32 results about "Higher order tensor" patented technology

The invention discloses a pumped storage power station building foundation dangerous point management and control system based on BIM, and the system comprises a data layer which enables linear engineering monitoring data to be organized into a high-order tensor of pile number * time * sensor type * spatial position through four-dimensional tensor modeling, and carries out the Tucker decomposition, strain rate abrupt change points are dynamically recognized in the compression process by combining sliding window anomaly detection, original data are directly stored, and then a hierarchical storage strategy is implemented on non-abrupt change data through a data value evaluation model driven by deep reinforcement learning; the model layer is used for fusing a physical information neural network, embedding a rock-soil mechanics constitutive equation into an LSTM network to construct a mixed loss function, pre-training a general geologic model through transfer learning, and then carrying out few-sample fine tuning in combination with project data; and the application layer is used for dynamically generating a hazard source list through a BIM model and triggering instant early warning based on the compressed and reconstructed data of the data layer and the output of the model layer, and simulating a disaster situation development path in combination with a digital twinborn technology.

A tensor contraction attention modeling method and a hyperspectral image reconstruction method and device thereof can directly act on a unified attention modeling framework of an original high-order tensor, and by introducing a similarity calculation mode based on n-mode projection and tensor contraction, accurate modeling of cross-modal dependence can be realized on the premise that an attention mechanism does not need to be flattened. Therefore, the inherent structural characteristics and interpretability of the multi-dimensional signal are maintained. The tensor contraction attention modeling method comprises the following steps: inputting any multi-dimensional signal; respectively applying multi-mode linear mapping on a preset projection mode set, constructing query tensor key tensor and value tensor, performing tensor contraction and Softmax operation on the tensor set to obtain attention weight, performing tensor contraction on the attention weight and the tensor, and obtaining attention output

The invention provides a cloud platform operation and maintenance method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining multi-dimensional data of a cloud platform, integrating the multi-dimensional data of the cloud platform into a high-order tensor based on a Tuck decomposition method, carrying out the non-uniform sampling of the high-order tensor, and constructing a high-order tensor structure of the cloud platform; generating a space-time multi-scale topological graph of the cloud platform based on the high-order tensor structure of the cloud platform; constructing a dynamic prediction model of the cloud platform based on the space-time multi-scale topological graph of the cloud platform; preprocessing the multi-dimensional data of the cloud platform, and sending a preprocessing result to the dynamic prediction model for prediction to obtain a state prediction result of the cloud platform in a preset time period; and obtaining a preset operation and maintenance scheme for operation and maintenance based on the state prediction result of the cloud platform in the preset time period. According to the method, the characteristics of long-range dependency and sudden fluctuation are combined, and resource scheduling and anomaly detection are automatically carried out.

The invention provides an intention-driven semantic evolution mechanism based on a tensor semantic field and an application system thereof, and relates to the technical field of artificial intelligence, semantic networks and cognitive computing. According to the method, five types of semantic primitives including data, information, knowledge, intelligence and intention are expressed as high-order tensor nodes, a semantic tensor field network is constructed, and dynamic evolution and intention driving of semantics are achieved. The system comprises a multi-scale semantic aggregation mechanism, an intention weight diffusion algorithm, a semantic tensor evolution operator and a white box interpretation interface, supports full-link semantic processing from original data to high-level wisdom to intention constraint, and overcomes the defects in semantic representation and evolution, intention fusion and system interpretability in the prior art. And the generative AI system has stronger intention perception, semantic self-optimization and process transparency capabilities, and is suitable for applications such as a semantic perception large model platform, an AI cognitive map system and an interpretable language generator.

