Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

527results about How to "Lower acquisition costs" patented technology

Fault root cause analysis method based on multi-source equipment data fusion

The invention discloses a fault root cause analysis method based on multi-source equipment data fusion. According to the method, multi-source heterogeneous data such as equipment operation data, maintenance records and environment data are collected and efficiently fused, a fault mode is automatically recognized from fused data, and time sequence evolution characteristics related to faults are mined. And based on the established knowledge base of the fault modes and reasons, and in combination with interactive Bayesian network reasoning and manual feedback, the root cause of the fault is deduced. According to the method, innovative technologies such as active learning and transfer learning are introduced, and the intelligent level, accuracy and efficiency of fault diagnosis are improved. And a visual interface visually presents an analysis process, supports man-machine interaction correction, and enhances interpretability. The method is suitable for the fields of industrial equipment, transportation tools, medical equipment and the like, and the system stability and usability are improved.
Owner:SHENHUA HOLLYSYS INFORMATION TECH CO LTD

Data asset management method based on knowledge graph

The invention discloses a data asset management method based on a knowledge graph, and relates to the technical field of data processing and data management.The data asset management method based on the knowledge graph comprises the steps of data collection and preprocessing, knowledge graph construction, data source integration, data asset management and intelligent recommending.The data asset management method based on the knowledge graph has remarkable advantages; comprising the steps of improving the utilization rate and safety of data assets, simplifying the management process of the data assets, reducing the management cost, and supporting intelligent decision and good expandability and customizability. The method is suitable for various scenes needing to manage a large amount of data, and an efficient and intelligent data asset management solution is provided for enterprises.
Owner:GUANGXI POWER GRID CORP

Cross-modal different-source image matching method based on unsupervised domain adaptation

The invention provides a cross-modal different-source image matching method based on unsupervised domain adaptation, and aims to solve the problem that an existing deep learning method depends on target domain annotation data in cross-modal remote sensing image matching. The conversion of a source domain image and a target domain image is realized through a style migration technology, and domain offset between the source domain image and the target domain image is reduced by using adversarial learning. According to the method, a source domain (with labels) and a target domain (without labels) are aligned from two angles of images and features, knowledge migration is realized, and a matching task in the target domain is solved. The technology fuses unsupervised domain adaptation, focuses on cross-modal different-source image matching, effectively reduces the demand of target domain annotation data, and is of great significance to practical application. Transition from labeled data to unlabeled data is promoted, high-precision target scene image matching is achieved, a new thought is provided for solving the data labeling problem, and the method is expected to be widely applied to various remote sensing image processing scenes.
Owner:SOUTHWEST JIAOTONG UNIV

Vehicle end visual angle accident scene restoration method based on automobile data recorder video

The invention belongs to the technical field of autonomous vehicles, and particularly relates to a vehicle end visual angle accident scene restoration method based on an automobile data recorder video. Comprising the following steps: step 1, preprocessing an accident video; 2, performing semantic understanding on the scene; step 3, extracting pixel tracks of the traffic participants; step 4, carrying out joint calibration on the inverse perspective mapping parameters; 5, carrying out inverse perspective transformation; step 6, carrying out post-processing on the road contour and track data; for accident video data with unknown and different camera parameters and lack of multi-source synchronization information, the invention provides a vehicle-end visual angle accident scene restoration framework taking a camera inverse perspective mapping parameter joint calibration strategy as a core. Scene space-time information including a road contour and a traffic participant track can be extracted from an automobile data recorder video without any prior information support, accident scene data is established for testing an automatic driving automobile, and the testing process of the automatic driving automobile can be effectively improved.
Owner:JILIN UNIVERSITY

