199 results about "Sparse coefficient" patented technology

The invention relates to the technical field of mechanical fault diagnosis, and discloses a gearbox fault diagnosis method and system based on lightweight variational Bayesian learning, and the method comprises the steps: collecting a to-be-diagnosed vibration signal of a gearbox, carrying out the preprocessing of the to-be-diagnosed vibration signal, and obtaining an original vibration signal and the fault feature frequency of the original vibration signal; determining amplitude modulation-frequency modulation sparse combination representation of the original vibration signal according to the fault characteristic frequency of the original vibration signal, and constructing a joint probability model according to classification distribution containing sparse vectors and the amplitude modulation-frequency modulation sparse combination representation of the original vibration signal; performing variational Bayesian inference solution on the joint probability model by using the non-overlapping sub-sequence of the original vibration signal and natural gradient optimization to obtain posterior probability estimation of a sparse coefficient; and determining an activation component according to the posterior probability estimation of the sparse coefficient and the sparse precision parameter, and matching the activation component with a pre-established multi-scale amplitude modulation-frequency modulation sparse dictionary to obtain a fault type and a confidence coefficient thereof.

The invention discloses a data processing method for industrial equipment for industrial control Internet of Things, which comprises the following steps: acquiring industrial equipment sensor data, and carrying out standardization processing to obtain a standardized matrix; initializing a sparse dictionary learning model, setting an initial dictionary structure and a sparse coefficient, and executing preliminary sparse decomposition; constructing a flower pollination algorithm search space, optimizing a layering number, a regular weight and a switching threshold, and updating dictionary parameters; calculating an optimal sparse coefficient matrix, and performing sparse reconstruction processing; and carrying out data denoising, compression and feature extraction, and outputting a final processing result. According to the method, the flower pollination optimization algorithm and the sparse representation dictionary learning model are fused, so that efficient denoising, compression and abnormal feature extraction processing of the industrial equipment data are realized.

The invention discloses a method for establishing a high-voltage circuit breaker fault detection model, and the method comprises the following steps: collecting current, voltage, mechanical response, temperature and other multi-dimensional signals of a circuit breaker under different working conditions, and unifying the signals into standardized time sequence data; a nonlinear dynamic sparse identification method is utilized to establish a dynamic model for describing equipment state evolution, and sparse coefficients reflecting physical change rules are extracted from the dynamic model to serve as health features. And the features are fused with current monitoring data to generate a joint feature input vector, and a health prediction model based on a TabPFN architecture is introduced for training and discrimination. And finally, accurate prediction of the current health state or the potential fault of the circuit breaker is realized, and the model self-adaptive updating capability is realized. According to the method, physical modeling and data analysis are combined, so that the accuracy and interpretability of fault prediction are improved.

The invention relates to a multi-dimensional transmission data compression sensing method and system for urban emergency rescue, and the method comprises the steps: obtaining multi-modal data, carrying out the normalization processing and sparse representation, and obtaining the sparse coefficient of each modal; constructing a block diagonal random matrix for each modal sparse coefficient to perform independent compression sampling, generating a low-dimensional observation value before coding, and performing arithmetic coding and low-density parity check code error correction coding to generate an anti-interference code stream; and performing low-density parity check code decoding and arithmetic decoding on the anti-interference code stream to obtain a decoded low-dimensional observation value, performing iteration by using an orthogonal matching pursuit algorithm, recovering sparse coefficients of each mode, performing reconstruction to obtain text, image and audio features, and projecting the text, image and audio features to a shared semantic space to obtain a shared semantic space. And calculating a joint semantic weight through a cross-modal attention mechanism, and generating a multi-modal fusion result with consistent semantics. The method disclosed by the invention provides an efficient, robust and semantic collaborative end-to-end solution for urban emergency rescue.

