1093 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.

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 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.

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.

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 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 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 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 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.

The invention discloses a space-time adaptive power prediction system and method for distributed photovoltaic power generation in a mountainous area, and particularly relates to the technical field of fault prediction and health management. The method is used for solving the problem that the accuracy of power prediction and equipment health state evaluation is influenced by environment characteristic data reconstruction reference drift caused by equipment performance degradation in the prior art. A spatio-temporal data sequence is constructed by acquiring historical data of a photovoltaic unit, a spatio-temporal association network of generated power among equipment is constructed, performance stability of a reference equipment group is evaluated, and when the stability does not meet conditions, a performance attenuation spatio-temporal mode is analyzed to identify common features and personalized features. The propagation path of performance degradation on the space-time correlation network is analyzed based on the characteristics, a critical point is evaluated, reference correction is performed on the environment characteristic data by using the common characteristics and the critical point, and finally, the corrected environment characteristic data is used for executing power generation power prediction and equipment health state evaluation. Therefore, the prediction accuracy and the health management reliability are improved.

A correlation-aware adaptive codebook compaction system for multi-modal data compression that preserves cross-modal relationships while providing enhanced reconstruction quality. The system analyzes temporal and spatial relationships between different data modalities to generate correlation maps that guide compression decisions. A virtual management layer performs stream characterization and adaptive routing, while a processing pipeline implements primary codebook compression with mismatch handling for novel data blocks. High-entropy data segments receive pre-compression processing before codebook compression. Sequential registration data is processed through matrix factorization and dedicated matrix codebooks. The system continuously monitors data distribution characteristics and automatically retrains codebooks when drift thresholds are exceeded. A neural upsampling subsystem uses correlation information to guide cross-modal enhancement processes through modality-specific networks and attention mechanisms. The unified output includes compressed data streams, correlation maps, synchronization metadata, neural model parameters, and updated codebooks, enabling synchronized reconstruction with preserved cross-modal relationships and enhanced quality through correlation-guided neural upsampling.

The invention relates to the technical field of intelligent traffic, in particular to a dynamic road network collaborative capacity expansion decision-making system based on federated learning-digital twinning, which comprises the following steps of: calibrating pulse type and periodic type data flow weights through a dynamic weight distributor, and generating a normalized feature vector; fusing the normalized feature vectors of all the domains through a privacy protection aggregation engine to obtain a passenger flow pressure distribution prediction matrix; the reconstruction module is used for constructing a digital twinborn body based on the prediction matrix and initializing the digital twinborn body; and based on the initialized twinborn environment, recognizing and sensing a missing region through a blind area data reconstructor, and fusing historical features and real-time data streams of adjacent nodes by adopting a space-time correlation algorithm to reconstruct a complete road network state. According to the method, the dynamic road network collaborative expansion decision system is constructed by fusing federated learning and digital twinning technologies, and the expansion decision efficiency of the traffic road network is improved.

The invention discloses a satellite signal distortion compensation and data reconstruction method, system and device and a medium, and belongs to the technical field of satellite communication, and the method comprises the steps: obtaining and processing a satellite communication time domain signal, obtaining a time-frequency graph and a local feature vector, calculating the local feature vector through an encoder, obtaining a global feature, and carrying out the calculation of the global feature; splicing the global feature and the local feature vector to generate a fusion feature vector, and recovering the resolution of the time-frequency graph based on an end-to-end compensation network; and inputting a time-frequency graph and the fusion feature vector to obtain a phase compensation factor, compensating the time-frequency graph by using the phase compensation factor, reconstructing a time-domain signal through inverse short-time Fourier transform, splicing the fusion feature vector and a combined data type label, and inputting the spliced fusion feature vector and combined data type label into a trained neural network to realize semantic reconstruction. The method solves the problem of joint compensation of signal amplitude and phase, guarantees data integrity, gets rid of dependence on complex physical parameter estimation, and can quickly adapt to ionosphere change and multipath effect environment.

