1351 results about "Data reconstruction" patented technology

The invention discloses an energy-saving control method and system for a water chilling unit, and relates to the technical field of energy-saving control. During operation of the system, a data set is synchronously collected from a water chilling unit system through a multi-channel asynchronous sampling mechanism, time sequence compression and redundancy removal are carried out, an embedded perturbation calculation mechanism is used for calculating and generating a non-dominant control core coefficient, and the non-dominant control core coefficient is used for controlling the energy-saving control of the water chilling unit; a three-dimensional coefficient space is converted and output through an entropy state change structure and is used for constructing a state balance atlas, comprehensively calculating a control state index SEEI, evaluating the current energy state offset degree of a system, determining whether intervention is carried out or not, carrying out rule search and nonlinear modeling based on the control state index SEEI value, generating an adjustment matrix, and carrying out state balance analysis. And starting a data reconstruction micro-strategy of a short-time historical window, receiving an adjustment matrix, converting the adjustment matrix into a device-level instruction, executing an action through an edge controller, feeding back a response error epsilon (t) in real time, and predicting a potential performance degradation trend based on long-time system operation data.

A method and apparatus for reconstructing a three-dimensional (3D) scene from a two-dimensional (2D) input image of the scene using a fully-differentiable transformer-based encoder-decode. A 2D input image encoded into a set of image features using a pre-trained vision transformer model, wherein the vision transformer model is pre-trained with multi-view RGB image supervision and point cloud supervision. The set of image features is projected onto a 3D triplane representation using a transformer decoder to obtain output triplane tokens. A triplane representation is created from the tokens and queried. 3D point features of color and density for volumetric rendering re predicted using a multi-layer perceptron. The geometry of the generated 3D asset is represented with a surface mesh including vertices and triangular faces. A texture map by is created with a multichannel image in UV space. Multiple views of the 3D scene are simultaneously generated based on the surface mesh.

A computer-implemented method for decoding a coded mesh bitstream of a dynamic mesh representing three-dimensional content includes that: geometry information of the dynamic mesh is reconstructed from a geometry component bitstream in the coded mesh bitstream, the reconstructed geometry information includes data specifying vertices of the dynamic mesh; connectivity information of the dynamic mesh is reconstructed from a connectivity component bitstream in the coded mesh bitstream, the reconstructed connectivity information includes data specifying faces of the dynamic mesh; the reconstructed connectivity information is refined based on the reconstructed geometry information to generate refined connectivity information by at least dividing a face specified by the reconstructed connectivity information into two faces based on a vertex specified in the reconstructed geometry information; the dynamic mesh is reconstructed based on the reconstructed geometry information and the refined connectivity information; and the reconstructed dynamic mesh is caused to be rendered for display.

The invention discloses a composite board ultrasonic defect detection method which comprises the following steps: S1, fixing a carbon fiber circumferential winding composite pressure container on a bracket, and establishing a coordinate system with the axis of the container as a z axis; s2, a 40 MHz dry coupling phased array ultrasonic probe is attached to the scanning starting point, and the contact angle of the probe is recorded; s3, moving the probe along the spiral track of the outer surface of the container at the speed of 20mm / s, and collecting A-scanning echo signals of all array elements; s4, performing pulse compression and time domain deconvolution processing on the acquired signal to obtain a time domain echo sequence; s5, delay time is calculated according to the shell curvature, the array element signals are compensated, and focusing B-scanning data are generated; s6, splicing the B-scanning data at the step length of 0.5 mm * 0.5 mm, and reconstructing C-scanning data corresponding to the space coordinates; and S7, inputting the C-scanning data into the trained Transform network, and outputting defect types, sizes and three-dimensional coordinates. The method realizes high-frequency ultrasonic composite board defect accurate detection, remarkably improves the microcrack recognition rate, and is widely applied to safety evaluation scenes of high-pressure hydrogen storage tanks and pressure vessels.

The invention relates to the technical field of smart cities, in particular to an urban climate risk monitoring system based on multi-source data fusion and early warning application thereof, and the urban climate risk monitoring system comprises a data reconstruction module, a precursor identification module, a trend chain extraction module, a grade assignment module and a risk diffusion module. According to the method, the reliability of multi-source meteorological data is effectively enhanced, the precision of data fusion and the reliability of spatial positioning are improved by carrying out credibility level evaluation on a plurality of data sources, and the sensitivity of risk precursor events and the accuracy of factor propagation prediction are enhanced by utilizing deep identification of trend consistency and response delay relation; according to the method, the regional spatial continuity factors are combined, the stability and spatial continuity of risk grade division are optimized, spatial impedance characteristics are brought into diffusion path prediction, accurate deduction of urban climate risk spatial diffusion paths and dynamic marking of risk regions are realized, and the accuracy and dynamic of urban climate risk monitoring and prevention and control decisions are enhanced.

