683 results about "Wavelet decomposition" patented technology

The invention belongs to the technical field of computer data processing, and provides a biodiversity inversion method based on multi-source remote sensing image fusion. Comprising the steps of remote sensing image data acquisition, image preprocessing, image fusion processing, multispectral resolution image data generation, spectral feature extraction, final frequency feature extraction, feature integration and target ecological variable prediction. According to the invention, through wave basis adaptive selection and multi-scale wavelet decomposition, spectrum fidelity and space structure maintenance are considered, differential fusion of high and low frequency components under different scales is realized, and multi-source data complementarity and fusion image quality are improved; through spectral resolution refinement processing and multi-bandwidth scale simulation, the limitation of single resolution is broken through, and the capability of capturing complex spectral features of vegetation is enhanced; the spatial correlation is enhanced through spatial neighborhood feature fusion; and through an ecological variable inversion estimation model, multi-index synchronous prediction is realized, and the universality of the model is improved.

The invention discloses a bearing defect detection method and system based on machine vision and ultrasonic detection, and particularly relates to the technical field of industrial automatic detection, and the method comprises the steps: S1, a synchronous collection module: carrying out pulse triggering synchronous collection, and generating a time-space reference table; s2, a feature extraction module: performing image noise reduction segmentation and ultrasonic frequency domain decomposition, and outputting a defect feature vector; s3, a fusion identification module: performing cross-modal feature alignment fusion to generate a defect classification conclusion; s4, a size measurement module: performing contour fitting to calculate inner and outer diameters, and outputting a size deviation value; and S5, a comprehensive judgment module: carrying out threshold comparison logic judgment, and generating a multi-modal detection report. According to the method, a space-time reference is established through an encoder, images are segmented in a self-adaptive mode, features are extracted through wavelet decomposition ultrasound, feature weights are re-calibrated through a parallel network and an attention mechanism, composite defects are recognized through cross-modal fusion, comprehensive judgment is conducted in combination with dimensional deviation, and a multi-dimensional quality evaluation system is achieved.

The invention provides a hydro meteorology early warning method for an offshore oil and gas platform, and belongs to the technical field of offshore hydro meteorology. Extreme weather events are identified by adopting minimum probability abnormal event identification vectors to match abnormal characteristic parameters, and abnormal signal characteristic parameters are input into an ocean dynamics prediction model to calculate real-time sea condition parameters; calling a multi-temporal-spatial-scale early warning fusion matrix to combine with a wavelet decomposition technology and a recurrent neural network to realize multi-scale information integration, analyzing an environmental parameter change trend through a sea condition jump identification model and triggering an emergency response, dynamically adjusting system parameters according to a stability evaluation index vector, and optimizing prediction precision by adopting an early warning residual value compensation matrix. And finally, multi-level early warning information is generated and a real-time early warning notification is sent to an operator, so that the technical problem of insufficient early warning precision of an offshore oil and gas platform hydro meteorology early warning system in multi-spatio-temporal scale data fusion processing is solved.

The invention discloses a high-resolution hyperspectral image reconstruction method based on wavelet domain feature fusion and contrast learning, and belongs to the technical field of image fusion and super-resolution reconstruction. The method comprises the following steps: constructing a fusion network model comprising a wavelet transformation module, a cross-modal feature fusion module, a high-frequency contrast learning module and an image reconstruction module; performing end-to-end supervised training by using a training data set containing the low-resolution hyperspectral image and the high-resolution multispectral image; and after training is completed, inputting a test image pair to realize image reconstruction. According to the method, the detail retention capability is improved by combining wavelet decomposition and a directional fusion mechanism, the cross-modal high-frequency feature alignment capability is enhanced through comparative learning, a fusion image with high spatial resolution and high spectral consistency is finally generated, and the method is suitable for multi-modal image reconstruction tasks such as remote sensing, medical and natural images.