Multi-point in-situ detection device for nitrous acid and nitric oxide

The invention relates to the technical field of air detection, in particular to a multi-point in-situ detection device for nitrous acid and nitric oxide, which comprises a split-flow collection pipeline, a multi-section extractor, an aspirator pump, a cleaning circulation pipeline and circulating cleaning equipment, the split-flow collection pipeline is mounted in a collection area, and is provided with a plurality of collection ends distributed in different collection areas; the multi-section extractor is installed at the output end of the split-flow collection pipeline, the interior of the multi-section extractor is connected with the nitrous acid detector and the nitric oxide detector, and the gas suction pump is connected with the split-flow collection pipeline and used for sucking gas in the split-flow collection pipeline; the cleaning circulation pipeline is installed above the flow dividing and collecting pipeline, the cleaning circulation pipeline is provided with a plurality of liquid outlet ends, and the liquid outlet ends of the cleaning circulation pipeline are communicated with the flow dividing and collecting pipeline; the input end of the circulating cleaning equipment is communicated with the split-flow collection pipeline, and the output end of the circulating cleaning equipment is connected with the cleaning circulation pipeline. The detection efficiency can be effectively improved, and meanwhile, the detection cost is reduced.
Owner:NORTHEAST INST OF GEOGRAPHY & AGRIECOLOGY C A S

Visual defect detection method and system based on context example learning

The invention provides a visual defect detection method and system based on context example learning, and relates to the field of power equipment detection.The method comprises the steps that on the basis of a power equipment image, text description of the power equipment image is generated through a large model; inputting the image and the text description of the power equipment into a trained anomaly detection network, judging the running state of the power equipment, and obtaining a detection result of whether the power equipment is abnormal or not; wherein the anomaly detection network takes a query image and a text description thereof as well as a plurality of sample images and text descriptions thereof of the same equipment as input during each training, and performs judgment by comparing image-text features of the query image and image-text features of the sample images; learning whether a query image is abnormal or normal under the condition of a given context example; according to the method, the multi-mode learning capability of a large model is combined, and the visual defects of the power equipment are efficiently detected through context example input of images and texts.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY

Video virtual fitting framework in real scene based on controllable image diffusion model

The invention discloses a video virtual fitting framework in a real scene based on a controllable image diffusion model. The video virtual fitting framework comprises a data preprocessing module used for constructing feature expressions of figures and clothes; the single-stage image fitting network is used for generating a virtual fitting image based on the preprocessed data and performing implicit deformation and fusion of clothes by using a cross attention mechanism; the diffusion guiding module is used for enhancing the time sequence consistency of the generated video, a self-supervision model Video MAE and a self-supervision image model DINO-V2 are introduced, the video is masked by the self-supervision model Video MAE, and a complete video is reconstructed through inter-frame information; and the long video generation module is used for generating a long video and keeping the consistency of the video, splitting the complete video into a plurality of short video clips, and reducing the jitter at the clip joints by using a time sequence common noise reduction strategy. The diffusion guiding module is designed, efficient time sequence consistent video virtual fitting is achieved through self-supervised learning, and the method has the advantages of being excellent in shielding processing, stable in long video generation and the like.
Owner:TUOYUAN (GUANGZHOU) SMART TECH CO LTD

Premature delivery prediction method and device, electronic equipment and readable storage medium

The invention provides a premature delivery prediction method and device, electronic equipment and a readable storage medium, and relates to the technical field of data analysis. The method comprises the following steps: based on a preset model, scoring acquired comprehensive information of a pregnant woman in an early pregnancy stage; wherein the comprehensive information comprises demographic information, clinical information and biochemical index information; and predicting the premature delivery risk of the pregnant woman according to the scoring result. According to the method, the comprehensive information of the pregnant women at the early pregnancy stage is scored through the preset model, the premature delivery risk of the pregnant women is predicted according to the scoring result, quantitative evaluation of premature delivery risk prediction of the pregnant women at the early pregnancy stage is achieved, and objectivity and certain accuracy are achieved; and the difficulty and the cost of obtaining the comprehensive information of the pregnant women in the early pregnancy are relatively low, the difficulty and the cost of predicting the premature delivery risk of the pregnant women in the early pregnancy are reduced, and medical resources are saved.
Owner:NINGBO UNIV

