683 results about "Wavelet transform" patented technology

The invention relates to a dynamic adjust gyroscope life forecasting method based on gray model. By data collection of vibration effective value, random drift and environmental temperature parameter which are preprocessed using radial neural networks, influence of environmental temperature on vibration effective value and random drift is eliminated and random drift and effective value just related to time are obtained by subtracting drift constant value term, then trend term of vibration effective value and random drift are extracted by using wavelet transformation and gray model are built separately for their trend term. The smaller data in two values of life predicted of dynamic adjust gyroscope unless two predicted values exceeding performance parameter limitation when dynamic adjust gyroscope is considered losing effect. The invention uses performance parameter of life probative period of product to predict its life, showing discipline of performance parameter and life of dynamic adjust gyroscope. It is easy and convenient economical and reliable.

The invention relates to a medical image segmentation method based on wavelet boundary enhancement and multi-scale perception, and the method comprises the steps: firstly carrying out the preprocessing of an input medical image, including size standardization, intensity normalization and data enhancement; then, inputting the processed image into a deep fusion segmentation network, extracting high-frequency boundary features through wavelet transform and generating a boundary attention map, and capturing global context information in combination with a multi-scale dynamic sparse attention mechanism; and finally, fusing the multi-scale features through a boundary enhancement up-sampling module in a decoder stage, and optimizing a segmentation result by adopting multi-scale supervision and a mixed loss function. According to the method, the boundary precision and the detail retention capability of medical image segmentation are effectively improved, and the segmentation performance under a fuzzy boundary, a multi-scale structure and a complex background is remarkably improved.

The invention provides a method for predicting the residual life of a power transformer based on digital-analog fusion, and belongs to the technical field of transformer detection.The method comprises the steps that multi-dimensional sensor data of the power transformer is collected, wavelet transform preprocessing is conducted, a normalized data matrix is established, a physical equation is established, and a deterministic physical model is formed; a data-driven model is established based on an improved adaptive multi-scale network to realize multi-scale feature adaptive extraction, a topological phase change algorithm is introduced to identify key transition points in an aging process, and a deterministic physical model and the data-driven model are fused to establish a digital-analog fusion prediction framework. A generative adversarial network is adopted to perform data enhancement to solve the problem of scarcity of fault samples, a Bayesian neural network and a Monte Carlo random inactivation technology are utilized to construct an uncertainty quantization framework to output a residual life prediction value and a confidence interval thereof, and the technical problem that the prediction precision of the residual life of the transformer is not high is solved.

The invention discloses a lung cancer gene mutation classification method based on frequency domain multi-scale fusion guidance, and relates to the technical field of medical image processing and gene detection. According to the MFHA mechanism provided by the invention, the pathological image is decoupled into low-frequency global and high-frequency detail sub-bands through wavelet transform, and extraction of key high-frequency features such as cell nucleus morphology and local texture is enhanced by combining multi-scale convolution and up-sampling guided by high-frequency information; the problems of insufficient feature detail mining and low feature fusion efficiency in a traditional pathological image analysis method are solved; key features are screened and focused through a channel, frequency domain-space feature deep fusion is realized through up-sampling, robust representation is constructed by combining space attention with cosine similarity and multi-dimensional statistical features, a frequency domain analysis-space focusing collaborative optimization mechanism is formed, information redundancy caused by simple feature splicing is avoided, and the robustness of the system is improved. And the classification stability of the model in a complex pathological scene is improved.

The invention provides a power system transient recording signal abnormal mode intelligent detection method and system, and relates to the technical field of power detection, and the method comprises the steps: obtaining multi-monitoring node recording signals, constructing a space-time coupling sequence set, and extracting a multi-dimensional feature matrix through dynamic scale wavelet transform; and mapping the feature matrix into a space-time topological structure, integrating the space-time topological structure into a graph convolution operator to construct an enhanced representation space, forming a discrimination criterion in the representation space to identify an abnormal mode and a diffusion link, and finally tracing and positioning an abnormal source and generating a fault diagnosis conclusion. According to the invention, the abnormal mode of the transient recording signal can be accurately detected and accurate fault positioning can be realized.

