35 results about "Wave packet" patented technology

The present application relates to the technical field of composite material structure monitoring, in particular to a composite material structure damage identification method based on acoustic emission wavelet packet energy characteristics, which comprises: S1, obtaining acoustic emission signal data of the composite material and performing pretreatment; S2, using a wavelet base function and a discrete wavelet inverse transform to perform wavelet packet decomposition on the denoised acoustic emission signal data of the composite material; S3, obtaining the processed acoustic emission signal data of the composite material, and extracting the characteristic energy of each acoustic emission signal data; S4, using a clustering method to perform clustering analysis and completing the composite material structure damage identification. The present application uses acoustic emission signals as the basis for analysis, uses wavelet transform and k-means clustering to accurately realize the structure damage identification and judgment of the composite material, can realize dynamic and continuous monitoring, is not affected by the complexity of the structure, has wide applicability, and is suitable for various composite materials.

This invention discloses an improved method for extracting gear fault diagnosis features by combining Complete Empirical Mode Decomposition (CEEMDAN) with wavelet packet segmentation threshold denoising and energy entropy. The reconstructed signal after CEEMDAN threshold denoising is re-CEEMDAN decomposed to obtain the energy values ​​of each modal component, which are then used as fault features of the gear. The method includes the following steps: 1) acquiring vibration signals in the X, Y, and Z mutually perpendicular directions at the gear of a rotating device using a vibration sensor; 2) performing CEEMDAN decomposition on the data to obtain multiple intrinsic modal components; 3) using the Pearson correlation coefficient method to divide the modal components into noise-dominant components and signal-dominant components; 4) applying different wavelet denoising methods to different dominant components; 5) reconstructing the signal and re-CEEMDAN decomposing it to extract the energy values ​​of each mode, which are then used as features under different fault states.

This application relates to the field of DC transmission protection technology, and particularly to a fault identification method for hybrid three-terminal high-voltage DC transmission lines based on the DC boundary voltage energy ratio and its application. By analyzing the boundary frequency characteristics of the DC line, rectifier side, and inverter side of the system, frequency characteristic curves of each boundary are obtained. Based on the frequency response characteristics of the overall system boundary frequency characteristic curve, highly distinguishable characteristic frequency bands are determined. When a fault occurs in the system, DC voltage signals at both ends of the rectifier / inverter side are acquired, and wavelet packet decomposition is performed on the acquired signals to extract the energy within the characteristic frequency bands. Based on the energy and characteristics of the two characteristic frequency bands, identification criteria for fault location and fault polarity are constructed. This enables rapid fault identification of hybrid three-terminal DC systems without the need for communication, thereby improving the safety and reliability of hybrid three-terminal high-voltage DC transmission lines. The aim is to solve the problem of fault type identification in hybrid three-terminal DC systems.

This invention discloses a training method for an equipment fault diagnosis model and a method for equipment fault diagnosis, relating to the fields of fault diagnosis and deep learning technologies. The method includes: acquiring at least one sound sample data and corresponding label data; processing the sound sample data through a background noise suppression channel and an impulse interference suppression channel to obtain a denoised sound sample vector; performing dual-tree complex wavelet packet decomposition on the denoised sound sample vector to obtain a sample time-frequency feature matrix; processing the denoised sound sample vector to obtain a sample operating condition auxiliary feature vector; the sample operating condition auxiliary feature vector is used to characterize the equipment operating condition state corresponding to the sound sample data; and training a deep learning model based on the sample time-frequency feature matrix, the sample operating condition auxiliary feature vector, and the label data to obtain an equipment fault diagnosis model. The above technical solution can improve the accuracy of equipment fault diagnosis.

