57 results about "Structural analysis" patented technology

The invention relates to a large document analysis model, a training method and a multi-task document structured analysis method, which are suitable for the fields of artificial intelligence, computer vision and natural language processing. The model comprises a visual coding module used for extracting an image feature vector from a document page image, and the extraction of the image feature vector comprises the step of capturing a dependency relationship on a spatial dimension and a channel dimension by adopting a double attention module; the visual feature projection module is used for mapping the image feature vector extracted by the visual coding module from a visual feature space to a feature space of the text decoding module to generate a visual projection feature vector; and the text decoding module is a large language model based on a Transform decoder architecture, and is used for generating document space layout information or document content corresponding to the document processing task on the document page image based on the visual projection feature vector and the token sequence after word segmentation of the cue word of the document processing task.

The invention discloses a deep foundation pit structure crack AI intelligent monitoring control method and system, and relates to the technical field of civil engineering structure health monitoring, and the method comprises the following steps: S1, measurement positioning: obtaining project control points of a field working face and feature data of foundation pit structure side lines, and carrying out positioning recheck based on positioning data of a positioning system; s2, unmanned aerial vehicle scanning: guiding the unmanned aerial vehicle to move in the deep foundation pit site based on the measurement positioning data, and scanning the site by a pre-loaded scanning radar to obtain point cloud data of the deep foundation pit structural surface; s3, modeling: modeling based on the point cloud data, identifying structure change features based on a model, and marking feature attributes; and S4, structural analysis and early warning: outputting a structural abnormity prompt based on the annotation information, and recording change information of the structure based on a time sequence for structural evolution analysis and prediction. The method has the effect of improving the monitoring effect of the deep foundation pit crack.

The embodiment of the invention discloses a stratum denudation data determination method and device, equipment and a medium. The method comprises the following steps: determining a target layer, a Shanghai generic surface and a Shanghai generic surface of which stratum denudation data needs to be calculated; wherein the upper marine flooding surface is located above the top surface of the target layer and closest to the top surface of the target layer, and the lower marine flooding surface is located below the bottom surface of the target layer and closest to the bottom surface of the target layer; determining denudation points according to the target layer and the underlying stratum; wherein the underlying stratum is a stratum located between the bottom surface of a target stratum and a lower sea flooding surface; and determining the stratum denudation amount according to the thickness between an upper line extending upwards in the stratum direction from the denudation point and the bottom surface of the target stratum. According to the scheme, the stratum denudation amount can be determined more accurately and quickly according to the stratum characteristics and the seismic data which are easy to obtain, higher practicability is achieved, and basic data are provided for later-stage structural analysis, hydrocarbon source rock evolution, oil and gas accumulation condition analysis and the like.

The application discloses a kind of quantitative description fault inversion process method based on balanced section, comprising the following steps: S1: selecting geological profile;S2: division different inversion stage sequence stratigraphy;S3: determine the geologic time of different activity stages of inversion fault;S4: use balanced section technology to restore the evolution history of inversion fault;S5-S7: calculate the slip distance of different stages inversion fault, and calculate the slip rate, inversion intensity coefficient of different inversion stages;S8: establish equivalent point distance, total slip distance, slip rate and inversion intensity coefficient trend chart with geologic time variation, the application is suitable for basin structural analysis technical field, introduce balanced section technology, can more accurately restore fault inversion process;Moreover, can clearly, accurately, quantitative characterization fault inversion process from fault slip distance, the activity intensity of different stages and inversion intensity etc., facilitate different inversion structure contrast, basin structural analysis etc. work is carried out.

This invention belongs to the field of reactor structural mechanics technology, specifically relating to a method for analyzing and evaluating high-temperature bolted connection sealing structures. The invention includes the following steps: selecting the location of the reactor pressure vessel flange and main bolt connection as the object of sealing structure analysis; analyzing and summarizing the influence of gasket data on the deformation and contact surface pressure of various components of the flange bolted connection structure; researching current standards and analyzing their limitations; using the finite element software ANSYS to perform finite element modeling of the reactor pressure vessel flange and main bolt structure; applying loads and constraints to the finite element model of the reactor pressure vessel flange and main bolt structure; calculating the deformation and stress of the structure using different creep and relaxation models; analyzing the relaxation behavior of the high-temperature flange bolted connection structure using experimental methods; and comparing and analyzing the results of the finite element method, the standard method, and the experimental method. This invention enables the analysis and evaluation of the sealing performance of flange bolted connection structures under high-temperature environments.

