Patents
Literature
64results about How to "Data augmentation" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Robot automatic navigation and homeward voyage method, device, equipment and storage medium
ActiveCN119311009Acapture comprehensiveaccurate captureVehicle position/course/altitude controlPosition/direction controlRobot environmentFeature extraction
The invention relates to the technical field of robot navigation, and discloses a robot automatic navigation and homeward voyage method, device and equipment and a storage medium, and the method comprises the steps: carrying out the multi-scale environment feature extraction of environment image data collected by a walking replacing robot, and obtaining environment feature data; constructing an initial navigation path; performing target detection and feature re-identification on the real-time environment image to obtain a real-time environment perception result; performing extended Kalman filtering fusion processing on the multi-sensor data to obtain robot-environment interaction state features; according to robot-environment interaction state characteristics, carrying out linear section and turning section trajectory analysis, and constructing a smooth navigation trajectory; continuously updating the environment characteristic data and the working state data of the walking-instead-of-walk robot in the navigation process, and constructing a dynamic environment map; and when a return flight signal is received, quickly planning an automatic return flight path based on the dynamic environment map. The autonomy and the working efficiency of the walking-replacing robot can be improved.
Owner:深圳市万德昌创新智能有限公司
Computer and television all-in-one machine control method, system and device
ActiveCN119620870Adata augmentationImprove viewing experienceInput/output for user-computer interactionCharacter and pattern recognitionComputer graphics (images)Element analysis
The invention relates to the technical field of computer television image communication, in particular to a computer television all-in-one machine control method, system and device. The method comprises the following steps: through multi-view image acquisition and processing, generating a three-dimensional scene grid and carrying out scene element analysis to form a scene element set, then chasing limbs of a user, generating a user limb image set, restoring an environment basic tone, obtaining display content of the all-in-one machine and carrying out content semantic analysis, and finally obtaining a user limb image set. Calculating interaction intensity to obtain content interaction intensity data, speculating a user body language and performing user intention prediction in combination with the interaction intensity data, adjusting display content of the all-in-one machine based on the predicted user operation intention, generating simulation adjustment content, performing composition optimization through a scene element set, and generating updated display content. The method for controlling the computer and television all-in-one machine is more accurate and more efficient.
Owner:SHENZHEN MEIJIA TECH CO LTD
Video saliency target detection method based on image annotation
ActiveCN119313885AReduce labeling costsdata augmentationImage analysisCharacter and pattern recognitionSalient objectsData set
The invention provides a video saliency target detection method based on image annotation. The method comprises the following steps: S1, establishing a training set and a test set; s2, constructing a progressive saliency target detection network; s3, training the progressive saliency target detection network by using the training set, and identifying video frames in the test set by using the coarse positioning network to generate a first space-time positioning tag; s4, acquiring adjacent frames of the video frame, and identifying the adjacent frames based on an adjacent frame difference method to generate a second space-time positioning tag; step S5, inputting the first space-time positioning tag and the second space-time positioning tag into a double-flow positioning network for positioning the video salient object; and S6, the attention sampler and the fine segmentation network are used to identify and segment the images corresponding to the video frames in sequence to obtain corresponding salient object positioning maps. The method has the beneficial effects that the marking cost of the video saliency target detection data set can be reduced, and adaptation to rich scenes is realized.
Owner:NINGBO UNIV
Unmanned aerial vehicle low-altitude visual angle target detection method and device based on deep learning
InactiveCN119580136AIncrease the number ofdata augmentationInternal combustion piston enginesCharacter and pattern recognitionData setVisual technology
The invention discloses an unmanned aerial vehicle low-altitude visual angle target detection method and device based on deep learning, and belongs to the technical field of computer vision. The method comprises the following steps: performing data enhancement on a collected target detection object image data set, and dividing the enhanced target detection object image data set into a training set, a verification set and a test set; an attention mechanism module is added in a backbone network of the YOLOV7-OBB model; the YOLOV7-OBB model is trained based on the training set, the YOLOV7-OBB model in the training process is evaluated based on the verification set, and the trained YOLOV7-OBB model is obtained; and inputting the test set into the trained YOLOV7-OBB model, and carrying out target detection to obtain a detection result. By enhancing a target detection object image data set and adding an attention mechanism module, the YOLOV7-OBB model fully learns key feature information of a target, and the detection precision and robustness are remarkably improved.
