71 results about "Tensor completion" patented technology

The invention provides a multi-source heterogeneous data dynamic updating and agent knowledge base construction method, and relates to the technical field of data processing, and the method comprises the steps: organizing heterogeneous data through a three-dimensional feature matrix, constructing feature mapping through singular value decomposition and cross decomposition, and executing recursive tensor completion to generate a fusion feature space; extracting multi-scale features and determining a stable knowledge entity based on comprehensive measurement; constructing a network structure and dividing knowledge clusters; and performing differentiation fusion of the knowledge clusters based on the life cycle parameters. According to the method, efficient integration of heterogeneous data, accurate extraction of knowledge entities and dynamic optimization of knowledge structures are realized, and the intelligent level of knowledge management is improved.

The invention relates to the field of electromagnetic signal completion, and particularly discloses a low-rank autoregression electromagnetic spectrum tensor completion method and device. Comprising the following steps: acquiring incomplete electromagnetic spectrum data, constructing a three-dimensional tensor to represent the incomplete electromagnetic spectrum data, determining unknown pixel points, performing translation invariant wavelet transform, constructing a wavelet coefficient tensor by using a coefficient after wavelet transform, performing data replacement by using the wavelet coefficient tensor, and introducing local consistency constraint of time. And obtaining a low-rank autoregression tensor completion model, solving the low-rank autoregression tensor completion model by using an ADMM algorithm to obtain an updated auxiliary variable, an updated unknown variable and an updated recovery tensor, judging whether a convergence condition is satisfied or a preset number of iterations is reached, and if so, outputting the completed electromagnetic spectrum data. The objective of the invention is to solve the problem that effective completion of electromagnetic spectrum data can still be realized under the conditions of large data missing amount and large continuous time dimension missing amount.

The invention provides a rock and soil construction quality monitoring and diagnosing method, which comprises the following steps of: modeling historical engineering events and expert rules, constructing an event causal atlas prototype containing weights, and realizing event sequence feature extraction and real-time causal atlas dynamic updating in combination with on-site multi-modal sensing data and construction logs; neural symbol reasoning and tensor completion technologies are adopted to predict a novel causal relationship, and a causal atlas structure is perfected through space, time and logic consistency verification; a multi-layer risk early warning mechanism is set, a causal map local risk assessment and event chain propagation are combined, spatial positioning early warning signals are generated in a grading manner, closed-loop backtracking optimization is supported, causal reasoning accuracy and early warning efficiency are improved, construction process risk identification and dynamic early warning can be realized, and the engineering safety management level is improved.

The invention relates to a water conservancy monitoring data abnormal state identification method based on multi-modal learning, and the method specifically comprises the following steps: deploying a heterogeneous sensor network at a water conservancy facility, collecting original monitoring data, combining the text modal data of a work log, and carrying out the abnormal state marking to form a training data set; constructing uniform time grid tensor alignment multi-modal data, and obtaining a complete alignment tensor by adopting a low-rank tensor completion algorithm of fusion modal mutual information constraint; constructing a machine learning model comprising a cross-modal feature collaborative enhancement module, a heterogeneous feature projection and gating fusion module and a spatio-temporal context sensing anomaly recognition module, inputting a complete alignment tensor into the model to obtain an anomaly probability value, and training the model through a loss function; new data is collected, preprocessed and input into the trained model, an abnormal probability value is compared with a set threshold value, and an abnormal type is judged. According to the method, the feature representation capability is enhanced through multi-module cooperation, and the accuracy and timeliness of water conservancy facility anomaly recognition can be improved.

The invention provides an image restoration method based on adaptive weighted tensor completion, and relates to the technical field of image processing and application, and the method comprises the steps: obtaining to-be-restored image data, and carrying out the tensor of the to-be-restored image data, and obtaining input tensor data; constructing a tensor completion model based on an adaptive weighted tensor nuclear norm; wherein a weight matrix in the tensor completion model can be adaptively updated along with input tensor data; and based on an alternating direction multiplier method or an approximate singular value decomposition method based on tensor QR decomposition, solving the tensor completion model, and outputting restored tensor data to realize image restoration. According to the scheme, the image restoration quality can be improved.