This invention relates to the field of traffic safety technology, specifically to an efficient simulation method for quantum systems based on parallel order reduction. The method includes the following steps: receiving the physical parameters of the quantum system and simulation requirements, whereby the physical parameters include electron mass, potential well size, and initial wave packet parameters; and the simulation requirements include simulation physical time and accuracy requirements. Based on the physical parameters, a time-dependent Schrödinger equation describing the dynamic behavior of the quantum system is established, and the Schrödinger equation is rearranged into matrix form using the Kronecker product. This invention utilizes Arnoldi to reduce the order of the matrix-form Schrödinger equation. By reducing the order, the large matrix in the original space is projected into a relatively small subspace, improving the efficiency of the simulation solution. The reduced-order Schrödinger equation is solved using a time-parallel algorithm. This approach overcomes the time step limitation imposed by the CFL condition, ensuring that a stable solution can be obtained with fewer time steps.

This application relates to a method, apparatus, equipment, medium, and program product for assessing railway track bed compaction. The method includes: acquiring simulated ground-penetrating radar (GPR) data corresponding to multiple simulated track bed models with different compaction degrees; performing wavelet packet decomposition on the simulated GPR data to obtain wavelet packet decomposition results for each of the multiple simulated track bed models; wherein the wavelet packet decomposition results include multiple dimensions; these dimensions include at least two of the following: energy entropy dimension, subband energy kurtosis dimension, and low-to-high frequency energy ratio mean dimension; based on the compaction degree of each of the multiple simulated track bed models and their corresponding wavelet packet decomposition results, determining a target dimension sensitive to the compaction degree from the multiple dimensions; and determining the compaction assessment result of the track bed under test based on the wavelet packet decomposition data of the target GPR data in the target dimension. This method enables the quantitative assessment of railway track bed compaction.

The application is based on the unmanned ship formation encounter risk space-time analytic method of quantum field theory, including the following steps: constructing the initial quantum state of the ship, accurately characterizing the uncertainty distribution of the ship position through the Gaussian wave packet model; calculating the probability density of the ship at a certain state at a certain time; superposition calculation of the sum of the probabilities of all position pairs of two ships satisfying the geometric collision condition; based on the sum of the probabilities of all position pairs of two ships satisfying the geometric collision condition, the total value of the risk potential field of the encounter risk of two ships is calculated; the total value of the risk potential field of the encounter risk of two ships is compared with the risk threshold value, and whether the two ships exist the risk of collision is judged, the method of the application realizes the fundamental paradigm conversion from the classical trajectory description to the quantum field operator description by establishing the multi-level calculation framework under the quantum mechanics form system, and provides a new mathematical theoretical basis for the ship navigation risk analysis.

The present application belongs to the technical field of oil liquid abrasive particle monitoring, and particularly relates to a kind of abrasive particle feature extraction methods based on differential signal band selection adaptive filtering, including obtaining the differential signal to be detected by carrying out common mode rejection to oil liquid abrasive particle signal;Obtain multi-decomposition scale feature vector by wavelet packet decomposition to the differential signal to be detected through orthogonal wavelet base function;Calculate similarity index on each decomposition scale, extract target scale feature vector;Obtain filter vector by processing target scale feature vector using improved least mean square root adaptive filter;Carry out wavelet reconstruction to zero vector and filter vector to obtain noise reduction signal;Divide noise reduction signal into multiple segments, calculate composite recognition index of each segment;According to composite recognition index, calculate the weight of each segment, and obtain oil liquid abrasive particle feature signal extraction result by weighting all segments;The present application improves the signal-to-noise ratio of abrasive particle signal, has stronger adaptive ability, and helps to improve the accurate detection of oil liquid abrasive particle feature.

The present application relates to a kind of based on path energy matching's no baseline ultrasonic Lamb defect positioning method, comprising the following steps: S1, on aluminum plate arrangement circular sensor array and construct sector area, simulate defect by punching on plate, gather the damage signal of sector scanning area;S2, pre-processing is carried out to damage signal, and all signals are normalized according to boundary echo signal;S3, according to sensor path length, all signals are grouped, and the first arrival wave packet energy ratio is calculated according to group;S4, the two paths of the lowest energy ratio in each sector scanning area are found out, and the intersection of path straight line is calculated, to further determine the defect position, draw defect positioning chart.Compared with prior art, the present application has the advantages of rapid and accurate detection and positioning of defect, clear imaging result and the like.