The invention discloses an efficient time sequence analysis method and device based on a convolutional neural network and a medium. Time sequence modeling analysis results for different downstream tasks are obtained through the steps of original data reading, sample standardization, adaptive time-frequency conversion, frequency domain component extraction and fitting, time domain data reconstruction and the like. In the time sequence analysis method, a time-frequency conversion and time domain data reconstruction step is realized through a dynamically adjustable wavelet analysis component, and a frequency domain data fitting step efficiently models distribution of frequency components in original data through a convolutional neural network with low time and space complexity. Raw data reading and sample standardization provide a starting point for time series analysis for different tasks. The method is based on data driving, has no special requirement for data, is high in universality, can maintain high modeling precision while greatly reducing time cost and hardware resource overhead, and has high theoretical property and practicability.

A federated system and method for data compression optimization in distributed device networks. The system comprises multiple edge devices that analyze local data patterns to generate device characteristic profiles while performing local compression optimization and maintaining data privacy. Edge devices contribute to collaborative learning by generating privacy-preserved updates without transmitting raw data. A central coordination system aggregates encrypted contributions using secure multi-party computation protocols, identifies device groups based on data pattern similarities, and generates optimized compression parameters for each group. The system coordinates collaborative training of data reconstruction models across device groups and deploys group-optimized reconstruction capabilities. Device grouping is performed by calculating similarity scores between device characteristic profiles and clustering devices with scores above predetermined thresholds. The system dynamically adapts compression and reconstruction parameters through federated learning while preserving individual device data privacy, enabling efficient data compression and near-lossless recovery across heterogeneous Internet-of-Things networks.

The invention discloses a smart city planning three-dimensional scene reconstruction optimization system combined with semantic segmentation, and belongs to the technical field of three-dimensional scene reconstruction optimization. The system comprises a data sensing module which collects aerial images and laser point clouds, and complements a sheltered area to obtain city modeling data; the preprocessing module performs denoising, data registration and data fusion on the city modeling data to generate texture point cloud data; the semantic understanding module realizes multi-modal semantic segmentation of the texture point cloud data through a fine-tuned SAM network and an improved RandLA-Net, and semantic tag data is obtained through restoration and optimization; the reconstruction optimization module constructs an initial three-dimensional grid model based on the texture point cloud data, and optimizes a ground feature boundary and a missing region of the model in combination with a semantic tag; and the output application module converts the optimized model into a standard format and outputs the model. Through deep coupling of semantic segmentation and reconstruction optimization, the precision of the three-dimensional scene model is improved, and reliable support is provided for smart city planning.

The invention relates to a DAS-VSP seismic data reconstruction method based on a multi-scale attention network, and belongs to a reconstruction method based on DAS-VSP missing data in a well. Comprising the following steps: constructing a vertical seismic profile data set, constructing and training a multi-scale attention network, and realizing seismic data reconstruction by using lacked-channel DAS-VSP data. The method has the advantages that a multi-scale network is adopted as a backbone network, potential feature information of different scales is dynamically extracted and fused from DAS-VSP data containing noise and missing, and the accuracy of a reconstruction result is enhanced; a local attention module is introduced, a network is focused on related features of DAS-VSP reconstruction signals through a self-attention mechanism, the reconstruction precision of data is improved, the performance defects of a traditional method are effectively overcome, the reconstruction precision is remarkably improved, a reliable basis is provided for follow-up analysis and explanation work of DAS-VSP data, and the method is suitable for popularization and application. And the recognition degree and the application value of the DAS-VSP technology in the field of oil-gas exploration are improved.

