213 results about "Line model" patented technology

The invention belongs to the technical field of BIM (Building Information Modeling), and particularly relates to a curved surface composite truss design and construction integrated method and device based on the BIM technology. The method comprises the following steps: considering four structural schemes for a building facade, generating a corresponding parameterized structural topology and a three-dimensional structural line model, adding a load, calculating, analyzing and optimizing a cross section, and generating four structural calculation models and building scheme models; the building space effects and the structure force transmission efficiency of the four structure schemes are compared, and the optimal one is selected as an implementation scheme; and forming a full-professional BIM model according to the selected implementation scheme. Building datamation is achieved through the BIM technology, digital delivery of design results is achieved, the link of two-dimensional plotting is reduced, steel structure deepening is further conducted through the BIM model in the construction stage, visual deduction is conducted on key procedures such as steel structure machining, assembling and hoisting, and digital construction is achieved.

An offline pre-training and online fine-tuning apparatus based on reinforcement learning includes a data management unit collecting and processing data for offline reinforcement learning in advance; an offline model training unit training an offline policy network and an offline state-action value function network using a previously collected dataset that includes a state, an action, a next state, a reward, and an accumulated reward collected by the data management unit; and an online model training unit performing fine-tuning to update parameters of the offline policy network using an online dataset that includes action information determined based on state information acquired through interaction with the offline policy network and an environment, state information at a next time point according to the action information, and the reward, and the previously collected dataset.

Disclosed in the present application are a method and apparatus for calculating carbon emissions from equipment, and a computer device and a storage medium. The method comprises: providing a utility and auxiliary facility model, an equipment model and a connection line model; by means of the connection line model, connecting the utility and auxiliary facility model and the equipment model; adding operating parameters to the models, and associating the models with a carbon emission database; and on the basis of the carbon emission database, calculating carbon emissions from equipment. In this way, a connection line model and an equipment model can be flexibly established, the connection line model is decoupled from the equipment model, and carbon emissions from an equipment group are rapidly calculated; moreover, the method enables adaptive adjustments for different scenarios, and has a wide range of application.

The invention relates to an intelligent tree barrier detection method and system based on multi-modal perception, and the method employs an unmanned plane to carry a sensor to collect data, including RGB images, LIDAR point clouds, multispectral data and the like. Firstly, data is preprocessed to form standardized input. Hough transformation is carried out on the LIDAR point cloud, the position of the power line is extracted, and a three-dimensional line model is generated. And then positioning a tree bounding box from the RGB image by using a deep learning algorithm, and screening a high-risk point cloud region in combination with a line model. And constructing a three-dimensional tree model, calculating the minimum safety clearance distance between the power line and the tree in real time through a collision detection algorithm, obtaining the three-dimensional tree model with a safety distance mark, and finally carrying out space risk assessment based on the model. According to the invention, the reliability and efficiency of power line inspection can be significantly improved.

The invention provides a gait monitoring system based on multi-modal sensing fusion, which comprises the following steps of: establishing an initial base line to form a personalized gait base line model; baseline updating is adopted, and after a system obtains new gait data, a weighted moving average algorithm is adopted for self-learning updating, so that the historical data weight is enhanced, and the baseline stability is improved. The technical problems of insufficient individual difference adaptation, lack of dynamic threshold adjustment, poor real-time performance and the like in the prior art are solved.

The invention relates to the technical field of civil engineering digitization, and discloses a steel structure physical digital twin model construction method, device and equipment and a medium, the method comprises the following steps: carrying out multi-source point cloud data acquisition on a steel structure, and generating a steel structure complete point cloud model based on the multi-source point cloud data; extracting a complete geometric line model and a section size of the steel structure from the complete point cloud model of the steel structure, and obtaining an actually measured material constitutive of the steel structure through a material property test; establishing a large-span space steel structure finite element model by adopting finite element analysis software based on the complete geometric line model, the section size and the actually measured material constitutive structure of the steel structure; and correcting the finite element model based on the residual error between the measured data of the steel structure and the simulated data of the steel structure output by the finite element model, and taking the corresponding finite element model when the residual error is less than a preset threshold value as the physical digital twinborn model of the large-span space steel structure. According to the method, millimeter-level geometric reduction, real material parameter association, lightweight efficient calculation and dynamic data correction are realized.