Owner:CHINA TELECOM UNMANNED TECHNOLOGY (JIANGSU) CO LTD
Fire smoke detection method based on improved YOLOv8 model
PendingCN119540714Aincrease diversityImprove sampling qualityInternal combustion piston enginesCharacter and pattern recognitionFeature extractionAlgorithm
The invention discloses a fire smoke detection method based on an improved YOLOv8 model, and the method comprises the steps: 1), replacing a Neck layer of the YOLOv8 model with a Gather-Distribate module, and adding a SimAM attention mechanism in front of an SPPF layer of a backbone network Backbone of the YOLOv8 model, and obtaining a fire smoke detection model; 2) iteratively training the fire smoke detection model by using a training set; and 3) inputting a to-be-identified fire smoke image into the trained fire smoke detection model to obtain a detection and identification result. The improved YOLOv8 model has strong generalization ability, improves multi-scale feature extraction ability, especially small targets in fire smoke, focuses network attention on the to-be-detected targets, reduces interference of uncorrelated backgrounds, and effectively improves the detection precision of the model.
Owner:QINGHAI UNIV OF SCI & TECH (UNDER PREPARATION)
Urban historical mountain landscape database construction method and platform based on GIS and BIM
ActiveCN119645959ASolve the accuracy problemdata augmentationGeographical information databasesDatabase design/maintainanceData graphEngineering
The invention discloses an urban historical mountain landscape database construction method and platform based on GIS and BIM. The method comprises the following steps: acquiring historical geographic information and historical surveying and mapping photography data of a target city; performing type division and attribute labeling on the spatial information of the target city based on historical geographic information through a GIS system platform, and generating a spatial information data total library; the GIS system platform and the BIM system platform are combined to carry out three-dimensional modeling on the building and mountain environment of the target city based on historical surveying and mapping photography data, and a total spatial model data library is generated; generating an associated data graph layer based on a GIS system platform for the target city; and constructing an urban historical mountain landscape database of the target city based on the spatial information data general library, the spatial information data general library and the associated data layer. According to the invention, three-dimensional modeling is carried out on the urban building and mountain environment by combining the GIS and the BIM system platform, and the modeling precision of the small and medium-sized building environment and the low mountain can be improved.
Owner:CHONGQING UNIV
A satellite image super-resolution method based on deep learning
ActiveCN114998101Beasy to refactorimprove fidelityImage enhancementImage analysisImaging processingImage resolution
The invention discloses a satellite image super-resolution method based on deep learning, which belongs to the field of image processing. The present invention builds an extensible deep super-resolution network, performs 4 times super-resolution on remote sensing satellite images, and can well reconstruct the characteristics of transmission line tower insulators, with the characteristics of high fidelity and fast processing speed; in order to improve the ability of the super-resolution network to learn the characteristics of remote sensing satellite images, further, a data augmentation method is adopted, and the weight normalization layer replaces the batch normalization layer to more accurately learn the characteristics of remote sensing satellite images; further, a jump-connected pixel reorganization and amplification module is introduced, which speeds up the calculation speed without a series of additional convolutions, and is well applied to power grid remote sensing image processing. It can be used for subsequent transmission line inspection, transmission line tower identification, insulator detection and other purposes.
