A method for reconstructing a grid of a communication process and related devices

Abstract

The present application discloses a method for reconstructing the grid of a communication process and a related device, which relates to the field of forging simulation technology. The method obtains the current structural data and physical field data of the local grids of multiple computing processes, and uses them as the initial structural data of the global grid of the communication process. The boundary structural data is determined from the initial structural data of the global grid, and the global grid is reconstructed using the boundary structural data, which can fully consider the influence of the grid boundary on the overall structure. By mapping the current physical field data of the local grid of each computing process to the initial physical field data of the global grid of the communication process, a smooth transition of data between different grid levels is achieved. Based on the unique identification correspondence between the communication process and the computing process, each computing process receives the reconstructed structural data and physical field data of the global grid, and can update its own local grid data to more accurately reflect the actual status and improve the quality of the reconstructed grid of the communication process.

Description

Technical Field

[0001] The present application relates to the field of forging simulation technology, and in particular to a method for reconstructing a grid of a communication process and a related device. Background Art

[0002] Finite element methods are widely used for modeling and simulation in hot forging simulations. When simulating die forging scenarios, upper and lower dies apply pressure to the blank, causing it to deform to fill the die cavity. However, as the blank model deforms, its mesh gradually becomes severely distorted, resulting in poor mesh quality and ultimately distorted simulation results. Therefore, reconstructing the mesh is crucial.

[0003] Currently, the physical field information of the old grid can be saved first, then the surface contour geometry of the old grid can be extracted to re-divide the grid, and finally the physical field information of the old grid can be interpolated into the newly divided grid to achieve grid reconstruction in the communication process.

[0004] However, during the hot forging process, the shape of the blank will continue to change with the forging steps, and its geometry may become complex and diverse. Re-meshing by extracting the surface contour geometry of the old mesh is difficult to adapt to the complex and changing geometry, which may result in poor quality of the new mesh. Summary of the Invention

[0005] In view of the above problems, the present application provides a method and related apparatus for reconstructing a grid of a communication process. In order to improve the quality of the reconstructed grid of the communication process, the specific solution is as follows:

[0006] In a first aspect, the present application provides a method for reconstructing a grid of a communication process, the method comprising:

[0007] Acquire current structural data of local grids of multiple computing processes and current physical field data of the local grids of the computing processes, and use the current structural data of the local grids of each computing process as initial structural data of the global grid of the communication process, wherein each unique identifier of the communication process corresponds to the unique identifier of each computing process;

[0008] determining boundary structure data of the global grid of the communication process from the initial structure data of the global grid of the communication process;

[0009] Based on the unique identifiers of the communication processes, reconstructing the boundary structure data of the global grid of the communication process to obtain the reconstructed structure data of the global grid of the communication process, and initializing the physical field data of the global grid of the communication process to obtain the initial physical field data of the global grid of the communication process;

[0010] Mapping the current physical field data of the local grid of each of the computing processes to the initial physical field data of the global grid of the communication process to obtain the reconstructed physical field data of the global grid of the communication process;

[0011] Based on the unique identifiers of the communication processes and the unique identifiers of the computing processes, the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process are distributed to the computing processes, so that each computing process updates the current structural data of the local grid of each computing process and the current physical field data of the local grid of each computing process.

[0012] In a possible implementation, the initial structure data of the global grid of the communication process includes a plurality of initial node structure coordinates of the global grid of the communication process;

[0013] Determining the boundary structure data of the global grid of the communication process from the initial structure data of the global grid of the communication process includes:

[0014] From a plurality of initial node structure coordinates of the global grid of the communication process, taking the maximum and minimum initial node structure coordinates in each direction as the target node structure coordinates of the global grid of the communication process;

[0015] The initial structural data of the edge where the structural coordinates of the target node of the global grid of the communication process are located is used as the boundary structural data of the global grid of the communication process.