The invention relates to the technical field of tunnel crack detection and artificial intelligence edge calculation, and provides a tunnel apparent disease detection method based on deep learning and knowledge distillation, which comprises the following steps: step 1, introducing spectral domain information enhancement to an original tunnel image, the edge texture features of the disease area in the image are enhanced through methods such as multi-scale wavelet transform and small-scale enhancement. Step 2, constructing a high-performance teacher model, introducing a flexible up-sampling structure to adapt to feature recovery requirements of different levels of semantic information, introducing an efficient visual coding module to enhance feature fusion capability of different scale channels, and designing a scale adaptive weighted loss function at the same time; by introducing a frequency spectrum enhancement mechanism, structural features of disease areas with low contrast, fuzzy edges and the like are remarkably enhanced in an image preprocessing stage, clearer information input is provided for a model, and the stable recognition capability of a system in environments of uneven illumination, complex background and the like is enhanced.

The invention discloses a depth-guided three-dimensional Gaussian reconstruction method and system suitable for a sparse view angle image, and belongs to the technical field of computer vision and three-dimensional reconstruction, and the method comprises the steps: carrying out the wavelet transformation super-resolution processing of a sparse multi-view angle image; outputting depth prior through a pre-trained monocular depth model, and extracting multi-view image features; constructing cross-view depth candidates by adopting a planar scanning stereo method, and generating initial depth distribution through feature similarity calculation; a self-attention-cross attention structure and deformable sampling are adopted to realize coarse-to-fine depth matching optimization; using an improved UNet network to fuse multi-scale features, and optimizing a depth estimation result; predicting three-dimensional Gaussian primitive parameters; and constructing a Gaussian field to generate a new visual angle image. According to the method, the problems of low accuracy, integrity and efficiency of existing sparse view angle three-dimensional reconstruction are solved. According to the invention, the precision and the detail fidelity of the depth map are improved, and high-fidelity three-dimensional reconstruction under the sparse visual angle condition is realized.

The invention discloses a bearing variable working condition fault diagnosis method fusing model migration and feature migration learning, and the method comprises the steps: processing bearing vibration signals of a source domain and a target domain through wavelet transform, and extracting a time-frequency diagram; expanding the two-dimensional time-frequency graph data set by using DCGAN, and balancing the number of the two-dimensional time-frequency graph data set; then, model parameter migration is adopted, AlexNet network parameters pre-trained in a source domain are migrated, a migrated AlexNet network is constructed, and depth features are extracted; then, a domain adaptation method based on improved migration joint matching is provided, multiple strategies are fused, and a low-dimensional feature space with small distribution difference and good discrimination performance is obtained; and finally, on the basis of a labeled source domain feature data training model after domain adaptation, realizing identification and classification of unlabeled target domain feature data. The method is ideal in diagnosis performance and high in accuracy under variable working conditions and data imbalance, domain data distribution difference can be reduced by improving the migration joint matching method, and feature discrimination performance and fault diagnosis accuracy are improved.

The present invention relates to the technical field of medical images. Disclosed are a deep learning-based CT artifact removal method and system. The method comprises: acquiring a CT image, and separately performing sine transform and wavelet transform processing on the CT image; constructing an image enhancement model, and performing image optimization on the processed image separately by means of the image enhancement model and a random inversion layer which are connected in sequence; coupling the optimized image and the original image and then inputting the coupled image into the image enhancement model for reprocessing; and performing element-wise addition on the reprocessed image and the optimized image to obtain an artifact-removed CT image. In the present invention, wavelet transform is introduced to process the CT image to extract the context and spatial information of the CT image, effectively extracting feature information in an artifact removal process and improving the performance of image enhancement; and a CT image resolution enhancement model based on a VMamba model is established, enhancing the long-term dependencies in network training, effectively recognizing and removing radioactive artifacts, and improving the network training efficiency.