The application discloses a blind separation anti-main lobe intermittent sampling cyclic repetition jamming method based on tensor decomposition, which is applied to the technical field of radar anti-jamming and aims at the problem that the existing blind separation algorithm is not applicable to all DRFM jamming. Firstly, the second-order time delay correlation matrix of multiple received signals is calculated and is reconstructed into a high-order tensor form; secondly, an optimization problem about an array manifold matrix is established based on a tensor decomposition principle and an ELS-ALS algorithm is adopted to solve the optimization problem; finally, the left inverse of the estimated array manifold matrix is calculated, the received signal is multiplied by the left inverse, the separated target echo and jamming signal are obtained, the separated target echo is processed, target range Doppler information is acquired, and the suppression of the main lobe intermittent sampling cyclic repetition jamming is realized.

The invention provides a discrete ballastless track tension-compression fatigue damage rapid calculation method, which comprises the following steps of: uniformly measuring a complex stress state and a simple stress state through a damage energy release rate, and decomposing tension-compression effective stress by utilizing a fourth-order projection tensor, so that the tension-compression effective stress value is equivalent to a uniaxial tension-compression stress value under a uniaxial loading condition; constructing a hyperbolic function with a natural constant as a base and a damage variable as an index on the basis of the damage energy release rate and in combination with three-stage damage characteristics of high-cycle fatigue of the material; carrying out integration on fatigue loading times through tension and compression damage, and deducing to obtain a discrete transcendental differential function of the damage related to the loading times; function variables are defined, an initial value is set, an iteration format is established, the discrete transcendental differential function is solved through a numerical integration method, and a calculation result graph is drawn. The model is simplified, and the calculation efficiency is improved; a high-order tensor stress updating algorithm does not need to be constructed, redundant calculation is reduced, and the data processing efficiency and the calculation speed during parameter analysis are greatly improved.

The invention relates to the technical field of kinetic analysis of mechanical structures, in particular to a structural modal parameter identification method based on joint low-rank tensor decomposition, which comprises the following steps: performing tensor modeling on expression X = phi Q of structural response under modal coordinates, performing segmentation operation on collected vibration response, and expressing the vibration response in a high-order tensor form; then, low-rank representation is carried out on each column of modal shape vectors and low-rank representation is carried out on each row of modal responses by utilizing the low-rank performance of the modal response vectors and the modal shape vectors; further, the combined low-rank tensor of the high-order tensor is decomposed and solved, and a matrix representation phi reflecting a modal shape and a matrix representation Q of modal response are obtained; and finally, extracting modal frequency and damping ratio information from the obtained Q. According to the structural modal parameter identification method, the dynamic parameters such as the structural modal frequency and the modal shape are effectively identified by using the low-rank characteristics of the modal response vector and the modal shape vector.

The invention discloses an anti-slide pile cantilever section internal force and displacement calculation method, equipment and a medium, and relates to the technical field of engineering design, and the method comprises the following steps: solving a time-varying support reaction field parameter set and a cantilever section depth computational domain execution structural mechanics equation, and generating a predicted displacement curve and a predicted internal force curve; reconstructing the predicted displacement curve and the predicted internal force curve into a high-order tensor field, extracting local response correlation features through a depth separable convolution kernel, and generating a coupling response feature field; based on the coupling response characteristic field, reverse constraint correction is carried out on the time-varying support reaction field parameter set, combined solving is carried out in combination with a cantilever section depth calculation domain, and a correction displacement curve and a correction internal force curve are generated. According to the method, the space-time Gaussian process prior model is constructed, in computer-aided engineering, the internal force and displacement prediction precision is improved, and the reliability and applicability of cantilever section structure analysis under the complex stratum condition are achieved.

The invention discloses a wide-load pumped storage unit multi-scale turbulence modeling method based on high-order tensor coupling and a dynamic memory effect. The wide-load pumped storage unit multi-scale turbulence modeling method comprises the steps of working condition parameter collection and geometric model grid division, initialization of a multi-scale turbulence field, correction of high-order curvature-rotation tensor coupling, cavitation vortex strip instability prediction and cross-scale data assimilation. Through fusion of a high-order curvature-rotation tensor coupling mechanism, a multi-scale time memory effect and a physical-data hybrid correction technology, the prediction precision of pressure pulsation, cavitation vortex strip instability and runner dynamic stress of a unit under complex working conditions of water pumping, power generation, phase modulation, rapid load change and the like is remarkably improved; and technical support is provided for safe operation and optimal design of the unit.