[0016] In one possible implementation, reconstructing the boundary structure data of the global grid of the communication process based on each unique identifier of the communication process to obtain the reconstructed structure data of the global grid of the communication process, and initializing the physical field data of the global grid of the communication process includes:

[0017] Traversing the boundary structure data of the global grid of the communication process, connecting the boundary structure data of the global grid of adjacent communication processes, and obtaining the closed structure data of the global grid of the communication process;

[0018] Based on the unique identifiers of the communication processes, the closed structure data of the global grids of the communication processes are grouped to obtain a plurality of group structure data of the global grids of the communication processes, wherein the group structure data of the global grid of each communication process includes a plurality of group node structure data of the global grids of the communication processes;

[0019] Based on the grouped node structure data of the global grid of each communication process, the closed structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

[0020] In a possible implementation, if the grouping structure data of the global grid of the communication process is a one-dimensional structure, the grouping node structure data of the global grid of each communication process includes the head and tail node structure data of the global grid of the communication process and the intermediate node structure data of the global grid of the communication process, and the intermediate node structure data of the global grid of the communication process is the grouping node structure data of the global grid of the communication process excluding the head and tail node structure data of the global grid of the communication process;

[0021] The reconstructing the closed structure data of the global grid of each communication process based on the grouped node structure data of the global grid of each communication process to obtain the reconstructed structure data of the global grid of the communication process includes:

[0022] For each of the grouping structure data of the global grid of the communication process, deleting the intermediate node structure data of the global grid of at least one of the communication processes to obtain the target intermediate node structure data of the global grid of the communication process;

[0023] Based on the head and tail node structure data of the global grid of the communication process and the target intermediate node structure data of the global grid of the communication process, the boundary structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

[0024] In a possible implementation, if the grouping structure data of the global grid of the communication process is a two-dimensional structure, the grouping node structure data of the global grid of each communication process includes boundary node structure data of the global grid of the communication process and internal node structure data of the global grid of the communication process, and the internal node structure data of the global grid of the communication process is the grouping node structure data of the global grid of the communication process excluding the boundary node structure data of the global grid of the communication process;

[0025] The reconstructing the closed structure data of the global grid of each communication process based on the grouped node structure data of the global grid of each communication process to obtain the reconstructed structure data of the global grid of the communication process includes:

[0026] For each of the grouping structure data of the global grid of the communication process, deleting the internal node structure data of the global grid of at least one of the communication processes to obtain target internal node structure data of the global grid of the communication process;

[0027] Based on the boundary node structure data of the global grid of the communication process and the target internal node structure data of the global grid of the communication process, the boundary structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

[0028] In one possible implementation, mapping the current physical field data of the local grid of each of the computing processes to the initial physical field data of the global grid of the communication process to obtain the reconstructed physical field data of the global grid of the communication process includes:

[0029] Determining corresponding positions of the local grids of each of the computing processes in the global grid of the communication process using a geometric mapping method;

[0030] The current physical field data of the local grid of each computing process is mapped to the corresponding position in the global grid of the communication process by using a spatial interpolation method to replace the initial physical field data of the global grid of the communication process.

[0031] In a possible implementation, the distributing, based on the unique identifiers of the communication processes and the unique identifiers of the computing processes, the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process to each computing process, so that each computing process updates the current structural data of the local grid of each computing process and the current physical field data of the local grid of each computing process, includes:

[0032] Based on the unique identifiers of the communication processes, the reconstructed structure data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process are divided into a plurality of reconstructed sub-structure data of the global grid of the communication process and a plurality of reconstructed sub-physical field data of the global grid of the communication process, each reconstructed sub-structure data of the global grid of the communication process and each reconstructed sub-physical field data of the global grid of the communication process corresponding to a unique identifier of the communication process;

[0033] The reconstructed substructure data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process are sent to the calculation process, so that each calculation process uses the reconstructed substructure data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process to update the current structure data of the local grid of each calculation process and the current physical field data of the local grid of each calculation process respectively, and the unique identifier of the communication process is consistent with the unique identifier of the calculation process.

[0034] A second aspect of the present application provides a computer program product comprising computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for reconstructing the grid of the communication process of the first aspect or any implementation of the first aspect.

[0035] A third aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0036] The memory is used to store computer programs;

[0037] The processor is used to execute the computer program so that the electronic device can implement the grid reconstruction method of the communication process of the first aspect or any implementation method of the first aspect.

[0038] The fourth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement a method for reconstructing the grid of the communication process of the above-mentioned first aspect or any implementation method of the first aspect.

