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

761 results about "Vector diagram" patented technology

Intelligent positioning and navigation early warning system and method for ships and boats

The invention relates to the technical field of navigation and positioning, in particular to an intelligent positioning and navigation early warning system and method for ships and boats. The method comprises the following steps: collecting and carrying out sea condition sensing and positioning signal evaluation according to a multi-source sensor synchronous data set to obtain a sensor reliability score table; performing target motion situation analysis according to the sensor reliability score table to obtain a fusion situation vector diagram; performing target motion state judgment according to the fused situation vector diagram to obtain a target motion state judgment result; performing multi-target collision risk assessment according to the target motion state judgment result to obtain a risk degree assessment matrix; performing navigation maneuvering performance constraint according to the risk assessment matrix to obtain a route planning maneuvering constraint rule set; and performing route trajectory search according to the route planning manipulation constraint rule set to obtain a navigation trajectory scheme. According to the invention, through the positioning navigation early warning technology, the positioning precision, the navigation safety and the early warning system practicability of the ship in a complex environment are obviously improved.
Owner:CHANGZHOU FRP SHIPYARD CO LTD

Remote sensing image ground object recognition method based on deep learning

The invention relates to a remote sensing image ground feature recognition method based on deep learning, and the method comprises the steps: carrying out the data collection and preprocessing of a ground surface target region, eliminating the position deviation through geometric correction, processing the illumination difference through combination with radiation equalization, and generating a ground feature registration image; performing multi-dimensional feature fusion processing on the image, performing tensor fusion on vegetation spectral features, earth surface texture features, point cloud data features and linear ground feature features, and constructing a ground feature fusion matrix; a bilateral convolutional neural network is adopted to extract spectral response characteristics and spatial correlation characteristics, and characteristic interaction is realized through an attention mechanism to generate a ground feature probability distribution diagram; and finally, carrying out noise filtering, boundary refining and vectorization conversion processing on a classification result, and outputting a ground feature classification vector diagram. According to the method, three technical bottlenecks of insufficient cooperative utilization of multi-source heterogeneous data, insufficient spectrum-space feature fusion and poor GIS compatibility are solved, and the operation efficiency of territorial investigation, disaster monitoring and other scenes can be remarkably improved.
Owner:YUNNAN DINGYU NONG FORESTRY TECHNOLOGY CO LTD

Scribble-to-vector image generation

A method, apparatus, non-transitory computer readable medium, apparatus, and system for image generation include obtaining a sketch input depicting an object, processing the sketch input to obtain sketch guidance, and generating a synthesized image based on the sketch guidance using an image generation model, where the synthesized image depicts the object from the sketch input.
Owner:ADOBE INC

Intelligent construction site construction safety supervision method and system based on artificial intelligence

The invention discloses an intelligent construction site construction safety supervision method and system based on artificial intelligence, and the method comprises the steps: obtaining an unmanned aerial vehicle aerial image and point cloud data every preset time period; generating a digital elevation model according to the point cloud data; elevation data are extracted from the digital elevation model; extracting ground feature features and edge features in the aerial image of the unmanned aerial vehicle; integrating the digital orthoimage, the ground feature features and the digital elevation model to obtain a vector diagram; matching edge features in an overlapped image in the aerial image of the unmanned aerial vehicle, and inputting the edge features into the machine learning model to generate an aerial triangulation model; creating a stereo image pair according to the aerial triangulation model, and generating a live-action three-dimensional model; integrating the live-action three-dimensional model and the vector diagram to obtain a construction site digital map; acquiring personnel position data; dangerous factors are determined, a potential safety hazard analysis warning area of the construction site is obtained through analysis, and the safety construction distance and the construction safety risk coefficient of the construction area are determined and displayed.
Owner:DUNFENG (WUHAN) TECH CO LTD

Automatic tool setting method of inspection machine based on visual identification