The invention provides a tensor completion method based on low-rank and sparse combined constraint, and the method is applied to radar high-resolution two-dimensional sparse reconstruction imaging so as to enhance sparse imaging performance. Radar high-resolution two-dimensional imaging is realized through the following steps: firstly, constructing a tensor model of radar data through a sliding window method to capture an internal structure of high-dimensional data and mine low-rank characteristics of the data; secondly, representing enhanced low-rank and sparse characteristics of the constructed radar tensor data by using a tensor low-rank and sparse combined constraint model represented based on a Kronecker basis; and then an optimal solution of the constraint model is efficiently solved in an iteration mode by using an alternating direction multiplier method, and related parameters are updated through a closed-form solution method. According to the method, the superiority of the tensor completion method based on the low-rank and sparse joint constraint in radar high-resolution two-dimensional imaging is verified through comparison experiments on electromagnetic simulation and actually measured radar data.

The invention relates to the technical field of data processing, in particular to a traffic data completion method and device based on a time autoregression low-rank tensor, and the method comprises the following steps: obtaining incomplete traffic data; constructing a three-dimensional tensor to represent incomplete traffic data, and obtaining an observation index set and a tensor matrix; taking a low-rank tensor completion model based on rank minimization as a framework, and introducing time autoregressive regularization and truncation weighted nuclear norms to obtain a low-rank tensor completion model; performing problem decomposition solving on the low-rank tensor completion model on the basis of an ADMM framework to obtain four variable parameters, namely, a variable parameter, a variable parameter and a variable parameter; and iteratively updating the variables according to the sequence until a preset convergence standard is reached, and outputting the complemented complete traffic data. According to the method, the time change is introduced into the completion of the three-order tensor as a new regularization item, so that the historical information can be learned during data recovery, the low-rank performance of the completed tensor can be ensured, and a complex missing scene can be better processed.

The invention relates to the technical field of fault diagnosis, in particular to a power grid fault analysis method and system, and the method comprises the steps: constructing a fusion tensor, and carrying out the dimension reduction of the fusion tensor, and generating a fusion feature matrix; constructing a convolutional auto-encoder model to detect an abnormal fusion feature matrix; and performing power grid fault classification according to abnormal data of the abnormal feature matrix, and calculating a power grid equipment fault area based on a power grid fault classification result. The method has the beneficial effects that the power grid operation data is complemented by adopting a high-precision low-rank tensor complementation algorithm, and the completeness and accuracy of the data are ensured. By using Tucker decomposition and matrix compression technologies, key features are extracted from multi-dimensional data collected by a multi-source sensor, and a fusion feature matrix is constructed, so that the data processing efficiency and the feature expression capability are effectively improved. The application of the convolutional auto-encoder model enhances the detection precision of abnormal features, and the method based on improved weighted summation and hierarchical clustering improves the accuracy of fault classification and positioning.

The invention relates to the technical field of electric energy dispatching, in particular to an electric energy dispatching method based on an energy storage system. The method comprises the following steps: deploying a distributed sensor array in a battery module to collect multi-source heterogeneous data, and carrying out standardization processing to generate a standardized energy storage data set; performing tensor completion on the standardized energy storage data set to generate energy storage tensor completion data; time-space dimension analysis is carried out on the energy storage tensor complemented data, cross-modal feature fusion is carried out, and an energy storage cross-modal feature space is generated; therefore, through structural processing of multi-dimensional fusion data and dynamic feedback optimization of the digital twinborn model, the problems that traditional cold chain storage environment prediction lags behind and the model adaptability is poor are solved, and the precision of temperature prediction and the intelligent level of storage management are improved.

The invention relates to a device and a method for 3D tensor completion. The device comprises • a device (I / O) for receiving an incomplete 3-dimensional matrix (MI), • a device (CPU) for generating permutations (M1,M2,M3) of the received 3-dimensional matrix, • a device (CPU) for unfolding the permutations (M1,M2,M3) into three 2-dimensional orthogonal matrices (N1,N2,N3) • a device (CPU) for removing elements from the matrices or permutations that have a deviation greater than a predetermined value with respect to neighboring elements, • a completion facility (AI) with a variable number of columns and a variable number of rows of a variable number of values ​​based on a hierarchical adaptation of the prediction space, • a post-processing unit (CPU) for the generated predictions to create an extended 3-dimensional matrix (MO),

The invention relates to a data completion method suitable for multiple types of massive power consumers. The method comprises the following steps: step 1, collecting power consumption data of multiple types of power consumers; 2, decomposing the power consumption data of different users into the sum of a trend term and a periodic term; step 3, cycle term verification is carried out; step 4, performing standard delay transformation on the power consumption data of the single user acquired in the step 1 and the time sequence vectors of the period term and the trend term decomposed in the step 2 to obtain a Hankel tensor; 5, establishing a time sequence smooth constraint and a periodic term constraint; step 6, establishing a comprehensive tensor completion objective function; and 7, solving the comprehensive tensor complementation objective function obtained in the step 6, and outputting complete data through an inverse MDT technology. The method can be suitable for one-dimensional and multi-dimensional data scenes, and the complementation effect is good.

