring, connected domain analysis of a fused thermodynamic diagram is combined with an LBP texture and morphological feature decision tree, and the defect of the prior art is overcome. Automatic equipment abnormity monitoring based on image processing is realized.

The invention discloses an offshore platform tide level data processing method, device and equipment and a storage medium, and relates to the technical field of signal processing. According to the scheme, standard time-frequency transformation and fast Fourier transformation are combined, periodic signals in signals can be completely recognized and extracted, the extraction precision of sea level data of an offshore platform is improved, and therefore reliable sea level data are obtained; and the de-noised tide data of various partial tides are obtained, so that the influence degree of different tides on the offshore platform can be analyzed.

The invention relates to the technical field of underwater acoustic signal processing in a sonar system, in particular to a large-aperture array robust adaptive waveform recovery method based on focusing covariance sparse reconstruction, and the method comprises the steps: carrying out the time-frequency transformation of all array element receiving time domain data, and obtaining array element domain-frequency domain data; constructing sampling covariance matrixes corresponding to different frequency points according to the array element domain-frequency domain data; constructing a multi-frequency-point focusing covariance matrix according to the sampling covariance matrix and the array manifold vector corresponding to each frequency point; constructing a sparse dictionary matrix adaptive to the focusing covariance matrix according to the linear relation between the focusing covariances of the frequency points, and obtaining a sparse expression of the focusing covariance matrix; according to the sparse representation form of the focusing covariance matrix, utilizing a sparse criterion to carry out iterative reconstruction on the focusing covariance matrix; and robust adaptive waveform recovery is carried out by using the focusing covariance matrix after sparse iteration reconstruction. According to the method, the short-time adaptive waveform recovery performance of the large-aperture array is remarkably improved.

The invention discloses a crystal oscillator circuit fault classification technology based on a multi-source information fusion network, and belongs to the technical field of analog circuit fault diagnosis. Firstly, a multi-source data set of different measurement points of the crystal oscillator circuit is acquired; carrying out conversion from a time domain to a frequency domain on the data set by utilizing fast Fourier transform; extracting data fault features by using a convolutional neural network, and performing a trust distribution function under each piece of source data by using a softmax classifier; fusing different trust distribution functions under the multi-source data by adopting a D-S evidence theory to obtain a final diagnosis result and diagnosis probability output, and calculating cross entropy loss; and finally, training model parameters through back propagation to obtain a final diagnosis model. According to the method, the time-frequency transformation algorithm, the deep neural network algorithm and the information fusion algorithm are combined, a multi-source information fusion network is constructed, the defects of an existing diagnosis model in crystal oscillator circuit fault classification are overcome, and the accuracy and stability of crystal oscillator circuit fault diagnosis are remarkably improved.

The invention belongs to the technical field of radar signal processing, and provides a radar signal detection and identification method and device based on deep learning. The method comprises the following steps: performing time-frequency transformation on a time-frequency aliasing radar signal to obtain two-dimensional time-frequency data, drawing a time-frequency graph in a matching manner, combining the time-frequency graph into a mask region of each time-frequency component in the time-frequency graph, and mapping the mask region of the time-frequency graph into the two-dimensional time-frequency data; filtering time-frequency components outside a mask area in the two-dimensional time-frequency data, performing mask filtering on a time-frequency overlapping area to filter an overlapping part, performing time-frequency inverse transformation on the filtered time-frequency data to obtain a time-domain incomplete waveform, and reconstructing a complete radar signal; obtaining a reconstructed radar signal time-frequency diagram; graying processing is carried out, an optimal image segmentation threshold value is determined, a radar signal and a background signal are completely stripped, and a radar signal contour is extracted; and obtaining a modulation mode corresponding to the current radar signal based on the radar signal contour and a pre-trained modulation identification model.

The invention belongs to the technical field of power quality disturbance detection, and particularly relates to a power quality disturbance detection method based on improved adaptive S transformation, which comprises the following steps of: designing window width control factors of two Gaussian windows, flexibly adjusting time domain window widths and frequency spectrum characteristics of the Gaussian windows, and forming a global adaptive Gaussian window; taking upper and lower limits of time-frequency two-domain resolution as constraint conditions, taking enhanced signal energy concentration ratio as a target function of an optimization scheme, and adopting an interior point method to carry out parameter solving; performing fast Fourier transform on the signal and setting a threshold value, and defining a part higher than a threshold value point as a characteristic frequency point ki; screening calculation at a non-characteristic frequency point, only performing time-frequency transformation at a characteristic frequency point ki, and constructing a fast algorithm for improving adaptive S transformation; and obtaining a final disturbance characteristic information value. According to the method, the global adaptive Gaussian window is constructed as a kernel function for improving adaptive S transformation, the effective window length and the frequency spectrum of the window function can be automatically adjusted along with the change of the detection frequency, window parameters are prevented from being frequently switched for improving the time-frequency resolution, and various power quality disturbances are efficiently and accurately detected.