The invention relates to the technical field of ocean engineering, and discloses a hydrodynamic load quick correction method for a large-diameter cylinder structure, which comprises the following steps of: establishing a digital model of a mixed structure comprising the large-diameter cylinder structure and defining a load working condition; aiming at the working condition, calculating an initial hydrodynamic load and an accurate hydrodynamic load according to a Morison formula and a three-dimensional potential flow theory respectively; generating a corresponding hydrodynamic load correction coefficient according to the ratio of the accurate hydrodynamic load to the initial hydrodynamic load; finally, the correction coefficient is applied to the initial hydrodynamic load, and the corrected hydrodynamic load is obtained and used for structural analysis. According to the method, the rapid calculation result is calibrated through the pre-generated correction coefficient, the problem that calculation efficiency and precision are difficult to consider at the same time in the prior art is solved, and the load calculation efficiency and engineering applicability are improved on the premise that the calculation precision is guaranteed.

The application discloses a kind of engine cooling fan assembly strength calculation method based on one-way fluid-solid coupling, comprising: the geometric model of cooling fan assembly is established;Utilize the finite element model of cooling fan assembly and external flow field generated by mesh division software;In structural analysis software, respectively, to cooling fan and fan support plate is endowed with material mechanics characteristics, and boundary condition is set;In computational fluid dynamics software, set the turbulence model and boundary condition of external flow field;Blade surface is set as fluid-solid coupling surface, first solve flow field using computational fluid dynamics software, pass blade surface pressure in calculation result to finite element software by interpolation, and finite element software is used as boundary condition to simulate and analyze the structural strength of cooling fan assembly, and obtain cooling fan assembly strength.The application improves the accuracy of the model and ensures the calculation efficiency by taking the aerodynamic pressure load on the blade as the boundary condition when predicting the structural strength of the cooling fan.

This technology enables the numerical analysis of the effect that anisotropic materials have on the overall rigidity of a structure when the material is anisotropic. [Solution] A structural analysis method for an anisotropic material according to one aspect of the present invention comprises the steps of: assigning calculation points to structural data (S11); assigning material properties including anisotropy to structural data (S12); assigning load points, support points, and arbitrary points to the calculation points (S13); and determining an index (A) based on the ratio of a first work required for the displacement of the load point when the material axis vector at the arbitrary point is set according to the anisotropy of the material properties, and a second work required for the displacement of the load point when the direction of the material axis vector is rotated to coincide with the displacement direction of the load point. * The steps involve calculating the index (A) while changing an arbitrary point. * ) is calculated, and the index (A) in the structural data is calculated. * The system comprises the steps of calculating the distribution of (S14-S16) and

A computer-implemented method for repairing a structural defect includes determining a size and position of a defect within a structural element and, in accordance with a structural analysis of the defect, determining a stitching pattern that counters loss of structural integrity due to the defect. A set of holes and channels are formed in the structural element in accordance with the stitching pattern. The set of holes and channels in the structural element are filled around the defect in accordance with the stitching pattern to increase strength around the defect.

A data processing system and method for generating structural engineering documents using artificial intelligence (AI) is disclosed. The system comprises a memory storing a dataset of engineered structures, including instances of structural failures, and a machine learning model trained on the dataset to perform structural analysis and generate optimized design documents. The AI system receives input data specifying design requirements, simulates the structure's behaviours under various conditions, and generates structural engineering documents, including 3D CAD models, based on an optimal combination of materials. The system may include a feedback integration module for continuous refinement of the machine learning model, an analytics engine for performance monitoring, and an electronic filing integration for streamlining the design approval process. The AI system learns from past projects to rapidly generate code-compliant, cost-optimized, and resilient structural designs.