The invention provides an edge cloud cache configuration method and device based on tensor complementation, and relates to the technical field of containerization deployment in an edge cloud network, the method comprises the steps of decomposing mirror image layer prefetching into prediction of mirror image layer cache and mirror image layer pre-scheduling, combining tensor complementation, an iTransform model and a CP decomposition algorithm, and after the tensor is complemented, obtaining an edge cloud cache configuration result. The iTransform model captures non-stationary dependence among dimensions of tensors through an inverted time sequence attention mechanism of the iTransform model while keeping high efficiency of parameters, steady inference on current time information is realized, so that an accurate mirror image layer prefetching task is supported, a CP decomposition algorithm performs tensor reconstruction on each selectable tensor to calculate a score of each selectable tensor, and the score of each selectable tensor is calculated to obtain a pre-fetching task of the mirror image layer. And finally, taking the selectable tensor with the highest score as a target tensor. Based on the method, efficient prefetching and cache optimization of the AI micro-service mirror image layer can be realized, so that challenges caused by resource limitation in an edge cloud environment are effectively relieved.

This invention relates to the field of industrial time-series data completion technology, and particularly to a method for industrial time-series data completion based on tensor weighted gamma norm. The method includes: collecting industrial time-series data through sensors and converting it into an observation tensor; processing the observation tensor for missing values ​​to obtain a tensor to be completed, and constructing a low-rank tensor completion model; defining a tensor weighted gamma norm and substituting it into the low-rank tensor completion model to obtain a low-rank tensor completion model using the tensor weighted gamma norm; solving the low-rank tensor completion model using the tensor weighted gamma norm using the alternating direction multiplier method to obtain the target solution; converting the target solution into the format of industrial time-series data to obtain the completed industrial time-series data. This invention utilizes tensor weighted gamma norm to complete industrial time-series data, and further leverages the interdependence and trends between data to mitigate the impact of the nuclear norm approximating the rank function on all singular values ​​to the same degree of contraction.

The present invention is an Internet of Things data reconstruction method based on structured low-rank tensor completion. First, the monitoring area is discretized into multiple grid points, and a sensor node is deployed inside each grid point. Assuming that the sensor node senses data every other time slot, the data received by the base station within time T forms a third-order tensor. Secondly, the data reconstruction is converted into a basic low-rank tensor completion problem, and a low-rank tensor completion model is constructed. Finally, the block Hankel matrix transformation is performed on the unfolding matrix of each mode i of the third-order tensor, and the basic low-rank tensor completion model is improved into a structured low-rank tensor completion model. The augmented Lagrangian function of the structured low-rank tensor completion model is solved to obtain the third-order tensor, and the Internet of Things data reconstruction is completed. The data collected at continuous moments are arranged in a third-order tensor to make full use of the spatial correlation of the data. The block Hankel matrix transformation is performed on the unfolding matrix of each mode i of the third-order tensor, and data reconstruction is carried out by combining structured and low-rank tensor completion, further exploring and utilizing the spatio-temporal correlation of the data, alleviating the influence of basis mismatch on the reconstruction performance in the sparse constraint-based method, and improving the data reconstruction accuracy.

The invention discloses a physiological signal extraction method based on self-adaptive ROI and ViM dual paths, which comprises the following steps: constructing a first quality perception space-time diagram of a first user and a second quality perception space-time diagram of a second user based on a self-adaptive region-of-interest selection mechanism and a low-rank tensor completion method; extracting a first time sequence prediction signal of the first quality perception space-time diagram and a second time sequence prediction signal of the second quality perception space-time diagram through a time path of the ViM dual-path network structure, and extracting a first frequency domain prediction signal of the first quality perception space-time diagram and a second frequency domain prediction signal of the second quality perception space-time diagram through a frequency path; and fusing the first time sequence prediction signal and the first frequency domain prediction signal to obtain a first physiological signal of the first user, and fusing the second time sequence prediction signal and the second frequency domain prediction signal to obtain a second physiological prediction signal of the second user. According to the method, the robustness, precision and efficiency of physiological signal extraction are improved, and different scene requirements can be considered.