The invention provides a brain-controlled unmanned aerial vehicle group method based on brain-computer deep collaborative fusion. The method comprises the following steps: firstly, designing a steady-state visual evoked brain control signal acquisition normal form, and generating a visual stimulation signal through combined frequency-phase coding; secondly, the electroencephalogram signals are preprocessed through filtering, independent component analysis and the like; then, constructing an intention decoding network with deep fusion of space-time frequency features, extracting multi-scale features of the electroencephalogram signals by using a convolutional neural network, and performing deep fusion decoding through a space-time frequency Transform module to realize accurate prediction of brain control intention; thirdly, a virtual pilot algorithm and an artificial potential field algorithm are used for flight decision making of the unmanned aerial vehicle group; and finally, displaying the flight state of the unmanned aerial vehicle in real time through a visual interface constructed by PyQt5. The method has the advantages that the brain control intention of the user can be accurately decoded, the formation control and obstacle avoidance capability of the unmanned aerial vehicle group is effectively improved, and meanwhile, a visual interface and personalized setting are provided.

The invention discloses a partial discharge signal multi-source cooperative detection method and system based on time-frequency fusion analysis, and relates to the technical field of multi-source cooperative detection, and the method comprises the following steps: obtaining partial discharge original signals of an electric signal channel and an ultrahigh frequency channel, respectively carrying out the time-frequency transformation, and generating a multi-source time-frequency characteristic spectrum; extracting high-frequency noise modes of different channels under a non-partial discharge condition based on the multi-source time-frequency characteristic spectrum, and constructing a cross-source interference fingerprint database; based on the cross-source interference fingerprint database, carrying out frequency-band-by-band difference mapping calculation on actually acquired multi-source time-frequency characteristics to generate a difference characteristic matrix; and introducing reverse consistency constraint into the differential feature matrix, carrying out weighted fusion to obtain multi-source coupling time-frequency feature mapping, and outputting a detection result of the partial discharge signal. According to the method, the multi-source time-frequency characteristic spectrum is constructed to carry out band-by-band differential mapping on the actual signal, so that cross-source noise interference is inhibited, and the accuracy and robustness of partial discharge detection in a strong noise environment are improved.

The invention provides a fan fault diagnosis method for recognizing a vibration map based on a convolutional neural network, and relates to the technical field of neural networks, and the method comprises the steps: obtaining a multi-dimensional vibration signal in the operation process of a fan, and generating a two-dimensional vibration map through time-frequency transformation; and a convolutional neural network is utilized to automatically extract multi-layer time-frequency features and realize fault category discrimination. In the training stage, parameter optimization is carried out based on known fault samples, in the reasoning stage, real-time signals are input into a trained model to obtain fault type probability distribution, the fault type is determined according to the maximum probability, a fault evolution result is generated in combination with the historical operation trend, and therefore automatic, intelligent and rapid diagnosis of fan faults is achieved.

The invention relates to the technical field of voice noise reduction, in particular to a data center scene-oriented voice noise reduction method and system, a terminal and a storage medium, and the method comprises the steps: carrying out the STFT time-frequency transformation of a to-be-denoised voice, and obtaining a complex frequency spectrum of the to-be-denoised voice; adopting a multi-scale CNN convolutional neural network to perform feature extraction on the complex frequency spectrum; performing time sequence modeling on the extracted features by using a bidirectional long short-term memory (LSTM) network; voice features in the features after time sequence modeling are separated; carrying out reverberation suppression on the separated voice features; and inverse STFT reconstruction is carried out on the voice features after reverberation suppression, and the voice after noise reduction is obtained. The method is used for solving the problem of time-frequency-space three-dimensional coupling of the noise of the data center.