The present invention relates to an intelligent tree barrier detection method and system based on multimodal perception. The method uses sensors carried by drones to collect data, including RGB images, LIDAR point clouds, multispectral data, etc. First, the data is preprocessed to form a standardized input. Then, a Hough transform is performed on the LIDAR point cloud to extract the position of the power line and generate a three-dimensional line model. Then, a deep learning algorithm is used to locate the tree bounding box from the RGB image, and the high-risk point cloud area is screened in combination with the line model. Then, a three-dimensional tree model is constructed, and the minimum safe clearance distance between the power line and the tree is calculated in real time through a collision detection algorithm to obtain a three-dimensional tree model with a safety distance annotation. Finally, a spatial risk assessment is performed based on this model. The present invention can significantly improve the reliability and efficiency of power line inspections.

The application discloses a curved surface structure zero state form finding method, comprising the following steps: (1) a model is established based on a design configuration, and deformation data is obtained by simulating the whole construction process; (2) a zero state configuration is deduced reversely: key node deformation values are extracted, arches are started, a simulation is re-performed after a linear model is fitted and adjusted, and iteration correction is performed until deformation error meets the requirement, and a zero state installation configuration is obtained; and (3) construction data is generated by extracting component line shapes and node coordinates. The application innovatively adopts an integral curvature adjustment strategy to replace a traditional node coordinate local adjustment mode, and through reverse deduction of 'construction simulation-control point arching-curved surface fitting-grid mapping', the problem of curved surface discontinuity caused by the traditional reverse superposition method is solved, construction precision and efficiency are significantly improved, and the application is suitable for intelligent construction of complex curved surface space grid structures.

The invention provides a casting joint line polishing method based on vision, and belongs to the crossing field of mechanical manufacturing automation and intelligent manufacturing, and the casting joint line polishing method comprises the following steps: obtaining template surface point cloud of a standard casting, carrying out reverse modeling on the template surface point cloud to obtain first template point cloud, and obtaining first measurement point cloud of a casting to be polished; performing rough matching and fine matching on the first template point cloud in sequence, and converting the original joint line model into a new joint line model; points, closest to track points of the template track, in the new joint line model are obtained, for each closest point, the point, having the largest vertical distance from the plane where the new joint line model is located, in the neighborhood of the closest point is obtained, and all the points having the largest distances form a path planning point cloud; and traversing all planning points in the path planning point cloud according to the machining direction, selecting a machining mode according to the machining allowance corresponding to each planning point, and generating a final machining track. The grinding precision, the grinding quality and the grinding efficiency of the joint line can be improved, and the grinding device is also applicable to complex curved surfaces.

The invention relates to the technical field of railway line planning, in particular to an improved SAC railway line planning method based on course learning, and the method comprises the steps: modeling a three-dimensional line selection environment; constructing an improved SAC decision model, and designing a 100-dimensional state space including topographic features, forbidden zone positions and unfavorable geological risks; constructing a reward function fusing engineering cost, terrain fitness and invalid action penalty; curriculum learning staged training is carried out; and generating and optimizing a line scheme. According to the improved SAC railway line planning method based on course learning, a continuous action space decision framework based on the SAC algorithm can effectively solve the high-dimensional continuous action optimization problem of railway line selection. By designing a multi-dimensional fusion state space, a continuous action space based on a proportionality coefficient and a reward function based on target guidance, the adaptability of the intelligent line selection model to topographic features is remarkably improved.

The invention relates to the technical field of image recognition, in particular to a building plane element recognition model construction method based on a convolutional neural network, and the method comprises the following steps: obtaining an input APN sample; elements in the APN sample are labeled, and a labeled file is generated; converting the annotation file into a format required by YOLO, and normalizing the annotation file; performing data enhancement on the APN sample, expanding the training data volume, and outputting to obtain an element detection result and a feature vector; installing dependency and carrying out data configuration; setting command line model parameters and customizing training scripts; and carrying out model training and model reasoning. According to the method, the plane layout is abstracted based on the machine learning method, and the vector data type has high flexibility and deformation capability, so that the vector output which keeps the original plane image form unchanged can be converted into various objects according to the purpose of a user. And classifying and identifying the plane elements by using the GNN.