The invention discloses an automatic tool setting method of an inspection machine based on visual identification, which relates to the technical field of automatic processing, and comprises the following steps: starting multiple sensors, and collecting initial state data of a tool; activating a multi-angle camera array, and collecting image data of the cutter from multiple view angles; fusing the initial state and the image data of the cutter to form a reconstructed three-dimensional model; based on the three-dimensional model, the error between the current space position and the expected position of the tool is analyzed; automatically adjusting the position and angle of the cutter according to an analysis result; using a deep learning algorithm to identify the adjusted tool wear characteristics, and outputting a wear evaluation result; judging whether the wear of the cutter needs to be compensated or not according to a wear evaluation result; according to the method, the error between the spatial position and the standard position of the tool is analyzed point by point, the deviation heat map and the vector diagram are generated, accurate error data are provided, a basis is provided for automatic tool adjustment, and efficient adjustment and wear compensation of the tool are ensured.
Owner:XIAOHENG YONGCHUANG (SUZHOU) INTELLIGENT TECH CO LTD

Test device and test method for visually monitoring tunnel seepage field

A test device and test method for visually monitoring a tunnel seepage field. The test device comprises a bearing platform (1), support columns (2), a transparent test box (3), a tunnel model (4), a pressure pump, a water drawing pump, a laser transmitter, a PIV camera (5) and a computer. According to the device, PIV technology is used in a test, and the PIV camera (5) is used for capturing an image of motion of tracer particles in the transparent test box (3) irradiated by laser light, so that a seepage field flow velocity vector diagram can be formed, and a tunnel seepage field can be visually monitored in real time. Compared with tunnel seepage field data obtained by means of sensor data in the prior art, the seepage field flow velocity vector diagram obtained in the test device is not affected by the precision of sensors, so that the obtained tunnel seepage field flow velocity vector diagram is more accurate and suitable for research of tunnel seepage field rules.
Owner:CCCC INFRASTRUCTURE MAINTENANCE GRP CO LTD +2

Geographic information processing method and device, equipment and storage medium

The invention provides a geographic information processing method and device, equipment and a storage medium, and relates to the technical field of GIS data processing, the method comprises the following steps: obtaining vector geographic information data of multiple formats, the vector geographic information data at least comprising a vector layer containing land class attributes; processing the vector of the vector layer through a data editing processing tool to obtain a target vector layer; obtaining an intersection region obtained after the plurality of target vector layers are subjected to intersection operation, and taking the intersection region as a first result layer; according to the layer attribute of the first result layer, performing classified rendering on the first result layer to obtain a second result layer; and performing map finishing on the second result layer to obtain a target map file. The technical effects of the application are that an efficient and intelligent solution is provided, the requirements of modern geographic information processing are met, and powerful support is provided for spatial decision and analysis of each industry.
Owner:BEIJING DIXING WEIYE DIGITAL TECH CO LTD

Semantic segmentation-based submarine sonar image processing method

The invention discloses a seabed sonar image processing method based on semantic segmentation. The method comprises the following steps: S1, obtaining preprocessed sonar image blocks; s2, generating a submarine landform boundary priori map corresponding to the preprocessed sonar image blocks pixel by pixel; s3, an improved U-Net double-branch semantic segmentation network is constructed, the improved U-Net double-branch semantic segmentation network comprises a semantic branch and a boundary branch, and a landform mutual feedback gating module is configured in each scale jumper connection layer; s4, obtaining a fusion feature map; s5, deploying to the autonomous underwater vehicle to form an onboard reasoning model; and S6, performing online semantic segmentation reasoning on the preprocessed sonar image block acquired in real time by using the onboard reasoning model, and outputting a semantic category diagram and a boundary vector diagram corresponding to the preprocessed sonar image block. According to the method, the average mIoU index of the model is improved in a small-target and multi-category hybrid scene.
Owner:SHENYANG LIAOHAI EQUIP

Building contour line extraction method based on deep learning and joint optimization

The invention discloses a building contour line extraction method based on deep learning and joint optimization, and the method comprises the steps: collecting a multi-view picture of an urban building, and constructing a DOM and a DSM; making a normalized digital surface model nDSM and a slope map, and marking a building contour line and a polygon; constructing a fishing net segmentation grid and a vector graph layer, establishing training sample images and labels, and substituting the training sample images and labels into a line feature extraction network MFLine-Net and a semantic segmentation network Res-UNet for respective training; extracting a line feature by using a line feature extraction network MFLine-Net; building roof semantic information is extracted by using a Res-UNet network; generating a cell cavity complex by using a motion space subdivision algorithm; correlating the semantic information of the cell units and the roof by adopting a graph cut optimization algorithm; and combining the cell units with the same roof semantic information to obtain a building contour map. According to the method, the city building contour map can be rapidly constructed, and the requirement for photogrammetry building drawing based on the unmanned aerial vehicle is met.
Owner:NANTONG UNIV