Owner:BEIJING XINGHONG AEROSPACE TECHNOLOGY CO LTD
Dynamic simulation corrosion experiment device
ActiveCN222364895Udata augmentationimprove accuracyWeather/light/corrosion resistancePreparing sample for investigationClassical mechanicsMechanics
The utility model belongs to the field of experimental devices, and particularly relates to a dynamic simulation corrosion experimental device which comprises a bottom plate, the edge of the upper end of the bottom plate is fixedly connected with a plurality of guide sleeves which are uniformly distributed, the inner side of each guide sleeve is slidably connected with a limiting piece, the upper end of each limiting piece is fixedly connected with a guide rod, and the guide rod is fixedly connected with the bottom plate. The guide rod penetrates through the guide sleeve and is in sliding connection with the guide sleeve, and the middle section of a rod body of the guide rod is sleeved with a first spring. According to the utility model, the motor is arranged below the experiment barrel, the special-shaped rod is arranged on the output shaft of the motor, and the elastic supporting mechanism composed of the guide sleeve, the guide rod, the limiting piece and the spring is arranged between the experiment barrel and the bottom plate, so that the motor is utilized to drive the special-shaped rod to rotate, and the special-shaped rod rotates on the inclined plane ring; and then the experiment barrel can vibrate up and down in cooperation with the elastic supporting mechanism, so that whether the scale inhibitor or the corrosion inhibitor takes effect or not in a vibration environment is simulated, and the experiment accuracy is improved.
Owner:TIANJIN KEDASI IND CO LTD
Cross-modal matching method, system and equipment assisted by fused semantic generation
PendingCN119646534Aimprove understandingdata augmentationDigital data information retrievalCharacter and pattern recognitionPattern recognitionRadiology
The invention discloses a cross-modal matching method, a cross-modal matching system and cross-modal matching equipment assisted by fusion semantic generation, and particularly relates to the field of cross-modal matching, and the cross-modal matching method comprises the following steps: calculating a cross-modal similarity between an initial image and an initial text according to a text feature, an image feature, a text attention feature and an image attention feature; inputting the image features into a text decoder of a Transform model to obtain text generation features corresponding to the image features, and inputting the text features into an image decoder of the Transform model to obtain image generation features corresponding to the text features; utilizing a cross attention mechanism to calculate text modal internal similarity between the text generation features and the text features and image modal internal similarity between the image generation features and the image features; and constructing a matching judgment score based on the cross-modal similarity, the image intra-modal similarity and the text intra-modal similarity, and matching the initial image and the initial text based on the matching judgment score.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
An image stitching processing system based on feature matching
ActiveCN118864237BImprove generalization abilityImprove real-time performanceGeometric image transformationCharacter and pattern recognition
The technical field of image stitching system of the present invention particularly relates to an image stitching processing system based on feature matching, including a feature detection module, a feature matching module and a stitching seam processing module; the feature detection module is used to extract features of the image to be stitched; the feature matching module is used to determine the feature matching relationship between the images to be stitched; the stitching seam processing module uses the connecting line of the overlapping areas of the two images to be stitched as the stitching seam, and then fuses the stitching seam through the image fusion module. The deep learning method of this system replaces the traditional algorithm, and an efficient network model is obtained through training to detect image features; the feature detection network inputs the image to be stitched, and extracts features through a convolutional neural network. And this system can train the network in combination with the isomorphic adaptation mechanism, so that the network can enhance the data of the feature points and descriptors output by the feature detection network through self-supervision learning.
Owner:FUDAN UNIVERSITY
Construction method of human marrow paraffin tissue space transcriptome sequencing map
PendingCN119479790Aprecise definitiondata augmentationMicrobiological testing/measurementBiostatisticsMyeloid leukemiaPathology diagnosis
The invention discloses a method for constructing a human marrow paraffin tissue space transcriptome sequencing map, which comprises the following steps of: obtaining high-quality space transcriptome data from a marrow paraffin section of an AML (acute myeloid leukemia) patient, and then integrating the space transcriptome with scRNA-seq and histopathology. Relatively complete transcriptome information is still preserved after the bone marrow specimen is subjected to better decalcification treatment, and meanwhile, higher-quality slicing treatment can be performed on the embedded paraffin tissue, so that very complete bone marrow space transcriptome sequencing data is obtained. Then, the cell type of each detection site in the bone marrow space transcriptome map can be accurately defined by integrating bone marrow single cell sequencing data and pathological morphology annotations, and subsequent analysis is carried out.
