Method, system and computer readable medium for converting pipe finite element models

Abstract

The application relates to a pipeline finite element model conversion method, a system and a computer readable medium, the pipeline finite element model conversion method comprising: analyzing a pipeline finite element model to obtain pipeline information, wherein the pipeline information comprises a connection relationship of units; constructing a pipeline model graph by using a graph structure according to the connection relationship of the units, wherein the pipeline model graph comprises a topological structure between pipe components; constructing the pipeline model graph into a pipeline model tree by using a tree structure; and performing coordinate mapping processing and data mapping processing on the pipeline model tree to generate a three-dimensional pipeline model. The application can improve the conversion efficiency and conversion accuracy of converting the pipeline finite element model into the three-dimensional pipeline model, and realizes efficient docking of the finite element analysis model and a three-dimensional digital design system.

Description

Technical Field

[0001] This application mainly relates to the field of finite element model conversion technology, specifically to a method, system, and computer-readable medium for converting a pipeline finite element model. Background Technology

[0002] With the rapid development of engineering digitalization technology, 3D modeling and finite element analysis are widely used in fields such as architecture and shipbuilding. In the nuclear power sector, scenarios involving complex piping systems and intricate structural designs have stringent requirements for safety, reliability, and data accuracy. Nuclear power plants previously used finite element models with piping systems (such as models in software formats like ANSYS, ABAQUS, PipeStress, and ProPipe). However, with increasing design demands, 3D digital models (such as models in software formats like PDMS and PDS) are required. Many existing nuclear power plants lack 3D digital models, and existing finite element models cannot be directly converted into 3D digital models. Reconstructing 3D digital models is costly, rendering existing finite element model data unusable and hindering the digital upgrade of existing nuclear power facilities.

[0003] The current digital upgrade of existing nuclear power facilities mainly relies on manually converting the finite element model of the nuclear power plant's pipeline system into a three-dimensional pipeline model. This is not only inefficient but also prone to introducing errors, making it difficult to guarantee the accuracy and consistency of the model, resulting in low model conversion efficiency. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a method, system and computer-readable medium for converting finite element models of pipelines, which can improve the conversion efficiency and accuracy of converting finite element models of pipelines into three-dimensional pipeline models, and realize the efficient docking of finite element analysis models and three-dimensional digital design systems.

[0005] The technical solution adopted in this application to solve the above-mentioned technical problems is a method for converting a pipeline finite element model, comprising: parsing the pipeline finite element model to obtain pipeline information, the pipeline information including the connection relationship of the elements; constructing a pipeline model diagram using a graph structure based on the connection relationship of the elements, the pipeline model diagram including the topological structure between pipe components; constructing a pipeline model tree using a tree structure based on the pipeline model diagram; and performing coordinate mapping processing and data mapping processing on the pipeline model tree to generate a three-dimensional pipeline model.

[0006] In one embodiment of this application, the pipeline information further includes unit cross-sectional attributes; constructing the pipeline model diagram into a pipeline model tree using a tree structure includes: performing loop structure preprocessing on the pipeline model diagram to obtain preprocessed pipeline units; sorting the unit cross-sectional attributes of the pipeline units from largest to smallest according to their outer diameter; using the pipeline unit corresponding to the first sorted unit cross-sectional attribute as the main structure of the pipeline model tree; using the two ends of the main structure as the start and end points of the tree structure, respectively; using the remaining multiple pipeline units as branch nodes of the pipeline model tree, using the end with the higher fluid pressure among the multiple pipeline units as the start point of the branch node and the end with the lower fluid pressure as the end point of the branch node; and connecting the branch nodes to the main structure to construct the pipeline model tree.

[0007] In one embodiment of this application, the loop structure preprocessing includes: taking any graph node in the pipeline model diagram as a target graph node, traversing other graph nodes connected to the target graph node; in response to returning to the target graph node during the traversal, determining that a loop exists in the pipeline model diagram; taking pipeline units in the loop with a diameter less than a preset threshold as pipeline units to be disconnected; disconnecting the graph nodes connected to the pipeline units to be disconnected and marking the pipeline units connected to the graph nodes in the pipeline model tree.

[0008] In one embodiment of this application, the structure of the pipe model tree includes a flange, which is identified by: identifying a straight pipe unit from the pipe model diagram; in response to the length of the straight pipe unit being less than or equal to a preset length, and the unit cross-sectional properties of the straight pipe unit changing; matching the unit cross-sectional properties of the straight pipe unit with a preset flange list; and in response to a successful match, designating the straight pipe unit as the flange.

[0009] In one embodiment of this application, the structure of the pipe model tree includes straight tees and / or oblique tees, which are identified in the following manner: pipe units are identified from the pipe model diagram; in response to the pipe unit having a first sub-unit, a second sub-unit, and a third sub-unit, the pipe unit is identified as a tee; in response to the first sub-unit and the second sub-unit having the same direction and the same length; in response to the third sub-unit being perpendicular to the direction of the first sub-unit and the second sub-unit, the tee is identified as the straight tee; or in response to the third sub-unit not being perpendicular to the direction of the first sub-unit and the second sub-unit, the tee is identified as the oblique tee.