The invention relates to a multi-branch power distribution network double-end traveling wave fault positioning method and system, and the method comprises the steps: deploying a plurality of measurement points based on the head and tail ends of a radial power distribution network and branch terminals, collecting topological information, and calculating the linear mode wave velocity; using the three-phase voltage data after the fault to extract traveling wave line mode and zero mode components through modulus decoupling; a line mode component with the strongest global mutation is selected as a reference, and a wave head time sequence table is generated through wavelet decomposition and mutation detection; and correcting the zero-mode wave velocity by combining the topology, the time sequence table and the line-mode wave velocity, and determining a fault interval and outputting a fault position after compensation and correction by using the line-mode and zero-mode wave head time difference. According to the invention, through a wave head time sequence analysis and time difference compensation mechanism based on cooperation of multiple measuring points, positioning errors caused by clock asynchronization and parameter disturbance are effectively overcome, accurate distance measurement which is not influenced by clock errors is realized, and the distance measurement precision is significantly improved; and meanwhile, the point distribution requirement is simplified, accurate judgment and positioning of a fault interval can be realized only by a branch single measuring point, and high economy and deployment flexibility are both achieved.

The invention relates to the technical field of power system communication, and discloses a fault diagnosis method and system for a substation communication network, and the method comprises the steps: obtaining multi-band signal data, and carrying out the fast Fourier transform to obtain spectrum distribution data; according to the spectrum distribution data, performing frequency band division to obtain an initial power ratio; performing adaptive filtering according to the initial power ratio and the multi-band signal data to obtain a fundamental wave amplitude fluctuation characteristic; performing wavelet decomposition according to the fundamental wave amplitude fluctuation characteristics to obtain abnormal signal time-frequency energy distribution; performing K-means clustering division according to the abnormal signal time-frequency energy distribution, and matching a harmonic fault database to obtain a fault type identifier; and according to the fault type identifier and the abnormal signal time-frequency energy distribution, ring network topology propagation time delay analysis is carried out, a fault position coordinate is positioned, and a fault diagnosis report is generated. According to the method, the network fault can be accurately diagnosed for multi-band complex signal interference.

The invention provides a pavement defect analysis and detection method and system, and relates to the technical field of defect identification. Through multi-source data fusion processing, a dynamic anchor frame adjustment mechanism, an improved feature extraction network and a multi-stage wavelet decomposition technology, the problem of missing detection of a traditional detection method under shadow interference is effectively overcome, the defect recognition precision in a complex scene is remarkably improved, refined quantitative evaluation of the pavement condition is achieved, and the method is suitable for large-scale popularization and application. The method has the technical advantages that the small-scale defect recognition precision in a complex scene is improved, the shadow interference resistance is enhanced, and multi-dimensional quantitative evaluation is realized.

The invention discloses a panchromatic sharpening method and system based on cross-resolution adversarial learning and a Mama network. The method comprises the following steps: acquiring a low-resolution multispectral image LRMS and a high-spatial-resolution panchromatic image PAN; extracting features of the low-resolution multispectral image LRMS to obtain a first feature map; extracting features of the high-spatial-resolution panchromatic image PAN to obtain a second feature map; performing wavelet decomposition and weighted fusion on the first feature map and the second feature map to obtain a multi-channel feature map, and performing dynamic fusion on the multi-channel feature map through a cross attention gating mechanism to obtain a fused feature map; and carrying out residual connection on the fused feature map and the low-resolution multispectral image, and then carrying out feature reconstruction to obtain a high-resolution multispectral remote sensing image. According to the method, the panchromatic sharpening performance of the remote sensing image can be improved, and the high-quality and high-resolution multispectral remote sensing image is obtained.

The invention relates to the technical field of data processing, and discloses a secondary equipment hidden danger mining method and system based on a wave recording file and monitoring data. The method comprises the steps of calculating a conditional probability and intervention probability difference identification causal relationship by analyzing a recording file in combination with equipment topology and protection logic to construct a correlation graph, and performing Fourier transform and wavelet decomposition on a sampling sequence to extract multi-scale features; small signal test excitation is injected, a system identification estimation transfer function is fused with monitoring data to form a health feature vector to judge a health state, and a correlation map and the health state are input into a map neural network to calculate weighted attention coefficients and aggregate neighbor information to predict a fault propagation path; and establishing a degradation model, correcting the failure rate, predicting the residual life and generating a graded early warning report. According to the method and the device, the transformation from passive post analysis to active predictive maintenance is realized, and the timeliness, accuracy and systematicness of hidden danger identification of the secondary equipment are improved.