The invention discloses a low-light image enhancement method combining a state space model and wavelet transform, and aims to solve the problems of detail loss, inaccurate illumination estimation and high calculation complexity of the existing low-light enhancement algorithm. According to the method, illumination estimation, frequency domain enhancement, wavelet transform, a high-frequency attention mechanism, dynamic state space modeling (Mamba) and a multi-scale U-Net structure are introduced, so that high-quality and detail-retaining enhancement of a low-illumination image is realized. According to the method, firstly, based on the Retinex theory, an illumination prior image is generated by calculating the global mean value of RGB channels of a low-illumination image, illumination features are extracted in combination with an illumination estimation module, and a preliminary enhanced image is generated; then, a multi-scale dynamic coding and decoding network is adopted, a coding layer compresses spatial dimensions step by step and increases feature channels, a decoding layer recovers resolution step by step to preliminarily enhance image fusion, and an enhancement result is well obtained.

The invention relates to the technical field of electrical equipment detection, and discloses a terahertz time-domain spectroscopy-based GIS insulating material nondestructive testing method, which comprises the following steps: acquiring GIS insulating material time-domain signals by using a reflection-type terahertz time-domain spectroscopy (THz-TDS), and separating and reconstructing defect echoes based on electromagnetic simulation modeling in combination with wavelet transform, STFT and a transmission matrix method; multi-dimensional features are extracted, SVM and RBFNN are trained after dimensionality reduction, and a classification and quantitative regression model fusing physical constraints is constructed; and inputting a signal of a sample to be detected into the model to realize rapid, non-contact and accurate detection on the type, size and depth of the defect. The method overcomes the defects that traditional detection is low in efficiency, has damage or is difficult to quantify, the signal-to-noise ratio, the sensitivity and the automation level are remarkably improved, the method can be widely applied to GIS production quality control, installation acceptance, operation and maintenance monitoring, health assessment and life prediction, and powerful support is provided for safe and reliable operation of an electric power system.

The invention discloses a motor current fault diagnosis method based on a de-noising diffusion probability model, and belongs to the technical field of mechanical equipment state monitoring and fault diagnosis, and the method comprises the steps: obtaining an original motor current signal sample, carrying out the wavelet transformation, obtaining a time-frequency grayscale image, and obtaining a time-frequency grayscale image; dividing the sample into a training sample used for diffusion model training and a test sample of a fault diagnosis model; constructing a diffusion model DDPM, carrying out training by adopting the training sample, and generating a pseudo sample based on the trained diffusion model; constructing a fault diagnosis model MAF-Cnet, and training the MAF-Cnet based on the training sample and the pseudo sample to obtain the trained MAF-Cnet; and inputting a test sample into the trained MAF-Cnet for diagnosis to obtain a motor current fault diagnosis result. The method solves the core problem that the generalization ability of the diagnosis model is insufficient due to scarcity of motor fault samples, improves the diagnosis accuracy, and is wider in application scene.

The invention discloses a defect detection system and method for a glass bottle, and belongs to the field of industrial visual defect detection and analysis. The system comprises a GBDM module, the GBDM module is a defect detection module, and the GBDM module comprises a front attention enhancement structure, a rear attention enhancement structure and a defect detection structure, a multi-branch feature extraction structure is used for generating four feature branch diagrams; and the feature fusion structure is used for fusing the four feature branch diagrams. The GBDM module is embedded in the backbone network of the YOLOv8 network model, and multi-branch structures such as wavelet transform, Gabor direction filtering and specular reflection suppression are utilized, so that the feature extraction capability of multiple types of complex defects such as cracks, smudginess and damage on the surface of the glass bottle is enhanced, the generalization capability of the model in a small sample scene is remarkably improved, and the accuracy of the model is improved. The real-time requirement of an industrial scene is met, continuous self-optimization is achieved, and the method has high robustness, high accuracy and high application value.