[0010] In one embodiment of this application, the structure of the pipe model tree includes a valve, which is identified in any of the following ways: the tee is designated as the valve in response to the main pipe unit of the tee being a rigid unit; the tee is designated as the valve in response to a branch unit of the tee being labeled as a valve; the tee is designated as the valve in response to the front and rear ends of the main pipe unit of the tee having concentrated mass and flanges; or the tee is designated as the valve in response to the rear end having concentrated mass and the rear end not being connected to other units.

[0011] In one embodiment of this application, coordinate mapping and data mapping processing are performed on the pipeline model tree to generate a three-dimensional pipeline model, including: mapping the local coordinates of each node in the pipeline model tree to the global coordinate system to obtain the global coordinates of each node; mapping the element section properties of each node to preset pipeline parameters in the three-dimensional model software to obtain the pipe component parameters of each node; mapping the finite element support constraints of each node to preset support and hanger types in the three-dimensional model software to obtain the support and hanger parameters of each node; and generating the three-dimensional pipeline model based on the global coordinates of each node, the pipe component parameters, and the support and hanger parameters.

[0012] In one embodiment of this application, generating the three-dimensional pipeline model based on the global coordinates of each node, the pipe component parameters, and the support parameters includes: matching the pipe component corresponding to the pipe component parameters from a preset pipe component library of the three-dimensional model software; positioning the pipe component in the global coordinate system according to the global coordinates; and connecting the pipe component with a straight pipe according to the support parameters, thereby generating the three-dimensional pipeline model.

[0013] In one embodiment of this application, after the step of generating the three-dimensional pipeline model, the method further includes: using a pre-trained neural network model to check the errors of pipe components in the three-dimensional pipeline model; in response to the deviation of the error of the pipe component from a preset error range, identifying the pipe component as an out-of-tolerance component and issuing a modification alarm; and in response to receiving an external pipe component modification instruction, modifying the out-of-tolerance component according to the pipe component modification instruction and reconstructing the topology of the three-dimensional pipeline model.

[0014] To address the aforementioned technical problems, this application also proposes a conversion system for a pipeline finite element model, comprising: a memory for storing instructions executable by a processor; and a processor for executing the instructions to implement the pipeline finite element model conversion method described above.

[0015] To address the aforementioned technical problems, this application also proposes a computer-readable medium storing computer program code, which, when executed by a processor, implements the above-mentioned method for converting the pipeline finite element model.

[0016] The technical solution of this application uses a graph structure to construct a pipeline model diagram, which can accurately express the topological connection relationship between pipe components; it uses a tree structure to construct a pipeline model tree, which can simplify the representation of complex pipeline systems and improve the processing efficiency of the model; through coordinate mapping and data mapping processing, the three-dimensional model and the original finite element model are kept consistent in geometry and properties. This application realizes an automated, efficient and high-precision model conversion from a finite element model to a three-dimensional pipeline model. Attached Figure Description

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings, wherein:

[0018] Figure 1 This is an exemplary flowchart of a method for converting a finite element model of a pipeline according to an embodiment of this application;

[0019] Figure 2 This is an exemplary flowchart of a method for converting a pipeline finite element model according to another embodiment of this application;

[0020] Figure 3 This is an exemplary flowchart of a method for converting a finite element model of a pipeline according to another embodiment of this application;

[0021] Figure 4 This is a schematic diagram of a finite element model of a pipe segment in one embodiment of this application;

[0022] Figure 5 It is based on Figure 4 A schematic diagram of a three-dimensional pipeline model constructed from the finite element model of the pipeline;

[0023] Figure 6 This is a schematic diagram of a finite element model of a pipe segment in another embodiment of this application;

[0024] Figure 7 It is based on Figure 6 A schematic diagram of a three-dimensional pipeline model constructed from the finite element model of the pipeline;

[0025] Figure 8 This is a system block diagram of a pipeline finite element model conversion system according to an embodiment of this application. Detailed Implementation

[0026] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0027] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein, and therefore this application is not limited to the specific embodiments disclosed below.

[0028] As illustrated in this application, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0029] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0030] In practical applications, pipeline stress analysis software includes ANSYS, ABAQUS, ProPipe (Professional Pipe Design Software), and PipeStress (Pipe Stress Analysis Software). Pipeline design software includes PDS (Plant Design System), PDMS (Plant Design Management System), and SP3D (SmartPlant 3D). Traditional manual conversion methods for transforming the finite element model of pipeline stress analysis software into a 3D pipeline model for pipeline design software have the following shortcomings:

[0031] (1) Manual modeling is inefficient and prone to errors.