The invention belongs to the field of magnetic resonance measurement signal noise filtering, and particularly relates to a ground magnetic resonance signal sparse denoising method of a combined dictionary, which comprises the following steps: reconstructing a power frequency harmonic component of a magnetic resonance signal according to frequency bands, and eliminating power frequency harmonics from the magnetic resonance signal to obtain a power frequency-removed signal; constructing a track matrix Z by adopting a Gaussian random matrix, constructing a track matrix Y by adopting a power frequency-removed signal, taking first K columns of the track matrix Z and normalizing to obtain an initial dictionary D, and using the track matrix Y as an original sample for constructing a sparse coefficient matrix X; updating the initial dictionary D and the sparse coefficient matrix X through K-SVD dictionary learning, and reconstructing a track matrix by adopting the updated dictionary # imgabs0 # and the sparse coefficient matrix # imgabs1 # to obtain a track matrix W; and obtaining a pure magnetic resonance signal by taking the first row of the track matrix W, and realizing effective removal of MRS signal noise in a complex electromagnetic interference scene under the condition of single signal acquisition.

The invention discloses a soil heavy metal inversion method and system integrating satellite remote sensing and near-end sensing, and the method comprises the steps: collecting a soil sample, and measuring the soil heavy metal content and a soil visible light-near infrared spectrum; obtaining a time sequence multispectral image of a research area, calculating a spectral index, and selecting and screening bare soil pixels through a threshold value to obtain a bare soil image; performing spectrum correction on the bare soil image; obtaining a joint dictionary and a sparse coefficient through sparse representation and dictionary learning, and reconstructing a hyperspectral image of the bare soil image; converting the one-dimensional spectral data into a two-dimensional spectrogram by using continuous wavelet transform, extracting spectral features in combination with a 2D-CNN algorithm, and constructing a soil heavy metal inversion model; and using the trained inversion model to predict the soil heavy metal content of the research area based on the reconstructed hyperspectral image. According to the method, satellite remote sensing and near-end sensing are integrated to obtain a large-scale accurate soil heavy metal content distribution map, deep features are extracted in combination with a 2D-CNN algorithm, and the inversion model precision and model efficiency are improved.

The invention relates to the technical field of satellite communication signal processing, and discloses a broadband satellite signal blind demodulation reconstruction method and system based on sparse representation. The method comprises the following steps: carrying out frequency domain transformation on broadband satellite mixed signals to extract pilot frequency features to construct a beam state feature matrix, inputting the matrix into an adversarial network to generate a beam adaptive sparse dictionary, constructing a topological relation graph according to a Doppler frequency shift set, and carrying out collaborative sparse decomposition to obtain a sparse coefficient matrix; and extracting a code rate candidate set to execute parallel sparse reconstruction, determining an actual code rate through self-consistency verification to obtain a complete signal, analyzing a switching instruction, extracting time sequence statistical characteristics, predicting target domain characteristics, generating a switched sparse dictionary, and executing demodulation. The sparse decomposition precision, the code rate blind estimation accuracy, the cooperative processing efficiency and the switching continuity of the broadband satellite mixed signals are improved.

The invention discloses a face recognition method based on sparse coding and dictionary learning. The method comprises the following steps: S1, collecting and preprocessing a standardized training image and a to-be-recognized face image; s2, training a dictionary set, labeling categories, and initializing and optimizing the dictionary; s3, performing sparse coding, and solving a sparse coefficient by using the optimization dictionary; s4, carrying out regional feature division and fusion of multi-region sparse coding, weighted compression and interactive modeling; s5, performing fusion feature normalization and classification, and performing joint discrimination by a reconstruction error and a discrimination classifier; s6, performing confidence evaluation and dictionary updating, and triggering an incremental learning updating mechanism with low confidence; and S7, performing model deployment and real-time identification, and deploying an optimization dictionary and a classification module to perform identification output. The invention provides a face recognition method suitable for a complex environment, and the method has the advantages of high precision, strong robustness and good practicability.