The invention discloses a tunnel rock-soil structure analysis method and system, and relates to the technical field of geotechnical engineering.According to the tunnel rock-soil structure analysis method and system, structured monitoring time sequence data with time and process labels are introduced, and a surrounding rock state evolution model coupling excavation disturbance factors and time effects is combined; the surrounding rock mechanical parameters are no longer regarded as fixed constants, but are predicted in a time sequence form, so that the change track of the parameters in a future preset time period can be directly obtained, and the transformation from post-event equivalent inversion to future prediction is realized; on the basis, the cost of calculating the mechanical response of the tunnel structure at a time is remarkably reduced through a forward simulation element model obtained by training a high-fidelity numerical simulation result, so that rapid evaluation on various support schemes and surrounding rock evolution conditions within reasonable time becomes possible, and a real-time iterative analysis tool is provided for site construction.

The invention relates to the field of underground powerhouse information of hydroelectric power engineering, and discloses an underground powerhouse three-dimensional model rapid construction method combining Grasshopper and Revit, comprising the following steps: S1, forming a three-dimensional terrain entity according to terrain contour line data and stratum exploration data, S2, determining a plurality of working planes on the basis of the three-dimensional terrain entity; s3, creating a drainage pipe family sample based on Revit, importing Excel data through Grasshopper to carry out parametric modeling, and generating a drainage hole curtain layout; s4, the drainage hole curtain layout generated by the Grasshopper is introduced into Revit through a Revit plug-in; and S5, performing quality inspection and repair on the constructed three-dimensional entity of the underground powerhouse. By combining Grasshopper and Revit parametric modeling technologies, rapid construction from topographic and geological data to an underground powerhouse structure entity is achieved, the problems that traditional manual modeling is long in time consumption and prone to errors are solved, meanwhile, the spatial precision of stratigraphic stratification, fracture simulation and building arrangement can be kept, and it is ensured that the model can be used for engineering numerical calculation and structural analysis.

The invention relates to the field of oil-gas field development, in particular to a quantitative evaluation method for an ultra-low permeability reservoir oil well yield contribution rate. The method mainly solves the problems that an existing method for evaluating the yield contribution rate of the ultra-low permeability reservoir fractured geology oil well is poor in accuracy of a judgment result of oil well potential detection and low in accuracy of an oil well reserve evaluation result. Comprising the following steps: S1, detecting an oil well, and performing structural analysis on a detection result; s2, carrying out oil well potential detection according to a structural analysis result; s3, reserve evaluation; and S4, contribution rate calculation. According to the quantitative evaluation method for the yield contribution rate of the ultra-low permeability reservoir oil well, whether the ultra-low permeability reservoir fractured geological oil well has potential or not can be accurately judged, the evaluation result is accurate and reliable, and a reliable basis is provided for subsequent rapid optimization of a tight oil area.

The invention provides a method for predicting off-axis tensile strength of a fiber web reinforced ECC composite material, and belongs to the technical field of novel building materials. The method specifically comprises the following steps: obtaining the axial tensile strength of the fiber woven mesh reinforced high-ductility cement-based composite material TR-ECC through a uniaxial tensile test along the warp direction of the fiber woven mesh; determining the off-axis tensile strength of the TR-ECC at at least one non-zero off-axis angle through a test; on the basis of the axial tensile strength and the off-axis tensile strength, an undetermined coefficient is calculated according to the function relation that the TR-ECC tensile strength changes along with the off-axis angle; the included angle between the load direction and the warp direction of the fiber woven mesh in the TR-ECC structure to be predicted is measured; predicting TR-ECC off-axis tensile strength according to the axial tensile strength, the undetermined coefficient and the included angle; and inputting the off-axis tensile strength as a key parameter into the TR-ECC structural analysis finite element model, and carrying out structural analysis design and optimization. The TR-ECC tensile strength at any off-axis angle can be predicted through a small amount of test data.

The application discloses a marine structure SPMT layout method based on a model structure analysis method, belongs to the technical field of SPMT layout, and is used for SPMT layout. The method comprises the following steps: determining a SPMT layout area range as a general constraint condition based on physical information of a deck piece; modeling a physical model of the deck piece on the physical information of the deck piece; and judging the distribution of a main beam in the deck piece. The method further comprises the following steps: taking a SPMT layout state as a chromosome structure to initialize a population; calculating hydraulic balance; connecting the physical model of the deck piece with a physical model of each SPMT; performing finite element analysis to obtain a structural strength value; taking the hydraulic balance and the structural strength value as two variables of a fitness function; and obtaining a unique solution of the SPMT layout state. Through automatic calculation, the method obtains a solution set of the best compromise scheme of the overall structural safety and hydraulic balance, and obtains a relatively optimized SPMT layout scheme of a marine structure.