The invention discloses an ancient textile image restoration system based on artificial intelligence. The system comprises a multi-source image acquisition module, a damaged area detection module, a pattern generation module, a color restoration module, a texture synthesis module and a multi-scale fusion module. The system introduces a wavelet guidance-frequency domain attention mechanism and a rotation invariant Haar wavelet basis function to realize accurate identification and classification of a damaged area; a saliency-guided wavelet decomposition control and self-adaptive threshold denoising method is combined, so that the perception capability of slant textures and edge details is improved; the texture synthesis module constructs a hierarchical modeling strategy fusing Gram style loss, Wasserstein style loss and a total variation regular term, and realizes generation of high-quality textures with unified styles and smooth edges; the system can be widely applied to cultural relic digital repair and display scenes.

The invention discloses a single image super-resolution reconstruction method and system based on wavelet transform and cross-domain feature fusion. According to the method, firstly, a low-resolution RGB image is mapped to a high-dimensional feature space through a shallow feature extraction module; performing up-sampling and discrete wavelet decomposition on the features by using a wavelet feature mixing module to obtain multi-band features; low-frequency and high-frequency depth features are respectively extracted through a double-branch structure, cross-domain fusion is realized by means of a deformable cross attention mechanism, and the feature expression ability is enhanced in combination with residual connection; and finally, reconstructing a high-resolution image through convolution, up-sampling and regularization processing. In the training process, a pixel-level loss function is adopted to optimize network parameters, the multi-frequency-domain feature sensitivity is effectively improved, texture and structure information is balanced, the image contrast, definition and structural integrity are improved, and high-quality real-time super-resolution reconstruction can be achieved.

The invention discloses an assembly type building node stress monitoring and design feedback system based on BIM, and relates to the technical field of building engineering structure monitoring, a building information modeling model is constructed, component geometric information, a connection mode and a load path associated with nodes are extracted, and a node mechanical attribute initial parameter set is formed; in combination with node real-time stress monitoring data, Fourier transform and wavelet decomposition are carried out, and frequency domain characteristic parameters are extracted; constructing a finite element correction model, and simulating a stress response path under a multi-load combination; the predicted stress peak value is compared with the actually measured stress peak value, structural abnormal nodes are identified, parameter optimization is executed according to node construction information, the component size, the steel bar anchoring length or the concrete grade are automatically adjusted, an optimized parameter set is generated and written back into a building information modeling model, and closed-loop correction is formed; continuous monitoring, abnormity diagnosis and intelligent optimization of the node stress state can be achieved, and the safety and the intelligent level of assembly type building structure design are improved.

The invention relates to the technical field of building electrical, and discloses a building electrical safety intelligent evaluation method and system based on Internet of Things dynamic monitoring, and the method comprises the steps: collecting multi-dimensional data in real time through an Internet of Things sensor network deployed in a building electrical system; carrying out wavelet decomposition on the collected multi-dimensional data, extracting time domain and frequency domain features, carrying out feature fusion and noise removal on multi-scale wavelet coefficients by using a convolutional neural network, and obtaining a denoised multi-dimensional feature vector; inputting the multi-dimensional feature vector into a dynamic evaluation model, and outputting a risk level, fault probability prediction and a key risk factor through the dynamic evaluation model; according to an output result of the dynamic evaluation model, performing graded early warning on the building electrical system; according to the invention, dynamic evaluation and early warning are carried out on the safety state of the building electrical system, evaluation is comprehensive and accurate, and the efficiency and level of building electrical safety management are improved.