Owner:THE FIRST AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
Data transmission control method and apparatus, computer-readable storage medium, computer device, and computer program product
Disclosed in the embodiments of the present application are a data transmission control method and apparatus, a computer-readable storage medium, a computer device, and a computer program product. The method is executed by a computer device, the method comprising: acquiring historical network performance data of each data transmission object of a plurality of data transmission objects, and calculating group network performance data of each object group of a plurality of object groups; performing weighted calculation on the group network performance data of each object group, so as to obtain overall network performance data of the plurality of data transmission objects; inputting the overall network performance data and the respective group network performance data of each object group into a trained reinforcement learning model to obtain a data transmission quality index of each object group; according to the data transmission quality indexes and the respective group network performance data of each object group, determining data transmission parameters of the object groups; and when receiving a data transmission request sent by any target data transmission object of the plurality of data transmission objects, according to an object group to which the target data transmission object belongs, determining a target data transmission parameter, and on the basis of target data transmission parameter, controlling a data transmission process corresponding to the data transmission request.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Audio data processing method and device, storage medium and electronic equipment
PendingCN119479685Aavoid misidentificationImprove recognition accuracySpeech analysisFrequency spectrumAudio frequency
The invention discloses an audio data processing method and device, a storage medium and electronic equipment. The method comprises the following steps: determining audio data required in a target model training process; determining a target spectrum based on the audio data; window division and splicing are carried out on the target spectrum to obtain a first feature sequence, the first feature sequence comprises a plurality of first features recorded according to a specified time sequence, and first overlapping data exist between two first features which are continuous in time; and determining audio features based on the first feature sequence. According to the method, window division and splicing are carried out on a target frequency spectrum to realize data enhancement of audio features, after data enhancement processing, long-sequence audio data are split into a plurality of data fragments with overlapped parts, multiple times of reasoning can be carried out, and the data fragments have relevance, so that the accuracy of reasoning is improved. Misrecognition caused by single reasoning of the target model can be effectively prevented, and the recognition accuracy of the target model is improved.
Owner:BEIJING JINGWEI HIRAIN TECH CO INC
Control cable comprehensive detection device based on multi-parameter fusion
PendingCN119245727AEasy to disassembleeasy to switchMeasurement apparatus componentsFault location by conductor typesControl engineeringStructural engineering
The invention relates to the technical field of control cable comprehensive detection, in particular to a control cable comprehensive detection device based on multi-parameter fusion, which comprises a bottom mounting seat, arc-shaped housings are movably assembled on two side walls of the bottom mounting seat, and communicated arc-shaped transition grooves are symmetrically formed in the inner side surfaces of the arc-shaped housings; and built-in electric control driving detection blocks are assembled in the arc-shaped transition grooves in the two sides of the bottom mounting seat in a staggered manner. According to the control cable comprehensive detection device based on multi-parameter fusion, the detachable structural design is adopted, so that the device can be conveniently assembled and disassembled, and different control cables can be conveniently switched; by adopting a two-side overturning and clamping mode, the assembling stability and firmness of the control cable are improved; and by means of the self-stabilization type structural design, the installation stability of the equipment can be improved.