The present invention relates to the field of fault diagnosis signal processing technology, and in particular to a second-class third-order tensor decomposition method, device, and bearing fault detection system thereof. The second-class third-order tensor decomposition method comprises: obtaining a vibration acceleration signal, constructing a multi-channel third-order tensor signal X based on the vibration acceleration signal; constructing a computational model for second-class multiplication and transposition of high-order tensors; performing second-class tensor singular value decomposition on the third-order tensor signal X to obtain tensors U, S, and V; and reconstructing the third-order tensor signal X based on the computational model for second-class multiplication and transposition of high-order tensors and tensors U, S, and V to obtain multiple component signals. The second-class third-order tensor decomposition method of the present invention achieves effective signal decomposition and feature extraction to ensure the completeness of rolling bearing status information, facilitates signal analysis and diagnosis, and provides basic support for electromechanical equipment monitoring and remaining life prediction.

The application specifically relates to a high-order tensor multi-modal fusion method and model based on double-mode spectrum interactive learning.A high-order tensor multi-modal fusion method based on double-mode spectrum interactive learning comprises the following steps: S10, inputting Raman spectrum and infrared spectrum data; S20, performing non-cascaded multi-mode spectrum fusion representation on the Raman spectrum and the infrared spectrum data through high-order tensor outer product; and S30, calculating orthogonality loss, reconstruction loss and adversarial loss, and compensating for heterogeneity difference by performing unique representation learning on the Raman spectrum feature and the infrared spectrum feature.The high-order tensor multi-modal fusion method and model based on double-mode spectrum interactive learning effectively realize multi-modal data information fusion by obtaining high-order interactive fusion features of double-mode spectrum information through BHTF, and realize more accurate cross-modal representation by learning the heterogeneity between multi-modal data through CMIL cross-modal learning, thereby improving the robustness of the model.

The present application belongs to the technical field of grain informatization processing, and particularly relates to a method and system for identifying imperfect grains based on spectral spatial coupling features. The method comprises inputting visible light images and hyperspectral data of the grains into a recognition model; a visible light image branch in the recognition model processes the visible light images of the grains to obtain the output of the branch; a hyperspectral data branch in the recognition model processes the hyperspectral data of the grains to obtain the output of the branch; the outputs of the visible light image branch and the hyperspectral data branch are used to obtain the recognition result; the recognition model is trained using grain sample images; the processing of the hyperspectral data branch comprises: expanding the hyperspectral data represented by a high-order tensor into a tensor factor multiplication mode containing spectral and spatial information features, and each mode is a tensor form in which all different spectral information features are superimposed; and the tensor form is subjected to feature extraction to obtain the branch output.

The application relates to a hyperspectral image anomaly detection method based on high-order tensor representation, introduces a promotion operation, performs high-order tensor expression on data, utilizes a tensor low Tensor-Train rank approximation framework, embeds suitable regularization constraints into hyperspectral prior knowledge while retaining the overall structure of the hyperspectral image, adopts a spatial spectral total variation norm regularization term expression for the spatial dimension segmentation continuous prior of the background tensor, adopts a logarithmic sum norm regularization term expression for the spectral dimension low rank prior of the background, and adopts an L 2,1 norm regularization term expression for the group sparse prior of the anomaly target tensor. Finally, in the tensor framework, the target equation is subjected to a convex optimization through an alternating direction multiplier method, the anomaly target is effectively extracted, the principle is clear, the experimental verification effect is superior, and the robustness is strong. The application provides theory, a model and support for tensor expression model processing and analysis of hyperspectral remote sensing images.