The invention discloses a line gradient design method with optimal energy saving as a target, and relates to the technical field of rail transit. According to the method, firstly, a train operation acceleration curve model, a corresponding traction force model and a braking force model are constructed, corresponding speed value, traction force and braking force data can be searched based on positions, secondly, on the premise that a speed curve is unique, the optimal line gradient design is optimized by taking the minimum traction energy consumption of an objective function as a target through a genetic algorithm, and the optimal line gradient design is obtained. And a certain reference can be provided for rail transit line design.

An online soft measurement method for dioxin emission concentration in MSWI process includes: performing principal component analysis on process data according to a historical process data set of the MSWI process to obtain a drift index control limit; constructing an offline model based on FTBL, and inputting the process data and historical DXN true value data of the MSWI into an off-line model; performing principal component analysis according to online data, judging whether the online data is drift data according to the drift index control limit; if the typical sample pool is the drift data, constructing an online model based on FTBL, and inputting the process data and the drift data of the typical sample pool and output data of the incremental layer of the offline model into the online model; and determining a DXN emission concentration predicted value according to an offline calculation result and an online calculation result.

The invention discloses a business database natural language question and answer processing method fused with a large model technology. The method comprises the following steps: S1, receiving an emergency query request input by a user in a natural language form; and S2, carrying out analysis and intention recognition on the emergency query request based on a large language model, and generating a group of candidate query intentions arranged in a descending order according to matching degree scores and corresponding key entity information. According to the method, a core link can be optimized by introducing a large language model technology: in an intention recognition stage, intention recognition accuracy is improved through a formula of fusing semantic similarity and entity type matching degree; a priority-based asynchronous execution strategy is adopted to improve the response efficiency; the response reliability is guaranteed through real-time and conflict verification; meanwhile, the system performance is continuously improved in combination with an offline model optimization link, the defects of an existing processing method are finally overcome, and an accurate, efficient and reliable solution is provided for business database natural language question answering in an enterprise emergency scene.

The invention relates to the technical field of hot continuous rolling material performance prediction, and discloses an efficient hot continuous rolling material performance prediction method and system, and the method comprises the steps: achieving the multi-source data cleaning through multi-dimensional outlier detection and cross-rack space-time interpolation, building a material component graph model, capturing the interaction of elements, and predicting the performance of a hot continuous rolling material. And fusing physical characteristics and gene coding characteristics by adopting a space-time attention mechanism. Cross-production-line model parameters are integrated based on a federated learning framework, model robustness is optimized in combination with physical conservation constraint and adversarial training, and finally, optimal process parameters are inverted through a sequential quadratic programming algorithm and PLC closed-loop control is realized. By adopting a multi-dimensional outlier detection algorithm and a cross-rack space-time interpolation technology, the problems of poor synchronism and abnormal missing detection of a traditional data cleaning method in a hot continuous rolling multi-source heterogeneous data scene are solved, and data quality enhancement in a high-noise environment is realized by joint distribution statistics and physical law constraints.

The invention belongs to the technical field of ship engineering CAD (computer-aided design) three-dimensional modeling, and particularly relates to a ship molded line parameterization modeling method, a storage medium and a ship molded line parameterization modeling system.The ship molded line parameterization modeling method comprises the steps that point models in three-dimensional modeling are classified and differentially expressed; classifying the line model of the hull molded line, and controlling the geometrical shape of the line model through parameters; based on classification of the point model and the line model, a relevance control mechanism is established, and a three-dimensional line frame is generated through interpolation, fairing and synchronous optimization of the molded line. Based on point and line categories and different parameter relevance, in the overall design stage, molded line three-dimensional modeling is carried out whether the molded line is designed preliminarily or under the condition of existing molded values, and the three-dimensional line frame is generated. The method has the advantages that the molded lines can be quickly created and optimized, the molded lines related to the points can be synchronously modified by modifying and fairing the points or the lines, and preconditions are provided for follow-up construction of the fairing hull molded surface by the molded lines.