The invention discloses a network measurement data completion method and device based on incomplete multi-view analysis, and the method comprises the steps: firstly decomposing a recovery problem of a fine-grained network measurement tensor into two perspectives of space consistency and time complementarity for joint modeling, constructing a deep learning model for tensor completion, and then training the model; and inputting a measurement tensor of network measurement data containing missing values into the trained model, performing forward propagation processing on the observation measurement tensor through a plurality of stages of the model, solving an optimization problem of joint modeling in an iteration mode, and outputting a recovered complete data tensor. According to the method, the tensor recovery problem is innovatively decomposed into two orthogonal views of space consistency and time complementarity for joint modeling, wherein the space view restrains a global topological structure through a graph tensor nuclear norm, and the time view captures a node heterogeneous evolution mode through CP decomposition. And a cross-node attention mechanism is further introduced to realize spatio-temporal feature alignment and fusion.

The present application relates to a kind of suitable for multiple types of mass power user data completion method, comprising the following steps: step 1, the power consumption data of multiple types of power users is collected;Step 2, the power consumption data of single different user is decomposed into the sum of trend term and periodic term;Step 3, periodic term verification is carried out;Step 4, the power consumption data of single user collected in step 1 and the periodic term, trend term time series vector after decomposition in step 2 are carried out standard delay transformation, obtain the hankel form tensor;Step 5, establish time series smoothing constraint and periodic term constraint;Step 6, establish comprehensive tensor completion objective function;Step 7, solve the comprehensive tensor completion objective function obtained in step 6 and output complete data by anti-MDT technology.The present application can be applied to one-dimensional and multidimensional data scene, and the completion effect is good.

The present invention provides a Bayesian tensor completion algorithm based on multi-measurements. The multi-measurement data is represented by multiple tensors, and it is assumed that each measurement value of each tensor element of the tensor follows a Gaussian distribution. Then, CP decomposition is performed on the tensor to obtain the corresponding factor matrices, and it is assumed that the parameters of the factor matrices follow a conjugate prior distribution. Furthermore, the Gibbs sampling method is used to sample the posterior conditional distributions of the respective parameters, and the estimated value of the tensor is output. The missing values in the multi-measurement data are interpolated based on the estimated value of the tensor, thereby realizing data completion. In summary, the completion method of the present invention is aimed at measurement data with low measurement accuracy, high cost, and repeated measurements in some regions. The Gibbs sampling method combined with CP decomposition is used to realize data completion. Compared with the completion methods in the prior art, since the method of the present invention can utilize the information of all measurement data, it can provide a more accurate estimated value, thereby realizing more accurate data completion.

The invention discloses a security constraint unit commitment method based on tensor completion approximate dynamic programming, and the method comprises the following steps: firstly, building a security constraint unit commitment model based on a Markov decision process; secondly, decoupling the multi-period security constraint unit commitment model into a single-period sub; then, obtaining a value function and a decision function by adopting an approximate dynamic programming algorithm based on tensor completion; according to the approximate dynamic programming algorithm based on tensor completion, the approximate dynamic programming algorithm is improved from the angle of tensor completion, and all value functions and decision functions are approximately obtained by sampling a small number of state variables and decision variables. Decision is made from the angle of tensor complementation, in the face of a discrete state space, the value function of the whole state space can be approximated only by sampling a small number of state points, the calculation burden of an approximate dynamic programming algorithm in the aspect of value function approximation is effectively relieved, and the calculation efficiency of the algorithm can be greatly improved.

This invention provides a pipeline leak location method based on tensor completion, comprising: collecting leakage vibration data of a leaking pipeline using wireless accelerometers, wherein the leakage vibration data includes data sampled by N wireless accelerometers over M time periods; constructing a tensor completion model using a truncated tensor weighted norm algorithm, and constructing an optimal three-dimensional tensor structure using the firefly algorithm based on the leakage vibration data of the leaking pipeline and the tensor completion model; inputting the optimal three-dimensional tensor structure into the tensor completion model for completion; and calculating the leakage location of the leaking pipeline based on the completed three-dimensional tensor. This invention utilizes a truncated tensor weighted norm to construct a tensor completion model, which efficiently preserves effective information in the missing data, improves the tensor completion accuracy, ensures effective recovery of effective feature information from the pipeline leak data, and improves location accuracy.