The application discloses an atmospheric storage tank bottom plate online micro-leakage and corrosion integrated detection method based on acoustic emission-vibration fusion, and belongs to the technical field of atmospheric storage tank nondestructive detection and online safety monitoring. The application realizes non-stop production, non-tank cleaning and non-invasive signal and temperature synchronous acquisition by arranging an acoustic emission-low-frequency vibration-temperature integrated annular sensing array at the lower part of the tank wall; noise reduction processing is carried out based on environmental noise baseline by using a wavelet packet and adaptive filtering hybrid algorithm; the signal propagation speed is automatically compensated and corrected by the environmental temperature; repeated alarm signals are removed by layered event clustering; a bimodal fusion feature vector is constructed and input into an intelligent identification model to realize the distinguishing identification of active corrosion and micro-leakage defects; the spatial positioning of defects is completed by using bimodal weighted time difference positioning, and a corrosion rate prediction model is established to realize defect quantitative evaluation, trend analysis and risk classification. The application effectively solves the problems of traditional detection, such as production stoppage, tank cleaning and anti-interference capability.

The application discloses a kind of drop lightning arrester multi-source signal discrimination and alarm method, it is related to the on-line monitoring and fault early warning technical field of power system equipment, the application can effectively separate high-frequency sub-band signal by wavelet packet decomposition technology, adapt to non-stationary vibration environment, ensure the robustness of feature extraction;The introduction of approximate entropy and peak factor and other characteristics, quantifies the randomness and impact of signal, can sensitively capture the subtle changes in the fatigue accumulation process of lead wire;Single-class classification model trained only by healthy sample is used, such as support vector data description, decision boundary is constructed, so that the model has high sensitivity to abnormal state, and can early warning before lead wire fracture occurs;This kind of evaluation mode based on healthy baseline avoids the false alarm problem of traditional threshold method in complex environment.

The application provides an animal behavior recognition method and system based on wavelet packet decomposition and a state space model, comprising the following steps: S1, acquiring a three-axis continuous motion signal of a sensor worn by an animal, and performing data stream segmentation by using a sliding window to construct an original sensor signal input; S2, performing adaptive enhancement and fusion of the sensor signal in the axial direction by using a dimension-aware data enhancement module (DAE) to generate a processed signal, so as to explicitly solve the direction heterogeneity problem of the three-axis signal; S3, performing wavelet packet decomposition (WPD) and Mamba module time series modeling on the processed signal, and performing adaptive weighted fusion by using a feature routing module to generate a fused multi-scale feature; and S4, inputting the fused multi-scale feature into a feature classifier to output a final animal behavior recognition result; and the technical scheme can realize accurate and efficient animal behavior recognition.

The application relates to a honeycomb sandwich composite structure hybrid manufacturing defect detection method based on wave packet energy integration, which comprises the following steps: exciting ultrasonic guided waves at a first boundary of a honeycomb sandwich structure to be detected, and collecting out-of-plane vibration time domain signals of at least one detection position at an excitation point; processing the out-of-plane vibration time domain signals, and extracting energy integration features of the signals in a pre-defined time window; and outputting a detection result of whether a defect exists in a propagation path corresponding to the detection position based on comparison between the energy integration features and preset baseline features. Compared with the prior art, the application has the advantages of high efficiency, strong reliability and excellent robustness.

The present application belongs to the field of crack detection, and particularly relates to a steel bar mechanical connection joint fatigue crack acoustic emission positioning monitoring system, comprising: through adaptive wavelet packet decomposition, micro-crack main frequency band coefficients are extracted and single node reconstruction is carried out, interface scattering is suppressed to obtain narrowband direct wave; the equivalent wave velocity is corrected in real time by using the contact stiffness-load curve, and the three-dimensional coordinates of the crack source are solved by combining the generalized cross-correlation time difference and the weighted iterative least square method; the event space is clustered in the unit load cycle, and the cumulative energy-cycle relationship is established, the residual life is evaluated according to the damage evolution model, and the alarm is triggered; the present application realizes high-precision positioning and early warning of micro-crack initiation under strong interference working conditions.