CFD-based liquefied natural gas after-condenser structure optimization method and device

The invention discloses a CFD-based liquefied natural gas after-condenser structure optimization method and device. The method comprises the steps that an initial model is established based on an assembly drawing, and geometric pretreatment is completed; extracting a fluid channel, segmenting and selecting a computational domain, and carrying out local encryption on a key region; generating a polyhedral grid by using a grid division tool, and completing grid independence verification; importing the polyhedral mesh into a solver, and carrying out model setting; boundary and wall surface conditions are set, and solver parameters are configured; setting an initial flow field through a hybrid initialization method, and establishing a flow monitoring window and a temperature monitoring window to adjust simulation until convergence; analyzing the temperature cloud picture and the flow vector diagram, and adjusting the structure of the baffle plate; the tower diameter and the height of the filler layer are adjusted according to a physical quantity field change curve of the filler layer, and the performance of the recondenser is continuously improved. The problem of how to deeply study the flow heat transfer rule in the after-condenser and obtain the flow field distribution characteristics is solved, so that the working performance of the after-condenser is improved.
Owner:XI AN JIAOTONG UNIV +1

Method for generating multidimensional landform vector data based on remote sensing image semantic segmentation

The invention provides a method for generating multi-dimensional landform vector data based on remote sensing image semantic segmentation, and belongs to the technical field of remote sensing image ground object recognition and artificial intelligence, and the method comprises the steps: training a landform recognition deep learning model based on a remote sensing image, adjusting a pre-training weight to optimize an image encoder, and generating a classification result; the landform recognition deep learning model comprises an encoder formed by a multi-layer convolutional network and a decoder of an up-sampling and feature fusion architecture; extracting a single-band label corresponding to each landform type from the classification result, and generating a binary raster image with the single-band labels; and converting the binary raster image with the single-band label into a vector diagram, and combining the vector diagram with the elevation information to generate multi-dimensional geographic data.
Owner:QINGDAO INST OF BIOENERGY & BIOPROCESS TECH CHINESE ACADEMY OF SCI

Colorization of images and vector graphics

Embodiments for colorizing images, including pixel-format images and vector-format images, include obtaining input data including an outline image and a color hint. The color hint includes a colored portion corresponding to a region of the outline image. Then, embodiments process the input data to obtain control guidance for an image generator using an outline encoder. Embodiments generate a synthesized image based on the control guidance using an image generator. The synthesized image depicts an object having a shape based on the outline image and a color based on the color hint. In some cases, embodiments also transfer the colors from the synthesized image to a base vector image to produce a colorized vector image.
Owner:ADOBE INC

Techniques for indoor wayfinding

Methods, systems, and devices are described. Indoor wayfinding may be performed using a set of layers overlayed on a map, such as a site map of the surrounding environment of a building, using a combination of static and dynamic images. For example, a user device may transmit a request to a server for a route to a desired location of a floor of a building. In some cases, the server may, in response to the request, generate the route using a set of map layers that includes a static image of the site, a static image of a floor plan of the floor housing the location, a vector image of features such as rooms and offices of the floor that includes the desired location, and a vector image of a route from a starting location of the floor, such as an entrance or elevator, and the desired location.
Owner:ALLY FINANCIAL INC

Highway bridge drawing multi-modal information extraction and semantic understanding method and system