The invention discloses an unmanned aerial vehicle power distribution network equipment identification method based on mutual neighbor density peak value clustering, and relates to the technical field of power distribution network equipment inspection, and the method comprises the steps: obtaining an original RGB image of a power distribution line; outputting the contrast characteristic coefficient of each channel; constructing a saturation retention item; calculating a contrast feature retention item, constructing a total energy function, solving an optimal channel weight by adopting a discrete search strategy, and outputting an initial grayscale image; sequentially carrying out weighted guide filtering, morphological reconstruction and super-pixel segmentation operation; performing two-dimensional wavelet decomposition on the super-pixel segmented image, and extracting a feature vector; and calculating the local density and the relative distance, selecting a clustering center, and completing sample distribution based on the shared mutual neighbor similarity to realize a power distribution network equipment identification effect. According to the method, the problems of detail loss, noise interference, edge breakage, disordered classification of multi-scale equipment and the like under complex illumination are effectively solved, and the identification precision and efficiency of unmanned aerial vehicle inspection are effectively improved.

The invention discloses a gas pipeline operation risk dynamic evaluation system based on big data analysis, and relates to the technical field of gas pipeline safety monitoring, and the system comprises a multi-source data processing module, a feature extraction module, a local risk modeling module, a risk evolution prediction module and a dynamic early warning module. The multi-source data processing module is used for acquiring original multi-source time sequence data from a pressure sensor, a flow sensor, a temperature sensor, a geological monitoring device and a third-party construction disturbance data interface of a gas pipeline network, and performing time alignment, abnormity elimination, normalization and characteristic standardization processing on the data; a uniform input feature vector is formed; and the feature extraction module is used for decomposing the normalized time series data into a low-frequency trend component and a high-frequency residual signal by using discrete wavelet decomposition. The gas pipeline risk assessment system solves the problems of low gas pipeline risk assessment precision, insufficient risk propagation modeling and lack of dynamic early warning and emergency strategies in the prior art.

The invention relates to the technical field of sealing performance testing, in particular to a breather valve performance online testing method for oil and gas storage and transportation, which comprises the following steps: acquiring a vibration signal of a breather valve body, a multi-band acoustic signal of a valve port and a total pressure signal in a storage tank; performing multi-scale complex wavelet decomposition, and constructing a time frequency-energy correlation feature tensor; the total pressure signal and the time frequency-energy correlation characteristic tensor serve as a combined observation value and are input into a preset continuous Gaussian mixture hidden Markov model containing four hidden states of sealing, transient micro-leakage, continuous leakage and full-amount opening, and the posterior probability is calculated; and calculating to obtain a real-time leakage rate. According to the method, the opening pressure can be accurately determined, the real-time leakage rate can be quantitatively calculated after the leakage state is recognized, comprehensive and accurate quantitative online evaluation of core performance parameters of the breather valve is achieved, and the multi-source information fusion degree and the anti-interference capacity are improved.

The invention relates to the technical field of data processing, and provides a battery performance detection device and method, and the method comprises the steps: obtaining transient voltage data and transient current data of a battery in different working states, carrying out the wavelet decomposition of the transient voltage data, obtaining a multi-state voltage feature, carrying out the time sequence mapping of the multi-state voltage feature and the transient current data, and obtaining a multi-state voltage feature; and obtaining an inflection point parameter set to construct a parameter stability matrix, analyzing a battery health state based on the parameter stability matrix, generating a battery life prediction based on a health state index, and performing trend analysis and residual life estimation to generate a battery performance detection result. When a complex electrochemical environment and various working states are processed, the efficiency and accuracy of battery performance detection are improved, and the problems of long battery test period and poor detection precision in practical application are solved.