Owner:GUANGDONG POWER GRID CO LTD DONGGUAN POWER SUPPLY BUREAU
Basket placing folding frame
ActiveCN222388729Udata augmentationImprove turnover rateDrawer-and-shell containersVehicle frameClassical mechanics
Owner:GENERAL HOSPITAL OF THE CENT WAR ZONE OF THE CHINESE PEOPLES LIBERATION ARMY
Image processing method, device, computer equipment and storage medium
ActiveCN110929730BImprove classification accuracyReduce the amount of parameter processingCharacter and pattern recognitionNeural learning methodsImaging processingEngineering
The present application relates to an image processing method, device, computer equipment and storage medium. The method comprises: obtaining an image to be classified; performing statistical processing on the image features of the image to be classified to obtain at least two image statistical features for the image to be classified; inputting the image statistical features into a pre-trained image classification neural network respectively; and determining the classification result for the image to be classified according to the output result of the pre-trained image classification neural network. The use of this method can improve the accuracy of image classification.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD
A method, system and medium for creating a text review model
ActiveCN113469212Bincrease diversitydata augmentationNatural language data processingData setEngineering
The present invention discloses a method, system and medium for creating a text audit model. The method comprises the following steps: setting a text data set to be audited, a word segmentation quantity threshold, a sensitive word library, a sample generator, a first classifier, a balance threshold and a second classifier; performing a negative sample generation operation to obtain a third training data set; performing a step of matching a numerical vector with a text vector to obtain a first article numerical vector; training the first article numerical vector, setting a score threshold in a first classifier, performing sample data screening, and obtaining a fourth training data set; training the fourth training data set to obtain a second classifier model, and performing a model optimization operation to obtain a text audit model; in the above manner, the present invention can expand the number of negative samples of different distributions through a sample generator, and expand the number of negative samples using a first classifier, so as to achieve a data enhancement effect.
Owner:SUZHOU MODUO INFORMATION TECH CO LTD
Data processing method of internet of things card, electronic equipment, storage medium and program product
ActiveCN119254479AAccurate monitoringdata augmentationSecuring communicationEntity typeLinguistic model
The embodiment of the invention provides a data processing method of an Internet of Things card, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring Internet of Things card data in a preset area in a preset statistical period; obtaining a first knowledge graph set and a second knowledge graph set according to the Internet of Things card data, a preset entity type and a preset attribute type; according to the first knowledge graph set and the second knowledge graph set, obtaining an entity pair set of data enhanced entity alignment; inputting a preset domain rule and the entity pair set into the large language model, and obtaining a target entity pair set output by the large language model; generating a plurality of knowledge graph communities according to the target entity pair set, monitoring the Internet of Things cards based on the knowledge graph communities to discover fraudulent Internet of Things cards, performing data enhancement when entity analysis is performed on knowledge graphs, and enabling the coverage range of risk communities to be more comprehensive through a large amount of enhanced data. Therefore, accurate monitoring of the Internet of Things card is realized.
Owner:CHINA UNITED NETWORK COMM GRP CO LTD +2
Data processing method, apparatus and system
A data processing method is provided, and the method includes: When performing iterative training on a first neural network deployed on a first edge device, a cloud-side device obtains a first training set based on an application scenario feature of data collected by the first edge device, obtains a trained first neural network based on the first training set and the first neural network deployed on the first edge device, and deploys the trained first neural network on the first edge device. The first training set obtained by the cloud-side device includes the data of the first edge device and sample data associated with the application scenario feature. In comparison with a limitation of sample data included in an incremental training set, the sample data for iterative training is added, and in comparison with broadness of sample data included in a full training set, data irrelevant to the application scenario feature is reduced. Therefore, data processing precision of an iteratively trained neural network is effectively improved.