The invention belongs to the technical field of engineering information intelligent processing, and relates to a highway bridge drawing multi-modal information extraction and semantic understanding method and system.The method comprises the steps that firstly, self-adaptive judgment is conducted on a vector drawing and a scanning drawing, geometric distortion correction, drawing frame and title bar positioning and layout segmentation are completed, and then the vector drawing and the scanning drawing are obtained; constructing a hierarchical document structure comprising texts, tables, images and two-dimensional drawing objects; then, a front-end target detection network and a rear-end cross-modal document understanding model are fused, and detection and relation reasoning of elements such as view blocks, labels, symbols and tables are achieved; and image-text feature alignment is further performed by using a visual coding network and a text coding network, structural description conforming to engineering semantics is generated by means of a multi-modal language model, an engineering parameter database is established, and parameter query and multi-modal question and answer output are supported. According to the method, the accuracy and efficiency of automatic acquisition and semantic understanding of the key information of the highway bridge drawing are improved.
Owner:YUNNAN TRAFFIC PLANNING DESIGN RESEARCH INSTITUTE CO LTD

Ai-assisted creation of 3D building models

Systems and methods allow prediction of semantic information and generation of a 3D model from one or more raster images of a structure. In embodiments, the raster images may be converted to vector images, and received semantic information may be used for generation of predicted semantic information. The combination of provided and predicted semantic information, along with the vector images, can facilitate generation of a 3D model that is scale-accurate to the structure illustrated by the raster images. Other embodiments may be described and / or claimed.
Owner:DIGS INC

Cultivated land resource protection evaluation method and system

PendingCN119090345AReliable and effective protection evaluation methodDetermine the degree of protectionData processing applicationsEnvironmental resource managementFarmland preservation
The invention discloses a cultivated land resource protection evaluation method and system. The cultivated land resource protection evaluation method comprises the following steps: acquiring a multi-period remote sensing image of a research area; extracting land utilization data from the remote sensing image of each period of the research area, and generating vector diagram blocks of different land utilization types in the research area; on the basis of the land utilization data, land utilization quantity change data, cultivated land utilization dynamic attitude and a cultivated land quantity change intensity index of the research area are obtained through calculation; a cultivated land change index, a cultivated land quality index and a cultivated land ecological index of the research area are constructed; calculating weight values of the cultivated land change index, the cultivated land quality index and the cultivated land ecological index; and calculating a comprehensive evaluation value of cultivated land resource protection of the research area, wherein the comprehensive evaluation value is used for evaluating the cultivated land protection degree of the research area.
Owner:GUANGZHOU URBAN PLANNING & DESIGN SURVEY RES INST

Cable outer semi-conductive layer stripping defect detection method and device, terminal equipment and storage medium

The invention discloses a cable outer semi-conductive layer stripping defect detection method and device, terminal equipment and a storage medium, and belongs to the field of power equipment detection. The method comprises the following steps: acquiring polarization images of a to-be-detected cable joint at a plurality of angles and corresponding camera pose parameters; performing stokes parameter calculation according to the polarization image and the camera pose parameter to obtain a stokes vector diagram; performing three-dimensional morphology reconstruction according to the camera pose parameters, a polarization derived parameter diagram generated by the Stokes vector diagram and the de-reflective polarization fusion image to obtain a submillimeter-level precision point cloud; according to a preset channel attention mechanism, carrying out weighted fusion on geometric features extracted from the submillimeter-level precision point cloud and texture features extracted from the de-reflective polarization fusion image to obtain a defect type probability and a surface topography parameter; and obtaining a stripping defect type and a defect position according to the defect type probability and the surface topography parameter. According to the invention, the problem of low defect detection accuracy in the prior art can be solved.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Fire safety inspection method and system based on machine vision recognition

The invention relates to the technical field of fire safety inspection, in particular to a fire safety inspection method and system based on machine vision recognition. The method comprises the following steps: carrying out inspection equipment deployment on an inspection area to obtain a camera deployment scheme and a sensor network deployment scheme; performing multispectral dynamic sensing according to the camera deployment scheme to obtain a time sequence spectral flow; performing multispectral channel motion estimation on the time sequence spectral flow, and performing motion vector noise suppression to obtain a filtered motion vector diagram; performing spectral characteristic-based motion enhancement on the filtered motion vector diagram to obtain a spectral enhanced motion vector; and performing motion amplification algorithm application on the time sequence spectrum flow according to the spectrum enhanced motion vector, and constructing an enhanced motion vector field to obtain the enhanced motion vector field. According to the invention, through multi-modal information fusion, context awareness and capturing of early fine features, early and accurate fire hazard identification and early warning are realized.
Owner:SICHUAN XINTAIRAN SAFETY TECH CO LTD