The invention discloses a boiler operation state intelligent monitoring method and system, and the method comprises the steps: collecting multi-source heterogeneous data in a boiler operation process, carrying out the cleaning and normalization processing of the multi-source heterogeneous data, extracting key features through wavelet transform, and obtaining standard multi-source heterogeneous data; modeling time series data in the standard multi-source heterogeneous data on the basis of an LSTM (Long Short-Term Memory) network, capturing a dynamic change trend of boiler operation to obtain time series characteristics, analyzing a hearth flame image and an infrared thermal image by using a CNN (Convolutional Neural Network), and extracting combustion state characteristics and thermal distribution characteristics; and based on the comprehensive state vector, a confidence interval of each feature dimension is calculated through a GMM Gaussian mixture model, an operation state deviation degree is analyzed and evaluated in combination with an entropy value, and when the deviation degree exceeds a preset threshold value, graded early warning is triggered. And the accuracy of boiler operation state intelligent monitoring is improved.

The invention relates to the technical field of industrial vision, in particular to an automobile part surface defect detection method and system based on machine vision, and the method comprises the steps: firstly loading a CAD three-dimensional model, and rendering an ideal fringe reflection map in a virtual environment; calculating an optical distortion correction matrix by comparing the phase distortion with the phase distortion of an actual initial reflection image, driving a programmable light source to project a compensation pattern, and generating a normalized reflection intensity image; signal object decoupling is achieved through multi-scale wavelet transform, and high-frequency components and low-frequency components are separated; homomorphic filtering is applied to the low-frequency component to construct a homogenized background model, the high-frequency component is reversely corrected, and a high-signal-to-noise-ratio defect signal image is output; generating a coarse segmentation mask by the high-frequency signal through an adaptive local threshold, generating a morphology anomaly mask by the low-frequency signal through Hessian matrix morphological analysis, and fusing to form a collaborative segmentation mask; and extracting multi-dimensional geometric attributes of connected domains in the masks, and inputting the multi-dimensional geometric attributes into a decision tree to realize accurate classification and confidence output of defects.

The invention relates to the technical field of power distribution lines, in particular to a power distribution line abnormal line loss analysis and treatment method and system, and the method comprises the following steps: synchronously extracting real-time monitoring data and historical data based on a power distribution line network, carrying out the data alignment and data cleaning, screening features associated with current leakage and voltage drop, and carrying out the analysis and treatment of the abnormal line loss of the power distribution line. Comprising load change rate and temperature fluctuation. According to the invention, through application of real-time and historical data analysis, the detection and management efficiency of the abnormal line loss of the distribution line is improved, the accuracy of data processing is improved through synchronous extraction and data alignment, early recognition of abnormal modes is allowed, the possibility of energy loss and unplanned power failure is reduced, and through adoption of Fourier transform and wavelet transform, the detection efficiency of the abnormal line loss of the distribution line is improved. According to the method, abnormal signals are accurately recognized, the analysis capability of the signals is enhanced, the accuracy of abnormal detection is improved, fault positioning and maintenance plan making are effectively optimized through combination of the GIS system, and the pertinence and efficiency of maintenance work are remarkably improved.

The invention relates to the technical field of automatic driving, in particular to a multi-modal three-dimensional target detection method, which comprises the following steps of: in a first stage, firstly acquiring neighbor depth information of point cloud to enhance image features, and then further enhancing image edges and reducing semantic confusion by utilizing wavelet transform; and then a cross attention mechanism is introduced to realize effective fusion of the enhanced image features and the point cloud, an initial region suggestion is obtained, and bounding box classification and prediction in the first stage are realized. And in the second stage, designing a double-attention module based on grid features to supplement more geometric detail information, acquiring more context information and position information by utilizing the initially suggested spatial features and channel features generated in the first stage, and then introducing a self-attention mechanism to dynamically distribute interaction weights of the grid features, so as to realize the self-attention interaction of the grid features. Rich context information is effectively captured, a local geometric structure is better coded, information loss is reduced, and the detection precision of the model is improved.