This invention discloses a fiber laser that achieves wave packet pulse train output based on pulse-pumped passive modulation technology. The device includes a pump source; a (2+1)×1 combiner; rare-earth-doped double-clad gain fiber; a passively Q-switched material; a flange; a high-reflectivity fiber Bragg grating; a low-reflectivity fiber Bragg grating; and a function generator. A TTL modulation signal is selected and input to the pump source to obtain wave packet pulses. By changing the modulation frequency of the signal, the number of sub-pulses within the wave packet is changed, thus providing a fiber laser solution that allows adjustment of the number of sub-pulses within the wave packet pulse train as needed.

The present disclosure belongs to the technical field of tunneling engineering, and specifically provides a tunnel shield behavior prediction method and system based on data-driven deep learning, wherein the method comprises: using an improved dynamic prediction model-subset simulation (SuS)-bidirectional long short-term memory method (Bi-LSTM) (namely, uS-Bi-LSTM), and incorporating subset simulation into Bi-LSTM to realize automatic parameter search. In addition, the framework also integrates wavelet packet transform as a filter to remove background noise recorded together with time series data in the tunnel excavation process. As a comparison, an improved dynamic prediction model SuS-LSTM is also constructed. Taking a large-diameter underwater tunnel project of a slurry balance shield tunneling machine as an example, the effectiveness and feasibility of the framework are verified, and the prediction accuracy can be improved to better avoid tunnel excavation risks.

The application discloses a kind of electric meter relay resonance fault detection method and system based on harmonic analysis, it is related to the field of measurement electric variable, method includes: obtaining current signal and voltage signal and pre-processing, obtain the current cycle of current analysis signal and power grid harmonic spectrum;Based on power grid harmonic spectrum, the resonance risk of power grid is quantified, and the resonance sensitivity index of current cycle power grid is obtained;Pre-set candidate wavelet basis set, obtain the time-frequency focusing ability evaluation index and task adaptability index of each candidate wavelet basis in set;Based on three indexes, construct dynamic comprehensive cost function and select optimal wavelet basis;Based on optimal wavelet basis, wavelet packet decomposition is carried out to current analysis signal, and the current working state of relay is extracted fault feature and identified to judge.The application can realize the adaptive selection of wavelet basis, solve the problem that fault feature extraction is not accurate, false positive rate is high, and computing resource is not reasonably utilized in existing detection method.

This invention discloses a gas pipeline leak location method based on wavelet packet transform and coherence function, comprising the following steps: for the characteristic frequency range of the acquired signal, by calculating the coherence function between signals, a frequency range greater than a threshold is selected as the effective frequency bandwidth; the acquired leak sound signal is decomposed into multiple scales using wavelet packet transform, and based on the effective frequency bandwidth, appropriate frequency components are selected for reconstruction to obtain the target signal; the cross-correlation function between the target functions is calculated to extract time delay information, and the influence of temperature on the propagation speed of the leak sound signal is considered and corrected; the leak point is located by combining the time delay, thus improving the accuracy of leak location. According to this invention, the signal-to-noise ratio of the signal is effectively improved, and it is applied to the problem of locating gas pipeline leak points in complex environmental conditions. Combined with the corrected propagation speed of the leak sound signal, the accuracy of locating gas pipeline leak points is improved, which is of great significance to urban public safety.

The present application relates to the technical field of fault diagnosis, in particular to a rolling bearing fault diagnosis method based on WPD and AFRB-LWUNet under small samples, which comprises the following steps: S1: collecting vibration signals of mechanical equipment bearings when various faults occur, carrying out wavelet packet decomposition and energy feature extraction on the vibration signals, reconstructing the vibration signals into one-dimensional time series signals, and completing preliminary data preprocessing; S2: changing the original UNet model from four layers of up-sampling layers and down-sampling layers to two layers of up-sampling layers and down-sampling layers to form a LWUNet model, embedding an attention fusion residual block in the jump connection part of the LWUNet model, and building an AFRB-LWUNet model; S3: training, verifying and testing the AFRB-LWUNet model; S4: using the trained AFRB-LWUNet model to diagnose faults under different working conditions and testing the robustness of the model; and S5: monitoring the bearing vibration data in the running process of the mechanical equipment in real time, inputting the preprocessed data into the trained model, and carrying out real-time fault diagnosis.