Energy-saving method and device for air conditioning system, electronic equipment and storage medium

The invention relates to an air conditioning system energy saving method and device, electronic equipment and a storage medium, and the method comprises the steps that according to the structure of a target data center machine room and the arrangement condition of computer equipment in the machine room, a physical model of the machine room is established; based on the physical model, the electrical load and heat dissipation wind speed of each computer device in the machine room and the cold water temperature and flow of each air conditioner serve as boundary conditions, and a temperature distribution cloud picture and an airflow vector diagram of the machine room are simulated through CFD numerical simulation software; based on a known mathematical model, the temperature distribution cloud picture and the airflow vector diagram serve as input, and the rotating speed of a fan to be adjusted of each air conditioner is output; and boundary conditions corresponding to the to-be-adjusted fan rotating speed are obtained, the simulation step is executed again until the temperature distribution cloud picture meets the preset conditions, the to-be-adjusted fan rotating speed corresponding to the cloud picture meeting the preset conditions serves as the target fan rotating speed, the air conditioner fan is kept at the optimal rotating speed, and optimal energy saving of the air conditioner is achieved.
Owner:CHINA NAT PETROLEUM CORP +1

Query condition analysis method and device and medium

The invention discloses a query condition analysis method and device and a medium, and the method comprises the steps: receiving a natural language query statement input by a user for a human resource management system, and extracting a core semantic unit in the natural language query statement; based on a preset knowledge base, mapping the core semantic unit into a semantic structure corresponding to an Elasticsearch database to generate a corresponding key vector diagram; based on a preset pseudo code normal form, generating a pseudo code according to the key vector diagram; wherein the pseudo code comprises a query node set and a logical relationship between query nodes; and performing code verification on the pseudo-code, and converting the pseudo-code into a DSL query statement in an Elasticsearch database under the condition that the pseudo-code passes the code verification, so as to realize semantic analysis on the natural language query statement through the DSL query statement.
Owner:SHENZHEN INSPUR HAIYUE HUMAN RESOURCES TECHNOLOGY CO LTD

Recognition and verification method and system for secondary drawing of transformer substation

The invention discloses an identification and verification method and system for a secondary drawing of a transformer substation, and belongs to the technical field of image identification, and the method specifically comprises the steps: analyzing a CAD vector diagram, obtaining four-corner references and pixel coordinates of a scanning graph, building initial mapping of pixels and engineering millimeter coordinates by taking an engineering millimeter coordinate system as a reference, and generating a unified intermediate representation model; constructing a terminal strip parameterization template based on the vector anchor point set and the visual anchor point set; a composite deformation field is calculated through vector-bitmap-vector closed-loop rendering calibration, terminal row alignment and terminal sequence binding are completed in the composite deformation field, and a terminal pixel position-terminal sequence-engineering millimeter coordinate consistent mapping table is formed; comparing the topological netlist to obtain an electrical node corresponding table; and performing source decomposition on the terminal position residual error based on the composite deformation field and generating a self-adaptive tolerance band, and finally executing wiring verification by taking the self-adaptive tolerance band, the electrical connectivity and the serial number consistency as criteria and outputting a verification report.
Owner:ZHEJIANG ELECTRIC TRANSMISSION & TRANSFORMATION ENG CO +1

Microplastic transportation path prediction method and device based on complex hydrodynamic environment, equipment and medium

The invention discloses a microplastic transportation path prediction method, device and equipment based on a complex hydrodynamic environment and a medium, and relates to the technical field of environment monitoring and water pollution governance, and the method comprises the steps: integrating a watershed digital elevation model, a river channel vector diagram, microplastic attributes and real-time hydrological data; a dynamic adjacency matrix is used for capturing water flow direction changes, multi-modal feature fusion is combined for modeling micro-plastic physical attributes and topographic resistance, the problem of monitoring data scarcity is solved through a cross-basin transfer learning strategy, a micro-plastic transfer path is accurately predicted, high-precision simulation of micro-plastic transfer in a complex hydrodynamic environment is achieved, and high-precision simulation of micro-plastic transfer in a complex hydrodynamic environment is achieved. The pollution prevention and control efficiency is improved.
Owner:CENT SOUTH UNIV