[0032] (2) The data formats of the pipeline finite element model (including information such as nodes, elements, materials, and constraints) and the three-dimensional pipeline model (including information such as pipeline grade, connection method, and process parameters) are incompatible and difficult to check manually.

[0033] (3) The conversion of complex pipeline branches, support structures and non-uniform cross sections is highly complex for manual operation.

[0034] (4) It is impossible to automatically match the pipeline grade library information of nuclear power standards with the model information.

[0035] Currently, the manual method of model conversion severely impacts the efficiency of engineering design and increases labor costs. Therefore, it is necessary to achieve automated conversion from finite element model to 3D pipeline model.

[0036] Considering the shortcomings of the aforementioned model conversion methods, this application proposes a conversion method for finite element models of pipelines. This method can be applied to nuclear power plant scenarios to automatically convert finite element models of pipelines into 3D pipeline models for computational analysis in nuclear power engineering. Finite element models of pipelines can be constructed using software such as ANSYS, ABAQUS, ProPipe, and PipeStress, while 3D pipeline models can be constructed using software such as PDS, PDMS, and SP3D. This application essentially proposes an automatic conversion scheme for nuclear power plant pipeline systems based on finite element models, enabling cross-platform model conversion and handling various types of pipe components.

[0037] The method for converting the pipeline finite element model according to this application can be run on a nuclear power plant or on a worker's local computer, such as within the controller of a local computer, or on a cloud platform. When the method is run on a cloud platform, data from the local computer and data from the cloud platform interact via a wireless network. For example, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, interconnected cloud, and multiple clouds, or any combination thereof. This application does not limit the operating environment of the method for converting the pipeline finite element model.

[0038] Figure 1 This is an exemplary flowchart of a method for converting a finite element model of a pipeline according to an embodiment of this application. (Refer to...) Figure 1 As shown, the conversion method of the pipeline finite element model in this embodiment includes the following steps:

[0039] Step S110: Analyze the finite element model of the pipeline to obtain pipeline information, which includes the connection relationship of the elements.

[0040] Step S120: Construct a pipeline model diagram using a graph structure based on the connection relationship of the units. The pipeline model diagram includes the topology between pipe components.

[0041] Step S130: Construct the pipeline model diagram into a pipeline model tree using a tree structure.

[0042] Step S140: Perform coordinate mapping and data mapping processing on the pipeline model tree to generate a three-dimensional pipeline model.

[0043] The following details steps S110 to S140:

[0044] In step S110, the pipeline information is obtained by analyzing the finite element model of the pipeline, which includes the connection relationship of the elements.

[0045] For example, a pipeline finite element model can be a pipeline finite element file (such as an ANSYS CDB format file, an ABAQUS INP format file, or a PipeStress FRE format file). The parsed pipeline information also includes node information (such as pipeline node coordinates), element types (such as straight pipes, bends, tees, valves, pipe fittings, flanges, and plugs), element section properties, element materials, constraint information (such as constraint directions of constraint points used to fix pipeline positions), and operating condition information (such as independent operating conditions, combined operating conditions, and evaluation operating conditions). Based on the parsed pipeline information, information such as pipeline direction, pipe diameter, pipe material, and pipe insulation can be determined.

[0046] In step S120, a pipeline model diagram is constructed using a graph structure based on the connection relationship of the units. The pipeline model diagram includes the topological structure between pipe components.

[0047] For example, this application generates a corresponding graph structure (i.e., a pipe model diagram) based on the connection relationships of the elements, and uses the graph structure to determine the tree structure of the pipe components (i.e., a pipe model tree). This application employs a topology reconstruction algorithm, which automatically reconstructs the topological connections of the piping system based on the pipe branch paths in graph theory. For instance, based on the node and element data provided in the pipe stress analysis calculation file, all elements are organized into a graph structure, which contains the topological relationships between the elements in the finite element model.

[0048] In step S130, a tree structure is used to construct the pipeline model diagram into a pipeline model tree. For example, this application establishes the topology of the main pipeline and branch pipelines by constructing the pipeline model diagram, and further forms a tree structure of the geometric model, which facilitates the subsequent establishment of the mapping relationship between finite element pipe components such as straight pipe units and bent pipe units and the standard library of 3D design software.

[0049] In some embodiments, the pipe information further includes element cross-section attributes; constructing the pipe model diagram into a pipe model tree using a tree structure includes:

[0050] Step S1301: Perform ring structure preprocessing on the pipeline model diagram to obtain preprocessed pipeline elements;

[0051] Step S1302: Sort the element cross-sectional properties of the pipe elements from largest to smallest according to their outer diameter;

[0052] Step S1303: Take the pipe element corresponding to the first sorted element (i.e. the one with the largest outer diameter) as the main structure of the pipe model tree;

[0053] Step S1304: Take the two ends of the main structure as the start and end points of the tree structure, respectively;

[0054] Step S1305: Take the remaining pipe units as branch nodes of the pipe model tree, and take the end with higher fluid pressure in the pipe units as the starting point of the branch node and the end with lower fluid pressure as the ending point of the branch node.