Pit digging device for tree planting

The invention relates to the technical field of tree planting, in particular to a pit digging device for tree planting, which comprises a vehicle body, a guide frame, a lifting plate, a soil taking guide rod, a soil taking spring, a soil collecting frame, a soil collecting cylinder and the like, a guide frame is fixedly connected to the vehicle body, a lifting plate is slidably connected to the guide frame, a spiral drill rod is rotatably connected to the lifting plate, a main motor used for driving the spiral drill rod is fixedly connected to the lifting plate, a soil taking guide rod is slidably connected to the lifting plate, a soil collecting frame and a soil collecting box are fixedly connected to the soil taking guide rod, and the soil collecting frame is communicated with the soil collecting box. A soil collecting barrel is fixedly connected to the soil collecting frame and used for guiding soil so that the spiral drill rod can lift the soil upwards into the soil collecting frame. According to the device, dug soil can be collected into the soil collecting box, and when a next pit is dug, the backfilling mechanism can backfill the collected soil into a previous pit, so that the backfilling of the previous pit is realized in the pit digging process, the physical labor of workers is reduced, and the tree planting efficiency is improved.
Owner:HENAN RUIHUA GARDEN ENG CO LTD

Building detection method, device and equipment based on remote sensing image and laser point cloud

ActiveCN119671960AImprove the efficiency of settlement detectionEasy extractionImage enhancementImage analysisPoint cloudEngineering
The embodiment of the invention discloses a building detection method, device and equipment based on a remote sensing image and a laser point cloud. A specific embodiment of the method comprises the following steps: carrying out single building segmentation processing on a building remote sensing image; for each building segmentation remote sensing image in the building segmentation remote sensing image group, the following processing steps are executed: an image edge node coordinate sequence and surface elevation information of the building segmentation remote sensing image are determined, and each edge node coordinate in the edge node coordinate sequence represents a key node of the building segmentation remote sensing image; extracting single building point cloud data corresponding to the building segmentation remote sensing image from the laser point cloud information; and generating building detection information according to the single building point cloud data and the corresponding standard building three-dimensional data. According to the embodiment, the building area edge detection precision and the building detection efficiency are improved.
Owner:CHINA SOUTHERN POWER GRID NEW ENERGY DESIGN RESEARCH INSTITUTE (GUANGDONG) CO LTD

Malicious code intelligent detection method and system based on large language model

The invention belongs to the technical field of network security, and aims to provide an intelligent malicious code detection method and system based on a large language model. The method comprises the following steps: acquiring a pre-trained large language model, and taking the pre-trained large language model as an initial malicious code detection model; acquiring a malicious code detection sample task to perform parameter fine tuning on the initial malicious code detection model to obtain a fine-tuned malicious code detection model; acquiring a specified prompt template to finely adjust the fine-adjusted malicious code detection model to obtain a final malicious code detection model; and acquiring a to-be-detected malicious code and additional information thereof, and constructing according to the to-be-detected malicious code and the additional information thereof to obtain a malicious code detection task so as to obtain a malicious code detection result matched with the to-be-detected malicious code according to the final malicious code detection model. According to the method, the malicious code detection cost can be reduced, real-time detection of network attacks can be realized, and the detection rate is higher.
Owner:SICHUAN UNIV +1

Multipath channel parameter reconstruction and beam coverage prediction method

PendingCN121966764AHigh physical fidelityOvercoming the problem of high coherenceSpatial transmit diversityTransmission monitoringAlgorithmChannel parameter
The invention discloses a multipath channel parameter reconstruction and beam coverage prediction method, and relates to the technical field of wireless communication. Aiming at the problems of low data utilization efficiency, limited environment modeling precision, strong coupling of measured data and antenna beam configuration and the like in the prior art, the method comprises the steps of configuring antenna beams and orientation parameters, collecting reference signal receiving strength, performing deterministic channel modeling simulation, establishing a mapping model, performing sparse recovery, constructing a channel propagation model, evaluating a channel map and the like. In combination with a coherence perception weighting network (CARE-Net) algorithm and ray tracing (RT) physical prior guidance, accurate reconstruction from a low-dimensional reference signal receiving strength (RSRP) measurement value to a high-dimensional multipath parameter is realized. The method has the advantages that the reconstructed multi-path parameters are decoupled from the antenna configuration, the method has the cross-beam / cross-configuration generalization prediction capability, the channel coverage performance under different antenna configurations can be accurately predicted, a reliable basis is provided for wireless network optimization, and the method is low in cost, high in precision and strong in generalization.
Owner:XIAMEN UNIV