The invention provides an avalanche monitoring and early warning method based on deep learning, and the method comprises the steps: obtaining environment monitoring data in a period of time before a current moment, carrying out the preprocessing, and constructing a training data set; an avalanche monitoring and early warning model is constructed and trained; inputting forecast data of environmental monitoring into the trained avalanche monitoring early warning model for data reconstruction to obtain corresponding reconstruction data; calculating a data reconstruction error; and determining that the data is abnormal according to the error and a preset threshold value, and completing the avalanche monitoring and early warning. The problem that an anomaly detection model is difficult to capture key features under high-dimensional and dependency complex data is solved, the precision and robustness of the anomaly detection model are improved, and the method is particularly suitable for processing multivariate time series data such as avalanche monitoring data, capturing data anomalies in the avalanche monitoring data and achieving avalanche monitoring and early warning.

The invention relates to the technical field of wire harness fault diagnosis, and discloses a vehicle-mounted wire harness fault diagnosis method and device and a storage medium. The method comprises the following steps: carrying out equivalent circuit modeling on a measurement node and a wire harness section of the vehicle-mounted wire harness to obtain a node connection relation matrix; performing feature analysis on the voltage data and the current data of the measurement nodes to obtain a fault feature vector and a fault type discrimination rule base; inputting the voltage data, the current data and the node connection relation matrix into a recursive variational graph automatic encoder for data reconstruction to obtain time sequence feature reconstruction data and topological relation reconstruction data; carrying out distributed sub-model division and model fusion to obtain a standardized feature vector; and performing matching analysis on the standardized feature vector and the fault type judgment rule base to obtain fault position information and fault type information, so that automatic optimization and screening of fault features are realized, and the reliability and interpretability of a diagnosis result are improved.

The invention provides a hybrid fault-tolerant control method and system for a multi-sensor simultaneous fault scene, and the method comprises the steps: inputting the historical time sequence feature data of sensors into a long short-term memory network and a Stacking model, and obtaining the output data prediction values, outputted by the long short-term memory network and the Stacking model, of the sensors at the current moment; according to a difference value between an output data prediction value and an output data actual value of the sensor at the current moment output by the long-short-term memory network, whether the sensor breaks down or not is determined through sequential probability ratio inspection; and under the condition that the sensor has a fault, determining an output data reconstruction value of the sensor at the current moment according to an output data prediction value of the sensor at the current moment, which is output by the long-short-term memory network and the Stacking model. According to the invention, fault detection and output data reconstruction can be carried out on the sensor in real time, and the stability and reliability of the system under the condition of multi-point observation failure are improved.

The invention discloses a river flow missing data reconstruction method, which comprises the following steps of S1, constructing a river network topological structure, and quantifying hydraulic correlation; s2, spatio-temporal feature fusion and multi-source information extraction; s3, performing multi-task cooperative flow reconstruction and confidence coefficient prediction; s4, dynamic weighting and result correction of meteorological factors; and S5, performing anomaly detection and model dynamic updating. According to the method, a river flow missing data reconstruction method is set, the steps are mutually fused and used, and topology-aware space-time diagram convolution is performed: a river network topology structure is encoded into a weighted adjacency matrix for the first time, space correlation features are extracted through a diagram convolution network, and the problem that a traditional method ignores hydraulic connection is solved; a multi-task collaborative learning mechanism: synchronously outputting a flow reconstruction value and confidence, combining topological smooth constraints, and realizing reconstruction reliability quantification while ensuring precision; and meteorological dynamic weighted correction: dynamically adjusting the node weight based on the real-time rainfall intensity, and accurately adapting to the nonlinear response of the water flow in the heavy rainfall period.