The invention relates to the technical field of water supply network monitoring, and discloses a water supply network leakage monitoring and positioning system and method based on big data analysis, and the method comprises the steps: obtaining continuous audio stream data and network topological graph data collected by a distributed sensor, and calculating background baseline parameters; performing multi-scale wavelet transform decomposition on the current audio frame, calculating an energy entropy feature and generating a single-frame abnormal score; applying a cumulative sum control chart algorithm to output a cumulative abnormal index; generating an enhanced anomaly score through a graph attention network; and performing leakage judgment and positioning based on the abnormal scores of the multiple sensors. The technical problem that weak leakage signal detection sensitivity is low is solved.

The invention provides a gait anomaly recognition and early warning method and system based on adaptive reinforcement learning, and the method comprises the steps: collecting the multi-modal gait data, such as three-dimensional acceleration, angular velocity and plantar pressure distribution, carrying out the preprocessing, such as filtering, normalization and periodic alignment, extracting the characteristics of different gait sub-phases in stages, and carrying out the recognition and early warning of the gait anomaly. A sliding window and wavelet transform are used to obtain multi-scale time features, and short-time local motion and long-time trend information are fused; on the basis of a multi-scale time sequence attention network, global and key local changes in a gait sequence are captured through a coarse and fine granularity attention mechanism, and high-dimensional feature representation is generated; finally, through dimension reduction and multi-model classification, in combination with confidence scoring, abnormal gait judgment and marking, dynamic online learning and model stability rollback are supported, the method also has multi-level early warning output and remote monitoring capabilities, and the real-time performance, adaptability and reliability of gait anomaly detection are effectively enhanced.

The invention discloses an interference suppression measurement method for a grounding resistor, and relates to the technical field of interference resistance, and the method comprises the steps: injecting a detection current into a grounding electrode, and synchronously collecting an original voltage signal at two ends of the grounding electrode and a time domain waveform of the detection current; performing time domain segmentation on the original voltage signal, performing linear frequency modulation wavelet transform on the signal in each time period, generating an initial time-frequency matrix, extracting a time-frequency ridge line from the initial time-frequency matrix, identifying interference information, obtaining an interference-removed time-frequency matrix, optimizing the interference-removed time-frequency matrix through robust kernel principal component analysis, and obtaining an interference-removed time-frequency matrix; a synchronous redistribution operator is used for carrying out signal purification, a pure time-frequency matrix is obtained, linear frequency modulation Z transformation is carried out on the pure time-frequency matrix, voltage amplitude and frequency are extracted, an energy centroid method is used for correcting the voltage amplitude and frequency, interference can be effectively restrained, and the grounding resistance measurement precision is remarkably improved.

The invention provides a comprehensive noise reduction performance evaluation method for a nonlinear ultrasonic detection signal noise reduction algorithm, and the method comprises the steps: firstly constructing a multi-working-condition noise reduction performance pre-screening mechanism based on error band analysis based on early-stage experimental data, and then introducing a radar map as an evaluation tool for the comprehensive noise reduction effect of the signal noise reduction algorithm. The noise reduction effects of a moving average method (MA), a spectral subtraction method (SS), a short-time Fourier transform method (STFT), a wavelet transform method (WT) and an orthogonal matching pursuit algorithm (OMP) are compared, and finally a signal noise reduction algorithm with the optimal comprehensive efficiency is screened out. On the basis of algorithm optimization, quantitative mapping rules between microcrack three-dimensional geometric parameters and relative nonlinear coefficients are analyzed through regression modeling, and the significant level of the correlation degree of the relative nonlinear coefficients and microcrack size parameters is effectively improved; and a high-confidence theoretical support is provided for quantitative nondestructive detection of the microcracks in engineering practice.

The invention discloses a power grid intelligent planning simulation platform based on AI and digital twinning, which relates to the technical field of power grid planning and comprises a multi-source data fusion module, a topological representation module, an event-driven twinning module, a power grid state prediction module, an intelligent planning generation module and a simulation verification module. The multi-source data fusion module performs fusion processing on the power grid multi-source data by adopting wavelet transform; the topological representation module adopts a graph convolutional neural network to learn power grid topological characteristics; the event-driven twin module adopts an event-driven mechanism to realize synchronization; the power grid state prediction module generates a power grid state prediction sequence by adopting a space-time diagram convolutional neural network; the intelligent planning generation module adopts a deep reinforcement learning algorithm to generate a power grid planning scheme; and the simulation verification module performs multi-scene verification and optimization on the planning scheme by adopting a Monte Carlo method. According to the method, the problems of difficulty in multi-source data fusion and insufficient state prediction precision in power grid planning are solved, and the intelligent level of a planning scheme is improved.