The invention discloses a spatial multi-omics data integration method based on graph attention and a multivariate loss function. Comprising the following steps that spatial multi-omics data and spatial position coordinates corresponding to the spatial multi-omics data are obtained, a preset spatial multi-omics data model is input, and the model comprises a graph attention encoder and a decoder; the spatial multi-omics data model constructs a graph structure according to spatial multi-omics data and spatial position coordinates, a graph attention encoder performs cell spatial multi-omics data fusion based on the constructed graph structure, and a decoder performs data reconstruction based on fused data to complete cell spatial multi-omics data integration; and constructing a multivariate loss function to carry out iterative optimization on the cell space multi-omics data integration process of the space multi-omics data model, and outputting an optimal cell space multi-omics data integration result. According to the method, the batch effect is solved, the smoothness of a final result in space and the accuracy of spatial analysis are improved, and the integration of multi-omics data of the cell space is realized.

The invention discloses a BIM (Building Information Modeling) lightweight and streaming rendering method and system, and the method comprises the steps: carrying out data separation, partitioning and simplification processing on an original BIM, and generating lightweight partitioned model data containing associated metadata; based on geometric features of each block in the lightweight block model data, adaptively determining a compression parameter and performing compression coding, and associatively storing the compressed block data and metadata; and according to a rendering request of a client, dynamically selecting to-be-transmitted block data based on the multi-dimensional evaluation model, transmitting the block data to the client in a streaming manner, and performing data reconstruction and rendering display by the client. Through collaborative optimization of fusion data separation, QEM simplification and Draco compression and in combination with intelligent streaming transmission based on a multi-dimensional evaluation model, high-fidelity and low-delay rendering of a large-scale BIM model at a Web end is realized.

The invention discloses a privacy protection evaluation method and a privacy protection evaluation device based on a diffusion model. The method comprises the following steps: acquiring a self gradient obtained by an attacker client in a federated learning system in a local training process and a global gradient after server aggregation; dynamically estimating gradient information of the damaged benign client based on gradient differences in historical communication rounds, and mapping the gradient differences into low-dimensional condition vectors through a condition encoder; injecting the low-dimensional condition vector into a noise prediction network of a diffusion model through a cross attention mechanism, driving the diffusion model to generate virtual data, and training in a local model by using the virtual data to obtain a forged gradient; and according to the similarity loss between the forged gradient and the estimated gradient, alternately optimizing the parameters of the diffusion model and the generated virtual data until the similarity loss converges. According to the method, the gradients of other clients can be fitted more accurately, and the accuracy and authenticity of data reconstruction are effectively enhanced by utilizing a multi-round gradient difference guide diffusion model.

The invention discloses a high-time-resolution flow field testing method and system based on sparse moment measured values and an intelligent power system, and belongs to the field of flow field testing and data reconstruction in bridge wind engineering. According to the method, overall low-frequency and local high-frequency sparse flow field data are obtained through a four-pulse fixed-frequency variable-frequency laser system and a four-exposure high-speed imaging PIV sampling system; a 32-dimensional nonlinear modal coefficient is extracted through a multi-scale convolution flow field sparse feature extraction model, then an unsampled time step coefficient is predicted through an LSTM intelligent power system model, and finally the unsampled time step coefficient is input into a multi-scale convolution auto-encoder to reconstruct a high-time-resolution flow field. The method does not need to depend on a pressure sequence, reduces the hardware and data processing cost through sparse sampling, accurately captures the flow field dynamics characteristics through intelligent modeling, solves the problems of expensive high-frequency hardware, loss of low-frequency reconstruction data and difficulty in model training in a traditional PIV test, and is suitable for flow field dynamics research and engineering optimization.

The invention discloses a raw coal quality data optimization and reconstruction method based on clean coal ash content feedback, and belongs to the technical field of computers. Data completion is achieved through the generative adversarial network; a generator predicts missing raw coal data according to the high-sampling-frequency clean coal ash content, and a discriminator evaluates the authenticity of the data. According to the method, the characteristic that the clean coal ash sampling rate is higher in the dense medium separation process is used for guiding data reconstruction; meanwhile, a composite loss function including adversarial loss, reconstruction loss and regression loss is designed, and the generation quality is improved. The method effectively solves the problem of raw coal quality data missing in the coal dressing process, and has high engineering application value.