Food packaging bag printing machine

The present invention relates to the field of packaging bag printing, and in particular to a food packaging bag printing machine, which specifically includes: a frame, on which a printing platform is arranged; a fixed frame, which is arranged on one side of the frame, and a mounting plate extends from one side of the fixed frame; a driving shaft, with a bearing connected to the mounting plate; a bevel gear, which is fixedly connected to one end of the driving shaft; a transmission belt, which is connected to one end of the driving shaft; and a stepping motor, which is connected to the transmission belt. A plurality of positioning seats are arranged around the center of the bevel gear and are hinged to the bevel gear; a plurality of printing components are respectively arranged on one side of the positioning seat; when the stepping motor drives the driving shaft to rotate step by step, the bevel gear is driven to rotate step by step, and the printing components with different colors of ink are switched. The present invention has the following beneficial effects: this food packaging bag printing machine can achieve multi-color printing through a single silk screen printing device, reduce the use area, and reduce costs.
Owner:温州德龙包装制品有限公司

A multi-UAV-multi-truck collaborative logistics distribution path planning method

The present invention discloses a multi-drone-multi-truck collaborative logistics distribution path planning method, which belongs to the field of drone logistics technology. It includes the following steps: Step 1: Establish a mixed integer linear programming model for the multi-drone-multi-truck collaborative logistics distribution path planning problem; Step 2: Perform initial planning of the truck distribution path based on the K-Means algorithm and the genetic algorithm; Step 3: Design a path planning search operator, introduce a variable neighborhood search framework on the basis of the truck distribution route to jointly optimize the distribution paths of drones and trucks, and solve the constructed mixed integer linear programming model. The method provided by the present invention takes into account the different purchase costs of trucks and drones, reasonably optimizes the purchase quantity and use quantity of transportation tools, effectively reduces the total distribution cost, further optimizes the drone-truck distribution plan, and makes up for the shortcomings of the existing joint distribution models and methods.
Owner:ZHEJIANG JIANDE GENERAL AVIATION RES INST +2

Model training method and device, electronic equipment, medium and program product

The embodiment of the invention discloses a model training method and device, electronic equipment, a medium and a program product, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. According to the embodiment of the invention, a training sample set is obtained, wherein the training sample set comprises an initial sample text corresponding to an initial scene and a newly-added sample text corresponding to a newly-added scene; translating the initial sample text through a teacher model to obtain a teacher translation result; translating the initial sample text and the newly added sample text through an initial student model to obtain a student translation result; calculating a loss value by combining the teacher translation result and the student translation result; and on the basis of the loss value, updating model parameters of the initial student model to obtain a trained student model, so that the trained student model is used for translating the to-be-translated text corresponding to the initial scene and the newly-added scene. Therefore, according to the scheme, the multi-scene adaptive capacity of the model can be enhanced while the model training efficiency is improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD +1

Processing method and device for generating electron microscope graph big data set

The embodiment of the invention relates to a processing method and device for generating an electron microscope graph big data set. The method comprises the following steps: constructing a first data set; taking the first-class visual semantic segmentation large model as a first segmentation model, and taking the SDXL model as a first generation model; performing fine adjustment on the first segmentation model according to the first data set, and then performing fine adjustment on the first generation model according to the first data set and the first segmentation model; constructing a first simulation semantic segmentation image library; and performing simulation electron microscope graph generation processing by a first generation model according to the first simulation semantic segmentation graph library, forming a second data record by each first simulation electron microscope graph and the corresponding first simulation semantic segmentation graph, and forming an electron microscope graph big data set by all the obtained second data records. According to the invention, a large number of electron micrographs can be automatically generated without the help of any manpower or external resources, and the data preparation difficulty of the electron micrograph big data set is reduced.
Owner:BEIJING DP TECH CO LTD