The invention discloses a deep reinforcement learning-based valve flow anomaly detection method. The method comprises the following steps of: obtaining a marked space-time synchronization industrial valve operation data set; generating an enhanced industrial valve image; inputting the enhanced industrial valve image into the improved YOLOv9 detection network, and outputting a candidate micro abnormal region set and corresponding time sequence anchor point information; forming a visual feature set and a time sequence feature set; inputting the visual feature set and the time sequence feature set into an improved coupling convolution sparse coding model to obtain a visual domain reconstruction residual error, a time sequence domain reconstruction residual error and a sparse coefficient consistency deviation; obtaining a normalized abnormal score; and comparing the normalized abnormal score with an abnormal threshold dynamically updated according to the valve flow physical prior constraint, and when the normalized abnormal score exceeds the abnormal threshold, generating micro-abnormal alarm information and an abnormal level. According to the method, false alarm and missing alarm caused by working condition change can be remarkably reduced in practical application, and the reliability of abnormal judgment is improved.

The invention relates to the technical field of signal processing, and discloses a flip chip vibration signal denoising method and system, and the method comprises the steps: obtaining a vibration signal responded by a to-be-detected flip chip under the action of external ultrasonic excitation, carrying out the segmentation processing of the vibration signal, constructing an initial sparse dictionary according to the segmented vibration signal, and iteratively updating the sparse dictionary; in the iteration updating process, sparseness parameters are adjusted in real time along with the number of iterations, and soft threshold denoising is conducted on residual terms; introducing a feature projection matrix to perform joint modeling on each section of vibration signal, and constructing a joint optimization model according to the updated sparse dictionary and the corresponding sparse coefficient; alternately optimizing the sparse coefficient and the feature projection matrix in the joint optimization model to obtain an optimal solution of the sparse coefficient; and combining the updated sparse dictionary and the optimal solution of the sparse coefficient to reconstruct the vibration signal to obtain a denoised vibration signal. According to the method, transient features can be effectively extracted, expression of key features is enhanced, noise is suppressed, and denoising robustness and reconstruction precision are improved.

The invention provides a logarithmic bus bearing roller defect detection method and system based on an ultrasonic technology, and the method comprises the steps: obtaining an ultrasonic detection signal of the surface of a logarithmic bus bearing roller, and carrying out the preprocessing of the ultrasonic detection signal, and obtaining a first echo signal sequence; obtaining an average value sequence, a skewness sequence, a kurtosis sequence and a first high-order cumulant sequence based on the first echo signal sequence; correcting the first high-order cumulant sequence based on the average value sequence to obtain a second high-order cumulant sequence; optimizing the first echo signal sequence based on the dictionary matrix and the signal sparse coefficient vector to obtain a second echo signal sequence; and fusing the sequences to obtain a multi-dimensional feature vector sequence, and comparing the multi-dimensional feature vector sequence with a preset vector threshold to detect whether the logarithmic bus bearing roller has defects or not. According to the method, the problem of beam distortion of traditional ultrasonic waves during detection of the roller defects of the logarithmic bus bearing is solved, and the detection precision is remarkably improved.

The present invention belongs to the field of rehabilitation therapy technology and discloses a longitudinal analysis method and system for magnetic resonance imaging data of mild brain injury. The method extracts BOLD signals from the magnetic resonance imaging data of subjects; constructs a symmetric positive definite sparse brain functional connectivity network set of subjects based on sparse inverse covariance matrix estimation; determines the brain functional connectivity network dictionary and sparse coefficient matrix in kernel space based on Riemannian manifold sparse coding; performs spatial distribution analysis of brain functional connectivity atomic networks; and performs longitudinal analysis of magnetic resonance imaging data of mild brain injury. By analyzing the differences in the spatial distribution of these highly present brain functional connectivity atomic networks in the brain, the present invention digs out brain functional connectivity imaging markers for distinguishing the three mild brain injury rehabilitation treatment stages: acute phase, subacute phase, and complete recovery, thereby realizing longitudinal analysis of the mild brain injury rehabilitation process.

The invention discloses a battery health state prediction model training method and device and a storage medium, and relates to the technical field of batteries, and the method comprises the steps: determining a source domain spatial-temporal characteristic matrix and a target domain spatial-temporal characteristic matrix according to source domain target time sequence data and target domain target time sequence data; performing battery health state prediction based on the source domain spatial-temporal characteristic matrix to obtain a source domain SOH prediction value; iteratively solving a source domain dictionary and a source domain sparse coefficient matrix of the source domain features, reconstructing target domain features based on the source domain dictionary, and determining the difference between the two domains; and obtaining a total loss value based on the source domain SOH predicted value, the source domain SOH true value and the difference between the two domains, and updating parameters of the health state prediction model based on the total loss value until a trained battery health state prediction model is obtained. The problem that in the prior art, a battery health state prediction model is poor in generalization performance when facing cross-domain data distribution offset is solved, and the prediction stability and accuracy of the model under different working conditions are improved.