[0039] By means of the above technical solution, the present application provides a method for reconstructing the grid of a communication process and a related device. The method obtains the current structural data and physical field data of the local grids of multiple computing processes and uses them as the initial structural data of the global grid of the communication process, thereby realizing the centralized integration and unified initialization of the local grid data of each computing process. By determining the boundary structure data from the initial structural data of the global grid and reconstructing the global grid using the boundary structure data, it is possible to fully consider the influence of the grid boundary on the overall structure and ensure that the reconstructed global grid structure is more in line with the actual computing needs and physical field distribution. At the same time, the physical field data of the global grid is initialized, providing a reasonable starting point for the subsequent mapping and updating of the physical field data. By mapping the current physical field data of the local grid of each computing process to the initial physical field data of the global grid of the communication process, a smooth transition of data between different grid levels is achieved, which ensures the continuity and consistency of the physical field data in the entire grid system. Based on the unique identification correspondence between the communication process and the calculation process, the reconstructed structural data and physical field data of the global grid can be accurately distributed to each calculation process. After receiving the updated data, each calculation process can update its own local grid data, so that the structure and physical field data of the local grid can more accurately reflect the actual state, thereby improving the quality of the mesh of the reconstructed communication process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0041] Figure 1 A schematic flow chart of a method for reconstructing a grid of a communication process provided in an embodiment of the present application;

[0042] Figure 2 A corresponding relationship diagram of a computing process and a communication process provided in an embodiment of the present application;

[0043] Figure 3 A schematic structural diagram of initial structural data of a global grid of a communication process and closed surface data of a global grid of a communication process provided by an embodiment of the present application;

[0044] Figure 4 A schematic structural diagram of initial structural data of a global grid of a communication process and closed volume data of a global grid of a communication process provided by an embodiment of the present application;

[0045] Figure 5 A schematic structural diagram of closed surface data of a global grid of a communication process and broken line structure data of a global grid of a communication process provided by an embodiment of the present application;

[0046] Figure 6 A schematic structural diagram of closed surface data of a global grid of a communication process and reconstructed structural data of the global grid of the communication process provided in an embodiment of the present application;

[0047] Figure 7 A schematic structural diagram of closed volume data of a global grid of a communication process and reconstructed structural data of the global grid of the communication process provided in an embodiment of the present application;

[0048] Figure 8 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0050] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0051] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] In order to improve the quality of the reconstructed communication process grid, the present application provides a communication process grid reconstruction method. The following is a further detailed description of the communication process grid reconstruction method provided by the present application in conjunction with the accompanying drawings and specific implementation methods.

[0053] Please see the attached Figure 1 , Figure 1 A flowchart of a method for reconstructing a grid of a communication process provided in an embodiment of the present application is provided. The method may include the following steps:

[0054] Step S101: Acquire the current structural data of the local grids of multiple computing processes and the current physical field data of the local grids of multiple computing processes, and use the current structural data of the local grids of each computing process as the initial structural data of the global grid of the communication process, and each unique identifier of the communication process corresponds to the unique identifier of each computing process.

[0055] During each calculation step in a hot forging simulation, the billet may undergo a small deformation. To ensure that the mesh accurately represents the billet's geometry and physical state, the mesh quality needs to be checked after each calculation step. Mesh quality is typically assessed based on parameters such as mesh cell shape, size, aspect ratio, and angle. For example, for quadrilateral elements, an ideal mesh cell should be nearly square, with an aspect ratio close to 1 and an angle close to 90 degrees. If a mesh cell exhibits excessive distortion, an excessively large aspect ratio, or an excessively small angle, the mesh quality is considered poor. If the mesh quality is found to have degraded to a level that could affect simulation accuracy and stability, it is necessary to obtain the current structural data and current physical field data for the local mesh across multiple calculation steps. For example, if the aspect ratio of a large number of mesh cells exceeds a preset threshold (such as 5), or if a large number of cells have small angles (e.g., less than 30 degrees), this indicates that the current mesh is no longer adequately adapted to the billet's deformation and requires reconstruction. Even if mesh quality hasn't significantly degraded, if simulation accuracy requirements are high and the current mesh may not meet them, it's possible to obtain the current structural data and current physical field data for the local meshes of multiple computational processes. For example, when simulating the fine forming process of a billet, mesh quality is critical and more frequent mesh reconstruction may be necessary to ensure the accuracy of the simulation results. It should be noted that a computational process is responsible for executing specific computational tasks in a parallel computing environment. In hot forging simulations, the entire simulation domain is typically divided into multiple sub-regions, each handled by a computational process. A computational process is primarily responsible for performing computations on the local mesh it manages, such as solving physical field equations and updating physical quantities at mesh nodes. A communication process is a process responsible for coordinating and managing communication and data exchange between computational processes in a parallel computing environment. It acts as a central node, collecting data from each computational process, performing global operations (such as mesh reconstruction and physical field data mapping), and distributing results back to each computational process. Computational and communication processes collaborate to complete complex parallel computing tasks. The computing process focuses on local computing tasks, while the communication process is responsible for global data management and communication coordination between processes.