Remote sporadic instrument data acquisition system

The utility model relates to the technical field of data acquisition, and discloses a remote sporadic instrument data acquisition system, which comprises a remote station instrument, an instrument cable, a first serial port to optical fiber converter, a converter optical cable, a second serial port to optical fiber converter, a connecting cable and an industrial control computer, the instrument cable is electrically connected with a first serial port to optical fiber converter, the first serial port to optical fiber converter is electrically connected with a converter optical cable, the converter optical cable is electrically connected with a second serial port to optical fiber converter, and the second serial port to optical fiber converter is electrically connected with a connecting cable. The utility model has the beneficial effects that the signal transmission of the device does not depend on communication operators completely, the device can be suitable for all application occasions, such as ocean platforms, deserts and other areas which are rarely popular and have no operator signal towers, the direct connection stability of cables or optical cables is good, and the acquisition cost of on-site measuring instruments and central control room terminal equipment can be reduced.
Owner:HUBEI YISI NEW MATERIALS CO LTD

Data processing method and device based on SaaS platform, equipment and storage medium

The invention relates to the technical field of data processing, and provides a data processing method and device based on an SaaS platform and a storage medium, and the method comprises the steps: collecting data from different data sources through a unified data collection interface provided by the SaaS platform; automatically identifying and converting data acquired from different data sources to obtain target format data; storing the target format data to a cloud database by adopting a distributed storage scheme; analyzing the target format data stored in the cloud database based on a configurable data processing pipeline provided by the SaaS platform; and displaying the analysis result of the target format data to a user in a visual mode. According to the technical scheme provided by the invention, data with relatively large data volume can be flexibly and efficiently processed at low cost.
Owner:深圳市青云端信息科技有限公司

Grouting diffusion prediction method, equipment and medium

The invention relates to the technical field of grouting diffusion, in particular to a grouting diffusion prediction method and device and a medium. Comprising the steps that a COMSOL grouting model is constructed, the model is initialized, and grid division is carried out; performing grouting simulation to obtain a first grout volume fraction; all grout volume fractions in the grouting range are exported, normalization processing is carried out to obtain a first data set, and the first data set is divided into a training set and a test set; constructing a plurality of neural network models, training by using the training set, and testing by using the testing set to obtain a corresponding slurry volume fraction; calculating an average absolute error value and a root-mean-square error value between each slurry volume fraction and the first slurry volume fraction, and selecting an optimal neural network model; and obtaining a to-be-measured data set, inputting the optimal neural network model to obtain a second slurry volume fraction, and obtaining the grouting diffusion condition based on the second slurry volume fraction. Therefore, the problems that an existing grouting prediction technology is high in cost, low in precision and narrow in application range are solved.
Owner:GUIZHOU UNIV

Multifunctional mini-tiller

The invention relates to the technical field of farming machinery, in particular to a multifunctional mini-tiller which comprises a rotary tillage tool bit and a switching mechanism, the rotary tillage tool bit is rotationally installed on a machine body and comprises a driving shaft and two rotary tillage tool sets, the driving shaft is in transmission connection with an engine, and the rotary tillage tool sets are symmetrically installed at the two ends of the driving shaft; the rotary blade group comprises a plurality of blades which are arranged in the annular direction of the driving shaft, handle parts of the blades are provided with inserting grooves, the switching mechanism comprises a plurality of limiting parts which are arranged corresponding to the blades, when the limiting parts are inserted into the corresponding inserting grooves, the corresponding blades are locked for rotary tillage work, and when the limiting parts are separated from the inserting grooves, the corresponding blades are adjusted in a floating mode. According to the invention, through the cooperation of the rotary tillage tool bit and the switching mechanism, the effect of flexibly adjusting the working state of the blade under different working conditions is achieved, the obstacle is effectively avoided, the damage risk of equipment is reduced, the maintenance cost and the downtime are reduced, and meanwhile, the safety of operators is also ensured.
Owner:TAIZHOU KUNSHAN MECHANICAL & ELECTRICAL CO LTD