The invention discloses a cross-language migration-based low-resource programming language corpus enhancement method, which comprises the following steps of: receiving a source language code, and driving a large language model to generate an initial target language code through a two-way retrieval mechanism fusing example guidance and knowledge constraint; secondly, constructing an automatic iterative repair closed loop by utilizing the feedback of a compiler, and carrying out self-correction on codes which fail to be compiled; thirdly, high-quality codes are screened out through automatic quality gating and fed back to a corpus and a knowledge base, and self-enhancement circulation of data and knowledge is formed; finally, the method further comprises an offline model evolution step based on grammar and semantic alignment driven by a compiler, a big language model is trained by collecting preference data generated by an online process, and the ability of the big language model to understand a target language is improved fundamentally. According to the method, the core problems of low quality, poor efficiency and lack of self-evolution ability of a low-resource programming language in code migration are solved.

The present invention relates to the technical field of buildings, and in particular, to a visual inspection and measurement method for a reinforcing mesh, comprising the steps of: using an RGBD camera to perform data acquisition on a building site; performing Mask R-CNN instance segmentation on RGB, preliminarily identifying a workpiece, and segmenting a 2D workpiece from the background; converting the obtained 2D workpiece into a 3D point cloud on the basis of an intrinsic mapping relationship of the RGBD camera; and for on-site acquired data, obtaining a segmentation result of rebar details by means of FPFH feature matching with an offline model; and on the basis of an identified rebar point cloud, performing cylinder fitting to obtain the number of rebars within the field of view. According to the present invention, preliminary identification of rebars is performed on a 2D site image by means of Mask R-CNN instance segmentation, and then rebar 3D geometry is precisely identified by using FPFH feature consistency.

The invention discloses a berthing state estimation method based on shipborne laser radar target detection, and the method comprises the steps: constructing a ship three-dimensional target detection network model through an improved PointPill coding network, and introducing an average pool layer and an attention pooling layer into the coding network to carry out the fusion of the global perception information and the local perception information of a target, and performing model training according to the constructed model loss function, detecting and confirming whether an anchored ship exists in a preset berth through an optimal detection network model, and respectively acquiring whether the anchored ship exists or does not exist in the preset berth by introducing an RANSAC plane fitting algorithm. A berthing speed used for ship berthing state estimation is obtained by combining the required berthing front edge plane or the outer contour surface of the target ship, namely a berthing berthing boundary surface and the position of the shipborne laser radar; the defect that the berthing state estimation accuracy is poor due to the fact that a berthing line model obtained through a traditional method based on linear fitting serves as the berthing state estimation reference is solved.

The invention relates to the technical field of intelligent auxiliary driving, and provides a 3D lane line generation method and device and a storage medium. After a lane line model is obtained, the abscissa of the vertex coordinate on the lane line model is modified according to a curvilinear function x = f (z), so that the lane line track generates transverse deformation; moreover, according to a curvilinear function y = f (z), longitudinal coordinates of vertex coordinates at the far end of the curved section track on the lane line model are modified, new vertex position coordinates are constructed, the curved section track is made to generate longitudinal deformation to form a YZ plane, and then target vertex coordinates are output to generate a 3D lane line, so that breakpoints at the far end when the lane line is bent are eliminated, the anti-aliasing effect is improved, and the accuracy of the lane line is improved. The phenomenon of breakage or flicker during lane line rendering is effectively avoided, the visual effect is improved, and the driving safety is improved.