The invention provides a wear coefficient correction method for a shield cutter, and relates to the technical field of wear monitoring, and the method comprises the steps: collecting a time sequence magnetic field signal obtained by a magnetic sensor array disposed on a non-rotating part of a shield tunneling machine, and synchronously obtaining a cutter angle coding signal; performing time-frequency conversion and filtering on the magnetic field signal to obtain a noise reduction time sequence signal; determining a geometric position sequence of each shield cutter in combination with the angle coding signals; based on the magnetic sensor pose, the tool position and the magnetic dipole model, theoretical magnetic field mapping between the tool and the sensor is constructed, and a system response matrix is generated; reconstructing an independent magnetic feature vector of each cutter to obtain an optimal feature set; generating a vector difference through comparison with a reference vector, inputting the vector difference into an abrasion identification model, obtaining the abrasion loss and type identification of each cutter, and correcting an abrasion coefficient; the method improves the wear recognition precision and reliability, and is suitable for tunnel construction under complex geological conditions.

The invention discloses an electroencephalogram signal time-frequency domain denoising method based on a noise attention mechanism. The method comprises the following steps: performing time-frequency transformation on a noisy electroencephalogram signal to generate a plurality of time-frequency features; time domain and frequency domain noise masks are extracted through a dual-path neural network and fused; a two-stage complex convolutional network is constructed, a noise attention module of the two-stage complex convolutional network uses a feature splitting and space weight mechanism, time-frequency distribution of noise is positioned in the first stage, and clean signal retention and noise suppression are collaboratively optimized in the second stage; and finally, reconstructing the de-noised signal through inverse transformation. According to the method, time domain and frequency domain information of the electroencephalogram signals of the complex convolutional neural network is combined at the same time, artifacts in the electroencephalogram signals are more accurately separated and useful electroencephalogram signals are fully reserved on the basis of a noise attention mechanism of time-frequency domain segmentation, meanwhile, the interpretability of the model is improved, and the accuracy of the model is improved. The method solves the problem that the existing electroencephalogram signal denoising method does not consider time-frequency domain combined denoising. In addition, the invention further comprises a system, equipment and a medium which can store and operate the method.

The invention relates to the technical field of electric power facility intelligent safety monitoring and early warning, in particular to a multi-sensor fusion electric power facility intelligent safety early warning method, which comprises the following steps: acquiring mechanical deformation, electrical parameters and environmental data; the edge node preprocesses the data, extracts vibration spectrum features by adopting time-frequency transformation, identifies video anomaly in combination with a lightweight convolutional neural network, calls a pre-trained dam rigidity degradation model, an insulation aging model and a temperature and seepage coupling model, and dynamically optimizes model weight parameters by adopting a genetic algorithm; the method comprises the steps of analyzing associated characteristics of a mechanical deformation gradient, current harmonic distortion and a seepage coefficient, triggering thermodynamic diagram pushing, load control and remote operation and maintenance instructions based on a hierarchical early warning mechanism, and realizing data integrity guarantee and closed-loop feedback optimization by combining 4G network and Beidou short message dual-channel transmission and redundancy check. According to the invention, the real-time performance and accuracy of electric power facility safety early warning are improved, and the problems of insufficient data fusion and response lag in a traditional method are solved.

The invention discloses a radar target template signal establishment method based on depth model adaptive segmentation, mainly relates to the technical field of template signals, and is used for solving the problems that a target contour is easy to fracture or false detection by clutters is easy to cause when a time-frequency map is subjected to binary segmentation by a simple threshold slice in the prior art. And the threshold parameter is very sensitive to the signal-to-clutter ratio and the environmental change. Comprising the following steps: reading a one-dimensional radar echo sequence, and mapping the one-dimensional radar echo sequence to a two-dimensional time-frequency domain to obtain a time-frequency image; multi-scale features are obtained, and a matrix is prompted; obtaining a binary mask corresponding to the mask feature through the multi-scale feature and the prompt matrix; determining the binary mask corresponding to the highest confidence score as a final mask; screening time-frequency transformation data corresponding to the radar echo sequence by using the final mask to obtain output data; and recovering the output data into a time domain signal by using inverse short-time Fourier transform, and taking the time domain signal as a target template signal.