The invention relates to the technical field of wavelength division multiplexing, and particularly provides a sparse representation-based lower wave enhancement method of a reconfigurable optical add-drop multiplexer, which comprises the following steps of: performing conversion processing on a lower wave mixed optical signal to obtain a digital electric signal vector; wherein the lower wave mixed optical signal at least comprises a target signal and an interference signal; performing sparse decomposition processing on the electric signal vector based on the over-complete dictionary to obtain a sparse coefficient vector; wherein the over-complete dictionary at least comprises target signal atoms and interference atoms; identifying and extracting a target coefficient corresponding to the target signal atom from the sparse coefficient vector; and combining the target coefficient with the target signal atoms to obtain an enhanced target signal. According to the sparse representation-based lower wave enhancement method for the reconfigurable optical add drop multiplexer, provided by the invention, the accuracy of extracting a target signal in ROADM lower waves can be improved, and adjacent channel interference and noise are effectively inhibited, so that the performance is improved.

The invention relates to a land surface temperature and emissivity joint inversion method and system and a medium. The inversion method comprises the following steps: acquiring radiation brightness vectors observed by a satellite sensor in a plurality of thermal infrared bands as observation radiation brightness vectors; constructing a standard emissivity spectrum dictionary database as a dictionary matrix; defining a generation rule of the surface emissivity; establishing a forward physical model, and taking an analog value of the observed radiance vector as model output; defining a likelihood function of an observation radiance vector, defining sparsity prior probability distribution for the sparse coefficient vector, and defining uniform prior probability distribution for the surface temperature; joint posterior probability distribution of the surface temperature and the sparse coefficient vector is calculated, and multiple groups of samples are extracted; calculating a posteriori estimation value and an uncertainty interval of the surface temperature; and calculating a posteriori estimation vector of the sparse coefficient vector, and multiplying the posteriori estimation vector with the dictionary matrix to obtain a posteriori estimation value of the surface emissivity. The automation level of remote sensing information extraction and the information output efficiency are improved.

An on-loop efficient multiplication optimization method based on a sparse ternary polynomial and precomputation belongs to the field of cryptography and comprises the following steps: compressing a cyclic matrix of a prime order domain loop into a single row to obtain a generation operator matrix temp; storing the second column of elements in the temp in an inverted sequence; according to the sparse property of a ternary polynomial and the algebraic structure characteristic of a finite ring (Z / q) [x] / (xp-x-1), through sparse coefficient traversal, table look-up operation is carried out on non-zero coefficients of the ternary polynomial. According to the method, traditional NTT multiplication is replaced by addition and subtraction, the sparse small polynomial characteristics are combined, the theoretical complexity of polynomial multiplication is reduced to be close to O (p) from O (p2), and the operation efficiency is remarkably improved; a compression type precomputation cyclic matrix and a reverse storage strategy are adopted, memory occupation is reduced, the resource utilization rate is improved, the application scene is expanded, and flexibility and practicability are remarkably improved.

The invention discloses a user health data monitoring method and system based on a smart watch, and relates to the technical field of smart wearable health monitoring, and the method comprises the steps: carrying out the optimization through Hilbert transform and cross-spectral density, carrying out the iteration of a sparse coefficient through employing MCMC, carrying out the dimension reduction construction of a track matrix through employing Ortho-SSA, carrying out the screening through ReliefF and VC-SSA, and initializing a GBTN model. NAS is used for adjustment, integration is carried out through federated average and incremental learning, and the health state is monitored. According to the method, through the VIB model, cross-spectral density optimization, GMM noise modeling and MCMC sparse iteration, the dynamic coupling relation between modes is accurately captured, the robustness of data representation is improved, and through fusion of causal reasoning and federated learning, the accuracy of the health monitoring state is improved.