[0055] Step S1306: Connect the branch nodes to the main structure to build the pipeline model tree.

[0056] For example, the tree structure of the pipeline model tree needs to be "loop-free." Therefore, when constructing the pipeline model tree, loop structure preprocessing is required to identify and handle loops. During the construction of the pipeline model tree, the elements are sorted by outer diameter based on their cross-sectional attributes. The part with the largest outer diameter is designated as the main structure. The start and end points of the tree structure are determined based on the two ends of the main structure. If there is more than one main structure with the same outer diameter, the structure with the most branches is selected as the main structure. When determining branch nodes, the end with higher fluid pressure in the pipeline can be defined as the start point of the branch node, and the end with lower fluid pressure can be defined as the end point. If the fluid pressures in the pipeline are the same, either end can be chosen as the start point of the branch node. Comparisons can be made between different fluid pressures, with the highest pressure considered as high fluid pressure and the lowest pressure considered as low fluid pressure. Alternatively, fluid pressures can be compared with a preset threshold, with pressures greater than the preset threshold considered as high fluid pressure and pressures less than or equal to the preset threshold considered as low fluid pressure. This application uses a graph structure to determine the branch nodes connecting the main structures, and the branches of the branch nodes can be iteratively formed using the above steps.

[0057] This application can effectively identify and handle loop problems in pipeline systems through loop structure preprocessing; the method of determining the main structure by sorting by outer diameter makes the pipeline model tree hierarchical; and the branch nodes are determined based on the magnitude of fluid pressure, so that the generated pipeline model tree can not only accurately reflect the system topology, but also have the pipeline physical characteristics required in practical applications.

[0058] In some embodiments, the ring structure preprocessing in step S1301 includes:

[0059] Take any graph node in the pipeline model diagram as the target graph node, and traverse other graph nodes connected to the target graph node.

[0060] In response to returning to the target graph node during traversal, determine if there is a loop in the pipeline model graph; and designate pipeline units with a diameter smaller than a preset threshold in the loop as pipeline units to be disconnected.

[0061] Disconnect the graph nodes of the pipe units to be disconnected and mark the pipe units connected to the graph nodes in the pipe model tree.

[0062] For example, during the preprocessing of the loop structure, connected elements and nodes can be found starting from any graph node. If the connected graph node is the initial node, it is determined that there is a loop in the piping system. This loop is then identified and broken at the point where the pipe diameter is smaller, and the loop element connected to this node is marked in the tree structure. This application solves the loop problem in the piping model diagram. By traversing the graph nodes, the loop structure can be accurately identified; using the pipe diameter as the breaking standard preserves the continuity of the main pipeline and simplifies the model structure; marking the connection information at the break point preserves the complete connection relationship and improves the accuracy of subsequent model conversion.

[0063] In some embodiments, the structure of the pipeline model tree includes flanges, which are identified in the following manner:

[0064] Identify straight pipe units from the pipe model diagram;

[0065] The response is that the length of the straight pipe element is less than or equal to the preset length, and the cross-sectional properties of the straight pipe element change;

[0066] Match the unit cross-section properties of the straight pipe unit with the preset flange list;

[0067] In response to a successful match, the straight pipe unit is used as a flange.

[0068] For example, this application identifies flanges based on unit cross-sectional properties. It searches for units with relatively short lengths and units with varying cross-sectional properties within straight pipe units, and determines whether the cross-sectional properties of the shorter units match the dimensions of a preset flange list. If they match, the straight pipe is identified as a flange. This application initially filters short pipe segments for flange characteristics by using preset lengths and variations in unit cross-sectional properties; using a preset flange list to match flanges improves the accuracy of flange identification.

[0069] In some embodiments, the pipe model tree structure includes straight tees and / or angled tees, which are identified in the following manner:

[0070] Identify pipe elements from the pipe model diagram;

[0071] In response to the fact that the pipe unit has a first sub-unit, a second sub-unit, and a third sub-unit, the pipe unit is treated as a tee pipe;

[0072] The first and second sub-units have the same direction and the same length.

[0073] In response to the fact that the direction of the third subunit is perpendicular to that of the first and second subunits, the tee is used as a straight tee; or

[0074] In response to the fact that the direction of the third subunit is not perpendicular to that of the first and second subunits, the tee is used as an oblique tee.

[0075] For example, this application determines four-way pipes and three-way pipes based on the connection relationship of the pipe units. If a node connects four sub-units, it is a four-way pipe structure. If a node connects three sub-units, it is a three-way pipe structure. If two of the three sub-units have the same direction and length, and the direction of the other sub-unit is perpendicular to the directions of the two sub-units, it is determined to be a straight three-way pipe. If two of the three sub-units have the same direction and length, and the direction of the other sub-unit is not perpendicular to the directions of the two sub-units, it is determined to be an angled three-way pipe.