The invention discloses an urban traffic passenger flow fluctuation prediction system based on a multi-agent model, and the system comprises a data collection and preprocessing module which is used for generating a traffic basic data set; the traffic agent construction module is used for mapping the objects into traffic agents and generating a traffic agent set; the behavior constraint construction module is used for generating a multi-agent behavior constraint set; the passenger flow reachable domain generation module is used for generating a passenger flow reachable domain; the morphological characteristic parameter generation module is used for structural analysis and morphological characteristic parameter generation; the passenger flow fluctuation window identification module is used for generating a passenger flow fluctuation generation window according to the change condition of the morphological characteristic parameters; and the passenger flow fluctuation result generation module is used for generating an interval range and a structural form result of future passenger flow fluctuation. Based on a multi-agent constraint reachable domain analysis mode, the urban traffic passenger flow fluctuation interval and the structural form are judged in advance, and the method has the advantages of being high in prediction perspectiveness and accurate in structural description.

A plurality of potential repair processes for a stack of IBRs may be determined. Each repair process may be associated with a defect on an inspected IBR. A finite element model of the stack of IBRs may be generated to model a potential repaired defect of each inspected IBR. The model may also include a plurality of vane stages disposed between adjacent inspected IBRs and an engine case. A structural analysis and an aerodynamic analysis may be performed. Whether the stack of IBRs with the potential repaired defect meets a structural criteria and an aerodynamic criteria may be determined. Each IBR in the stack of IBRs may be repaired with the repair process for the potential repaired defect for each inspected IBR in the stack of IBRs in response to determining the stack of IBRs meets the structural criteria and the aerodynamic criteria.

The present application relates to the field of building structure fire prevention design, especially to a kind of super high-rise giant steel pipe concrete special-shaped column fire performance design method, determine super high-rise giant steel pipe concrete special-shaped column basic parameter and fire prevention design target, fire retardant coating selection and coating thickness design, giant column thermal analysis model is established, giant column structure analysis model is established;Giant column fire resistance bearing capacity checking;Giant column fire resistance finite element analysis and verification.The present application has beneficial effects: the integration of super high-rise giant steel pipe concrete special-shaped column fire prevention design is realized, systematization, integrates fire retardant coating selection, thermal analysis, structure analysis, fire resistance bearing capacity checking and five big core links of finite element verification, solves the problem of the disconnection of existing design each link, low design efficiency, ensures the scientificity and integrity of design scheme;For the characteristics of irregular special-shaped column section, uneven heating, a refined thermal analysis model is established, the accuracy of the design model and the reliability of the design scheme are ensured.

The invention discloses a part standard detection model construction method and computer equipment, and the method comprises the steps: taking a part design model as input, extracting a grading reference, classifying geometric features and dimensional form and location tolerances through structural analysis, and intelligently complementing missing tolerances in combination with part function requirements and industry specifications, so as to obtain a part standard detection model; binding of dimensional form and location tolerance and geometric features is achieved through a core-auxiliary element dynamic association mechanism, association rationality is automatically checked through a geometric constraint rule, a three-dimensional tolerance zone model is constructed based on an environment-equipment double-compensation algorithm, a tolerance domain with a working condition adaptation boundary is generated, and by means of an equipment-method library of working condition adaptation, a three-dimensional tolerance zone model is established. And according to the part material, the feature priority and the detection environment, automatically matching a measurement device and an evaluation method, integrating detection information through a three-layer verification structured storage architecture, and finally generating a part standard detection model. According to the invention, a function-oriented, working condition-adaptive and standard-unified detection model can be provided for digital transformation in the field of part detection.