The invention relates to the technical field of image data processing, in particular to a data reconstruction method and system for a building house remote sensing surveying and mapping model, and the method comprises the steps: obtaining the three-dimensional point cloud data of a building house, and carrying out the initial layering through the local geometric features of the three-dimensional point cloud data, and obtaining all target levels; determining whether false point cloud data exist in the target levels and determining correction parameters of the false point cloud data by utilizing a geometric structure relationship of joint surfaces between the target levels of the adjacent building stages; under the condition that the false point cloud data exists in the target hierarchy, correcting the point cloud data in the target hierarchy by using the correction parameter to obtain corrected point cloud data; and determining a thinning parameter of the target level by using the corrected point cloud data, and determining a target point cloud model of the building house by using the thinning parameter. According to the method, error points or irrelevant points can be effectively removed, the three-dimensional data of the building is ensured to be more suitable for the actual situation, and meanwhile, the processing amount of false point cloud data is reduced.

A unified platform for multi-type data compression and decompression is disclosed. The platform employs a virtual management layer to receive, organize, and route input data to corresponding compression subsystems. Multiple compression methods, including homomorphic encryption-based techniques, are utilized to compress data sets while maintaining data privacy. A data manager associates and manages related data sets throughout the compression and decompression processes. Compressed data is routed to appropriate decompression subsystems, where it is decompressed and reconstructed using advanced techniques, such as neural upsampling, to recover lost information and enhance data quality. The platform supports various data types and compression methods, enabling efficient and secure compression and decompression of data. By integrating homomorphic encryption and data reconstruction techniques, the platform provides a comprehensive solution for data compression and decompression while preserving data privacy and enhancing data quality.

The invention provides a power big data-based sparsity feature adaptive compression method, which comprises the steps of adaptively optimizing a sensing matrix through a dictionary learning method aiming at a screened multi-granularity feature subset, introducing a sparse regularization item to enhance the sparsity of data reconstruction, and according to a missing mode of a missing value and context information, carrying out adaptive compression on the sparse feature of the power big data. Establishing a mapping relationship among the compression ratio, the reconstruction error and the feature subset, and determining a self-adaptive compression strategy; based on a self-adaptive compression strategy, a compressed sensing method is adopted to carry out self-adaptive compression on the multi-time-granularity power data, the compression ratio is dynamically adjusted according to reconstruction error feedback, the data compression and reconstruction quality is balanced, and the reconstructed multi-granularity power data is synchronized according to timestamp precision.

The invention discloses a compressed sensing MRI (Magnetic Resonance Imaging) reconstruction method and system based on a double-domain fusion expansion model. The method comprises the following steps: acquiring an MRI image, preprocessing the MRI image to obtain a preprocessed image and a corresponding compressed sensing measurement value, and constructing a data set; training, testing and verifying the double-domain fusion expansion model by using the data set; and outputting a reconstructed image from the MRI image after mask sampling by using a double-domain fusion expansion model. According to the double-domain fusion expansion model, a complex convolutional neural network and a K-space attention mechanism are introduced for complex value data processing and double-domain information fusion in compressed sensing MRI reconstruction. The complex value data is processed through the complex network, the amplitude and phase information of the complex field is fully utilized, the detail recovery capability and the noise suppression effect of the model are enhanced, and particularly, excellent robustness is shown at a low sampling rate. The method is excellent in performance in complex MRI data reconstruction, and has high reconstruction precision and generalization ability.

In various examples, a language model may be trained and used as part of an interface for a simulation system. For instance, user inputs may be applied to the language model and the language model may be trained to generate code, make API calls, or perform any other operations to interact with and / or control various aspects of the simulation. In some examples, the language model may generate code for, among other things, creating and / or customizing a virtual environment associated with the simulation. For instance, the generated code may include, but is not limited to, code for rendering the virtual environment, code for rendering and simulating behaviors of virtual agents (e.g., pedestrians, vehicles, animals, etc.) and / or any other objects (e.g., road signs, buildings, trees, etc.) within the virtual environment, code for recreating and simulating real-world events from recorded sensor data, etc.

A magnetic resonance image reconstruction device according to an embodiment is a magnetic resonance image reconstruction device that reconstructs magnetic resonance image data in which an artifact due to undersampling is removed or reduced based on undersampled k-space data, and includes a reconstruction unit reconstructing the magnetic resonance image data using a reconstruction network having a correction module. The correction module includes a regularization block generating second image data by performing a regularization process on first image data using a first neural network, and a data consistency block generating third image data by performing a data consistency process so that k-space data corresponding to the second image data approaches the undersampled k-space data. The correction module further includes at least one of a data consistency adjustment block adjusting the data consistency process and a regularization adjustment block adjusting the regularization process.