[0076] This application achieves automatic classification of straight tees and oblique tees through an intelligent tee identification method, improving the accuracy of distinguishing tee types in the pipeline model and enabling the pipeline model tree to accurately reflect the layout of different types of tees in actual engineering projects.

[0077] In some embodiments, the structure of the pipeline model tree includes valves, which are identified in any of the following ways:

[0078] The main pipe unit responding to the tee pipe adopts a rigid unit, treating the tee pipe as a valve;

[0079] The branch unit of the tee pipe is marked as a valve, so the tee pipe is treated as a valve;

[0080] The front and rear ends of the main pipe unit of the tee pipe have concentrated mass and flanges, and the tee pipe is used as a valve;

[0081] In response to the fact that the rear end of the tee pipe has a concentrated mass and is not connected to other units, the tee pipe is used as a valve.

[0082] For example, this application automatically identifies valve structures in the pipeline model tree through multiple dimensions, which can effectively distinguish valves from ordinary tees. This flexible identification method enables the pipeline model tree to accurately reflect the installation position and structural characteristics of various valves in actual engineering projects.

[0083] In step S140, coordinate mapping and data mapping processes are performed on the pipeline model tree to generate a 3D pipeline model. For example, each node in the pipeline model tree has its own local coordinates; coordinate mapping processes can uniformly convert the local coordinates of all nodes into global coordinates.

[0084] In some embodiments, step S140 involves performing coordinate mapping and data mapping processing on the pipeline model tree to generate a three-dimensional pipeline model, including:

[0085] Step S1401: Map the local coordinates of each node in the pipeline model tree to the global coordinate system to obtain the global coordinates of each node;

[0086] Step S1402: Map the element section properties of each node to the preset pipe parameters in the 3D modeling software to obtain the pipe component parameters of each node;

[0087] Step S1403: Map the finite element support constraints of each node to the preset support type in the 3D modeling software to obtain the support parameters of each node;

[0088] Step S1404: Generate a 3D pipeline model based on the global coordinates of each node, pipe component parameters, and support parameters.

[0089] For example, step S1402 is equivalent to using the section equivalence rule to determine the pipe component parameters (such as nominal diameter, weight, and material selection) in the standard library of the 3D modeling software (such as PDMS or SP3D) based on the finite element beam element section and material. Step S1403 is equivalent to using the constraint transformation rule to map the finite element support constraints to the standard support and hanger types (such as sliding supports, rigid hangers, spring hangers, and dampers) of the 3D modeling software (such as PDMS or SP3D). Supports and hangers are supports used to support pipes.

[0090] This application improves the accuracy of pipeline spatial layout by mapping local coordinates to global coordinates; it improves the standardization of model parameters by mapping element section properties to standard pipeline parameters of 3D modeling software and converting finite element support constraints into preset support and hanger types; this application realizes high-precision automatic conversion from pipeline model tree to 3D pipeline model.

[0091] In some embodiments, step S1404 above, generating a three-dimensional pipe model based on the global coordinates of each node, pipe component parameters, and support parameters, includes:

[0092] Match the pipe component corresponding to the pipe component parameters from the preset pipe component library of the 3D modeling software;

[0093] Position the pipe component to the global coordinate system based on the global coordinates;

[0094] Based on the support and hanger parameters, straight pipes are used to connect pipe components, thereby generating a three-dimensional pipe model.

[0095] For example, during the generation of a 3D pipeline model, pipe components such as valves, flanges, pipe seats, plugs, and orifice plates are matched from the preset pipe component library of the 3D modeling software (such as PDMS or SP3D) according to the element type; the cross-sectional properties and materials of each element are supplemented and matched with the pipe component library. The positions of the pipe components are located according to the node coordinates, such as the direction of the straight pipe, the direction of the valve's center of gravity, and the positioning of the orifice plate, etc. The pipe components are generated in the 3D modeling software and arranged according to the positioning.

[0096] This application ensures the consistency of model components by automatically matching corresponding pipe components from a pre-set pipe component library; it improves the accuracy of the spatial layout of the pipeline system by positioning the pipe components to the global coordinate system; and it achieves continuous pipeline modeling and fully preserves the support constraint information by connecting pipe components with straight pipes according to the support and hanger parameters.

[0097] In some embodiments, after the step of generating the three-dimensional pipeline model, the method further includes:

[0098] A pre-trained neural network model is used to check the errors of pipe components in a 3D pipe model;

[0099] In response to a deviation between the error of a pipe component and the preset error range, the pipe component is identified as an out-of-tolerance component and a correction alarm is issued.