Seawall terrain extraction method and system fusing vehicle-mounted laser point cloud and inclination model

The invention provides a seawall terrain extraction method and system fusing a vehicle-mounted laser point cloud and an inclination model. The method comprises the following steps: forming a seawall range according to a seawall vector diagram and a satellite image; dividing a seawall range into a vehicle-mounted laser radar acquisition range and an unmanned aerial vehicle oblique photogrammetry range; acquiring a vehicle-mounted laser point cloud collected by a vehicle-mounted laser radar, and performing preprocessing and precision optimization on the vehicle-mounted laser point cloud; obtaining oblique photography image data collected by a five-splicing camera carried by the unmanned aerial vehicle, and generating an oblique photography model and an oblique three-dimensional model point cloud; extracting edge line elements and angular point feature points of a common overlapping area in the inclined three-dimensional model point cloud and the vehicle-mounted laser point cloud, and performing point cloud fusion based on the edge line elements and the angular point feature points; filtering the fused point cloud to screen seawall terrain point cloud data; according to seawall terrain point cloud data, resolution-adaptive digital elevation models are constructed for different areas of a seawall, and seawall structure features can be accurately represented.
Owner:INTERSTELLAR SPACE (TIANJIN) TECH DEV CO LTD

Bridge displacement monitoring method based on visual identification of unmanned aerial vehicle

The invention relates to the technical field of bridge monitoring, in particular to a bridge displacement monitoring method based on unmanned aerial vehicle visual identification, which comprises the following steps: S1, generating a flight path covering all key parts of a bridge, and collecting a bridge image by adopting an unmanned aerial vehicle according to the flight path; the method comprises the steps of S1, preprocessing a bridge image, S2, carrying out feature extraction after the bridge image is preprocessed, S3, carrying out matching on image feature points at different time points, and calculating the displacement of a bridge, S4, carrying out model optimization by adopting a convolutional neural network to optimize image features, and S5, carrying out hierarchical monitoring on displacement magnitude differences of different components of the bridge, and superposing a displacement calculation result on the bridge image in the form of a thermodynamic diagram or a vector diagram, and representing the displacement by using a color gradient. The method adopts the unmanned aerial vehicle visual identification technology, only needs the unmanned aerial vehicle and the camera, combines the image processing algorithm and the deep learning model to calculate the bridge displacement, is high in precision, is low in cost, and is suitable for various types of bridge structures.
Owner:SHENZHEN CHENGAN SOFTCOM TECH GRP CO LTD

Method and system for evaluating running state of deep peak regulation process of fluidized bed unit

The invention discloses an operation state evaluation method and system for the deep peak regulation process of a fluidized bed unit, and relates to the technical field of fluidized beds, and the method comprises the steps: collecting the combustion condition data of the deep peak regulation process of the fluidized bed unit; generating a particle flow velocity vector diagram, and identifying and marking different flow modes and paths in the particle flow velocity vector diagram; generating a non-uniform index of the whole flow field through particle flow velocity and particle concentration distribution of each flow mode area in the flow field; generating a bed temperature distribution diagram, recognizing a high temperature-flow mode region by combining with the particle flow velocity vector diagram, and calculating a coking risk index of the high temperature-flow mode region; and calculating a coking risk index of the whole flow field, comparing the coking risk index of the whole flow field with a risk threshold value, and when the coking risk index of the whole flow field is greater than or equal to the risk threshold value, giving out an early warning, identifying potential risks, and avoiding serious problems such as coking.
Owner:SHENHUA SHENDONG POWER +1

Graph drawing method, graph drawing device, electronic equipment and storage medium

The invention relates to a graph drawing method, a graph drawing device, electronic equipment and a storage medium, and belongs to the technical field of graph drawing. The method comprises the steps of obtaining user drawing board operation event information, obtaining a user drawing board operation element method through a predefined drawing board operation method mapping table, obtaining user drawing board operation element change data through drawing board updating logic calculation, and obtaining user drawing board operation element change cache data through caching of a data storage mechanism, the method comprises the steps of generating a real-time preview image through WebGL, determining user drawing board operation element difference data through data comparison, obtaining user drawing board operation element difference data vector diagram data through SVG format conversion, and performing drawing board local rendering through a Canvas API. The rendering precision of the drawing board is dynamically adjusted according to equipment performance data, multiple rendering tasks are calculated in parallel through a multi-core processor, and a next drawing board operation type label of a user is predicted through a user drawing board operation prediction model, so that related operation controls are preloaded, and the response speed is increased.
Owner:GUANGZHOU LANGO ELECTRONICS TECH CO LTD