The invention provides a wind power mixed tower drum structure damage prediction method and system, and relates to the technical field of structure analysis and design. Bolt hole periphery strain and anchor bolt axial force data are collected according to fixed time intervals for tower drums of the same specification, the fan rotating speed is synchronously recorded, intervals are divided, data of a conventional operation rotating speed interval are screened, and the wind power mixed tower drum structure damage prediction method is provided. Calculating an allowable stress threshold value, determining a design pre-tightening force as a threshold value, when any one of the instantaneous stress or the axial force is greater than a set corresponding threshold value, judging that the damage is high-degree damage, screening a target rotating speed interval for the tower drum which does not reach the high-degree damage, extracting strain and axial force amplitudes of two continuous sliding windows in the interval, and calculating a change rate; and for the tower drum which does not reach the middle-degree damage and the high-degree damage, extracting transverse comparison data of historical reference data and other tower drums with the same specification, calculating a dynamic time warping distance, and comparing with a preset distance threshold to judge whether the tower drum is low-degree damage.

The invention belongs to the technical field of metal corrosion and protection, and relates to a nuclear power explosion valve stainless steel welded joint stress corrosion cracking evaluation method, which comprises the following steps: dissecting and sampling a welded joint simulation piece at a specified part, and carrying out simulation piece hardness measurement, metallographic analysis and SCC crack growth rate measurement to obtain a measurement result; establishing a relation curve of the crack growth rate and the hardness and a relation curve of the crack growth rate and the load; carrying out hardness detection on the welding joint area of the in-service component, and drawing a base metal-heat affected zone SCC crack growth rate cloud chart; analyzing a finite element structure of a welding joint, measuring residual stress of a welding part of a structural component, and determining a cracking sensitive position of a heat affected zone SCC; and according to the SCC cracking sensitive position of the heat affected zone and the wall thickness of the in-service part welding joint, calculating the residual life of the heat affected zone of the in-service part welding joint. The method can effectively predict the service life of the welding joint on the main pipeline.

The application relates to a method and device for tracing potential influencing factors of an engineering system based on prediction residuals. The method constructs residual information variables by taking the deviation between prediction results and actual observation values, and performs state division and structural analysis on the residual information. In the case of failure in model explanation, the conditional dependence relationship between the residual information and system observation variables is further analyzed, a residual dependence structure is constructed, and the candidate sources of potential unmodeled influencing factors are determined. Without significantly increasing the complexity of the system, the method improves the perception and tracing ability of the engineering system operation diagnosis for potential unmodeled influencing factors, enhances the explainability and reliability of the diagnosis results, and provides an effective technical means for the operation management and decision support of the engineering system.

A multiphysics-coupled method for analyzing the structure of motor end caps relates to the field of finite element analysis (FEM) for motor end caps. This method effectively improves simulation accuracy and design reliability, and shortens product development cycles, thereby optimizing the design to enhance the overall reliability and service life of the motor system. The multiphysics-coupled method organically combines electromagnetic field analysis, thermal stability analysis, and static structural analysis into a complete and efficient multiphysics simulation process for comprehensive evaluation of the end cap. The maximum radial force of the rotor obtained from the electromagnetic field analysis is used as the load input for the static structural analysis, while the temperature field from the thermal stability analysis is directly imported into the static structural analysis to achieve effective coupling and transfer of multiple data. Through the final static structural analysis, the total deformation, equivalent stress, and safety factor of the end cap are obtained, providing crucial information for the reliability and durability design of the end cap.

This invention discloses a parametric design and iterative optimization design method and system for building structural morphology. The method includes the following steps: S1: Converting the architectural design surface into a structural analysis model; S2: Determining the direction vector of the principal axis section of the components; S3: Calculating the β angle; S4: Importing the structural analysis model and member information into finite element analysis software to establish an initial spatial reticulated shell model; S5: Iteratively optimizing the spatial reticulated shell model and simultaneously correcting the node coordinates and β angle to obtain the initial geometric model; S6: Iterative construction simulation analysis; S7: High-precision initial state reverse engineering based on construction steps; S8: Determining the initial alignment using the structural design form-finding logic; S9: Detailed design and delivery. Through the above parametric design and iterative method, the architectural surface is accurately matched, ensuring that the morphology of the completed structure approximates the architect's design intent to the greatest extent possible.