[0056] In a parallel computing environment, each computing process is responsible for processing a specific local grid. A unique identifier for a computing process is used to accurately identify the source and destination of data during inter-process communication. A communicating process needs to communicate with multiple computing processes, so multiple unique identifiers are required, one for each computing process. This allows the communicating process to distinguish between communications with different computing processes. During program initialization, a correspondence is established between the unique identifiers of the communicating process and the unique identifiers of the computing processes. This correspondence can be implemented through configuration files, mapping tables, and other means.

[0057] The structural data of the local mesh defines the topological structure of the mesh, which may include node coordinates, element types (such as triangular elements, quadrilateral elements, etc.), the node numbers contained in each element, and the connection relationship between elements. For example, in a two-dimensional quadrilateral mesh, each quadrilateral element consists of four nodes, and the structural data will record the node numbers and node coordinates of the four nodes of each element. The physical field data of the local mesh describes the values ​​of various physical quantities on the mesh nodes or elements. In the hot forging process, the physical field data may include temperature, stress, strain, velocity, etc. These data reflect the physical properties of the billet in its current state. For example, each node may have a temperature value, which represents the temperature distribution at that location.

[0058] During a hot forging simulation, a global mesh object can be initialized in the communicating process (such as the root process). This global mesh object represents the mesh structure of the entire simulation domain. If a global mesh does not exist, a new one must be created. To obtain the structural data of the local meshes of each computing process (such as an MPI process), the relevant mesh information must be retrieved from the memory or storage of each computing process. This typically involves inter-process data communication. A computing process must package its local mesh structural data and send it to the communicating process via a data communication interface (such as the MPI message passing interface). Each computing process carries its unique identifier when sending data. After receiving the local mesh structural data from all computing processes, the communicating process integrates this data to form the initial structural data of the global mesh. This integration process considers the relative positions and connectivity between the local meshes to ensure that they can be stitched together into a complete global mesh. For example, if the local meshes of two computing processes are spatially adjacent, the integration process must ensure that they are properly connected in the global mesh. Since the local grid of each computing process may use the same unit number, the communication process needs to unify and coordinate these numbers so that the node numbers of the entire global grid are continuous and unique to avoid conflicts.

[0059] For easier understanding, please refer to Figure 2 , Figure 2A correspondence diagram of a computing process and a communication process provided in an embodiment of the present application. The two computing processes on the left side of the figure are computing process No. 0 and computing process No. 1 respectively. The unique identifier corresponding to computing process No. 0 is 0, and the structural data of the local grid management unit 1-3 of computing process No. 0; the unique identifier corresponding to computing process No. 1 is 1, and the structural number of the local grid management unit 1-3 of process No. 1. The global grid of the communication process on the right is a 6x1 grid, and there are two unique identifiers 0 and 1. The structural data of the units 1-3 of the local grid management of computing process No. 0 are mapped to the units 1-3 of the global grid of the communication process, and the structural data of the units 1-3 of the local grid management of computing process No. 1 are mapped to the units 4-6 of the global grid of the communication process.

[0060] Step S102: Determine the boundary structure data of the global grid of the communication process from the initial structure data of the global grid of the communication process.

[0061] It should be noted that the initial structure data of the global grid of the communication process includes initial node structure coordinates of the global grid of multiple communication processes.

[0062] In this application, the maximum and minimum initial node structure coordinates in each direction of the initial node structure coordinates of the global grid of multiple communicating processes are used as the target node structure coordinates of the global grid of the communicating process. The initial structure data of the edge where the target node structure coordinates of the global grid of the communicating process are located is then used as the boundary structure data of the global grid of the communicating process.

[0063] Specifically, in the global grid of the communication process, each node has its corresponding coordinates, which define the node's position in space. In a two-dimensional grid, node coordinates are usually represented by (x, y); in a three-dimensional grid, they are represented by (x, y, z). From the initial node structure coordinates of the global grids of multiple communication processes, find the maximum and minimum coordinate values ​​in each direction. For example, in a two-dimensional grid, find the maximum and minimum values ​​of the x coordinate and the maximum and minimum values ​​of the y coordinate among all nodes; in a three-dimensional grid, find the maximum and minimum values ​​of the z coordinate. The maximum and minimum initial node structure coordinates in each direction are used as the target node structure coordinates of the global grid of the communication process. These target node structure coordinates represent the boundary positions of the global grid in each direction, providing key reference points for the subsequent determination of boundary structure data.