The invention relates to the technical field of aero-engine rotating blade health monitoring, and provides an aero-engine rotating blade timing undersampling vibration signal reconstruction method and system, and the method comprises the steps: constructing a reconstruction model and a recovery matrix; setting an initial residual error and a support set of the recovery matrix; calculating the inner product of the column vector of the recovery matrix and the initial residual error; the column vectors with the absolute values of the inner product values exceeding a threshold value are selected as matching vectors to be combined into a first set; projecting the first set to a parameter space; clustering is carried out by adopting a K-nearest neighbor algorithm, and column vectors with maximum inner products in each class are reserved to form a second set; adding the second set into a support set, and solving a sparse coefficient by adopting a least square method by taking the minimum initial residual error as a target; a new residual error is calculated, iteration is terminated until the support set is not updated any more, and a final vibration signal sparse coefficient is obtained; and calculating to obtain a blade end vibration signal of the rotating blade of the reconstructed aero-engine. According to the invention, the non-contact online real-time health monitoring effect of the blade can be improved.

The invention provides a business load prediction method and device, equipment, a storage medium and a product, and relates to the field of financial science and technology or other related fields, and the method comprises the steps: obtaining historical business feature data and a historical business load value; converting the historical business feature data into an original sparse coefficient matrix of a sparse linear equation set; converting a first element value in the original sparse coefficient matrix into a semi-precision format for storage; generating an approximate inverse matrix of the original sparse coefficient matrix based on the first element values stored in the semi-precision format, and storing second element values in the approximate inverse matrix in the semi-precision format; converting the first element value and the second element value in the semi-precision format into a single-precision format; and based on the historical business load value, the first element value of the single-precision format and the second element value of the single-precision format, executing solving operation of the equation set, and determining a predicted value of the business load according to a solution vector obtained by solving. According to the method, the storage space occupied by the matrix data and the data transmission bandwidth pressure can be reduced.

The invention discloses a surveying and mapping geography multivariate data fusion processing method. The method comprises the following steps: S1, data preprocessing; s2, constructing a sparse representation model; s3, estimating posterior distribution, and assuming a data generation mode; s4, carrying out sparse coefficient fusion, and carrying out joint modeling by using a multi-task sparse coding model; s5, enhancing relevance, and constructing a semantic network graph model; and S6, performing global optimization and output. According to the method, the defects of a traditional method in processing diversified scales can be effectively overcome in the data preprocessing link, the data quality is greatly improved, local optimum is avoided and the convergence speed is increased through self-adaptive step length adjustment and a random restart mechanism when the sparse representation model is constructed, and meanwhile, in the global optimization and output stage, the algorithm is simple and convenient to operate. A multi-objective evolutionary algorithm is adopted, multiple optimization objectives can be considered at the same time, an optimization strategy is flexibly adjusted according to an actual application scene, deep data fusion is achieved, and the comprehensive utilization value of surveying and mapping geography multivariate data is improved.

The invention relates to the technical field of data processing and state monitoring, and discloses an intelligent ring main unit fault real-time diagnosis method and system, and the method comprises the steps: constructing a fault feature over-complete dictionary; collecting and preprocessing high-frequency operation data streams of the ring main unit in real time; carrying out online sparse decomposition and manifold mapping based on the dictionary, and converting a high-dimensional signal into a low-dimensional sparse coefficient and manifold features; and a lightweight classification model is used for rapid reasoning, and fault early warning and data uploading are triggered when abnormity is detected. The system comprises a data acquisition module, a preprocessing unit, an edge computing engine, an intelligent diagnosis module and a communication gateway. According to the method, depth dimension reduction and feature enhancement are realized through a manifold sparse coding technology, the bandwidth pressure and the calculation overhead are reduced on the premise of ensuring the fault feature integrity, and the real-time performance and the accuracy of diagnosis are improved.