The present invention provides a cloud platform operation and maintenance method and system, which relates to the field of data processing technology. The method comprises obtaining multi-dimensional data of a cloud platform, integrating the multi-dimensional data of the cloud platform into a high-order tensor based on the Tucker decomposition method, and performing non-uniform sampling on the high-order tensor to construct a high-order tensor structure of the cloud platform; generating a spatiotemporal multi-scale topological map of the cloud platform based on the high-order tensor structure of the cloud platform; constructing a dynamic prediction model of the cloud platform based on the spatiotemporal multi-scale topological map of the cloud platform; preprocessing the multi-dimensional data of the cloud platform, and sending the preprocessing results to the dynamic prediction model for prediction to obtain a state prediction result of the cloud platform in a preset time period; and obtaining a preset operation and maintenance plan based on the state prediction result of the cloud platform in the preset time period for operation and maintenance. The present invention combines the characteristics of long-range dependence and sudden fluctuations to automatically perform resource scheduling and anomaly detection.

This invention relates to the field of big data analysis and public safety monitoring technology, and discloses a method for identifying abnormal behavior in student communities based on big data. The method includes constructing a dynamic spatiotemporal hypergraph sequence from multi-source data slices, mapping it to a higher-order tensor and performing non-negative Tucker decomposition, determining semantic impedance values ​​based on core tensor matching degrees, calculating instantaneous energy dissipation values ​​by combining behavior intensity and semantic impedance, and generating a relative dissipation index; calculating global structural entropy based on node degree distribution, and generating a structural sensitivity index through counterfactual inference by virtually removing nodes to be detected; and weighted fusion of the above indicators to determine explicit violations or implicit structural anomalies. This invention, by introducing semantic impedance and structural entropy counterfactual inference, effectively distinguishes between high-intensity normal activities and violations, and can identify implicit topological risks, achieving refined hierarchical identification of abnormal behavior.

The invention relates to the technical field of power grid risk assessment, and discloses a power grid risk assessment method based on integrated load flow calculation and topology analysis, and the method comprises the steps: collecting and preprocessing power grid operation data, and organizing the preprocessed data into a four-dimensional high-order tensor structure; constructing a power grid topological relation tensor network; constructing an optimization problem through an L1 norm form, and solving the optimization problem by using an augmented Lagrangian multiplier method; the complex coupling relation among time, space and parameters is revealed by analyzing the relation among different dimension factor matrixes; performing risk assessment on different granularity levels under a multi-scale tensor analysis framework, and coordinating analysis results of each level to form comprehensive assessment; designing a tensor completion estimation algorithm, constructing an optimization model by using low-rank hypothesis, and solving a complete data set through a tensor low-rank decomposition method; according to the method, the high-order tensor representation and tensor network decomposition technology is adopted, so that the dimension and complexity of data are effectively reduced, and the calculation complexity is reduced.

The application discloses a hyperspectral image compression reconstruction method based on Hankel rank increasing tensor decomposition, and belongs to the technical fields of image processing and spectral remote sensing, and comprises the following steps: step 1, a basic hyperspectral image compression reconstruction model based on a regular term constraint is constructed to obtain a compression measurement value of the hyperspectral image; step 2, a high-order tensor based on a Hankel transformation is constructed; step 3, a regular term based on Hankel rank increasing tensor decomposition is constructed for the high-order tensor obtained in step 2; step 4, the regular term of the Hankel rank increasing tensor decomposition constructed in step 3 is substituted into a sparse regular term of the basic compression reconstruction model in step 1 to form a final hyperspectral image compression reconstruction model; and step 5, an alternating optimization method is used to solve the hyperspectral image compression reconstruction model constructed in step 4. The application can effectively solve the problems of large data volume of the hyperspectral image, storage and transmission difficulties and the problem that the existing compression reconstruction method ignores multi-dimensional structure information.