Various embodiments of the present technology relate to synthetic aperture radar image capturing and scene reconstruction using a cluster of multi-static satellite receivers. More specifically, in some embodiments, the cluster of receivers retrieves a flight path over a communication network. Flying in-formation, a lead or main satellite sends radio or wave pulses to a target area and additional satellites capture an echo of the wave pulses after the waves bounce off the target area to capture SAR radar data. The radar data can be transmitted from the cluster of satellites to a radar stations or to the main satellite. The radar stations or the main satellite receive the SAR radar data and mapping to reconstruct the data as SAR image data that can be reconstructed as 2D or 3D landscapes and scenes using the SAR image data.

The invention discloses a PCIe cross-version link capability mapping and transaction data reconstruction method, which comprises the following steps: link negotiation and physical layer opposite end simulation: a cross-generation PCIe bridging device simulates high-version equipment behavior training and establishes a first link between the cross-generation PCIe bridging device and a host, the cross-generation PCIe bridging device simulates behavior training of low-version equipment and establishes a second link between the cross-generation PCIe bridging device and the low-version equipment; data processing and transmission: the cross-generation PCIe bridging device processes data received from the host to adapt to and transmit the data to the low-version device, the cross-generation PCIe bridging device processes data received from the low-version device to adapt to and transmit the data to the host, the high version is a PCIe Gen6 protocol, and the low version is a PCIe Gen6 protocol. The low version is a PCIe (Peripheral Component Interconnect Express) Gen5 protocol or a PCIe Gen4 protocol.

The invention relates to a dynamic calibration method and device of a motion sensor for intelligent terminal equipment, and the method comprises the following steps: carrying out the real-time collection of a multi-source sensor on target intelligent terminal equipment through a multi-sensor fusion technology, and obtaining a multi-mode sensor data set; performing feature extraction on the multi-modal sensor data set to obtain a feature vector set; performing error mode recognition on the feature vector set to obtain a sensor error mode; performing error compensation on the multi-modal sensor data set based on the sensor error mode to obtain a compensated multi-modal sensor data set; and performing data reconstruction based on the compensated multi-modal sensor data set to obtain a reconstructed motion trail, thereby solving the technical problem that the measurement precision is reduced due to the fact that the traditional sensor data is often influenced by external interference and self-drift.

The invention relates to the technical field of ultrasonic detection, and discloses an ultrasonic scanning path optimization and three-dimensional reconstruction method, device, equipment and medium, and the method comprises the steps: positioning a key mark point of a target area, generating an initial scanning path, and controlling an ultrasonic probe to move along the initial scanning path to collect first ultrasonic image data, extracting target structure features to construct an initial three-dimensional point cloud model; establishing a surface projection model; fitting to generate a surface profile curve and calculating the tangential direction of a sampling point; optimizing the orientation of an ultrasonic probe based on the tangential direction to generate an optimized scanning path; and reconstructing a final three-dimensional model. According to the invention, through key mark point positioning and incident direction optimization based on the tangential direction, the scanning path of the probe is enabled to be adaptive to curvature change of the target area, and through combination of real-time contact force adjustment and multi-stage image data acquisition, three-dimensional point cloud space coverage and imaging consistency are improved, and high-precision three-dimensional reconstruction of a complex anatomical structure is realized.

The invention belongs to the technical field of point cloud semantic segmentation, and discloses a power corridor laser point cloud semantic segmentation method and system collected by an unmanned aerial vehicle, and the method comprises the steps: collecting laser point cloud and image data; reconstructing point cloud data based on the image data to obtain an image point cloud, performing spatial registration on the laser point cloud and the image point cloud, and projecting the registered laser point cloud onto the image; operating the image data to obtain a depth image and a normal image, and performing fusion operation on the depth image, the normal image, the image and the projected laser point cloud to obtain multimode fusion data; and carrying out two-dimensional semantic segmentation on the multi-mode fusion data, and carrying out back projection operation on a segmentation result to obtain a three-dimensional point cloud semantic segmentation result. According to the method, the visible light image of the power corridor and the laser point cloud data are fused, high-precision semantic segmentation of the laser point cloud is realized by using the appearance information contained in the visible light image, and the accuracy, efficiency and fineness of semantic segmentation of the laser point cloud of the power corridor are improved.