[0100] In response to receiving external pipe component modification instructions (such as manually input pipe component modification instructions), the out-of-tolerance components are modified according to the pipe component modification instructions and the topology of the 3D pipe model is reconstructed.

[0101] For example, the positional accuracy of a 3D pipeline model needs to be higher than that of a pipeline finite element model. This application uses a large number (e.g., tens of thousands) of pipeline stress analysis files as the training dataset for an artificial intelligence neural network model. The pre-trained neural network model obtained after training the model has the ability to identify element errors in the pipeline finite element files, such as errors in pipeline loops, tee assembly directions, pipeline slopes, tangential errors between straight and curved pipes, and errors in the perpendicularity of the support constraint direction to the pipeline direction. The pre-trained neural network model can check these errors and promptly detect deviations and prompt for correction. During the inspection of the 3D pipeline model, it can recommend pipeline grade matching schemes (such as material compatibility, pressure rating, etc.), standardized pipe components (such as standard-sized tees, reducers, and flanges), and valves (such as valves with matching functions, structures, and sizes) based on historical engineering data.

[0102] This application uses a pre-trained neural network model to perform error checks on a 3D pipeline model, which can efficiently identify deviations between pipe components and preset error ranges; automatically mark out-of-tolerance components and issue alarms, and promptly provide feedback to staff on the quality of the generated 3D pipeline model; and quickly correct out-of-tolerance components and automatically reconstruct the model's topology based on staff feedback, thereby improving the accuracy of the reconstructed model.

[0103] For example, in practical applications, the method for converting the finite element model of the pipeline in this application can be encapsulated into a Programming Macro Language (PML) script for 3D pipeline design software, and a corresponding interface can be built. By calling this interface, the finite element model of the pipeline can be automatically converted into a 3D pipeline model, thereby automatically creating 3D pipe components such as tees, valves, and flanges.

[0104] The following sections will use other embodiments to illustrate the conversion method of the pipeline finite element model of this application.

[0105] Figure 2 This is an exemplary flowchart of a method for converting a finite element model of a pipeline according to another embodiment of this application. (See reference...) Figure 2 As shown, in step S210, the finite element model file of the pipeline is read; in step S220, the finite element modeling statements are identified based on the parsed information, including: independent working cases, evaluation working cases, combined working cases, element cross-sectional properties, element type, element material, node coordinates, element nodes, and node constraints; in step S230, the pipe component data is aligned, specifically, based on the parsed information from the previous steps, as well as the externally acquired pipe component and support tables, a working case list, a pipe component list, a pipeline model diagram, a pipeline model tree, and a support list are generated; in step S240, the pipe component model is generated; in step S250, a pre-trained neural network model is used to check model errors; and in step S260, a three-dimensional pipeline model is generated. Step S240 can directly jump to step S260.

[0106] Figure 3 This is an exemplary flowchart of a method for converting a finite element model of a pipeline according to another embodiment of this application. (See reference...) Figure 3 As shown, in step S310, the finite element model file of the pipeline is read; in step S320, the finite element modeling statement is identified; in step S330, the pipeline model tree is established; in step S340, the pipeline model tree is subjected to coordinate mapping processing; in step S350, the pipeline model tree is subjected to data mapping processing; in step S360, the pipe component model is generated; in step S370, the three-dimensional pipeline model is generated; in step S380, the model error is checked using a pre-trained neural network model; and in step S390, the final three-dimensional pipeline model is generated.

[0107] Figure 4 This is a schematic diagram of a finite element model of a pipe segment according to one embodiment of this application. Figure 5 It is based on Figure 4 A schematic diagram of a three-dimensional pipeline model constructed from the finite element model of the pipeline. Figure 6 This is a schematic diagram of a finite element model of a pipe segment according to another embodiment of this application. Figure 7 It is based on Figure 6 A schematic diagram of a 3D pipeline model constructed from a finite element model of the pipeline. For example, refer to... Figures 4 to 7 As shown, the conversion method of the pipeline finite element model in this application can convert... Figure 4 The pipeline finite element model 400 was converted to Figure 5 A 500-dimensional pipe model; capable of... Figure 6 The pipeline finite element model 600 was converted to Figure 7 The 3D pipeline model 700. Figure 5 and Figure 7 The 3D model was built using PDMS.

[0108] The conversion method for the pipeline finite element model in this application can achieve the following functions:

[0109] (1) Finite element model analysis: Automatically extracts data such as node coordinates, element type, material properties and constraints from the finite element model.

[0110] (2) Pipeline logic reconstruction: Based on the topological relationship of finite element units, pipeline branch paths and connection logic are automatically generated to ensure the accuracy of the geometric structure.

[0111] (3) Attribute mapping: The finite element parameters (such as cross-sectional dimensions and support positions) are automatically mapped to the engineering attributes (such as pipe grade and flange type) of the target 3D design software (such as PDMS, SP3D, etc.), thereby solving the data compatibility problem.