The invention discloses a method, a system and a related device for controlling a motor based on an adaptive algorithm, which are used for improving the accuracy of motor control. The method comprises the following steps: acquiring initial data of a motor; decomposing the initial data into intrinsic mode function components, and performing time-frequency transformation on the intrinsic mode function components; dynamic time-frequency features of the intrinsic mode function component are extracted, cross-band weighted fusion is carried out on the dynamic time-frequency features through a preset attention weighting mechanism, and a multi-dimensional feature vector is generated; inputting the multi-dimensional feature vector into a preset deep learning model, and constructing a target prediction model in combination with a loss function and an adaptive momentum optimization algorithm; transmitting the target prediction model to an analysis module of the motor to obtain a load change trend and a confidence coefficient; dynamically adjusting the proportion of the weight of the PID controller according to the load change trend and the confidence coefficient, and optimizing the parameters of the unit of which the proportion is adjusted through a gradient descent method; and dynamically regulating and controlling the motor based on the PID controller.

The invention discloses a double-end traveling wave positioning optimization method, device and equipment and a readable storage medium. The positioning accuracy is improved from the three aspects of signal processing, fault detection and positioning calculation. Multi-level wavelet packet decomposition is carried out on an original traveling wave signal, a sub-band adaptive soft threshold is generated according to noise statistical characteristics, a traveling wave head signal with a high signal-to-noise ratio is reconstructed through filtering and inverse transformation, and the problem that signal integrity and noise suppression cannot be considered at the same time in a traditional method is solved. And time-frequency transformation and instantaneous energy envelope analysis are carried out on the reconstructed signal, after a correlation matrix and a sequence are generated, a lightweight time sequence model is input, and a fault triggering moment is output in combination with a constraint condition, so that the detection sensitivity of the weak high-resistance fault signal in a low signal-to-noise ratio environment is effectively improved, and the omission ratio is reduced. The coefficient compensation time difference is calculated according to the original time difference in combination with the wave amplitude value, and the positioning parameters are continuously corrected by dynamically updating the parameters and the coefficients, so that the limitation of the existing algorithm is overcome, and the positioning accuracy under a complex line is improved.

The invention discloses an inertial navigation system periodic oscillation suppression method based on time-frequency transformation, and relates to the technical field of underwater navigation, and the method comprises the following steps: S1, modeling an error propagation model of an INS, and defining coordinate systems required by INS navigation, including an inertial coordinate system, a navigation coordinate system and a body coordinate system; based on the INS navigation equation, obtaining an INS error model, and carrying out time domain analysis to obtain an analytical solution of time domain error divergence; s2, designing a time-frequency transformation NTFT, proposing a normal phase time-frequency transformation method, and constructing a complete observation equation; s3, substituting a null method into a calculated longitude and latitude result, and accurately extracting frequency, phase and instantaneous amplitude in inertial navigation longitude and latitude; and S4, establishing a resolving framework of the inertial navigation system periodic oscillation suppression method based on time-frequency transformation, and constructing a negative feedback loop through input gyroscope and acceleration information to suppress periodic errors.

The invention relates to a welding seam abnormity identification method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring ultrasonic scanning data of a target welding seam; wherein the ultrasonic scanning data comprises an ultrasonic scanning result and corresponding time data; according to the time data, carrying out time-frequency conversion on the ultrasonic scanning data to obtain ultrasonic time-frequency data; inputting the ultrasonic time-frequency data into a preset anomaly detection model, and outputting to obtain an anomaly detection result; wherein the anomaly detection model is used for extracting target features according to input time-frequency data, and outputting a recognition result of the anomaly of the target welding seam based on the target features. By adopting the method, the abnormal welding seam can be identified more accurately, effective mapping from abstract time-frequency data to specific defect characteristics is realized, and a reliable basis is provided for welding seam quality evaluation.

The invention relates to the technical field of power equipment state monitoring, and discloses a power equipment fault detection method and device, equipment and a medium, and the method comprises the steps: obtaining a voiceprint signal of power equipment, carrying out the time-frequency transformation to obtain an original logarithmic Mel spectrogram, inputting a multi-scale context sensing auto-encoder model, and outputting a reconstructed spectrogram. According to the model, multi-scale long-range dependence features of voiceprints in time and frequency dimensions are respectively extracted by using a double-flow expansion convolutional network, and complete spectrum reconstruction is carried out based on the extracted features; and calculating an abnormal score based on a reconstruction difference degree between the original logarithmic Mel spectrogram and the reconstructed spectrogram, and when the abnormal score exceeds a dynamic threshold value, judging that the equipment has a fault. Compared with the prior art, the problems that weak fault features are difficult to extract and reconstruction details are fuzzy under strong background noise are solved, and high-robustness non-contact fault detection is achieved.