2716 results about "Computer-aided" patented technology

The invention discloses an insulator defect detection method based on multi-scale features and channel perception, and belongs to the technical field of computer-aided algorithms. The method comprises the following steps: firstly, constructing a multi-scale feature fusion module, and fully extracting context information by combining multi-scale feature information and through a series of parallel deep convolution; secondly, a self-adaptive channel sensing down-sampling module is embedded in the backbone network, so that small-scale feature information is prevented from being lost during down-sampling of a feature map, and the sensing capability of the model to important channel information is improved; and finally, on the basis of adding a small-scale target detection layer, designing a lightweight shared phantom convolution detection head so as to improve the multi-scale target detection capability of the model under the condition of reducing the model parameter quantity. According to the method, a good effect is achieved on insulator defects of different types and multiple scales, the average detection precision is 91.4% and is improved by 5.2% compared with a reference model, and the overall performance is superior to that of other insulator defect detection algorithms.

A presentation assistance system receives information about a presentation to be given and automatically provides feedback to improve the presentation either offline or in real time as the presentation unfolds using computer models, where a presentation is a collection of multi-media content, including but not limited to text, slides and graphics, and audio and video streams. The computer models may be trained based on prior presentations and performance metrics of relevant entities. In particular, the presentation includes interactions with audience members and computer models are used to generate likely participants and related interactions, such as questions or recommendations for improved interactions, relevant to the current presentation based on a set of machine learning and AI models, and, in particular, language models. The language model may be prompted with prior relevant questions to determine questions for the current presentation and evaluate the likelihood that the current presentation effectively answers them.

The invention relates to the technical field of computer aided design, in particular to a text-driven CAD modeling method and system based on a diffusion and visual language model.The method comprises the steps that natural language text description is obtained, and CAD semantic features of the natural language text description are extracted; carrying out geometric standardization on the CAD semantic features by adopting a fine-tuning diffusion model, and generating a CAD view image conforming to engineering specifications; carrying out fusion by adopting a fine-tuned visual language model to generate a parameterized CAD construction sequence; a three-mode alignment mechanism is adopted, and the semantic consistency of the CAD semantic features, the CAD view images and the CAD construction sequences is checked; performing verification and post-processing on the CAD construction sequence, and outputting an executable Python code or STEP file; the CAD modeling method disclosed by the invention performs explicit modeling based on flexible modal description, and has the characteristics of high geometric constraint and high usability.

The invention discloses a multi-agent computer-aided engineering and a computer-aided design method. CAE simulation and design optimization for the design of a complex product are high in threshold and difficulty. According to the method, autonomous planning and automatic execution of CAE simulation and CAD design optimization tasks are realized by using a multi-agent technology based on a large language model. A user interacts with the multi-agent system in the modes of text input, voice, a graphical user interface and the like, the multi-agent system autonomously plans workflow steps according to the requirements of the user, all agents cooperatively execute the working steps in a labor division mode, CAE and CAD software is called to execute simulation and design change, CAE and CAD result data are read and analyzed, the task completion condition is evaluated, and the task completion condition is evaluated. And the task can be re-planned if necessary. The system can automatically process error information, and can notify a user to process when user intervention is needed. The performance of the system can be improved through fine tuning of a large language model and retrieval enhancement generation technology.

The present disclosure presents systems, methods, and non-transitory computer-readable media for transforming civil, architectural, or engineering drawings into Building Information Modeling (BIM) or Computer-Aided Design (CAD) models. One such method comprises training an artificial intelligence algorithm on a collection of 2D civil and architectural blueprint designs to enable the artificial intelligence algorithm to efficiently extract elements from the blueprint designs and map them into 3D data model objects; creating a 3D data model using the trained artificial intelligence algorithm, from an input collection of 2D blueprint designs; creating a project database by adding metadata from the input collection of 2D blueprint designs; generating a database of code rules and regulations; performing, using the project database, and the database of code rules and regulations, a compliance check to determine if the 3D data model complies with the database of code rules and regulations; and presenting results of the compliance check.