The invention provides a method and device for extracting a revit structure line model based on dynamo, and the method comprises the steps: obtaining the information of a revit model beam column member through customizing nodes in dynamo software, adding and configuring the nodes to extract the geometric position information of the revit model beam column member, carrying out the processing and conversion of the extracted information through employing dynamo nodes, obtaining a beam column three-dimensional curve model, and carrying out the extraction of the beam column three-dimensional curve model. And finally, checking the connection relation of the three-dimensional curve model of the beam column, and exporting a file in a dwg format. According to the method, the three-dimensional line model of the revit structure model is rapidly extracted, and the method is used for analysis and calculation of other structure calculation software. By using the nodes customized and configured in dynamo, automatic information extraction and processing are realized, and the working efficiency is improved. And all necessary information is directly extracted from the Revit source file, so that the high accuracy of the generated three-dimensional curve model in size and spatial position is ensured. And furthermore, the file is exported in a dwg format, so that seamless integration with other structural calculation software is facilitated.

The invention discloses a self-supervised generative adversarial network defect detection method based on physical model constraint, and belongs to the technical field of industrial visual inspection. A physical model is embedded in a traditional GAN network structure, a physical constraint loss function is defined to control a generated sample, and meanwhile, a field adaptive migration mechanism is introduced; and mapping the generated image to a target production line domain to realize cross-production line model migration. A self-supervised consistency discriminator is further constructed, the robustness of the discriminator is enhanced through image disturbance invariance, and finally few-sample self-learning of high-precision defect detection can be completed without manual labeling. According to the defect detection method, a physical modeling mechanism and a generative adversarial network are combined, stress release constraint is introduced, a domain discrimination loss function, a cyclic consistency loss function and a self-supervision loss function are introduced to construct a high-performance discriminator, and the problems that defect samples are scarce, data are difficult to mark, and models are difficult to migrate in an industrial scene are solved.

The invention relates to the technical field of hydrology, and discloses a construction method of a watershed instantaneous unit line model based on a hydraulic energy complementation equation, a construction device of the watershed instantaneous unit line model based on the hydraulic energy complementation equation, a watershed instantaneous unit line determination method, a watershed instantaneous unit line determination device, electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining sample rainfall runoff data of a sample drainage basin, constructing a basic model of a drainage basin instantaneous unit line model based on a hydraulic energy complementation equation, substituting the sample rainfall runoff data into the basic model, solving the basic model, performing parameter calibration by taking a precision index Nash efficiency coefficient as a target function, and obtaining a drainage basin instantaneous unit line model. And determining model parameters by maximizing the objective function, and substituting the model parameters into the basic model to obtain a watershed instantaneous unit line model based on the hydraulic energy complementation equation. The application range of the construction method of the instantaneous unit line is widened, and the accuracy of the construction result is improved.

The invention relates to an intersecting line welding seam extraction method, a medium and equipment. The method comprises the following steps: constructing an initial intersecting line welding seam model, collecting workpiece contour point clouds, obtaining a plurality of main pipe local point clouds and a plurality of branch pipe local point clouds, fitting elliptic equations for the local point clouds, obtaining circle centers corresponding to the local point clouds, fitting straight lines according to the circle centers, and extracting intersecting line welding seams. Obtaining the surface parameters of the main pipe according to the elliptic equations, updating the initial intersecting line welding seam model according to the axis equations and the surface parameters of the main pipe, obtaining an optimized intersecting line model, obtaining the included angle between the axis equations of the main pipe and the branch pipes and a conversion matrix, and substituting the included angle and the conversion matrix into the optimized intersecting line model. And obtaining an intersecting line parameter equation so as to extract an intersecting line welding seam. The problems that in the prior art, machining precision is low, adaptability is insufficient, meanwhile, collection precision is low due to high workpiece reflective rate, and welding quality is affected are solved.

The present invention discloses a cable status assessment method, device, and non-volatile storage medium. The method comprises: constructing a fault arc model and a line model corresponding to a target cable; generating a simulation waveform based on the fault arc model and the line model; determining target fault parameters based on the measured waveform and the simulation waveform at the fault point in the target cable, wherein the target fault parameters represent indicator data describing the fault characteristics and status; determining the waveform characteristics of the fault point based on the target fault parameters; and determining the target cable status assessment result based on the waveform characteristics. The present invention solves the current technical problem of difficulty in sensitively capturing and accurately assessing early-stage faults in cable equipment, particularly transient fault characteristics, resulting in inaccurate cable assessments.