The invention discloses a video generation method and device, computer equipment and a storage medium, belongs to the technical field of artificial intelligence, and is applied to the financial field or the health medical field. In the tensor algebraic level, high-order tensor decomposition is carried out on an input image by using a transformation tensor product, and the input image is projected to an orthogonal potential subspace. Then, in a feature processing process, weighting the space factor matrix by adopting a local attention window, and combining with a preset mask matrix constraint; a recursive converter with orthogonal constraints is introduced to process a time sequence factor matrix, and it is ensured that the hidden state sequence is stably expressed in long-time dependence modeling. And finally, in a video reconstruction stage, performing up-sampling and reconstruction on the fusion tensor by adopting a tensor completion algorithm based on nuclear norm constraint and a low-rank synthesis strategy. According to the method, the unification of spatial decoupling, time sequence stability and global low-rank performance is realized, so that the generated video reaches a better level in the aspects of spatial resolution, time sequence dynamics and overall visual quality.

This invention relates to the field of cloud-edge collaborative computing technology, specifically to a method and system for processing integrated air-space-ground metal mineral exploration data. The method includes the following steps: extracting node resistance anisotropy features to generate corrected topological weights and constructing a Laplace tensor matrix to output a reduced-rank profile matrix; establishing a high-order tensor for cross-domain routing record flow by combining the profile spatial gradient and the network node signal-to-noise ratio; constructing an anisotropic correction matrix based on local covariance matrix analysis to extract three-dimensional normal vectors; solving the implicit scalar field and extracting isosurfaces to finally complete three-dimensional reconstruction. In this invention, by analyzing the reduced-rank structural features of the multi-dimensional exploration network and integrating node dynamic attributes to determine link steady-state scores to guide the priority cross-domain flow of compressed tensors, and by relying on the proportion of spatial local distortion to correct the grid gradient and reshape the implicit surface constraint field, this effectively avoids long-distance congestion transmission of massive heterogeneous data and improves the accuracy of three-dimensional morphological reproduction of complex underground ore bodies.

The application provides an informationization project book entity and relationship joint extraction method and system, each word in the informationization project book is context-aware coded to obtain a word vector containing context information, a high-order tensor representation of the word vector is projected by using a task field vector to obtain entity task feature representation and relationship task feature representation respectively, and uniqueness between different tasks is ensured; the entity and relationship extraction tasks are modeled as task nodes in a graph to realize efficient interaction between tasks, an adaptive boundary guide factor and a multiplication attention mechanism are used to capture head and tail positions of the entity and the relationship, accurate calculation of relationship types between word pairs is improved, and finally the relationship types between the word pairs are decoded to accurately extract entity and relationship information in the informationization project book.

The invention discloses a method for detecting implicit defects on a glass surface. The method comprises the steps of image acquisition, tensor decomposition, spectral residual optimization, adaptive segmentation and result output. The invention belongs to the technical field of data processing, and particularly relates to a glass surface implicit defect detection method, which adopts tensor decomposition, focuses implicit defect information through a high-order tensor component, separates a background and a residual error in a logarithmic spectrum by using Gaussian filtering through spectrum residual error optimization, and generates a residual image with significantly enhanced defects through inverse transformation. Interference of background textures is inhibited fundamentally; the mean value and the standard deviation of a residual image are calculated, a dynamic threshold value is generated, binarization processing is conducted on the residual image according to the threshold value, the problem that glass batches are different on a production line is solved, a high-speed interface and a real-time network are adopted to guarantee extremely low delay from result obtaining to execution, automatic defect judgment and automatic sorting, and the production efficiency of the production line is greatly improved.