[0064] In the global mesh of the communication process, edges containing the target node's structural coordinates (i.e., the maximum and minimum coordinates in all directions) are searched. These edges, located at the edge of the global mesh, are key elements that constitute the boundary. In a two-dimensional mesh, an edge is a line segment consisting of two nodes and is a component of a surface. In a three-dimensional mesh, an edge is also composed of two nodes, but it is a component of a volume. The initial structural data of these edges containing the target node (including edge node information, edge number, etc.) is extracted and used as the boundary structural data of the global mesh of the communication process. This boundary structural data defines the shape and position of the global mesh boundary, providing the basis for subsequent mesh processing and analysis.

[0065] Step S103: Based on the unique identifiers of the communication processes, the boundary structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process, and the physical field data of the global grid of the communication process is initialized to obtain the initial physical field data of the global grid of the communication process.

[0066] In the present application, first, the boundary structure data of the global grid of the communication process can be traversed, and the boundary structure data of the global grids of adjacent communication processes can be connected to obtain the closed structure data of the global grid of the communication process. Then, based on the unique identifiers of the communication processes, the closed structure data of the global grid of the communication process can be grouped to obtain grouped structure data of the global grids of multiple communication processes. The grouped structure data of the global grid of each communication process includes grouped node structure data of the global grids of multiple communication processes. Finally, based on the grouped node structure data of the global grids of each communication process, the closed structure data of the global grid of the communication process can be reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

[0067] It should be noted that the closed structure data of the global grid of the communication process may include the closed surface data of the global grid of the communication process and the closed volume data of the global grid of the communication process. The group structure data of the global grid of the communication process may include the broken line structure data of the global grid of the communication process and the broken surface structure data of the global grid of the communication process. The group structure data of the global grid of each communication process contains the group node structure data of the global grids of multiple communication processes. The group node structure data specifically includes the relevant information of all nodes in the group, such as node coordinates, node numbers, etc. These nodes originate from the same computing process and are the basic units that constitute the grid. The distribution and connection relationship of the nodes determine the shape of the grid.

[0068] Specifically, first, the boundary structure data of the global grid of the communication process is traversed. In a two-dimensional grid, the boundary structure data consists of a series of edges. Adjacent edges, i.e. edges with common nodes, are found and connected in sequence to form a closed loop, i.e. a closed surface. For ease of understanding, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of the initial structural data of the global grid of a communication process and the closed surface data of the global grid of the communication process provided in an embodiment of the present application. In a three-dimensional grid, the boundary structure data is composed of edges and faces. Adjacent edges and faces, i.e., edges with common nodes and faces with common edges, are found, and the adjacent edges and faces are connected to form a closed three-dimensional entity, i.e., a closed body. The closed structure data finally obtained defines the complete boundary range of the global grid of the communication process, ensuring the integrity of the boundary. For ease of understanding, please refer to Figure 4 , Figure 4 A schematic structural diagram of initial structural data of a global grid of a communication process and closed volume data of a global grid of a communication process provided in an embodiment of the present application.

[0069] Then, in order to divide the entire complex global grid structure into multiple smaller and more manageable parts, the polyline and polyhedral structure data of the global grid of the communication process are grouped according to the unique identifiers of the communication processes. Each group corresponds to a computing process and only contains the polyline or polyhedral structure data of the area that the computing process is responsible for. In this way, the communication process can manage and process the data of each group more efficiently without having to deal with the complex structure of the entire global grid, ensuring the orderliness and traceability of the data. When the closed body structure data of the global grid is a complete two-dimensional boundary definition, the communication process is cut according to the unique identifier of each computing process. The cutting operation divides the closed surface data of the global grid of the communication process into multiple parts, each part corresponds to the group structure data of a computing process, and each group structure data after cutting is a polyline structure data composed of a series of connected edges. The polyline structure data of the global grid of each communication process represents a part of the closed structure data of the global grid of the communication process, which is not necessarily closed and corresponds to the responsible area of ​​a computing process. For ease of understanding, please refer to Figure 5 , Figure 5A structural diagram of the closed surface data of the global grid of a communication process and the broken line structure data of the global grid of the communication process provided in an embodiment of the present application. In the figure, two line types, solid and dashed, are used to distinguish the closed surface data of the global grid of the communication process that should have different unique identifiers. When the closed body structure data of the global grid is a complete three-dimensional boundary definition, the communication process is cut according to the unique identifier of each computing process. The cutting operation divides the closed body data of the global grid of the communication process into multiple parts, each part corresponds to the group structure data of a computing process, and each group structure data after cutting is a broken surface structure data, which is composed of a series of connected faces. The broken surface structure data of the global grid of each communication process represents a part of the closed structure data of the global grid of the communication process, which is not necessarily closed and corresponds to the responsible area of ​​a computing process.