Vehicle overall dimension measuring method

The invention relates to the technical field of vehicle detection, and particularly discloses a vehicle overall dimension measurement method. The method comprises the following steps: 1, respectively installing a left laser radar and a right laser radar on two sides of a detection area where a vehicle runs, 2, unifying point cloud data sets collected by the left laser radar and the right laser radar to the same coordinate, and denoising the point cloud data according to a set threshold range to obtain a left point cloud data set L and a right point cloud data set R; 3, subtracting the X coordinate of the R from the X coordinate of the L to obtain the width of the vehicle; obtaining a Z coordinate value from the data set R or L to obtain the height of the vehicle; 4, detecting the time T1 and T2 of the vehicle entering and exiting the detection area through the left laser radar and the right laser radar; the photoelectric switch array measures the average speed V of the vehicle, and the vehicle length is obtained through calculation according to a formula; and 5, measuring the wheelbase of the vehicle through the photoelectric switch array. The objective of the invention is to solve the problems that three laser radars are adopted to measure the overall dimension of a vehicle, the required vehicle site is large, and the equipment cost is high.
Owner:GUIZHOU XIAOCHENG IND DEVELOPMENT CO LTD

Seam network complexity determination method and device and nonvolatile storage medium

The invention discloses a seam network complexity determination method and device and a nonvolatile storage medium. The method comprises the steps that geomechanical parameters corresponding to a fracturing section are determined; fracturing transformation parameters and oil and gas productivity corresponding to the fracturing section are obtained, and the fracturing transformation parameters are parameters used for conducting fracturing treatment on the fracturing section to obtain oil and gas output; and based on the geomechanical parameters, the fracturing transformation parameters and the oil and gas productivity, the fracture network complexity in the fracturing section is determined. According to the invention, the technical problem of high time and material resource cost caused by high limitation and low universality of obtaining the complexity of the seam network in the prior art is solved.
Owner:PETROCHINA CO LTD

Brain perfusion parameter acquisition method and device based on radiography, equipment and medium

The invention provides a brain perfusion parameter acquisition method and device based on angiography, equipment and a medium. The method comprises the following steps: acquiring a cerebral angiography image, segmenting a target blood vessel image from the cerebral angiography image, and extracting a plurality of radiomics data features and cerebral vessel anatomical data features from the target blood vessel image; screening the plurality of image omics data features according to the correlation coefficients of the plurality of image omics data features to obtain a target image omics data feature; inputting the target radiomics data features as a pre-trained classification model, outputting a prediction result of brain perfusion parameters, and constructing a final parameter set according to the anatomical data features and the prediction result; by adopting the method, the brain perfusion parameter acquisition efficiency can be improved, and the acquisition cost is reduced.
Owner:GUANGDONG GENERAL HOSPITAL

Method and equipment for finely disassembling square shell or blade type single battery

The invention relates to the technical field of battery recycling, in particular to a fine disassembling method and equipment for a square shell or blade type single battery. The method comprises the following steps: vertically stacking a plurality of batteries to obtain a stacked body, wherein battery terminals in the stacked body are positioned at the longitudinal end part of the stacked body; conveying the stacked body to a saw cutting station, and cutting the two longitudinal ends of the stacked body by adopting a saw blade so as to cut off the two end surfaces of all the battery shells and the battery terminals of the whole stacked body together; the stacked body is conveyed to a laser cutting station, at least one transverse side face of the stacked body is cut through a laser cutting device, and a fracture penetrating through the longitudinal direction is cut in at least one side face of each battery shell; and separating the stacked body, and detaching the battery shells of the batteries from the fractures to expose the battery contents of the batteries. The fine disassembling method and equipment for the square shell or blade type single battery are high in cutting efficiency and low in equipment acquisition cost.
Owner:HONGSUN LASER TECH (FOSHAN) CO LTD

Leather surface cleaning device

The utility model discloses a leather surface cleaning device, and relates to the field of leather manufacturing. The leather cleaning device comprises a device main body, a filter screen is arranged in the device main body, a motor is arranged above one side of the device main body, and the output end of the motor is connected with a reciprocating screw rod. The leather cleaning device has the advantages that the leather cleaning device is simple in structure and convenient to use, accordingly, clamping plates clamp and fix the two sides of leather, workers rotate first screws to enable a set of fixing frames to move, the leather is stretched, the tensile force of the leather is improved, a motor rotates to enable a reciprocating lead screw to rotate, a threaded sleeve is moved after the reciprocating lead screw rotates, and then a fixing column drives a cleaning frame to move left and right; in the moving process, the scraping plate can scrape away intractable impurities on the leather, and the first cleaning brush moves to repeatedly brush the leather.
Owner:SIHUI SHUNLI LEATHER CO LTD