The invention provides an informatization project book entity and relation joint extraction method and system, and the method comprises the steps: carrying out the context sensing coding of each word in an informatization project book, obtaining a word vector containing context information, carrying out the projection of the high-order tensor representation of the word vector through a task field vector, and obtaining a high-order tensor representation of the word vector; entity task feature representation and relation task feature representation are respectively obtained, and uniqueness among different tasks is ensured; entity and relation extraction tasks are modeled into task nodes in a graph, efficient interaction between tasks is achieved, the head and tail positions of entities and relations are captured through self-adaptive boundary guidance factors and a multiplication attention mechanism, accurate calculation of relation types between word pairs is improved, finally, the relation types between the word pairs are decoded, and therefore the efficient interaction between the tasks is achieved. And the entity and relation information in the informatization project book can be accurately extracted.

Disclosed in the present invention is a method for estimating a direction of arrival of a sub-array partition type L-shaped coprime array based on fourth-order sampling covariance tensor denoising. The implementation steps are as follows: constructing an L-shaped coprime array partitioned with linear sub-arrays; modeling a receiving signal of the L-shaped coprime array and deriving a second-order cross-correlation matrix thereof; deriving a fourth-order covariance tensor based on the cross-correlation matrix; realizing fourth-order sampling covariance tensor denoising based on kernel tensor thresholding; deriving a fourth-order virtual domain signal based on denoised sampling covariance tensor; constructing a denoised structured virtual domain tensor; obtaining a direction of arrival estimation result by decomposing the structured virtual domain tensor. The present invention makes full use of the statistical distribution characteristics of the high-order tensor of the constructed sub-array partition type L-shaped coprime array, realizes high-precision two-dimensional direction of arrival estimation through denoised virtual domain tensor signal processing, and can be used for target positioning.

The embodiment of the invention discloses a city knowledge graph embedded learning method and device, a server side, a medium and a product. The method comprises the steps that multiple pieces of event data generated in a target city and related to a preset task are acquired; based on the multiple pieces of event data, determining an urban knowledge graph, and mapping the multiple pieces of event data corresponding to the urban knowledge graph into a to-be-used high-order tensor; the plurality of modes in the to-be-used high-order tensor comprise a time mode and a space mode; inputting the to-be-used high-order tensor into the multi-relational graph convolutional network to learn modal basic information of a plurality of modals in the to-be-used high-order tensor and modal cross information between any two modals; and outputting an embedded learning vector corresponding to the urban knowledge graph. According to the technical scheme provided by the embodiment of the invention, the enhanced graph convolution operator based on high-order tensor decomposition can deeply mine the high-order time sequence sensitivity of entities and relationships in the urban knowledge graph, so that the effect of high-quality embedded learning vectors is generated.

The present application discloses a method and device for accessing heterogeneous data, which relates to the fields of smart transportation and big data. The method includes: obtaining a high-order tensor space model, the high-order tensor space model includes a unified representation of each multi-source heterogeneous data in the vehicle-road-cloud integration, the high-order tensor space model is obtained by fusing the low-order sub-tensors of each multi-source heterogeneous data into the tensor basis space model, and the order of each low-order sub-tensor is determined according to the attribute information of the corresponding multi-source heterogeneous data; determining the order tensor model of the data to be extracted from the high-order tensor space model; performing modular expansion on the order of the order tensor model to obtain the corresponding matrix; performing matrix singular value decomposition on the matrix, performing modular multiplication processing on the decomposition result, and obtaining the data to be extracted. In this application, a high-order tensor space model is proposed for the attribute information of heterogeneous data to achieve a unified representation of multi-source heterogeneous data, and then fast access to data can be achieved according to the characteristics of different heterogeneous data.

A sparse sensor layout optimization method for turbine disk temperature field inversion, which obtains snapshot data of turbine disk temperature field evolution over time by finite element simulation at equal time intervals, and constructs it as structured tensor data, then constructs a reduced order model through high order tensor decomposition, subsequently obtains an optimized sensor layout through tensor fiber-pivoted orthogonal triangular decomposition, and finally realizes accurate reconstruction of turbine disk temperature field based on tensor compressive sensing method. The invention solves the problem of difficulty in realizing accurate turbine disk temperature field inversion using limited sparse sensor layout by capturing the physical information of turbine disk temperature field and constructing an accurate reduced order model, and has broad application prospects in the field of surface temperature field measurement of large rotating thermal mechanical hot end components.