Systems / techniques that facilitate de-identified search of part designs are provided. In various embodiments, a system can access a part design file provided by a client device, wherein the part design file can comprise a computer-aided design (CAD) geometry of a part. In various aspects, the system can determine whether the part design file is subject to any manufacturing restrictions, via performance of a multi-staged search of an historical database. In various instances, the multi-staged search can be based on a cryptographic hash of the part design file, on a spatial hash of the CAD geometry, and on an anonymized feature vector extracted from the CAD geometry. In various cases, the system can return, to the client device and in response to the multi-staged search, an electronic notification indicating whether the part design file is subject to any manufacturing restrictions.

The invention relates to a method for checking spacing in a large-scale integrated circuit layout, which belongs to the technical field of integrated circuit computer aided design, and comprises the following steps: S1, dividing an integrated circuit layout to be processed into a plurality of local layouts according to a preset division rule, including an original local layout and an interference local layout; outwards expanding the edges, determined by a preset division rule, of the interference local layouts to obtain expanded local layouts; s2, checking whether the edges of all the functional parts in all the local layouts meet the constraint condition upper limit corresponding to the selected preset checking rule one by one according to the currently selected preset checking rule so as to screen out the edges meeting the potential conditions; s3, forming associated edge pairs, and screening the associated edge pairs through a filter to obtain associated edge pairs meeting filtering conditions; and S4, carrying out secondary cutting on the associated edge pairs according to the cutting ranges of the associated edge pairs meeting the filtering conditions.

A computerized method for generating a 3D Computer-Aided Design (CAD) is provided. The method comprising: receiving an input comprising requirements for a new design; processing the input to generate a CAD design using a trained AI model, wherein the CAD design is an assembly of at least two separate components; and outputting the CAD design.

The invention discloses a digital steel structure embedded part accurate positioning system, and belongs to the technical field of computer aided design and digital twinning, and the system comprises a data acquisition module which is used for obtaining a correction vector of a digital twinning model, the currently measured local positioning precision and the current global attitude consistency deviation; the model entropy calculation module is used for calculating a model authority entropy representing the accumulated deviation degree of the digital twin model based on the correction vector and a preset reference correction scale; the model authority calculation module is used for determining the model authority of the digital twin model according to the model authority entropy and a preset attenuation sensitivity coefficient; and the correction decision module is used for generating a correction acceptance probability in combination with the model authority and the local positioning precision, and performing probabilistic screening on the execution of the correction vector based on the correction acceptance probability, thereby providing a solid quantitative basis for subsequent judgment of the health condition of the model.

The invention discloses a new energy automobile body frame lightweight design method based on digital twinning, and relates to the technical field of new energy automobile body structure design and computer-aided engineering simulation, and the method comprises the following steps: S1, building a digital twinning body connected with a physical automobile body sensing system; s2, a dynamic precision topology network module is used for dynamically dividing a simulation precision area of the vehicle body frame according to the mechanical energy transmission path and the real-time sensing data. According to the new energy automobile body frame lightweight design method based on digital twinning, intelligent allocation of computing resources is realized through a dynamic precision topology network, and the computing burden of multi-physics coupling simulation is effectively reduced while precise prediction of a key structure is ensured; the sharp contradiction among the model precision, the real-time response and the optimization efficiency is effectively solved, and effective closed-loop iteration of the lightweight design is achieved under the complex constraint condition.

The invention provides a computer-aided slide-resistant pile and anchor cable build-in depth design method, and relates to the technical field of slide-resistant pile and anchor cable design, and the method comprises the following steps: collecting drilling data of an engineering site, and establishing a three-dimensional geologic model containing spatial distribution of each soil layer; determining a feasible range of design parameters; according to the soil layer space distribution and parameters, a slope stability analysis model considering the supporting effect of the slide-resistant piles and the anchor cables is established and used for calculating the slope stability safety coefficient under the given design parameters; and taking the minimum construction cost as a target function, determining an optimization constraint condition according to the slope stability analysis model, carrying out iterative optimization on the design parameters in a feasible range by adopting an optimization algorithm until an optimization convergence condition is met, and outputting an optimal design parameter. The problems that a traditional design method excessively depends on experience, multiple influence factors are difficult to consider, and the calculation efficiency is low can be solved, and the design level of the built-in depth of the slide-resistant pile and the anchor cable is improved.