The invention discloses a high-precision positioning method and system based on a multi-band single Beidou signal, and the method comprises the steps: receiving a multi-band signal from a single Beidou satellite, the multi-band signal comprises three bands B1I, B1C and B2a, extracting a pseudo-range measurement value and a carrier phase measurement value of the signal of each band, and calculating the pseudo-range measurement value and the carrier phase measurement value of the signal of each band according to the pseudo-range measurement value and the carrier phase measurement value; constructing an observation value model containing multi-path errors and ionosphere delay; performing wavelet transform decomposition on the multi-band observation value sequence to obtain signal characteristics on different frequency scales, and constructing a multi-path-ionosphere coupling separation discriminator using pseudo-range and carrier phase observation value characteristic difference and a frequency dependency relationship based on a wavelet decomposition result; the error dominant type is determined according to the size of the discriminant value output by the separation discriminator, the observation value is corrected by applying a corresponding error correction strategy, the corrected observation value is used for position calculation, and a high-precision positioning result is obtained.

The invention relates to the field of image processing, and particularly discloses a rural highway pavement disease intelligent identification and positioning system comprising an image standardization module used for obtaining a standardized grayscale image; the wavelet decomposition module is used for obtaining a low-frequency sub-band and a plurality of high-frequency sub-bands; the high-frequency processing module is used for carrying out soft threshold processing on the high-frequency coefficient and retaining high-variance region features; the inverse transformation module is used for reconstructing the de-noised image; the edge enhancement module is used for highlighting crack and pit slot target contour information; the binarization module is used for segmenting a foreground disease candidate region; and the edge filling module is used for separating the disease from the background. According to the method, the core contradiction between background impurity removal and disease feature retention in rural highway tiny disease recognition is effectively solved, a traditional denoising algorithm either smooths tiny disease features or cannot thoroughly remove background impurities, and the system achieves the balance of the background impurity removal and the disease feature retention through cooperation of multiple modules.

The invention provides a structure health early warning method and system based on space-time correlation characteristics and digital twinning, and relates to the technical field of data processing. The method comprises the following steps: acquiring multi-source heterogeneous data of a target structure; performing dynamic sampling alignment and wavelet packet decomposition on the multi-source heterogeneous data to extract energy features to obtain synchronous data, and performing abnormal data filtering on the synchronous data to obtain cleaned fusion data; performing wavelet decomposition on a high-frequency vibration signal in the fused data to obtain a damage impact feature, performing time sequence processing on low-frequency temperature data in the fused data to obtain a temperature time feature, and performing dynamic graph convolutional network processing on strain data in the fused data to obtain a spatial correlation feature; constructing an input vector; calculating a damage degree index; and according to the damage degree indexes, early warning grades are divided, and corresponding control instructions are triggered for different early warning grades. By implementing the technical scheme provided by the invention, the accuracy of structural health early warning can be improved.

The invention relates to the technical field of ultrasonic signal processing, in particular to a wavelet and MAD adaptive threshold combined laser ultrasonic signal denoising method. The method comprises the following steps: firstly, preprocessing an acquired trigger channel signal and an ultrasonic channel signal, determining a signal starting point through differential positioning, and intercepting an effective signal segment; carrying out multilayer wavelet decomposition on the effective signal segment to obtain a wavelet coefficient of each layer; extracting a detail coefficient of the highest decomposition layer, and adaptively estimating a noise standard deviation based on a median absolute deviation criterion; calculating an adaptive threshold according to the noise standard deviation and the signal length, and processing each layer of wavelet coefficient by adopting a hard threshold function; and finally, carrying out wavelet inverse transformation reconstruction to obtain a denoised signal. According to the method, prior noise information is not needed, the noise level can be adaptively estimated, the optimal threshold value can be determined, the signal features are reserved while noise is effectively suppressed, and the signal-to-noise ratio is remarkably improved.

The invention discloses an ultra-low illumination-oriented SPAD active imaging data compression method, which comprises the following steps of: performing wavelet decomposition on histogram data of a single pixel in a time-frequency domain based on wavelet transform to obtain low-frequency data of each pixel after wavelet decomposition; by taking each pixel as a center, performing non-maximum suppression and data enhancement on the low-frequency data after the wavelet decomposition of the current pixel by using adjacent pixels to obtain processed compressed data; customizing different Gaussian kernel parameters for each pixel according to the possibility that each pixel is located at the boundary, and performing Gaussian filtering on the processed compressed data of each pixel to obtain filtered data; and performing depth estimation on the filtered data to obtain a final depth image. According to the method, the depth reconstruction performance of the laser pulse can be improved by utilizing the multi-resolution characteristic of wavelet transform, the space-time correlation of signal photons and the smoothness of Gaussian filtering.