The invention provides a signal optimization method and system for wireless transmission equipment, and relates to the technical field of wireless communication, and the method comprises the steps: constructing a movement track prediction model, and carrying out the prediction processing of communication state parameters through the movement track prediction model, and obtaining a speed sequence and a position track; performing conjugate gradient optimization and dynamic step length adjustment on the speed sequence, and further performing dynamic phase compensation on the position trajectory by the optimized and adjusted speed sequence to obtain a trajectory compensation parameter; sparse compressed sensing is carried out on communication signals of the wireless transmission equipment to obtain a sparse coefficient matrix, and a power distribution vector is determined based on the sparse coefficient matrix and the track compensation parameters; and determining a communication evaluation value according to the signal to interference plus noise ratio change and the power distribution vector of the wireless transmission equipment, and optimizing and updating the power control parameter of the wireless transmission equipment based on the communication evaluation value, thereby realizing the dynamic power control of the mobile Internet of Things terminal based on prediction compensation so as to improve the stability of signal optimization.

The invention relates to a phased array radar reflectivity factor simulation method based on sparse sounding data, belongs to the field of radio, designs a sparse reconstruction simulation scheme based on acquired multi-point multi-height-layer sparse sounding data, and realizes high-quality restoration and three-dimensional continuous field construction of original sparse observation data. A multivariate dictionary base matrix is constructed; through a sparse representation theory and a Bayesian optimization model, a sparse coefficient reflecting rainfall essential characteristics is obtained, and high-spatial-resolution reconstruction of a temperature and humidity field and a rainfall micro-physical parameter field is realized. Thereafter, a meteorological parameter-driven phase judgment and probability field calculation model is constructed, and three-dimensional simulation of liquid, solid and mixed rainfall echoes is realized. And finally, calculating a unit direction vector and an azimuth guidance coding matrix of a beam ray of the phased array radar, introducing a radar volume scanning data implicit sampling simulator, and realizing high-precision reflectivity factor simulation of the phased array radar in a three-dimensional scanning mode.

The invention discloses an existing concrete beam bridge crack diagnosis method based on an influence line sparse coefficient, which is characterized in that force method graph multiplication and a crack nonlinear damage function are substituted into an analytical solution for solving, and finite element simulation relates to respiration crack simulation. A nonlinear spring is adopted to simulate crack opening and perform grid division and encryption processing on the tip of the crack, bridge section rigidity change caused by the breathing crack is accurately simulated by constructing a crack rigidity damage function, and the model is introduced into an influence line analytical solution to obtain a nonlinear influence line of the cracked bridge. In combination with a sparse coefficient representation method, damage position and damage degree information is extracted from influence line data, and accurate positioning and quantitative evaluation of beam bridge section cracking are achieved; the method not only improves the accuracy and efficiency of damage identification, but also provides a reliable technical means for rapid detection and state evaluation of the existing beam bridge.

The invention provides a power grid ultra-high-order harmonic detection method and device based on adaptive compressed sensing. The detection method comprises the following steps: step 1, acquiring a power signal of a detected area in a power grid to obtain a discrete power signal; step 2, sampling an original signal vector; 3, carrying out DFT operation on the sampled signal matrix, and carrying out modular operation to obtain a modular value matrix and a maximum modular value; 4, constructing a module value distribution matrix according to the distribution of module values in the module value matrix; step 5, carrying out compression processing on the original signal vector by adopting a compressed sensing method, and carrying out signal reconstruction to solve a sparse coefficient vector; step 6, carrying out Fourier transform on the sparse coefficient vector, and selecting a plurality of maximum peak values in a module value sequence to carry out characteristic frequency calculation; and step 7, constructing a filter bank according to the characteristic frequency, filtering the module value sequence, and converting to obtain an ultra-high-order harmonic detection result. According to the invention, the efficiency and precision of power grid ultra-high-order harmonic detection can be improved.