The invention relates to the technical field of data transmission, in particular to a supply chain data security sharing method and system based on the Internet of Things. The method comprises the following steps: collecting supply chain node transmission data, and constructing a node transmission trust prototype to obtain a trusted original visa unit set; performing path hierarchical verification based on the credible original visa unit set and supply chain node transmission data to obtain a chain control path authorization mapping structure; acquiring supply chain node sensing data, and fusing the sensing data to obtain supply chain node sensing data to be transmitted; executing data unit sovereign attribution deconstruction analysis on the to-be-transmitted supply chain node sensing data to generate a sovereign access instruction set; on-chain data reconstruction is executed based on the credible original visa unit and the sovereignty access instruction set, and a chain-level reconstruction data image is obtained; and verifying the chain-level reconstruction data image to generate a verifiable access image. According to the method, the structural integrity, the safety protection performance and the real-time performance of the supply chain data can be improved.

The invention discloses a turbofan engine compressor blade crack multi-modal monitoring system, and belongs to the field of multi-modal monitoring, and the system comprises a multi-modal acquisition module which obtains the multi-modal data of each compressor blade, carries out the dynamic filtering denoising and temperature compensation preprocessing, completes the time axis alignment, and carries out the data reconstruction and feature extraction; and constructing a multi-modal feature vector. And the triggering module carries out preliminary abnormality diagnosis according to the judgment result, judges whether the blade is abnormal or not through a key feature threshold, determines whether to trigger depth evaluation or not by combining a periodic threshold, identifies a potential crack blade and generates an excitation decision. And when an excitation decision is executed, the intelligent diagnosis module monitors the strain gradient change to perform excitation monitoring, compares the vibration characteristics of a potential crack blade with the vibration characteristics of a contrast blade, judges whether a crack exists or not, and realizes multi-stage early warning, so as to solve the problem that the crack of the turbofan engine compressor blade is difficult to quickly detect in real time in the prior art. And safe and stable operation of the engine is guaranteed.

The invention discloses a lithium battery health state estimation method and system based on partial charging curve reconstruction, and the method comprises the steps: carrying out the preprocessing and dividing of a lithium battery charging and discharging data set, obtaining a partial charging segment data set, training a partial charging data reconstruction model through the partial charging segment data set, and obtaining a partial charging data reconstruction model; and inputting the partial charging curve in the low correlation range into a partial charging data reconstruction model, reconstructing the partial charging curve into a high correlation curve, extracting health feature information, and inputting the extracted health feature information into a lithium battery health state estimation model based on Gaussian process regression for model training and testing. According to the method, the trained lithium battery health state estimation model is obtained, real-time and accurate evaluation can be provided for the health state of the lithium battery only by using charging fragment data with a relatively small length based on the trained partial charging data reconstruction model and the lithium battery health state estimation model, and a guarantee is provided for safe, stable and reliable operation of the lithium battery. The invention can be applied to the technical field of lithium batteries.

The invention relates to the technical field of brain-computer interfaces, and discloses an electroencephalogram-voice mixed interaction method, device and equipment based on a brain-computer AI earphone. The method comprises the following steps: acquiring a bimodal signal of the AI earphone, performing data classification and processing on the bimodal signal, and outputting a pure waveform after output time sequence information is purified; performing two-way analysis on the pure waveform and dividing feature dimensions, outputting a feature identifier to perform time sequence analysis so as to identify a key time sequence feature set, establishing an alignment feature mapping structure combination mode, then generating an association mode to execute path analysis, and marking a combination node output representation structure; performing hierarchical fusion on the representation structure, extracting a fusion region, and outputting fusion elements according to the fusion region; and carrying out missing supplementation on the fusion elements, positioning missing parts, carrying out data reconstruction, outputting complete contents, carrying out intention analysis to obtain key elements, converting the key elements into interaction information, outputting an interaction intention, generating an interaction command, and completing electroencephalogram-voice mixed interaction based on the brain-computer AI earphone.

The invention discloses an EDR-oriented traceability model and a method of a behavior chain preservation mechanism of the EDR-oriented traceability model. According to the method, traceability analysis of network attack behaviors is realized through functional modules such as data collection, threat detection, forensic analysis, archiving storage and attack traceability, and behavior chains are stored as electronic forensic evidences. The method comprises the following specific steps: collecting data such as system logs, operation logs and memory mirror images from terminal equipment through an EDR system and a GRR tool; a threat detection algorithm and MITRE ATTamp which are built in the EDR are utilized; the CK framework performs real-time behavior analysis, discovers potential threats and triggers a response; analyzing a memory mirror image and file data in combination with a third-party evidence obtaining tool, and reconstructing an attack behavior chain; through a hybrid mechanism of decentralized storage (IPFS) and local storage and a block chain technology, the integrity and non-tampering property of data are ensured; and finally, analyzing the relevance between the behavior chains by using an attack traceability module, and constructing a complete attack traceability graph. According to the method, the accuracy of attack behavior tracing and the security of data storage are effectively improved, the risk of data loss and tampering in a traditional tracing method is reduced, and powerful support is provided for subsequent network security event investigation and legal evidence obtaining.