The invention discloses a DC GIS partial discharge signal multi-dimensional joint fault diagnosis method and system, and belongs to the technical field of power equipment fault detection. The method comprises the following steps: acquiring a typical defect partial discharge UHF signal of the high-voltage direct-current GIS; extracting time domain and frequency domain characteristics of the signal; extracting time-frequency domain features by using empirical wavelet transform and multi-scale permutation entropy; performing normalization processing on the signal to obtain a time domain sequence and a frequency domain sequence; and constructing a double-input neural network, taking the time domain, frequency domain and time-frequency domain features as first input, taking the time domain sequence and the frequency domain sequence as second input, and performing feature fusion and classification to realize fault diagnosis. According to the method, deep information of the partial discharge signals is fully mined and fused through multi-domain feature combination and a double-input deep learning model, the problems that a direct-current GIS partial discharge fault mode is difficult to recognize and low in precision are solved, and accurate, reliable and rapid diagnosis of typical insulation defects is achieved.

The present disclosure relates to digital watermarking systems that may use visual masks to optimize watermark embedding in digital imagery. A visual mask provides guidance for adjusting digital watermark signal strength, enabling improved trade-offs between watermark imperceptibility and robustness. Multiple embodiments generate visual masks including: (1) a Perceptual Modeling Candidate approach using contrast masking and texture classification based on standard deviation mapping; (2) a wavelet-based approach using Dual-Tree Complex Wavelet Transform for translation-invariant frequency analysis; (3) artificial intelligence approaches employing convolutional neural networks trained to optimize embedding strength while minimizing perceptual distance metrics such as LPIPS; and (4) LPIPS threshold masking that determines optimal embedding strengths by testing multiple candidate strengths. Visual masks enable content-adaptive digital watermarking that places stronger signals in textured regions while maintaining imperceptibility in flat regions, improving visibility-robustness performance compared to uniform embedding approaches.

The invention discloses a low-illumination image enhancement method and system based on multi-domain fusion and lightweight design. Firstly, a multi-domain feature fusion module fusing wavelet transform and Fourier transform is provided, and the global structure and detail information of a low-illumination image can be jointly extracted and enhanced; secondly, correlation modeling among multi-scale features is enhanced through a cross-scale attention module, and self-adaptive and multi-scale feature fusion is achieved; furthermore, a gating attention alignment module is provided, the accuracy of feature alignment of the encoder and the decoder is improved, and effective transmission of detailed information is ensured. According to the method, on data sets such as LOLv1, LOLv2-real, LOLv2-syn and the like, the performance expressions of 25.03 dB PSNR and 0.863 SSIM are achieved with the calculation expenditure not exceeding 1.2 M parameters and 1.41 G FLOPS, and the enhancement effect and capability of the model on a low-illumination image are remarkably improved.

The invention provides a plastic toy surface defect detection method based on machine vision, and the method comprises the steps: firstly collecting and standardizing a plastic toy surface multi-parameter original image, and carrying out white balance correction and histogram equalization to improve the image quality; secondly, decomposing image frequency domain features by applying multi-scale wavelet transform, and enhancing defect area spatial positioning and texture sensing capabilities by combining cross guidance of frequency domain and spatial domain attention mechanisms; and inputting the fused features into a lightweight convolutional neural network to extract a high-discrimination feature vector, executing defect classification and position regression, and introducing an adaptive mechanism to dynamically optimize a decomposition scale and an attention strategy according to recognition confidence and detection history. The method is suitable for automatic surface quality detection under a complex background.