The invention relates to the technical field of ion beam physical calculation, in particular to an ion beam optical property evaluation method based on a CPU-GPU hybrid parallel stable double-gradient conjugate algorithm. According to the technical scheme, the method comprises the following steps that a CPU-GPU hybrid parallel architecture is initialized, and CPU end and GPU end memory allocation, CUDA related object creation and GPU equipment initialization and parameter setting are completed; constructing a linear equation set, a sparse coefficient matrix A and a right-end vector b, and setting an initial solution vector, convergence precision epsilon and related parameters of the number of iterations; and analyzing the sparseness of the coefficient matrix A. Through combination of three core mechanisms of CPU-GPU cooperative calculation, dynamic load balancing and intelligent preprocessor selection, efficient, stable and universal evaluation of the ion beam optical characteristics is successfully realized, and an excellent solution is provided for solving the solving problem of a large-scale sparse linear equation set in the field of high-performance calculation.

This invention discloses a noise reduction method, a bearing fault diagnosis method, and a system based on dual sparse dictionary adaptive learning. The method performs wavelet decomposition on the signal to be denoised to obtain high-frequency and low-frequency signals, constructing high-frequency and low-frequency matrices. Then, threshold-adaptive DDTF dictionary learning is applied to both the high-frequency and low-frequency matrices. Specifically, an initial dictionary is set and learned to obtain an initial sparse coefficient matrix. An adaptive threshold update is then applied to the initial sparse coefficient matrix, selecting sparse coefficients from the initial sparse coefficient matrix in descending order as dynamic thresholds during the iteration process to update the initial sparse coefficients. After determining the final threshold, the final sparse coefficient matrix is ​​obtained, and the dictionary is updated again to obtain sub-signals. Finally, inverse transformation and matrix rearrangement inverse operations are performed on the obtained sub-signals to obtain the denoised signal. This invention combines wavelet decomposition and DDTF to construct a dual sparse pattern, effectively improving the sparse representation capability of a fixed basis.

The application provides an abnormal audio detection method and a computer device, which can be applied to the field of device detection, and comprises the following steps: obtaining first audio data (including running audio of a to-be-detected device and surrounding environment audio), respectively performing time domain representation and frequency domain representation on the first audio data, then calculating correlation according to obtained first time domain data and first frequency domain data, and obtaining second audio data according to the correlation, extracting target features of the second audio data through a trained first model, obtaining sparse coefficients based on the target features, and judging whether the second audio data is abnormal audio according to the sparse coefficients. The application describes audio change conditions from two dimensions of time domain and frequency domain, simultaneously smoothes a sound scene through correlation comparison of the two dimensions, removes interference, and corrects a starting point and an ending point of current audio data. In addition, key features in the second audio data are identified by using the trained first model, so that various types of abnormal sound can be identified.

The invention relates to the technical field of image fusion, in particular to a hesitant fuzzy variable granularity dictionary learning-based multi-modal image fusion method, which comprises the following steps of: firstly, adaptively selecting division granularity according to image quality, and partitioning a source image into blocks; then extracting image block features and calculating hesitant fuzzy membership degrees of the image block features so as to quantitatively represent uncertainty information in the image; obtaining a joint over-complete dictionary and a sparse coefficient through dictionary learning, and fusing the hesitant fuzzy entropy and a granularity coefficient to construct an adaptive weight; and finally, fusing the sparse coefficient by using the weight and reconstructing a fused image. The problems of image fuzzy processing, structure multi-scale expression and insufficient adaptive feature extraction capability are effectively solved.

The application discloses an aero-engine bearing fault diagnosis method and system, which carries out amplitude normalization preprocessing on the vibration signal of the aero-engine bearing, unifies the signal data magnitude, and eliminates the analysis interference caused by the signal amplitude difference; a convolution sparse coding optimization objective function is built relying on a non-separable learnable sparse regularizer, the limitation of traditional norm and other separable regularization methods is broken, the sparse coefficients are no longer regarded as independent individuals, the structural interaction relationship between the multi-channel sparse coefficients can be fully mined, the interference caused by strong background noise, multi-source vibration coupling and complex transmission path under actual working conditions can be effectively stripped, the weak impact characteristics of the early bearing damage submerged by noise can be accurately separated, the early fault signal extraction effect under complex operating conditions is greatly improved, and the local impact fault characteristics in the aero-engine bearing vibration signal are effectively enhanced, so that the fault diagnosis is completed without any label.