Owner:HUAWEI TECH CO LTD
Method for calculating fire endurance of concrete filled steel tubular column in fire
InactiveCN119558092AImprove applicabilityimprove accuracyDesign optimisation/simulationComplex mathematical operationsCorrelation coefficientFire - disasters
The invention provides a method for calculating the fire endurance of a concrete filled steel tubular column in a fire disaster, which belongs to the technical field of safety risk assessment, and specifically comprises the following steps of: carrying out numeralization and normalization processing on collected literature data, analyzing an obtained data parameter group by adopting a Spearman correlation coefficient method, determining important parameters according to the correlation level, and calculating the fire endurance of the concrete filled steel tubular column in the fire disaster; according to the determined important parameter data, establishing a fire endurance prediction model, establishing a database, performing single-parameter analysis on the determined important parameters, and fitting a result to correct a calculation formula; the method has the beneficial effects that the calculation formula can more comprehensively reflect the fire resistance of an actual structure, so that the applicability and the accuracy of the formula are improved, the formula not only shows good applicability in different sample data, but also has relatively high calculation precision, and a reliable basis is provided for fire resistance design in actual engineering.
Owner:SHANDONG JIANZHU UNIV
Subtask-based image emotion mark distribution learning method
ActiveCN119580028Areduce dependenceImprove generalization abilityCharacter and pattern recognitionBiological modelsData miningLearning methods
The invention provides an image emotion mark distribution learning method based on subtasks, and aims to solve the problem that an existing mark distribution learning method based on auxiliary tasks depends on expert knowledge. The method comprises the steps of image emotion data collection, structured feature preprocessing, subtask mark distribution set construction, and a shallow / deep model-based learning method considering subtasks. Compared with the prior art, the method has the advantages that the sub-task mark space mask matrix is learned, the mark distribution is subdivided into the sub-task mark distribution, so that the pseudo supervision information containing new knowledge is generated, the sub-task mark distribution is constructed, the sub-task mark distribution is regarded as an auxiliary task for joint learning, and the prediction accuracy of the image emotion mark distribution is effectively improved. The method can be widely applied to the fields of mental health monitoring, emotion calculation, man-machine interaction and the like, and a reliable technical scheme is provided for complex emotion recognition.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Transfer learning method for solving multi-fidelity data fusion rigidity problem
InactiveCN119150708Adata augmentationBiological modelsDesign optimisation/simulationAlgorithmTheoretical computer science
The invention discloses a transfer learning method for solving a multi-fidelity data fusion rigidity problem, which aims to solve the rigidity problem existing in model training, and comprises the following steps: taking low-fidelity data in a multi-fidelity modeling method as a trainable parameter, and carrying out constraint by using a designed transfer path to establish an intermediate domain; the rigid phenomenon caused by obvious difference of high-fidelity data volume and low-fidelity data volume in the process of processing multi-source data fusion by a block type network framework is solved. An original migration task is divided into a multi-segment migration process, and a migration path is constrained by establishing a plurality of intermediate domains. According to the path, the model migration loss is at a minimum value, the model parameters are always in a stable state in the updating process, and data participating in migration module parameter updating are increased through establishment of the intermediate domain, so that the model can capture more data features.
Owner:CHINA AERODYNAMICS RES AND DEV CENT ULTRA-HIGH SPEED AERODYNAMICS RES INST
Blasting vibration peak velocity prediction method fusing parameter uncertainty and data driving optimization
PendingCN121960111AConfidence of prediction resultsFully reflect the true fluctuation characteristicsBiological modelsDesign optimisation/simulationOriginal dataEngineering
The invention provides a blasting vibration peak velocity prediction method fusing parameter uncertainty and data-driven optimization, which comprises the following steps of: firstly, acquiring data such as blasting parameters, lithologic indexes, geological conditions and actually measured vibration peak velocity (PPV), and establishing a basic database; a prior probability model is constructed, a joint uncertainty model is established in combination with probability disturbance and a fuzzy triangular number, a multi-dimensional disturbance sample is generated through a joint central value and a joint standard deviation and is fused with original data, and an extended database is formed. Feature analysis is carried out on the fused data, and input variables which have obvious influence on the vibration peak velocity (PPV) are screened; and constructing a BP neural network model based on the screened features, carrying out global optimization on a network weight and a threshold by adopting a PSO algorithm, and then carrying out local fine tuning by utilizing Adam. Finally, through training and verification, prediction of the vibration peak velocity (PPV) is realized, and model precision is evaluated through RMSE, MAE, MAPE, Rand other indexes. The influence of rock and soil parameter uncertainty on prediction precision can be effectively processed, and the reliability and applicability of blasting vibration prediction are improved.