The invention belongs to the technical field of geometric pretreatment in computer aided engineering (CAE), and particularly relates to a dirty geometry restoration method for a complex three-dimensional geometric model, which comprises a dirty geometry detection and restoration module based on heuristic rules and geometric topology analysis. By means of a multi-model collaborative alignment and bonding mechanism, high-precision assembly between parts is achieved through geometric feature matching and adjacent domain self-adaptive adsorption; acquiring material attributes provided by the simulation platform, and performing accurate cutting and boundary reconstruction on an intersection domain based on an intersection domain intelligent segmentation algorithm of the material attributes to ensure correct mapping of boundary conditions of a physical field; a geometric Boolean processing engine iterative learning mechanism of a general merging algorithm is integrated, and a high-quality model for simulating a grid is generated through multi-round iterative optimization. According to the method, double challenges of internal dirty geometry of a single model and derivative dirty geometry of intersection / adjacent areas among multiple bodies are solved, and key physical attributes and topological continuity of electromagnetic signal links are ensured and are completely reserved during repair.

The invention relates to the technical field of data processing and three-dimensional model construction, in particular to an intelligent three-dimensional model design method and system based on small-opening press-blow molding equipment. The method comprises the following steps that an intelligent sensor is used for collecting parameters of small-opening press-blow forming equipment, and initial equipment parameter information is recorded; according to the initial equipment parameter information, establishing an equipment three-dimensional initial model by using computer aided design software; and acquiring characteristic data of the glass material drops, inputting the characteristic data of the glass material drops into the three-dimensional initial model of the equipment, simulating a press-blow molding process by utilizing simulation software, and carrying out influence evaluation on the simulated press-blow molding process to obtain a molding process evaluation result. Through a data processing technology, a three-dimensional modeling technology and an automatic control technology, various parameters of the small-opening press-blow molding equipment are associated and evaluated, and an intelligent three-dimensional model of the equipment is constructed; and the accuracy of control operation of the forming equipment is improved, so that the produced glass containers are kept consistent in specification.

The invention relates to the technical field of fuel cell system anomaly detection, in particular to a fuel cell system time series data anomaly detection method based on residual analysis, and the method comprises the specific implementation steps: obtaining multi-source design simulation data of a system, and constructing a multi-source design simulation data tensor; constructing a computer aided design model, performing behavior simulation on the simulation data tensor, and outputting a simulation design behavior value; the simulation data is used as a simulation observation value to be compared with a simulation design behavior value, a multi-dimensional residual sequence is obtained through calculation, and online self-adaptive updating is conducted on the design model; establishing a physical reachability matrix, and adjusting a dynamic threshold value based on the matrix and a real-time simulation working condition; performing weighted fusion on the multi-dimensional residual sequence to generate a collaborative design constraint index, and comparing the collaborative design constraint index with the dynamic threshold to generate a computer aided design verification result; and inputting the design verification result into a preset residual-control mapping rule, and outputting a design parameter optimization instruction to optimize the design parameters.

The invention relates to a computer-aided classification method (10) for a joining geometry (12; 12a-e) of a contact joint (14) between two workpieces (16, 18) to be joined of a workpiece arrangement (20; 20a-e), comprising the method steps: - Positioning (22) a sensor (24) of a measuring system (26) in a predetermined processing position of a processing optic (28) of a laser processing machine (30) at a joining point (32) of the workpiece arrangement (20; 20a-e); - Creating (38) a geometric profile (40; 40a-e) of the workpiece arrangement (20; 20a-e) by scanning a surface (42) of the workpiece arrangement (20; 20a-e) at the joining point (32) in a measuring plane (44) transverse or perpendicular to a principal extension direction (46) of the contact joint (14); - Determining (50) the joining geometry (12; 12a-e) by evaluating and comparing the geometry profile (40; 40a-e) with stored reference profiles (52; 52a-e) for specific joining geometries (12; 12a-e). The invention also relates to a manufacturing process (60) and a manufacturing system (70).