The invention discloses a process monitoring method for an abnormal operation state in a safe water treatment process. The method comprises the following steps: firstly, segmenting original data from the dimension of time by adopting a sequential division method, and standardizing the interiors of blocks; then, a multi-scale feature extraction network is adopted to extract restrictive multi-scale spatio-temporal features from spatial dimensions by adding network function independence and information diversity constraints; and a deep stationary subspace network is established, and decoupling of stationary and non-stationary features is realized by applying difference constraints to network output features. And finally, constructing a process state change statistic by using the non-stationary features, performing data reconstruction by using the stationary features reflecting the process equilibrium state, constructing a statistic of a residual space, and completing process monitoring of the non-stationary process. According to the method, non-stationary faults influencing process safety and stationary faults caused by process mechanism abnormity can be effectively identified, and the method has high practical application value and effectiveness.

The invention provides a marine meteorological data quality control method based on a cross-parameter correlation network, which belongs to the technical field of marine meteorology, and comprises the following steps: constructing a cross-parameter correlation network model comprising an air temperature and air pressure correlation rule, a humidity and air temperature linear correlation rule and a wind speed and air pressure gradient extraction correlation rule; a sliding window algorithm is adopted to calculate a correlation coefficient in real time and identify correlation abnormity, a multivariate abnormity detection mechanism of four dimensions of parameter threshold overrun, spatio-temporal change rate abnormity, probability density distribution offset and correlation verification failure is established, a fuzzy comprehensive evaluation method is adopted to calculate a comprehensive abnormity index, and data abnormity is judged. And the authenticity of the abnormal data is confirmed in combination with a multi-sensor cross validation mechanism, and finally the abnormal data is restored by adopting a virtual sensor data reconstruction algorithm based on correlation network reverse calculation, so that the technical problem of poor abnormal data detection effect in the prior art is solved.

The invention relates to the field of integrated circuit and chip architecture design, and discloses a storage and calculation integrated chip dynamic reconstruction system supporting multi-precision hybrid calculation, which comprises a fuzzy precision sensing module, a heterogeneous multi-precision calculation array module, a data reconstruction distribution module, an energy consumption prediction control module, a multi-target intelligent scheduling module and a calculation storage mapping module, the system carries out modeling through precision analysis and computing power requirements, calls a heterogeneous array to carry out dynamic precision matching, completes rearrangement and multi-level storage mapping, carries out calculation and storage path joint optimization, evaluates a power consumption load in advance, and carries out balanced scheduling among performance, power consumption and resources through a multi-target scheduling module. Dynamic adaptation of tasks under different precisions, efficient data reconstruction and distribution, intelligent mapping of storage paths and energy consumption control can be achieved, the calculation efficiency and the energy efficiency ratio of the system under a multi-task heterogeneous load are improved, and the method is suitable for edge AI, embedded reasoning and other high-performance low-power-consumption application scenes.

The invention relates to an electric power system load fluctuation section data compression method based on compressed sensing, which is characterized by comprising the following steps of: 1, dividing an event section and a non-event section based on available load power consumption data; 2, dividing a non-event section into a fluctuation section and a stationary section; 3, performing compression processing on the fluctuation segment data extracted in the step 2 by adopting a compressed sensing-based data compression and reconstruction method; 4, reconstructing the original data of the fluctuation section data by adopting an optimized SAMP method; and 5, evaluating the reconstruction precision by taking the RMSE and the MPPE as evaluation indexes. According to the method, the data compression efficiency can be further improved while certain data reconstruction precision is ensured.

The invention provides an atmospheric temperature and humidity profile repairing method integrating a statistical method and a deep learning technology, belongs to the technical field of meteorological observation, and aims to solve the problem of large-area data missing caused by cloud pollution by taking an FY-4B satellite temperature and humidity profile product as a processing object. Data reconstruction is realized through a three-stage architecture of random cloud mask generation, statistical filling and pre-restoration, and deep learning and fine correction; according to the method, the problem of data truth value missing is solved, meanwhile, the advantages of a statistical method and a deep learning technology are combined, the repair precision in an extreme missing scene is remarkably improved while physical reasonability is guaranteed, and meanwhile the method has the advantages of being few in needed computing resources, high in computing speed and the like.