Owner:CHINA THREE GORGES UNIV
WSI image preprocessing method and system
PendingCN119131790Aquality improvementimprove consistencyImage enhancementBiological modelsPattern recognitionComputation complexity
The invention provides a WSI image preprocessing method and system, and the method comprises the following steps: firstly, obtaining an original WSI image, and then carrying out the data processing and cutting of the original WSI image, and obtaining a plurality of WSI image blocks; according to the process, the workload of manual operation is effectively reduced, subjective errors are reduced, and the calculation complexity and memory consumption are remarkably reduced. And then, based on a PatchGAN algorithm, carrying out dyeing standardization on the WSI image blocks so as to ensure the consistency of image features and color distribution and realize a highly unified dyeing effect. The standardized processing can significantly reduce the influence of the dyeing difference between different laboratories on the performance of the model, and improve the generalization ability of the model. And finally, performing data enhancement on the standardized WSI image blocks, increasing the data volume and enhancing the robustness of the model, so that the model can better deal with image deformation and noise in practical application. Through the preprocessing system, the quality and the consistency of the WSI image are improved, reliable data support is provided for subsequent analysis and processing, and finally the accuracy and the effect of the whole pathological image analysis system are improved.
Owner:GUANGZHOU KUNYUAN FANGQING MEDICAL TECH CO LTD
Power transformation equipment local area defect generation method
InactiveCN119131527AConsider qualityTaking into account the integration consistencyBiological modelsInformation technology support systemPattern recognitionData set
The invention relates to a power transformation equipment local area defect generation method. The method comprises the following steps: determining a defect type possibly existing on each piece of target power transformation equipment; the method comprises the following steps: for any target power transformation equipment, acquiring a plurality of normal power transformation equipment images and a plurality of original defect images of the target power transformation equipment to obtain a defect-normal image data set; wherein the normal power transformation equipment image is an image of the target power transformation equipment in a normal state, and the original defect image is an image of any power transformation equipment containing at least one defect type; and training the original ADD-GAN model based on the plurality of defect-normal image data sets to obtain a trained ADD-GAN model, and the trained ADD-GAN model can generate a local defect equipment image according to a normal power transformation equipment image of any input power transformation equipment and an original defect image containing any defect type.
Owner:ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER
A method, apparatus, medium and electronic device for processing lead data
ActiveCN115712602BImprovement is time consuminghigh speedFile system administrationFile/folder operationsData storeComputational resource
Embodiments of the present application provide a method, device, medium and electronic equipment for processing lead data, the method comprising: storing process data corresponding to a first type of lead in a temporary partition, wherein the first type of lead belongs to an uncompleted lead, and the uncompleted lead is a lead that needs business tracking; monitoring each lead stored in the temporary partition, and deleting process data corresponding to a second type of lead from the temporary partition and storing the process data in a fixed partition, wherein the second type of lead is a completed lead, and the completed lead is a lead that does not need continued business tracking. Through the embodiments of the present application, the data processing amount can be effectively reduced by monitoring the leads in the temporary partition, thereby saving the computing time and computing resources wasted by the join association operation of massive data.