The invention relates to the technical field of computer aided design and intelligent optimization, in particular to a sponge park multi-objective collaborative optimization design method based on an LID technology, and the method comprises the steps: building an LID facility parameterized database through collecting the multi-source data of geographic space, hydro meteorology and the like; a multi-objective collaborative optimization model covering hydrological, ecological, economic and social benefits is established, a mixed intelligent optimization algorithm composed of an improved NSGA-II algorithm and an enhanced particle swarm optimization algorithm is used for solving, and a Pareto optimal solution set is generated; screening a comprehensive optimal scheme by means of an SWMM and GIS coupling technology and an improved TOPSIS method; an Internet of Things monitoring network and a digital twinborn system are deployed, and self-adaptive dynamic optimization of a design scheme is realized according to triggering conditions such as runoff coefficient deviation and vegetation coverage rate change. The method breaks through the limitation of a traditional single target, remarkably improves the comprehensive benefits of the sponge park through multi-target cooperation, intelligent algorithm optimization and dynamic adjustment, and guarantees the long-term stable operation of the sponge park in a complex environment.

The invention relates to the technical field of computer aided design, in particular to a distributed building structure intelligent design system and method under a low-carbon background, and the method comprises the steps: a BIM parameter optimization module constructs a building group adjacent matrix and a sunlight shielding coefficient based on building structure data, calculates a ventilation score, combines a window heat transfer coefficient, and employs an SQP algorithm to optimize a window-wall ratio; and the route generation module constructs energy nodes and connection paths by using the adjacent matrix of the building group. And the carbon emission analysis module comprises construction carbon emission calculation, multi-factor coupling prediction and net carbon emission polymerization, can predict future carbon emission based on an LSTM algorithm, and evaluates the net carbon emission of the building group in combination with ecological restoration. And the routing optimization module generates an initial feasible solution by adopting a heuristic algorithm according to a carbon emission analysis result, and optimizes energy node configuration and an optimal connection path of the building group through mixed integer programming, so that the intelligent design efficiency of the building structure is improved.

The invention discloses an unsteady flow field dimension reduction and prediction method fusing physical modeling and deep learning, and belongs to the technical field of computer-aided fluid mechanics analysis. According to the method, firstly, a modal coefficient reflecting global dynamics is extracted from an unsteady flow field by using a DMD, and meanwhile, low-dimensional feature representation of a potential space is learned from a flow field snapshot through CVAE; the two types of features have complementarity in physical and statistical meanings, and the complex dynamic evolution law of the unsteady flow field is more effectively represented through the low-dimensional features constructed in a combined mode. On the basis, an LSTM model is used for carrying out time sequence modeling on the joint features, and high-precision prediction of future evolution of the flow field is achieved. The hybrid modeling method provided by the invention improves the dimensionality reduction efficiency and prediction precision of a high-dimensional nonlinear unsteady flow field while keeping physical consistency, and is suitable for intelligent simulation and rapid prediction tasks in a complex flow scene.

The invention discloses a multidisciplinary software co-simulation method and device, equipment and a medium, and relates to the technical field of computer-aided engineering, and the method comprises the steps: when a simulation request sent by a client is received, determining target CAE software and a target control flow for executing the simulation request according to a simulation application scene of the simulation request; and performing control process description and software parameter description on the target control process and each piece of target CAE software to obtain a first configuration file and a second configuration file, sending the first configuration file to the client, so that the client analyzes the first configuration file, analyzes the second configuration file based on the feedback control process parameter, and sends the analyzed second configuration file to the client. Obtaining software parameter information of each piece of target CAE software; and scheduling the target CAE software in sequence according to the software parameter information and the control process parameters, and executing a simulation process to obtain a simulation result after co-simulation. A convenient flow free customization and component rapid combination mode is provided for a user, and co-simulation is realized.