[0112] (4) Model output: Automatically generate files or compatible configuration files that can be recognized by the target 3D design software. The generated model files can be directly imported into the engineering design management system.

[0113] This application uses the conversion method of pipeline finite element model to conduct an experiment on the model of the main steam pipeline system of a nuclear power plant. The parameters and results of the experiment are as follows.

[0114] 1. Input data: Pipeline finite element model (containing 500 beam elements).

[0115] 2. Data analysis: Extract node coordinates, element connection relationships and material properties (SA335 P91).

[0116] 3. Logical mapping: Perform cross-section mapping to map the outer diameter Φ219mm in the finite element model to the corresponding DN200 SCH60 pipe specification in the PDMS standard library.

[0117] 4. Constraint Conversion: Map the fixed end to the rigid support of the PDMS and the sliding end to the spring hanger.

[0118] 5. Test Results: A three-dimensional pipeline model (such as a MACRO file in PDMS) was generated. The overall error of the model was less than 0.01%, which can be used for digital models of nuclear power plants. The local error was less than 0.2%, and there were prompts to facilitate verification by staff.

[0119] This application also includes a conversion system for a pipeline finite element model, comprising a memory and a processor. The memory stores instructions executable by the processor; the processor executes these instructions to implement the pipeline finite element model conversion method described above.

[0120] Figure 8 This is a system block diagram of a conversion system for a finite element model of a pipeline according to an embodiment of this application. (Reference) Figure 8 As shown, the pipeline finite element model conversion system 800 may include an internal communication bus 801, a processor 802, a read-only memory (ROM) 803, a random access memory (RAM) 804, and a communication port 805. The pipeline finite element model conversion system 800 may also include a hard disk 806. The internal communication bus 801 enables data communication between the components of the pipeline finite element model conversion system 800. The processor 802 can perform judgments and issue prompts. In some embodiments, the processor 802 may consist of one or more processors. The communication port 805 enables data communication between the pipeline finite element model conversion system 800 and external systems. In some embodiments, the pipeline finite element model conversion system 800 can send and receive information and data from a network through the communication port 805. The conversion system 800 for the pipeline finite element model may also include different types of program storage units and data storage units, such as a hard disk 806, read-only memory (ROM) 803, and random access memory (RAM) 804, capable of storing various data files used for computer processing and / or communication, as well as possible program instructions executed by the processor 802. The processor executes these instructions to implement the main part of the method. The results of the processor processing are transmitted to the user equipment via a communication port and displayed on the user interface.

[0121] The above-described method for converting the pipeline finite element model can be implemented as a computer program, stored in the hard disk 806, and loaded into the processor 802 for execution to implement the pipeline finite element model conversion method of this application.

[0122] This application also includes a computer-readable medium storing computer program code that, when executed by a processor, implements the aforementioned method for converting the pipeline finite element model.

[0123] When the conversion method of the pipeline finite element model is implemented as a computer program, it can also be stored as an article of manufacture in a computer-readable storage medium. For example, computer-readable storage media can include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic stripes), optical discs (e.g., compact discs (CDs), digital multifunction discs (DVDs)), smart cards, and flash memory devices (e.g., electrically erasable programmable read-only memory (EPROM), cards, sticks, key drives). Furthermore, the various storage media described herein can represent one or more devices and / or other machine-readable media used for storing information. The term "machine-readable medium" can include, but is not limited to, wireless channels and various other media (and / or storage media) capable of storing, containing, and / or carrying code and / or instructions and / or data.

[0124] It should be understood that the embodiments described above are merely illustrative. The embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For hardware implementation, the processor may be implemented within one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, and / or other electronic units designed to perform the functions described herein, or combinations thereof.

[0125] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The aforementioned hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." The processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. Furthermore, aspects of this application may manifest as computer products residing in one or more computer-readable media, including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical discs (e.g., compressed CDs, digital multifunction DVDs, etc.), smart cards, and flash memory devices (e.g., cards, sticks, key drives, etc.).

[0126] A computer-readable medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0127] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0128] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0129] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used to describe embodiments are sometimes modified by the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in this application are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

Claims

1. A method for converting a finite element model of a pipeline, characterized in that, include: The pipeline information is obtained by analyzing the finite element model of the pipeline, and the pipeline information includes the connection relationship of the elements. Based on the connection relationship of the units, a pipeline model diagram is constructed using a graph structure, and the pipeline model diagram includes the topological structure between pipe components; The pipeline model diagram is constructed into a pipeline model tree using a tree structure; as well as The pipeline model tree is subjected to coordinate mapping and data mapping processing to generate a three-dimensional pipeline model, including: The local coordinates of each node in the pipeline model tree are mapped to the global coordinate system to obtain the global coordinates of each node; wherein, the nodes in the pipeline model tree are pipeline units obtained after performing ring structure preprocessing on the pipeline model diagram; The unit section properties of each node are mapped to preset pipe parameters in the 3D modeling software to obtain the pipe component parameters of each node; The finite element support constraints of each node are mapped to the preset support and hanger type in the 3D model software to obtain the support and hanger parameters of each node. The three-dimensional pipe model is generated based on the global coordinates of each node, the pipe component parameters, and the support parameters.