Owner:LINGXI TECHNOLOGY CO LTD
Special-shaped steel member measuring device and measuring method
PendingCN119533235Adesign scienceReasonable structureMechanical measuring arrangementsReinforced concreteMeasurement device
The invention discloses a special-shaped steel member measuring device and measuring method, and belongs to the technical field of building construction, and the special-shaped steel member measuring device comprises a reinforced concrete bearing platform, a steel platform, a track, a sliding block, a fixed base, a bidirectional vernier sliding block, an X-direction calibrated scale, a Y-direction calibrated scale and a Z-direction calibrated scale. The measuring device is scientific in design, reasonable in structure, easy to manufacture and convenient to operate, the graduated scales in the three directions are arranged through the X axis, the Y axis and the Z axis which are perpendicular to one another, numerical values corresponding to measuring points can be accurately displayed finally through respective sliding adjustment, and X, Y and Z three-dimensional coordinates are represented. Compared with the prior art, the measuring device provided by the invention solves the problems that the measuring difficulty is high, the operation is complicated, the measuring efficiency is low and the measuring precision is not easy to control when a traditional measuring method is adopted for the special-shaped steel member; according to the measuring device, the purposes of convenience, rapidness, accurate data and high measuring efficiency during measurement of the boundary dimension and the shape of the special-shaped steel member are achieved.
Owner:SHANXI WUJIAN GRP CO LTD
Structural health monitoring emergency abnormal data diagnosis method based on hierarchical network
ActiveCN119445112AEfficient identificationImprove fault toleranceCharacter and pattern recognitionNeural learning methodsMedicineStructural health monitoring
The invention discloses a structural health monitoring emergency abnormal data diagnosis method based on a hierarchical network, belongs to the technical field of machine learning and health monitoring, and particularly relates to recognition of emergencies in structural health monitoring. The problems that in an existing sensor monitoring data analysis technology, emergency data and abnormal data cannot be accurately distinguished, intrinsic characteristics of a detected object are lost due to the fact that internal connection between sensor data is neglected, and then emergencies cannot be accurately recognized are solved. The method comprises the following steps: inputting an image sample set into an emergency and abnormal data classification and identification network to obtain an emergency and abnormal data classification and identification result. The structural health monitoring emergency abnormal data diagnosis method based on the hierarchical network is suitable for identifying emergency data mixed with various abnormal data types.
Owner:HARBIN INST OF TECH
Automatic analysis device
Provided is an automatic analysis device capable of detecting an abnormality in pipes of two or more systems while avoiding a drop in abnormality detection accuracy, an increase in data volume, an increase in device size, and higher costs. The automatic analysis device has an A-system 35 and a B-system 36 which are mutually independent. The A-system 35 and the B-system 36 individually include an A-side two-way solenoid valve 101 and a B-side two-way solenoid valve 102 such that aspiration states are individually controlled. A determination part 103 detects an abnormality of the automatic analysis device by comparing pressure measurement values in the aspiration that pertain to the A-system 35 and the B-system 36, based on pressure measurement values of a reagent probe cleaning tank-side vacuum tank 87 measured by a reagent probe cleaning tank-side pressure sensor 71.
Owner:HITACHI HIGH TECH CORP
Concrete pavement damage detection equipment
ActiveCN222506016UEasy to testdata augmentationMaterial strength using tensile/compressive forcesGear wheelArchitectural engineering
The utility model relates to the technical field of concrete pavement detection for housing construction, and discloses concrete pavement damage detection equipment which comprises a device shell, driving motors are fixedly connected to the two parts of the right side of the front end of the device shell, worms are fixedly connected to the driving ends of the driving motors, worm wheels are connected to the outer walls of the opposite ends of the worms in a meshed mode, and the worm wheels are fixedly connected to the worm wheels. The rear end of the worm gear is fixedly connected with a transmission rod, the rear end of the transmission rod is fixedly connected with a transmission gear, the outer wall of the transmission gear is in meshed connection with a rack plate, the left end of the rack plate is fixedly connected with a connecting frame, the inner wall of the connecting frame is connected with a simulation roller through a replacement assembly, and the rear end of the connecting frame is slidably connected with an auxiliary sliding rod. According to the utility model, the device can be conveniently tested by the simulation rollers with more diameters, the test data of the cement board is increased, the stability of the cement board during detection is improved, and errors caused by movement or shaking of equipment are reduced.
Owner:SICHUAN SIZHENG CONSTR ENG QUALITY TESTING CO LTD