The application discloses a six-dimensional data decomposition method, a terminal device and a storage medium, which are applied to analysis of a six-dimensional number array, obtain pure analysis signals of each chemical component, and realize six-dimensional correction. The method is not sensitive to excessive component numbers, has a fast convergence speed, is suitable for processing high-dimensional data arrays with high collinearity and high noise. Moreover, stable and accurate qualitative and quantitative results can be obtained in the presence of known interference, unknown interference, peak overlapping and strong collinearity. Compared with a three-dimensional correction method, the method has a "high-order advantage", provides more abundant information, improves the anti-collinearity ability of the algorithm, and improves the sensitivity and selectivity of the method. In conclusion, the application can be successfully applied to qualitative and quantitative analysis of six-dimensional six-linear data, provides a data analysis means for future possible high-order instruments, and provides real data support and method reference for theoretical research of high-order tensor algebra.

The present invention relates to a high-order tensor spectral image super-resolution reconstruction method based on spectral information fusion, which is a method for realizing super-resolution reconstruction of hyperspectral images by weighted low Tensor-Train (TT) rank tensor analysis using weighted group sparsity and spectral unmixing. The present invention utilizes the high spatial-spectral correlation and non-local self-similarity of high-multispectral images, utilizes low TT rank tensor decomposition to approximate the recovery of block tensor data, and mines the non-local self-similarity contained in the block tensor data; weighted group sparsity is used as a regularization term to describe the spatial-spectral continuity of hyperspectral images; linear spectral decomposition based on weighted non-convex regularization is used as an effective spectral regularization to reduce spectral distortion. This method solves the problems of super-resolution reconstruction, high-multispectral fusion, noise removal, and image detail restoration, and its effectiveness and advancement are experimentally verified.

The invention discloses a hyperspectral image compression and reconstruction method based on Hankel rank increase tensor decomposition, which belongs to the technical field of image processing and spectral remote sensing, and comprises the following steps: step 1, constructing a basic hyperspectral image compression and reconstruction model based on regular term constraint, and obtaining a compression measurement value of a hyperspectral image; step 2, constructing a high-order tensor based on Hankel transformation; step 3, aiming at the high-order tensor obtained in the step 2, constructing a regular term based on Hankel rank increase tensor decomposition; 4, replacing the sparse regular term of the basic compression reconstruction model in the step 1 with the regular term of Hankel rank increase tensor decomposition constructed in the step 3 to form a final hyperspectral image compression reconstruction model; and 5, solving the hyperspectral image compression reconstruction model constructed in the step 4 by adopting an alternating optimization method. The method can effectively solve the problems that a hyperspectral image is large in data size and difficult to store and transmit, and an existing compression reconstruction method neglects multi-dimensional structure information.

The application relates to the technical field of power grid risk assessment, and discloses a power grid risk assessment method based on integrated power flow calculation and topology analysis, which comprises the following steps: collecting power grid operation data and preprocessing, organizing the preprocessed data into a four-dimensional high-order tensor structure; constructing a power grid topology relation tensor network; constructing an optimization problem in the form of L1 norm, and solving the optimization problem by using an augmented Lagrange multiplier method; analyzing the relationship between different dimension factor matrices to reveal the complex coupling relationship between time, space and parameters; performing risk assessment on different granularity levels under a multi-scale tensor analysis framework, and coordinating the analysis results of each level to form a comprehensive assessment; designing a tensor completion estimation algorithm, constructing an optimization model by using a low-rank assumption, and solving a complete data set by using a tensor low-rank decomposition method; by adopting high-order tensor representation and tensor network decomposition technology, the application effectively reduces the dimension and complexity of data, and the calculation complexity is reduced.