The invention discloses a network digital twinning-oriented dual-view flow data sampling method and system, and mainly solves the problems of difficult key path capture and low flow reconstruction precision caused by lack of frequency domain perception of a flow sampling method in the prior art. According to the implementation scheme, historical flow interaction data in a network node sliding window are collected to form a third-order flow tensor and normalized, and node frequency domain features are extracted and then smoothly updated to obtain a smooth feature vector; mapping the vector to determine a node category, and dividing source-destination OD pair traffic categories of the whole network; calculating statistics lever scores of all OD pairs, dynamically allocating sampling budget of each category according to the statistics lever scores, and generating a sampling set and a binary sampling mask by adopting a determinacy and random combination strategy; and collecting the flow data of the corresponding position at the current moment based on the mask, constructing a tensor completion optimization model for solving completion, and outputting the recovered whole network flow data. According to the method, through double-view cooperation of the frequency domain features and the statistical lever fraction, precise coverage of a high-value traffic path is realized, and the traffic reconstruction precision of the digital twin network is effectively improved while the sampling overhead is reduced. The method can be applied to measurement and reconstruction of large-scale network traffic.

This invention belongs to the field of industrial time-series data completion technology, specifically relating to a method based on truncated L... 2,P A scalable industrial time-series data completion method based on norms includes: acquiring multi-dimensional industrial time-series data through distributed sensors; processing missing values ​​in the acquired tensors to obtain sparse tensors to be completed, and constructing a low-rank tensor completion model; integrating linear unitary transforms to enhance the scalability of the model; and defining a truncation L... 2,P Norm, based on truncated L 2,P A low-order smooth tensor completion model based on the norm is proposed. This model decomposes a complex optimization problem into multiple parallelizable subproblems to obtain the objective solution. The objective solution is then adapted to an industrial time-series data format to obtain completed industrial time-series data. This invention utilizes truncated L... 2,P The norm better approximates the tensor rank, and by integrating linear unitary transformation, it can complete high-dimensional, large-scale industrial time series data, effectively improving data quality and providing reliable support for the accurate analysis and optimization of industrial processes.

The present invention proposes a tensor completion method based on low-rank and sparse joint constraints and applies it to radar high-resolution two-dimensional sparse reconstruction imaging to enhance sparse imaging performance. The present invention realizes radar high-resolution two-dimensional imaging through the following steps: first, a tensor model of radar data is constructed by a sliding window method to capture the intrinsic structure of high-dimensional data and mine the low-rank characteristics of the data. Secondly, a tensor low-rank and sparse joint constraint model based on Kronecker basis representation is used to characterize the enhanced low-rank and sparse characteristics of the constructed radar tensor data. Then, the alternating direction multiplier method is used to efficiently solve the optimal solution of the constraint model in an iterative manner and update the relevant parameters by a closed-form solution method. The present invention verifies the superiority of the tensor completion method based on low-rank and sparse joint constraints proposed in the present invention in radar high-resolution two-dimensional imaging through comparative experiments on electromagnetic simulation and measured radar data.

The invention relates to the technical field of oil and gas exploration and development, and particularly discloses a robust mixed norm constraint high-dimensional seismic data reconstruction method and device, and the method comprises the steps: carrying out the Fourier transformation of five-dimensional data along a time axis, and obtaining the Fourier transformation data; unfolding 4D data of each frequency slice of the Fourier transform data along a mode-(m, n) to obtain a near-square matrix; a non-convex Frobenius / Nuclear mixed norm and L1 norm combined regularization constraint is applied to the near-square matrix, and a target functional of observation seismic data and reconstruction data is constructed; and alternately solving the target functional by adopting an ADMM algorithm, and carrying out inverse Fourier transform on a solving result along a frequency axis. According to the method, a high-dimensional tensor completion method under the robust Frobenius / Nuclear mixed norm constraint is introduced, accurate representation of nonlinear high-dimensional seismic data is achieved, the seismic data reconstruction and denoising precision is improved, and therefore regularized reconstruction and abnormal noise suppression of the seismic data with the low signal-to-noise ratio are achieved.

The present invention relates to the field of electromagnetic signal completion, and specifically discloses a low-rank autoregressive electromagnetic spectrum tensor completion method and device. It includes obtaining incomplete electromagnetic spectrum data, constructing a three-dimensional tensor to characterize the incomplete electromagnetic spectrum data, determining unknown pixel points, performing a translation-invariant wavelet transform, and using the coefficients after the wavelet transform to construct a wavelet coefficient tensor, using the wavelet coefficient tensor to replace data, and introducing a local consistency constraint of time to obtain a low-rank autoregressive tensor completion model, using the ADMM algorithm to solve the low-rank autoregressive tensor completion model, obtaining updated auxiliary variables, updated unknown variables and updated recovery tensors, judging whether the convergence conditions are met or the preset number of iterations is reached, and if so, outputting the completed electromagnetic spectrum data. It is intended to solve the problem of being able to effectively complete electromagnetic spectrum data even when there is a large amount of missing data and a large number of continuous missing time dimensions.