The invention relates to the technical field of mechanical manufacturing and machining, in particular to a dressing wheel and honing wheel design method for improving contact line stability in the gear honing machining process. Based on workpiece gear parameters, a left and right tooth surface mathematical model is established, a honing process space coordinate conversion relation is established, a conjugate meshing relational expression is derived by combining the relative slip speed of meshing contact points and a normal vector, and a tooth surface contact line model is established; and the calculation modeling of the two-dimensional projection of the left and right tooth surface contact lines, the projection intersection point position and the variation under the same rotation angle is realized. And a honing wheel dressing contact line model under dressing wheels with different tooth numbers and a tooth surface contact line intersection projection model in the dressing and honing process under the tooth number difference are established. A honing wheel and variable tooth number dressing wheel design method is provided, and geometric and technological parameters of the honing wheel and the variable tooth number dressing wheel are determined; and a trimming and honing two-degree-of-freedom conjugate meshing relation and a modified tooth surface numerical model are constructed and verified, discretization and point cloud processing are conducted on the model, high-precision tooth surface point cloud is obtained, and accurate machining of a trimming wheel and a honing wheel is guided.

According to the unmanned aerial vehicle aerial photo three-dimensional inspection power line intelligent extraction method, firstly, a sampling area is drawn on an image through manual intervention, an LSD straight line segment detection algorithm is adopted as a basic algorithm for power line extraction, and according to the gradient symmetry characteristics of the power line, a straight line method is combined to extract the power line; establishing a method suitable for unmanned aerial vehicle inspection image power line extraction; then, based on the linear features of the aerial image power line, matching is conducted by adopting a method based on epipolar constraint, the intersection point of the power line and the epipolar constraint is used as a homonymy point, coordinates of sampling points are automatically calculated by adopting a method based on shape factor constraint, finally, fitting is conducted on the power line through the sampling points and a catenary equation, and a three-dimensional power line preliminary model is obtained; the line hanging point is extracted based on the two-dimensional constraint method and is incorporated into the catenary equation for re-fitting, a more complete three-dimensional power line is extracted, the system stability is good, the space inspection efficiency is high, the power line detection and extraction speed is high, and the accuracy rate is high.

The invention discloses a resonant grounding power distribution network single-phase grounding fault line selection method and system. The method comprises the following steps: when a single-phase earth fault occurs in the power distribution network, acquiring real-time zero-sequence current data of each feeder line; and inputting the real-time zero-sequence current data into the fault line selection model to judge a fault line and output a result. The training process of the fault line selection model comprises the following steps: acquiring a noisy source domain data set from an electromagnetic transient simulation platform and a target domain data set from a real power distribution network; constructing a noise reduction automatic encoder as a feature extractor, and performing unsupervised pre-training by using the source domain data set to minimize a reconstruction error; pre-trained feature extractor parameters are frozen, and a trainable fault classifier is connected to form a transfer learning model; and carrying out supervised training on the model by using the source domain and target domain data sets and taking the fault line selection accuracy as a target to obtain a final model. By implementing the method provided by the invention, the accuracy and generalization ability of the line selection model in a real noise environment can be effectively improved through transfer learning and noise reduction feature extraction.

This invention discloses a method for porting intelligent models based on domestically produced intelligent chips. The method involves using a porting tool provided by the domestically produced intelligent chip to rewrite the model, obtaining a model file corresponding to the version of the porting tool. If the internal logic of the original model has been changed, operators are added to the model file corresponding to the version of the porting tool, resulting in a model file with added operators, and proceeding to the next step. If no changes have been made, the method proceeds directly to the next step. The model file is then quantized to obtain a quantized model file. An offline model is generated based on the quantized model file. The original intelligent model and the offline model are loaded with the same computational example, and the results of the two models are compared. If the difference in the results meets the requirements, the porting process ends; otherwise, the porting problem is identified and the process restarts. This invention solves the compatibility problem of intelligent models without affecting the operating efficiency, response speed, and accuracy of the artificial intelligence model.