This invention relates to the field of track bridge engineering technology, and particularly to a method, medium, and equipment for constructing characteristic irregularities based on a damage evolution model. The method includes: establishing a track damage evolution model based on a simplified track structure model and an adaptive grid evolution mechanism; constructing characteristic residual irregularities based on the track damage evolution model under different load steps and different pier settlement amplitudes, including: selecting different pier settlement amplitudes based on the damage evolution model corresponding to different load steps and performing coupled analysis with two working conditions: design earthquake and rare earthquake, to calculate the track residual irregularities; constructing characteristic residual irregularities based on the statistical characteristics of the track residual irregularities using wavelet packet transform, which compensates for the deficiencies of short-time Fourier transform and wavelet transform in terms of time-frequency resolution, and the damage evolution model can identify the location of inter-layer damage and shorten the calculation time.

The application provides a kind of underground disease detection method based on diffusion model denoising and adaptive wavelet packet decomposition. The diffusion model is used to deeply denoise the ground penetrating radar data, effectively suppressing random noise and structural interference while retaining the weak scattering characteristics caused by cavities, loose, void and leakage. The optimal basis search of wavelet packet based on reinforcement learning strategy is adopted to realize the adaptive selection of sub-band and frequency domain enhancement, and to construct multi-channel high-frequency enhancement features. Combined with low-frequency features and convolution multi-scale features, after spatial scale alignment, input the YOLOv8 detection network with attention enhancement, through the improved backbone, FPN+PAN fusion structure and stable prediction mechanism to realize accurate identification and positioning of diseases. The method effectively improves the detection accuracy and robustness of underground diseases under complex noise conditions.

The application discloses a rotating machinery cross-domain fault diagnosis method based on dynamic evolution and wavelet double-path structure, and relates to the technical field of fault diagnosis. The method comprises the following steps: obtaining labeled vibration signals under a certain working condition of rotating machinery and a large number of unlabeled vibration signal samples under an actual variable-speed working condition to be measured. Firstly, batch normalization processing is performed on the input original vibration signals to reduce signal distribution differences caused by speed changes. Secondly, a double-path feature extraction structure is constructed based on wavelet packet transformation, low-frequency global and high-frequency detail features are fused, and the model cross-domain fault feature extraction capability is improved. Then, a domain self-adaptive method based on a dynamic evolution mechanism is adopted to construct a series of mixed domains evolving from a source domain to a target domain, the domain offset mutation problem in the migration process is relieved through gradual transition and gradual migration, and finally the trained model is saved to realize the rotating machinery cross-domain fault diagnosis by using a small amount of labeled samples in the source domain and a large amount of unlabeled samples in the target domain.

The small current grounding system single-phase grounding fault line selection method solves the problem of how to improve the line selection accuracy, and belongs to the field of small current fault line selection. The two power frequency period data before the fault are used as the reference, and the data after the fault are compared by difference, so that the inherent interference such as load imbalance, harmonic background and line parameter asymmetry during normal operation of the system is eliminated, and the fault characteristics are more prominent. Secondly, four criteria (differential steady-state phase, wavelet packet differential energy spectrum, differential instantaneous phase consistency and envelope weighted cumulative polarity) are used to describe the fault from different physical aspects. Each criterion independently outputs a 0~1 confidence level, forming a multi-dimensional complementary verification mechanism. Even if a certain criterion fails under certain conditions, other criteria can still provide reliable evidence. Finally, the prior probability and the four criterion likelihood values corrected by dynamic weight are fused through the Bayes formula to obtain the posterior probability of each branch and bus grounding, and the high and low threshold values are used for hierarchical decision-making.