Automatic equipment modeling method and system based on artificial intelligence

The invention relates to the technical field of artificial intelligence and digital modeling, and particularly discloses an automatic equipment modeling method and equipment based on artificial intelligence, and the method comprises the steps: obtaining data to construct a multi-modal fusion data set; extracting target features and integrating the target features into a unified high-dimensional feature vector so as to generate a semantic feature map for modeling equipment; obtaining geometric modeling parameters and assembly constraint conditions of modeling equipment by using a parameter optimization model constructed based on a reinforcement learning framework; based on the fault data, optimization is carried out through a Markov decision principle to generate a preliminary 3D model; and performing key point detection and feature alignment on the planar projection of the model and the BIM drawing vector diagram through a hierarchical matching strategy, correcting model deviation based on vertex information to generate a 3D model, and generating a digital twin 3D model. Thus, by means of multi-source data collaborative acquisition and deep feature fusion, the precision, efficiency and adaptability of equipment modeling are remarkably improved in combination with dynamic optimization and a closed loop verification mechanism.
Owner:BEIJING ZHONGBEI SIGNAL SOFTWARE CO LTD

Personnel emergency evacuation method and system based on improved vector vector diagram

The invention discloses a personnel emergency evacuation method and system based on an improved vector vector diagram, and belongs to the technical field of emergency simulation, and the method comprises the steps: carrying out the initialization of an evacuation environment, including the initialization of static environment space elements and the initialization of evacuation crowd individual positions; establishing a visual field containing a plurality of sensing points according to individual positions and speed directions of the evacuated crowd; and for each individual in the evacuated crowd, individual movement is carried out based on the established visual field and through continuous perception of the static environment and interaction among the individuals in the crowd, and crowd evacuation is completed. According to the method and the system, the information exchange among the groups and the perception-feedback process of the crowd to the environment are fully considered in the evacuation simulation process, and the authenticity of the simulation process is improved.
Owner:INST OF ENG MECHANICS CHINA EARTHQUAKE ADMINISTRATION

Generating vector drawings based on a three dimensional representation of a physical scene at a location

The described systems and methods are configured generate a 3D virtual representation of a physical scene at a location, and output isometric and / or orthographic vector drawings based on the 3D virtual representation. The vector drawings are generated by rendering views of the 3D virtual representation in a scalable vector graphics (SVG) format, so that the views can be zoomed without blurring or other decreases in image viewability. Further, sub-rooms, tags, labels, and / or dimensions may be added to the output. Rather than taking hours to generate drawings, the described systems and methods enable generation in a few milliseconds, among other advantages.
Owner:YEMBO INC

Intelligent clamping method and system for universal joint transmission shaft machining

The invention relates to the technical field of transmission shaft machining, and discloses an intelligent clamping method and system for universal joint transmission shaft machining. The method comprises the steps that the geometric dimension, the form and location tolerance number, vibration signal data, unbalance data and pressure distribution data of a transmission shaft are obtained; performing precision correction based on preset machining precision to obtain transmission shaft positioning parameters; adjusting parameters in real time through an adaptive control algorithm to obtain real-time positioning parameters; performing feature extraction to obtain vibration spectrum features; outputting a vector diagram to obtain an unbalanced vector diagram; performing Kalman filtering processing to obtain filtering parameters; calculating by adopting a fuzzy control algorithm to obtain a vibration compensation amount and an unbalance correction amount; performing data processing to obtain a corrected pressure matrix; inputting into a pre-trained neural network model to obtain a predicted risk level; and risk prediction and judgment are carried out, clamping strategy adjustment is carried out, a corrected clamping strategy is obtained, machining of the transmission shaft is carried out, and the machining accuracy is improved.
Owner:NINGBO KAIMINSHENG MASCH CO LTD