[0070] Finally, during the grid reconstruction process, the grouped node structure data of the global grid of each communication process is a key reference. By analyzing and processing the grouped node structure data of the global grid of each communication process, it is possible to determine which nodes to retain or delete during the reconstruction process.

[0071] If the grouping structure data of the global grid of the communication process is a one-dimensional structure, the intermediate node structure data of at least one communication process can be deleted from the grouping structure data of the global grid of each communication process to obtain the target intermediate node structure data of the global grid of the communication process. Then, based on the head and tail node structure data of the global grid of the communication process and the target intermediate node structure data of the global grid of the communication process, the closed structure data of the global grid of the communication process can be reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

[0072] It should be noted that the grouped node structure data of the global grid of each communication process includes the head and tail node structure data of the global grid of the communication process and the intermediate node structure data of the global grid of the communication process. The intermediate node structure data of the global grid of the communication process is the grouped node structure data of the global grid of the communication process excluding the head and tail node structure data of the global grid of the communication process.

[0073] Specifically, the grouped structure data of the global mesh of the communicating process is a one-dimensional structure, that is, the grouped structure data of the global mesh of the communicating process is a polyline structure data of the global mesh of the communicating process. This data can be viewed as a polyline consisting of multiple line segments, composed of a series of nodes and edges. In a one-dimensional polyline structure data structure, the head and tail nodes are the starting and ending points of the polyline. They define the boundaries of the polyline. The intermediate nodes are nodes located between the head and tail nodes and are used to define the shape and details of the polyline. These nodes provide more information about the polyline path. Deleting some intermediate nodes can simplify the polyline structure data, reduce data volume, and improve processing efficiency. This is very useful when reconstructing or optimizing the mesh. For example, if some intermediate nodes have little impact on the overall shape of the polyline or if they cause mesh quality to degrade, these nodes can be considered for deletion. After deleting some intermediate nodes, the remaining intermediate nodes are called target intermediate nodes. Two node structure data are randomly selected from the head and tail node structure data of the global mesh of the communicating process and the target intermediate node structure data of the global mesh of the communicating process, and a line segment is generated to connect the two nodes corresponding to the two node structure data. This process can be repeated multiple times to generate multiple segmentation lines, providing multiple options for mesh reconstruction. Figure 6 , Figure 6 A schematic diagram of the structure of closed surface data of a global grid of a communication process and reconstructed structural data of the global grid of the communication process is provided in an embodiment of the present application. When the grouped structural data of the global grid of the communication process is a two-dimensional structure, the internal node structural data of at least one global grid of the communication process can be deleted from the grouped structural data of the global grid of each communication process to obtain the target internal node structural data of the global grid of the communication process. Then, based on the boundary node structural data of the global grid of the communication process and the target internal node structural data of the global grid of the communication process, the closed structural data of the global grid of the communication process can be reconstructed to obtain the reconstructed structural data of the global grid of the communication process.

[0074] It should be noted that the grouped node structure data of the global grid of each communication process includes the boundary node structure data of the global grid of the communication process and the internal node structure data of the global grid of the communication process. The internal node structure data of the global grid of the communication process is the grouped node structure data of the global grid of the communication process excluding the boundary node structure data of the global grid of the communication process.