To provide a process planning method and a marine structure capable of shortening the process of a construction project.SOLUTION: A process planning method for planning a process of a construction project of a marine structure supporting a tower of an offshore wind turbine includes a structure analysis process SA3 for performing structure analysis of the marine structure, and a first manufacturing process SA3 for manufacturing at least a part of members constituting the marine structure after start of the structure analysis process SA3 and before completion of the structure analysis process SB1.SELECTED DRAWING: Figure 5

This invention relates to a method for evaluating the fidelity of seismic data based on sandstone reservoir structure models, comprising the following steps: conducting fine-grained well-seismic calibration of the internal structure of the reservoir using well logging and seismic data; determining the target reservoir structure pattern using rock physical analysis results; establishing a typical geological model based on the reservoir structure pattern, and conducting forward modeling analysis of geological models for different reservoir structure patterns based on the fine-grained well-seismic calibration results; and performing seismic data structure fidelity analysis based on the forward modeling analysis results. This method for evaluating the fidelity of seismic data based on sandstone reservoir structure models guides the analysis of the internal structure of reservoir sand bodies based on seismic data, optimizes the development well network, and provides important technical support for the efficient development and scheme adjustment of underground oil and gas reservoirs.

A thermal offset correction device (90) for a machine tool comprises a temperature acquisition unit (91) that acquires a temperature at a predetermined section of a structure (20) of the machine tool (1), a finite element method analysis unit (92) that performs a structural analysis using a finite element method with a coefficient matrix [W] to calculate temperatures at all nodes of the structure (20) from each temperature at the predetermined section acquired by the temperature acquisition unit (91) and estimates an amount of thermal offset at a predetermined node of the structure (20) of the machine tool (1), and a correction unit (96) that corrects a command position of a moving body of the machine tool by means of an NC program based on the amount of thermal offset.The coefficient matrix [W] is pre-optimized to minimize the difference between the amount of thermal offset estimated by the finite element method analysis unit (92) and the amount of thermal offset obtained by an actual measurement or simulation.

The application provides a kind of floating wind turbine foundation strut structure strength calculation method and system, it is related to marine engineering structural analysis technical field, the application obtains the geometric size of floating wind turbine foundation strut, establishes parameterized finite element model, material attribute is regarded as random variable, calibrates key cross section stress concentration coefficient, data acquisition is carried out in key cross section deployment sensor, and the probability distribution model of strain extreme value is established by extreme value statistics;Limit state function is constructed with yield strength as random variable, the strain extreme value model is combined with stress concentration coefficient, the maximum stress is expressed as the product of elastic modulus, strain extreme value and stress concentration coefficient, the reliability index is calculated by using first order second moment method, the reliability index is compared with the preset target value, whether the strength is qualified is judged, and the reliability index and determination conclusion are output, to solve the problem that traditional method cannot evaluate the real strength of in-service structure by using monitoring data, and realize quantitative evaluation based on reliability.

This invention discloses an online monitoring and early warning management system and method for the health status of urban building structures, relating to the field of building structure health monitoring technology. It includes a building structure acquisition module, a building data analysis module, a structural analysis module, and an early warning management module. The system collects building structure data, environmental data, and operational status data to form time-series data; it performs joint analysis of current and historical data to identify data drift points and calculate drift differences; it assesses building health status through drift compensation and an isolated forest anomaly detection model; it integrates health status levels, trend coefficients, and drift differences for comprehensive risk assessment to determine early warning levels; and it classifies structural units into safety point categories based on risk propagation values ​​and evolution rates, establishing a safe passage network and dynamically planning optimal evacuation paths. This invention achieves effective compensation for data drift and accurate identification of structural anomalies, improving early warning accuracy and emergency response capabilities.

This invention relates to the field of bridge construction monitoring technology, and discloses a method and system for monitoring the construction safety of cable-stayed bridge pylons based on multiple sensors. The method collects data in real time from various sensors deployed on the cable-stayed bridge pylon structure, including displacement monitoring values, stress change values, and ambient temperature readings. Combining the sensor data with a pre-set bridge construction specification knowledge base, the current construction stage status is identified. Based on the current construction stage status and associated safety monitoring standard documents, the sensor data is divided into a macroscopic structural analysis area and a microscopic detail assessment area. Based on the macroscopic structural analysis area and the microscopic detail assessment area, a safety risk detection operation is performed to output the construction safety assessment result. This method achieves accurate monitoring of pylon construction safety through multi-dimensional data fusion and regional analysis, and is applicable to the safety management of the entire cable-stayed bridge pylon construction process.