A dry-type transformer and its production process

A dry-type transformer and its production process, the dry-type transformer comprises a base, two lower clamps installed on the base, three iron cores installed on the lower clamps at intervals, two upper clamps installed on both sides of the top of the iron core, three high and low voltage coil groups respectively sleeved on the three iron cores, and a body insulation member arranged on the high and low voltage coil groups and a hardware connector for connecting the high and low voltage coil groups and the iron core, and its production process comprises step 1, winding a high voltage coil; step 2, winding a low voltage coil; step 3, assembling the high voltage coil of step 1, the low voltage coil of step 2, the iron core, the base, the upper clamp, the lower clamp, the body insulation member and the hardware connector. The high voltage coil of the dry-type transformer of the present invention is not easy to crack and has a longer service life.
Owner:FUJIAN YONGJIA TECH CO LTD

Generative adversarial network sedimentary facies modeling method and device based on single training image

The present invention relates to a method and device for modeling sedimentary phases based on a generative adversarial network with a single training image. The method constructs a sedimentary phase simulation model with a multi-level generative adversarial network of a pyramid structure, obtains a single real sedimentary phase training image, and generates a multi-scale hierarchical training image based on the training image to train each level of the generative adversarial network. During the training process, the error between the output image of the generator in each layer of the network and the preset condition is judged, and the output image is corrected when the error threshold is exceeded. Finally, the sedimentary phase simulation model with complete training is used to simulate the sedimentary phase based on the given river channel training image and sedimentary phase generation conditions. The present invention reduces the acquisition cost of training data, has a fast modeling speed and high efficiency, and can perform random modeling of sedimentary phases and simulate the uncertainty of sedimentary phases on the premise of meeting given conditions.
Owner:YANGTZE UNIVERSITY

Virtual simulation data intelligent generation and enhancement method based on deep learning

The invention discloses a virtual simulation data intelligent generation and enhancement method based on deep learning. The method comprises the following steps: step 1, collecting and converging multi-source heterogeneous simulation data; 2, simulation data preprocessing and feature extraction; step 3, constructing and configuring a depth generation model; step 4, iterative training and optimization of the depth generation model; step 5, intelligently generating and synthesizing new simulation data; step 6, generating data quality verification and enhancement feedback; step 7, carrying out controllability adjustment and directional enhancement on the generated data; and 8, model online learning and data generation closed-loop optimization are carried out. The method can automatically learn the internal law and distribution of the simulation data, efficiently generate highly-vivid and diversified new simulation data meeting specific requirements, and deeply enhance the existing limited data, thereby significantly reducing the simulation data acquisition cost, improving the data quality and richness, and improving the simulation data acquisition efficiency. And powerful data support is provided for development and test of a virtual simulation system and simulation-based AI model training.
Owner:BEIJING JUNHE CHUANGXIANG TECH DEV CO LTD

Flow field surface pressure measuring method based on reflection spectrum

The invention provides a flow field surface pressure measurement method based on a reflection spectrum, relates to the field of high-speed flow field pressure measurement, and solves the problems of low spatial resolution, damage to a flow field structure, weak anti-electromagnetic interference capability, poor stability and the like of an existing high-speed flow field pressure measurement technology. The method comprises the following steps: designing a one-dimensional grating waveguide structure device based on a grating abnormal phenomenon in a grating theory, and preparing the designed one-dimensional grating waveguide structure device; carrying out pressure calibration on the prepared one-dimensional grating waveguide structure device, placing the device into a test pressure measurement system of a high-speed flow field after calibration is completed, and carrying out flow field pressure measurement on the surface of the model through a reflection spectrum of the one-dimensional grating waveguide structure device; the grating structure is designed through the pressure sensitive mechanism of the flexible grating structure, real-time measurement of the high-speed flow field pressure is achieved through reflection spectrum frequency movement, interference to the flow field is small, electromagnetic interference to the environment is small, the device is simple, and the measurement and maintenance cost is low.
Owner:INST OF HIGH SPEED AERODYNAMICS OF CHINA AERODYNAMICS RES & DEV CENT