The invention provides a PCB multi-type defect detection method and device based on frequency domain perception enhancement, a storage medium and a program product, and relates to the technical field of computer vision target detection.The method comprises the steps that a to-be-detected PCB image is input into a backbone network for shallow feature extraction, and shallow feature maps of different processing stages are obtained; respectively inputting the shallow feature maps into a multi-domain collaborative feature enhancement network, performing decomposition enhancement on the shallow feature map in each stage through wavelet transform to obtain an enhanced low-frequency component and an enhanced high-frequency component, and performing first reconstruction on the enhanced low-frequency component and the enhanced high-frequency component through first inverse wavelet transform to obtain an enhanced low-frequency component and an enhanced high-frequency component; obtaining a frequency domain enhanced feature map of each stage; inputting the frequency domain enhanced feature map into a neck network, and enabling the neck network to perform multi-scale feature fusion on the frequency domain enhanced feature map to obtain a fused feature map; and inputting the fusion feature map into a prediction output end for target prediction to obtain a PCB defect detection result.

The invention discloses a dam micro-variation response identification method and system based on multi-scale information reconstruction, the method fuses multi-source heterogeneous data such as images, strain, displacement, acoustic emission and the like, adopts a time axis alignment and spatial registration strategy to construct standardized input, enhances disturbance feature expression based on wavelet transform and a significance attention mechanism, and improves the accuracy of dam micro-variation response identification. The method comprises the following steps: constructing a small-scale disturbance modeling module by introducing expansion convolution and a spatial saliency map, carrying out micro-variation trend identification and risk assessment in combination with a Transform model, carrying out lightweight compression on the model and then deploying the model at an edge terminal, realizing local rapid identification and network disconnection alarm, supporting model hot update and structure health trend analysis in cooperation with a cloud platform, and improving the reliability of the model. The method has the advantages of being high in recognition sensitivity, high in anti-interference performance, wide in deployment adaptability and the like, and is suitable for early-stage anomaly detection and intelligent safety supervision of multiple types of dam structures.

The invention relates to the technical field of power grid safety evaluation, in particular to a power system short-circuit parameter prediction method, system and device based on time-space relevance and a storage medium. A multi-dimensional state vector including a node voltage vector, a branch current vector, a short-circuit impedance matrix, spatial position information and a time feature vector is constructed, and a space-time correlation feature vector including a time-dimensional feature, a spatial-dimensional feature, a space-time coupling feature and a state feature is extracted. Wavelet transform, Fourier analysis and graph theory analysis are adopted to identify a parameter change rule and a propagation effect. A multi-level prediction model of a statistical prediction layer, a deep learning layer and a fusion layer is constructed, and comprehensive description of dynamic characteristics of short-circuit parameters is realized through spatio-temporal feature fusion. A staged training strategy is adopted, and comprises the steps of establishing a basic model through offline training, updating parameters in real time through online learning, and quantifying uncertainty through a probability prediction framework. And a prediction correction mechanism and a reliability evaluation system are established, and a complete prediction-evaluation-correction closed loop is formed.

The invention discloses a seismic wave velocity model inversion method based on time-space coupling deep learning, and the method achieves a time-space coupling mechanism through a Fourier neural operator framework of a wavelet transform-attention mechanism, and supports the reconstruction of a spatial two-dimensional velocity model from a time sequence track of multiple seismic sources. Firstly, the local time-frequency representation of each seismic time-domain trajectory is extracted by adopting continuous wavelet transform, and then a wavelet time-frequency spectrogram is coded through a convolution feature extractor. Then, information from multiple sources is fused at each receiver point location through a multi-head attention mechanism, enhancing correlation between multiple sources. And finally, projecting the fused features into a two-dimensional Fourier neural operator to efficiently learn space mapping and reconstruct a bottom-layer velocity model based on sound velocity. According to the method, the time sequence characteristic and the spatial distribution characteristic of the seismic channel are fully utilized, the precision and robustness of an inversion result are improved, and a more reliable speed model is provided for geological structure interpretation and acoustic imaging.