The invention belongs to the technical field of satellite remote sensing data processing and atmospheric pollution monitoring, and discloses a remote sensing image tensor completion reconstruction method and system based on space-time adaptive partitioning to solve the problems that the existing tensor completion technology is poor in partitioning adaptability and unbalanced in completion precision and convergence efficiency. The method comprises the following steps: preprocessing original remote sensing image data, and constructing a three-dimensional space-time tensor; calculating an average effective pixel proportion of a space-time region based on pixel effectiveness, dynamically matching blocks, and performing tensor block rearrangement; adaptively adjusting a low-rank threshold value and a dimension weight, and solving the low-rank tensor complementation model by adopting an economical singular value; and normalizing, weighting and fusing the block overlapping region through a weight matrix, recovering a three-dimensional space-time tensor, and expanding and outputting a complete result. According to the method, high-efficiency and high-precision space-time seamless reconstruction of the large-size remote sensing image is realized, the data complementation precision and processing efficiency in different missing modes are remarkably improved, and high-quality data support is provided for refined treatment of regional atmospheric pollution.

The present invention relates to the technical field of data visualization, and specifically discloses a method for constructing a three-dimensional electromagnetic spectrum map based on tensor completion, comprising: S1, acquiring a region to be measured in a simulation scene, collecting spectrum data in the region to be measured, and obtaining a missing data set; S2, obtaining a completed tensor based on a tensor singular value decomposition method and the missing data set; S3, constructing a three-dimensional electromagnetic spectrum map based on a Poisson surface reconstruction algorithm and the completed tensor.

The invention discloses a radar signal reconstruction method based on maximum multiple correlation entropy, which adopts a maximum multiple correlation entropy criterion to define an error function, and replaces an error function based on # imgabs0 # norm commonly used in a traditional tensor completion method, and in an abnormal value pollution environment, the maximum multiple correlation entropy criterion is used to determine the error function, and the maximum multiple correlation entropy criterion is used to replace the error function based on # imgabs0 # norm. The maximum multiple correlation entropy is generally more robust than a traditional # imgabs1 # error function, and can better suppress the influence of an abnormal value, so that the radar signal reconstruction model based on the maximum multiple correlation entropy can effectively suppress the interference of the abnormal value on the system performance, thereby improving the reconstruction precision of the radar signal; therefore, accurate reconstruction and recovery of the radar signal polluted by the abnormal value are realized, the problem of poor performance caused by the influence of the abnormal value on the reconstruction of the radar signal at present is solved, and the signal processing capability of the system in a complex electromagnetic environment is further improved.

The present application relates to the technical field of electric energy scheduling, and particularly relates to an electric energy scheduling method based on an energy storage system.The method comprises the following steps: deploying a distributed sensing array inside a battery module to collect multi-source heterogeneous data, and performing standardization processing to generate a standardized energy storage dataset; performing tensor completion on the standardized energy storage dataset to generate energy storage tensor completion data; performing time-space dimension analysis on the energy storage tensor completion data, and performing cross-modal feature fusion to generate an energy storage cross-modal feature space;Therefore, through the structured processing of multi-dimensional fused data and the dynamic feedback optimization of the digital twin model, the present application solves the problems of lagging prediction and poor model adaptability in traditional cold-chain warehouse environments, and improves the accuracy of temperature prediction and the intelligent level of warehouse management.

The present application relates to the technical field of fault diagnosis, in particular to a power grid fault analysis method and system, which comprises constructing a fusion tensor and performing dimension reduction processing on the fusion tensor to generate a fusion feature matrix; constructing a convolutional autoencoder model to detect abnormal fusion feature matrix; classifying power grid faults according to abnormal data of the abnormal feature matrix, and calculating power grid equipment fault area based on the result of power grid fault classification. The present application has the beneficial effect of ensuring the integrity and accuracy of data by using a high-precision low-rank tensor completion algorithm to complete power grid operation data. Key features are extracted from multi-dimensional data collected by multiple source sensors and a fusion feature matrix is constructed using Tucker decomposition and matrix compression technology, effectively improving the efficiency of data processing and the ability of feature expression. The application of the convolutional autoencoder model enhances the detection accuracy of abnormal features, and the improved weighted summation and hierarchical clustering-based method improves the accuracy of fault classification and positioning.