2. The method for converting the finite element model of a pipeline as described in claim 1, characterized in that, The pipeline information also includes unit section attributes; the pipeline model diagram is constructed into a pipeline model tree using a tree structure, including: The pipeline model diagram is preprocessed with a ring structure to obtain preprocessed pipeline units; Sort the cross-sectional properties of the pipe units from largest to smallest according to their outer diameter; The pipe unit corresponding to the first sorted unit cross-section attribute is used as the main structure of the pipe model tree; The two ends of the main structure are respectively used as the start and end points of the tree structure; The remaining pipe units are used as branch nodes of the pipe model tree, with the end of the pipe unit with higher fluid pressure as the starting point of the branch node and the end with lower fluid pressure as the ending point of the branch node. The branch nodes are connected to the main structure to construct the pipeline model tree.

3. The method for converting the finite element model of a pipeline as described in claim 2, characterized in that, The ring structure pretreatment includes: Take any one of the graph nodes in the pipeline model diagram as the target graph node, and traverse the other graph nodes connected to the target graph node; In response to returning to the target graph node during the traversal, it is determined that there is a loop in the pipeline model graph; pipeline units in the loop with a diameter less than a preset threshold are identified as pipeline units to be disconnected. Disconnect the graph node connected to the pipe unit to be disconnected and mark the pipe unit connected to the graph node in the pipe model tree.

4. The method for converting a pipeline finite element model as described in claim 1, characterized in that, The pipeline model tree structure includes flanges, which are identified in the following manner: Identify straight pipe units from the pipeline model diagram; In response to the length of the straight pipe unit being less than or equal to a preset length, and the cross-sectional properties of the straight pipe unit changing; Match the unit cross-sectional properties of the straight pipe unit with the preset flange list; In response to a successful match, the straight pipe unit is used as the flange.

5. The method for converting a pipeline finite element model as described in claim 1, characterized in that, The pipe model tree structure includes straight tees and / or angled tees, which are identified in the following manner: Identify pipe units from the pipe model diagram; In response to the fact that the pipe unit has a first sub-unit, a second sub-unit and a third sub-unit, the pipe unit is configured as a tee pipe; In response to the fact that the first subunit and the second subunit have the same direction and the same length; In response to the fact that the third subunit is perpendicular to the direction of the first subunit and the second subunit, the tee is used as the straight tee; or In response to the fact that the direction of the third subunit is not perpendicular to that of the first subunit and the second subunit, the tee is used as the oblique tee.

6. The method for converting a pipeline finite element model as described in claim 5, characterized in that, The pipeline model tree structure includes valves, which are identified using any of the following methods: In response to the fact that the main pipe unit of the tee pipe adopts a rigid unit, the tee pipe is used as the valve; In response to the fact that the branch unit of the tee pipe is annotated as a valve, the tee pipe is regarded as the valve; In response to the presence of a concentrated mass and a flange at the front and rear ends of the main pipe unit of the tee pipe, the tee pipe is used as the valve; In response to the fact that the rear end of the tee pipe has a concentrated mass and the rear end is not connected to other units, the tee pipe is used as the valve.

7. The method for converting a pipeline finite element model as described in claim 1, characterized in that, The three-dimensional pipe model is generated based on the global coordinates of each node, the pipe component parameters, and the support parameters, including: Match the pipe component corresponding to the pipe component parameters from the preset pipe component library of the 3D model software; The pipe component is positioned in the global coordinate system according to the global coordinates; The pipe components are connected with straight pipes according to the support parameters, thereby generating the three-dimensional pipe model.

8. The method for converting a pipeline finite element model as described in claim 1, characterized in that, Following the step of generating the three-dimensional pipeline model, the following is also included: An error in the pipe components of the three-dimensional pipe model is checked using a pre-trained neural network model; In response to the deviation of the error of the pipe component from the preset error range, the pipe component is identified as an out-of-tolerance component and a correction alarm is issued; In response to receiving an external pipe component modification instruction, the out-of-tolerance component is modified according to the pipe component modification instruction, and the topology of the three-dimensional pipe model is reconstructed.

9. A conversion system for a finite element model of a pipeline, characterized in that, include: Memory is used to store instructions executed by the processor; A processor for executing the instructions to implement the method for converting the finite element model of a pipeline as described in any one of claims 1-8.

10. A computer-readable medium storing computer program code, characterized in that, The computer program code, when executed by a processor, implements the method for converting the pipeline finite element model as described in any one of claims 1-8.

Images