[0075] Specifically, the grouping structure data of the global grid of the communication process is a two-dimensional structure, that is, the grouping structure data of the global grid of the communication process is the folded surface structure data of the global grid of the communication process. The grouping structure data of the global grid of the communication process can be regarded as a folded surface composed of multiple faces, consisting of a series of nodes and faces. In the two-dimensional folded surface structure data, boundary nodes are nodes that constitute the boundary of the folded surface. These nodes define the boundary range of the folded surface, identify the edge position of the folded surface, prevent the grid from extending infinitely, and ensure that the simulation area is clear. Internal nodes are nodes located inside the area enclosed by the boundary nodes. They are used to define the structure and details inside the folded surface and affect the grid density and simulation accuracy. Deleting some internal nodes can simplify the two-dimensional folded surface structure data, reduce the amount of data, and improve processing efficiency. This is very useful when the grid needs to be reconstructed or optimized. For example, if the internal nodes in a certain area are too dense, or these nodes have little effect on the overall shape of the grid, you can consider deleting these nodes to optimize the grid structure. After deleting some internal nodes, the remaining internal nodes are called target internal nodes. From the boundary node structure data of the global grid of the communication process and the target internal node structure data of the global grid of the communication process, two node structure data are randomly selected and a line segment is generated to connect the two nodes corresponding to the two node structure data. This process can be repeated multiple times to generate multiple segmentation lines, providing multiple options for grid reconstruction. For easier understanding, please refer to Figure 7 , Figure 7 A schematic structural diagram of closed volume data of a global grid of a communication process and reconstructed structural data of the global grid of the communication process provided in an embodiment of the present application.

[0076] Furthermore, an intermediate node may be added between the head and tail nodes, or an internal node may be added between the boundary nodes.

[0077] Step S104: Mapping the current physical field data of the local grid of each computing process to the initial physical field data of the global grid of the communication process to obtain the reconstructed physical field data of the global grid of the communication process.

[0078] In this application, a geometric mapping method can be used to first determine the corresponding position of the local grid of each computing process in the global grid of the communicating process. Then, a spatial interpolation method can be used to map the current physical field data of the local grid of each computing process to the corresponding position in the global grid of the communicating process, thereby replacing the initial physical field data of the global grid of the communicating process.

[0079] It should be noted that geometric mapping is used to establish the geometric correspondence between the local grid and the global grid. Through geometric mapping, the node positions of the local grid can be mapped to the space of the global grid, determining the corresponding position of each local grid node in the global grid. Spatial interpolation is used to estimate the physical field data of unknown points based on the physical field data of known points. In grid mapping, spatial interpolation is used to map the physical field data of the local grid to the corresponding position on the global grid.

[0080] Specifically, you can first obtain the geometric information of the local grid and the global grid, including node coordinates, element type, boundary conditions, etc. Then, based on the geometric information of the local grid and the global grid, establish a mapping function. This function can convert the node coordinates of the local grid into the node coordinates of the global grid. Then use the mapping function to calculate the corresponding position of each local grid node in the global grid. Then select a suitable spatial interpolation method, such as nearest neighbor interpolation, bilinear interpolation, bicubic interpolation, etc. Then, based on the physical field data and interpolation method of the local grid, calculate the physical field data of the corresponding position of the global grid. Finally, the calculated physical field data replaces the initial physical field data of the global grid.

[0081] Step S105: Based on the unique identifiers of the communication processes and the unique identifiers of the calculation processes, the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process are distributed to each calculation process, so that each calculation process updates the current structural data of the local grid of each calculation process and the current physical field data of the local grid of each calculation process.

[0082] In the present application, first, based on the unique identifiers of the communication processes, the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process can be divided into reconstructed sub-structural data of the global grid of the communication process and reconstructed sub-physical field data of the global grid of the communication process. The reconstructed sub-structural data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process correspond to the unique identifier of a communication process. Then, the reconstructed sub-structural data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process can be sent to the computing process, so that each computing process uses the reconstructed sub-structural data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process to update the current structural data of the local grid of each computing process and the current physical field data of the local grid of each computing process respectively. The unique identifier of the communication process is consistent with the unique identifier of the computing process.

[0083] It should be noted that each unique identifier of a communication process has a one-to-one correspondence with the unique identifier of a computation process. This correspondence allows the reconstructed structural data and reconstructed physical field data of the global grid to be accurately divided into multiple sub-data, each corresponding to a computation process. This ensures that each computation process receives only the data relevant to it, improving data transmission efficiency and targeted subsequent processing.