The invention provides a patterned reinforcing material 3D printing method and system based on an acoustic manipulation technology, relates to the combination of the acoustic manipulation technology and a digital light processing (DLP) technology, and is used for manufacturing a composite material sample piece containing patterned reinforcing filler distribution. According to the technology, a three-dimensional model is designed through computer aided design software, plane ultrasonic waves are converted into a specific three-dimensional sound field through a digital acoustic hologram, and accurate control over reinforcing filler in photosensitive resin is achieved. The acoustic control system controls the distribution of the reinforcing filler, and the DLP projector is used for curing the composite material layer by layer. The method allows the digital acoustic hologram to be adjusted in real time so as to adapt to different reinforcing filler patterning assembly and reinforcing requirements. According to the technical scheme, the control capability of 3D printing on reinforcing filler distribution is improved, and the application field of the composite material is widened.

The invention provides a boiler combustion state visualization method, which comprises the steps of embedding a plurality of thermocouple temperature sensors in gaps of refractory bricks on the inner wall of a boiler hearth, acquiring temperature data of the hearth at different depths in real time, and transmitting the temperature data to a data acquisition terminal through a wireless communication module; fitting the normalized temperature data matrix by adopting a three-dimensional thin-plate spline interpolation algorithm to generate a hearth three-dimensional real-time temperature distribution model, performing mesh generation on the three-dimensional temperature distribution model by combining hearth geometric structure parameters obtained from computer aided design software, and constructing a hearth temperature finite element model; the hearth temperature finite element model is imported into ANSYS finite element analysis software, hearth wall surface material attributes and combustion heat load boundary condition parameters are set, transient thermal analysis of a hearth temperature field is carried out, and a temperature estimation value of any position of the hearth changing along with time is obtained.

A surgical navigation system for providing computer-aided surgery. The surgical navigation system includes a handheld surgical tool with computer-aided navigation, a graphical user interface module, and optionally an imaging device. The handheld surgical tool includes a handle that may comprise at least one sensor for detecting orientation of the. A computing device and at least one display device are associated with the handheld surgical tool and configured to display a target trajectory of the handheld surgical tool for the surgical procedure.

The invention discloses a personalized computer-aided decision-making method and system fusing multi-modal data, and relates to the field of personalized computer-aided decision-making, and the method comprises the steps: mapping multi-source heterogeneous modal data to a unified semantic embedding space, and obtaining a multi-modal unified representation vector set; carrying out three-layer progressive fusion on a feature layer, a situation layer and a decision layer of the multi-modal data to generate a global decision context vector; based on a cross attention mechanism, outputting a fused context sensing personalized vector; based on the behavior cloning model, outputting probability distribution on all decision options; according to the user feedback operation data, generating a user personalized decision strategy and performing dynamic optimization; and generating a structured decision report containing visual traceability information based on the hierarchical fusion process and decision reasoning logic. End-to-end intelligent generation from multi-source heterogeneous data to personalized decisions is realized, and a standardized process is converted into personalized customized decisions.

The invention relates to the technical field of computer vision, computer aided design and artificial intelligence, and discloses a geometric feature recognition method based on a large language model, which comprises the steps of three-dimensional model natural linguistization, large language model feature reasoning, incremental learning and optimization, and feature verification and output. According to the geometric feature recognition method based on the large language model, three-dimensional geometric data are converted into structured text description, and a joint representation space of'geometric parameter-topological relation 'is constructed, so that the large language model can better understand the meaning of geometric features and the structure of parts; the method comprises the following steps: analyzing topological association among geometric features by utilizing long context understanding ability of a large language model, capturing dependency among the features through an attention mechanism, realizing hierarchical recognition of the features in a complex assembly, dynamically updating a geometric feature knowledge base of the large language model by continuously learning new geometric cases and engineering specifications, and realizing hierarchical recognition of the features in the complex assembly. Adaptive recognition of novel features is supported, and the model does not need to be retrained.

A system and method are provided for aligning a tool with a targeted axis in tissue to perform a medical procedure. A medical plan is registered to the location of the tissue using a computer-assisted medical system, where the medical plan include a planned position for the targeted axis based on pre-procedure data. The tool is aligned with the planned position for the targeted axis using a computer- assisted medical system. The computer-assisted medical system includes a hand- held device having a handle and a working portion adjustable relative to the handle so as to orient the tool. A computing system is also provided comprising a tracking system and a control system for registering the medical plan to the location of the tissue, tracking the hand-held device relative to the tissue and the medical plan, and adjusting the working portion of the hand-held device relative to its handle.