The invention belongs to the technical field of spectral analysis, and discloses a Raman spectrum characteristic peak segmentation method based on distance vector and probability vector output. Spectral detail features are extracted through multi-scale wavelet decomposition, and a spectral multi-layer structure representation matrix is constructed; identifying a potential peak site and a hierarchical affiliation relationship thereof based on the local curvature change rate; generating an adaptive distance calculation kernel function in combination with the asymmetry index and the peak shape complexity coefficient; and calculating a distance vector of hierarchical perception and a probability vector extracted by deep learning, and constructing a joint segmentation decision function of a multi-layer peak structure. According to the method, the hierarchical relationship among the main peak, the shoulder peak and the sub-peak can be accurately distinguished, the complex conditions of peak overlapping, asymmetric peak shapes, low signal-to-noise ratio and the like are effectively processed, and the accuracy and the reliability of Raman spectrum analysis are improved.

The invention discloses a heart sound and electrocardio acquisition and analysis system, which relates to the technical field of biomedical engineering, and comprises a time-frequency analysis module for acquiring a heart sound and electrocardio original data set through an electrocardio and heart sound lead suction ball and an electrocardio and heart sound simulation complete machine and transmitting the data set to an upper computer to execute wavelet decomposition and short-time Fourier transform, the system comprises a heart sound time-frequency spectrum matrix and an electrocardio time-frequency energy matrix output module, a chaotic feature extraction module, the heart sound time-frequency spectrum matrix and the electrocardio time-frequency energy matrix are subjected to phase-space reconstruction, a high-dimensional dynamic track is formed, an improved wolf algorithm is applied to conduct dynamic index calculation on the high-dimensional dynamic track, and a dynamic parameter set is obtained. According to the method, through the improved wolf algorithm and the constructed heart sound space propagation model, the multi-modal fusion capability and analysis discrimination between the heart sound and the electrocardiosignal are improved, and the intelligent level of heart sound and electrocardiosignal collection and analysis is also improved.

The invention belongs to the technical field of artificial intelligence and data analysis, and discloses a time sequence prediction method and device based on wavelet transform and a large language model. The time sequence prediction method comprises the following steps: obtaining known historical time sequence data; based on the obtained known historical time sequence data, performing time sequence prediction in a future time period by using the trained time sequence prediction model to obtain predicted values of three frequency domain components of low frequency, intermediate frequency and high frequency; adding the obtained predicted values of the low frequency domain component, the intermediate frequency domain component and the high frequency domain component, and carrying out inverse normalization processing on the added result to obtain a final time sequence prediction result; the time sequence prediction model comprises a wavelet decomposition module, a backbone network of a pre-training large language model and a prediction head. According to the technical scheme disclosed by the invention, the accuracy of time sequence prediction can be remarkably improved.

The invention relates to the field of image defect detection, in particular to an SMT defect detection method and system based on image recognition, and the method comprises the steps: shooting a to-be-detected circuit board through an optical detection device to obtain an original circuit image, carrying out the illumination compensation of the original circuit image to obtain a target circuit image, carrying out the two-dimensional wavelet decomposition of the target circuit image, and carrying out the detection of the SMT defect. The method comprises the steps of obtaining a horizontal component floating-point diagram and a vertical component floating-point diagram, performing edge identification on a target circuit image according to the horizontal component floating-point diagram and the vertical component floating-point diagram to obtain an edge pixel point set, clustering the edge pixel point set by using the number of elements to obtain a plurality of element edge point sets, and constructing a plurality of surface-mounted component areas based on the plurality of component edge point sets, determining a defect component area group in the plurality of surface-mounted component areas, and transmitting the defect component area group to a display device. According to the invention, the accuracy of SMT mounting defect detection can be improved, and the defect response speed of a production line is improved.