This invention relates to a method for inverting the delamination damage profile of composite laminate structures based on Lamb wave data, belonging to the field of composite structure damage detection technology. The propagation behavior of Lamb waves in CFRP composite laminates with delamination damage was studied using numerical methods. The influence of delamination damage on Lamb wave characteristics was analyzed using wavelet packet decomposition and reconstruction methods and constructed eigenvalues. Through eigenvalue analysis and selection, effective features sensitive to the size and location of delamination damage were obtained. An XGBoost machine learning model was established based on these effective features. A Lamb wave feature sample set of laminates with random delamination damage was constructed using numerical methods, and the XGBoost model was trained to predict the size and location of delamination damage.

The application discloses a kind of station track circuit fault detection method and system based on cluster analysis, comprising the following steps: current signal data is collected by outdoor branch exchange arranged in each section of track circuit, and data is transmitted to indoor host for pre-processing, and the characteristic data of current signal is extracted.Cluster analysis algorithm is used to recognize and classify the current signal characteristic data of each section, and normal signal and abnormal signal are identified.For abnormal signal, further identify and locate fault type and position through historical fault database and pattern matching algorithm.Generate fault alarm information, and assist maintenance through host computer monitoring software.The method uses Kalman filter and wavelet packet decomposition technology for signal preprocessing, effectively removes noise and extracts features in each frequency band, improving the accuracy of fault detection.Through cluster analysis, fault type and position can be automatically identified and located, reducing human judgment error, improving operation efficiency and safety.

The application provides a signal classification method for sub-surface damage mechanism of hard and brittle materials based on acoustic emission technology. Firstly, the original acoustic emission signals and surface topography of the hard and brittle materials are obtained through grinding tests at multiple grinding speeds. Then, the wavelet packet signal processing algorithm and the short-time Fourier transform are used to pre-process the acoustic emission signals and extract time-frequency domain features. Finally, the micro-crack signals, radial crack signals and transverse crack signals are distinguished from the characteristic space by combining the damage characteristics of the hard and brittle materials with the acoustic emission characteristic parameters, and the characteristic frequency band range corresponding to each crack damage mode is obtained. A signal classification model for the sub-surface damage mechanism of the hard and brittle materials is constructed, which provides a theoretical basis for realizing the sub-surface damage monitoring of the hard and brittle materials under complex working conditions. The method can quickly identify the damage mechanism of the hard and brittle materials, realize the online evaluation of the subsequent sub-surface damage of the hard and brittle materials, and solve the technical problem of non-destructive and accurate monitoring in the grinding process.

The application relates to the technical field of nondestructive testing, and discloses a steel structure weld defect intelligent detection method, which comprises the following steps: collecting a weld area A-scan echo sequence signal by using an ultrasonic probe; performing adaptive noise reduction processing on the signal based on wavelet packet transformation, obtaining pure echo by using a minimum Shannon entropy criterion and soft threshold denoising; converting the pure echo into a two-dimensional time-frequency spectrum by using continuous wavelet transformation; inputting the time-frequency spectrum into a preset convolutional neural network model, extracting multi-layer convolutional features, and outputting a defect type through classification; and calculating the depth and horizontal position of the defect in the weld according to the sound path time of the pure echo signal and the probe parameters. The application combines signal adaptive enhancement with time-frequency image depth learning, effectively overcomes structural noise interference, and realizes automatic high-precision identification of the weld defect type and accurate positioning of physical coordinates.

This invention relates to a deep learning-based method for inverting bedrock ground motions, comprising: constructing a paired dataset of surface ground motions and bedrock ground motions and extracting parameters; performing wavelet packet decomposition to obtain normalized wavelet packet coefficients for surface ground motions and bedrock ground motions; establishing a bedrock peak ground acceleration (PGA) prediction module based on a deep neural network and a normalized wavelet packet coefficient prediction module based on a generative adversarial network (GAN), outputting PGA and normalized wavelet packet coefficients for bedrock ground motions; and obtaining the inverted bedrock ground motion time history using PGA and the normalized wavelet packet coefficients for bedrock ground motions. This invention proposes a novel deep learning-based method for inverting bedrock ground motions to reduce the dependence of traditional inversion methods on strong theoretical assumptions and improve the accuracy, robustness, and applicability of bedrock ground motion inversion under complex site conditions.