The invention relates to the technical field of data processing, in particular to a computer-aided air conditioner load prediction model simulation construction method, which comprises the following steps of: acquiring data of each environmental parameter in a building at all moments in each period in real time to form a monitoring sequence; the method comprises the following steps: performing analogue simulation on energy consumption of an air conditioner to obtain load data of an air conditioner load at all moments in each period, and forming a load sequence; acquiring a lagging time length; extracting a time delay subsequence of each environmental parameter in each period; the trend synchronization degree between each environment parameter and the air conditioner load in each period is determined; determining a coupling coefficient of any two environmental parameters in each period; determining a reference evaluation value between the current period and each of the rest periods; obtaining each reference period; and constructing a load prediction model. According to the method, prediction deviation caused by neglecting interaction influence and lag influence among various environmental parameters can be avoided, and the prediction accuracy of the air conditioner load is improved.

The invention relates to the technical field of information, in particular to a forming process and system of a high-precision injection hook in the technical field of injection hook forming. The forming process includes the steps that computer aided design and finite element analysis are applied, the forming process of the injection hook in a mold is simulated, the mold structure is optimized, and the mold testing frequency is reduced; a high-precision mold is integrated with a cooling channel of a preset ejection hook arrow-shaped structure, a temperature sensor is arranged in the cooling channel, the cooling state is monitored in real time, cooling parameters are adjusted based on monitoring data, and precise structure forming is achieved. And the machine vision system detects the integrity and direction consistency of the arrow-shaped structure of the molded ejection hook on line, identifies unqualified products, automatically removes the unqualified products, records defect types, and sends defect type data and corresponding product batch information to the production data acquisition module.

The invention discloses natural language computer-aided engineering and a computer-aided design method. CAE simulation analysis and design optimization on complex product design are high in threshold and difficulty. According to the method, an artificial intelligence large language model is finely adjusted by using professional knowledge of CAE and CAD, an agent is developed to call an API service of the large language model, an engineer dialogues with the agent by using a natural language, and the large language model can understand purposes and requirements of the engineer and generate corresponding operation instructions or program codes of CAE software and CAD software; the agent drives the CAE software and the CAD software to execute instructions or run programs to complete simulation analysis and design optimization tasks, and an engineer can cooperate with a plurality of professional CAE software and CAD software to perform simulation analysis and design optimization of multi-physics coupling only by dialogue with the agent. The intelligent agent can autonomously complete loop iteration simulation analysis and design optimization tasks according to formulated scheme steps and rules.

The invention belongs to the technical field of computer-aided manufacturing, and relates to a method and system for predicting the propagation rate of fatigue cracks across welding zones in electric arc additive remanufacturing, and the method comprises the following steps: S1, manufacturing a sample; s2, performing in-situ SEM fatigue test on the sample; s3, obtaining a corresponding relation between the crack growth rate and the stress intensity factor range of the sample; s4, fitting to obtain a fatigue crack propagation rate model of the sample; s5, establishing a CZH sample fatigue crack growth rate prediction model; and S6, predicting the fatigue crack propagation rate of the sample across the welding zone. The system further comprises an electric hydraulic fatigue test system, a data acquisition module, a database, a fitting module and a prediction module. According to the method, by using the correction coefficient, the fatigue crack growth rate is predicted by using the fatigue crack growth rate parameter of the matrix material area.

A method of manufacturing a foam component includes generating, via a computer aided design (CAD) software, three-dimensional data corresponding to the foam component. The method further includes scaling, using the CAD software, the three-dimensional data to correspond to a preform. The preform is smaller than the foam component based on a scaling factor. The method further includes fabricating the preform from a thermoplastic elastomer and adding a foaming agent to the preform. The method further includes foaming the preform by exposing the preform to a target temperature for a target time via a heat generating device.