The invention relates to an underwater single target tracking method based on a wavelet token and a space-time Transform. The method comprises the following steps: firstly, constructing a reference frame sequence, a search frame and a previous frame historical token into a space-time input sequence, and extracting cross-frame features through a Transform encoder; then, Haar wavelet decomposition is carried out on the historical token, and a low-frequency component representing a target structure and a high-frequency component capturing motion details are separated out; then, adaptively fusing the global features and the historical components of the current search frame by using a gating mechanism, and generating a wavelet token; and finally, inputting the wavelet token and the global feature into a prediction head, and outputting a target classification confidence map and a bounding box regression map to determine the position and the scale of the target. According to the technical scheme of the invention, the interference of underwater low-illumination noise can be effectively suppressed through the wavelet token, and the space-time continuity of target motion modeling is maintained in combination with a gating strategy, so that the tracking robustness of an underwater complex scene is effectively improved.

The invention discloses an energy storage lithium ion battery capacity abnormity identification method, system and equipment, and relates to the technical field of lithium ion batteries. The method aims to overcome the defects that an existing battery capacity diagnosis method needs to depend on complete charging and discharging data, a complex battery model or large-scale historical operation data support, and it is difficult to meet capacity anomaly judgment requirements under the conditions of rapidness, disturbance and data sparseness in actual operation. Obtaining a standing voltage curve after charging and discharging of the energy storage lithium ion battery are stopped, and constructing a standing voltage time sequence; selecting a group of wavelet functions satisfying multi-scale orthogonality, performing wavelet decomposition on the standing voltage sequence, and extracting low-frequency approximate components; performing feature extraction on the obtained low-frequency approximate components to obtain standardized three-dimensional features of each battery monomer; and clustering the batteries with abnormal capacities by adopting a clustering algorithm to obtain a normal battery category and an abnormal battery category. The method is mainly used for identifying the capacity abnormity of the energy storage lithium ion battery.

The invention relates to a semi-supervised medical image segmentation method based on double-path feature alignment, and belongs to the field of medical image processing. Aiming at the problems that medical image annotation is scarce, high-frequency information is sensitive and feature fusion is not accurate in an existing method, a three-branch network architecture is provided, a main network extracts original image features, and an auxiliary network processes high-frequency and low-frequency images subjected to discrete wavelet decomposition respectively; cross-branch feature deformation correction and fusion are realized through a wavelet feature alignment module (encoder) and a simple feature alignment module (decoder); and unsupervised loss dynamic training is carried out in combination with supervised loss and pseudo-label, so that label dependence is relieved. According to the method, the segmentation precision and the boundary detail retention capability are effectively improved, the noise robustness is enhanced, the annotation data dependence is remarkably reduced, meanwhile, the cross-branch fusion efficiency is improved through a feature alignment mechanism, and the method has high clinical application value.

The invention discloses a method and device for predicting carbon emission data of a gas turbine of a thermal power plant, and the method comprises the steps: carrying out the standardization processing of a trend term through reversible instance normalization, and enabling m variable channels to be clustered into n channel clusters through employing a K-Means algorithm for the trend term after the standardization processing; through a cluster-driven prediction module, applying an exclusive independent prediction model for each channel cluster to carry out parallel prediction, and carrying out inverse standardization on a prediction result to obtain a final trend prediction value, and carrying out structured multi-scale wavelet decomposition on a seasonal item to obtain a final approximate component and a plurality of high-frequency detail components; performing collaborative coding on the final approximate component to obtain depth context representation; performing dynamic fusion on the depth context representation and the plurality of high-frequency detail components by adopting an attention cross-scale fusion module to obtain fusion representation; and reconstructing a seasonal component according to the fusion representation and the plurality of high-frequency detail components through inverse wavelet transform to obtain a seasonal predicted value and a trend predicted value to form a final long-term time sequence prediction result, and outputting the result.