[0084] Specifically, the reconstructed structure data and reconstructed physical field data of the global grid can be traversed first. Then, for each data element, the unique identifier of the corresponding communication process is determined according to the area or feature to which it belongs. Then, based on the unique identifier, the data element is divided into the corresponding substructure data or subphysical field data. The communication process sends each substructure data and subphysical field data to the corresponding calculation process based on the unique identifier. After receiving the data, the calculation process uses these data to update the current structure data and physical field data of its local grid. After receiving the substructure data and subphysical field data, the calculation process compares and fuses them with the current data of the local grid. Finally, based on the reconstructed substructure data, the structural information such as the node position and unit connection relationship of the local grid is updated. Based on the reconstructed subphysical field data, the physical field values ​​of the local grid, such as temperature and stress, are updated. Ensure that the updated local grid data is consistent with the reconstructed data of the global grid to improve the accuracy and consistency of the simulation.

[0085] After reshaping the mesh, boundary conditions need to be reinitialized. Based on the nature of the physical problem and the simulation requirements, the constraints on the global mesh boundaries are redefined. For example, in a hot forging simulation, the temperature, displacement, and other conditions on the boundaries are reset to ensure the physical authenticity of the simulation process. The mapped physical field data is used as the initial values, or the initial physical field distribution is recalculated according to the laws of physics. For example, in a fluid dynamics simulation, the initial velocity and pressure fields are recalculated based on the reshaping of the mesh to ensure that they conform to the new mesh structure and physical conditions.

[0086] In summary, the present application provides a method for reconstructing the grid of a communication process, which obtains the current structural data and physical field data of the local grids of multiple computing processes and uses them as the initial structural data of the global grid of the communication process, thereby realizing the centralized integration and unified initialization of the local grid data of each computing process. By determining the boundary structure data from the initial structural data of the global grid and reconstructing the global grid using the boundary structure data, it is possible to fully consider the influence of the grid boundary on the overall structure and ensure that the reconstructed global grid structure is more in line with the actual computing needs and physical field distribution. At the same time, the physical field data of the global grid is initialized, providing a reasonable starting point for subsequent mapping and updating of physical field data. By mapping the current physical field data of the local grid of each computing process to the initial physical field data of the global grid of the communication process, a smooth transition of data between different grid levels is achieved, which ensures the continuity and consistency of the physical field data in the entire grid system. Based on the unique identification correspondence between the communication process and the calculation process, the reconstructed structural data and physical field data of the global grid can be accurately distributed to each calculation process. After receiving the updated data, each calculation process can update its own local grid data, so that the structure and physical field data of the local grid can more accurately reflect the actual state, thereby improving the quality of the mesh of the reconstructed communication process.

[0087] An electronic device is also provided in an embodiment of the present application. Figure 8 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0088] like Figure 8 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 802 or programs loaded from a storage device 808 into a random access memory (RAM) 803. When the electronic device is powered on, the RAM 803 also stores various programs and data required for the operation of the electronic device. The processing device 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0089] Typically, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a memory card, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 8 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0090] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements a method for reconstructing a grid of any communication process provided in the embodiment of the present application.

[0091] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement a grid reconstruction method for any communication process provided in an embodiment of the present application.

[0092] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0093] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0094] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0095] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A method for reconstructing a grid of a communication process, characterized in that: The method comprises: Acquire current structural data of local grids of multiple computing processes and current physical field data of the local grids of the computing processes, and use the current structural data of the local grids of each computing process as initial structural data of the global grid of the communication process, wherein each unique identifier of the communication process corresponds to the unique identifier of each computing process; determining boundary structure data of the global grid of the communication process from the initial structure data of the global grid of the communication process; Based on the unique identifiers of the communication processes, reconstructing the boundary structure data of the global grid of the communication process to obtain the reconstructed structure data of the global grid of the communication process, and initializing the physical field data of the global grid of the communication process to obtain the initial physical field data of the global grid of the communication process; Mapping the current physical field data of the local grid of each of the computing processes to the initial physical field data of the global grid of the communication process to obtain the reconstructed physical field data of the global grid of the communication process; Based on the unique identifiers of the communication processes and the unique identifiers of the computing processes, distributing the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process to the computing processes, so that the computing processes update the current structural data of the local grids of the computing processes and the current physical field data of the local grids of the computing processes; The step of reconstructing the boundary structure data of the global grid of the communication process based on each unique identifier of the communication process to obtain the reconstructed structure data of the global grid of the communication process, and initializing the physical field data of the global grid of the communication process, includes: Traversing the boundary structure data of the global grid of the communication process, connecting the boundary structure data of the global grid of adjacent communication processes, and obtaining the closed structure data of the global grid of the communication process; Based on the unique identifiers of the communication processes, the closed structure data of the global grids of the communication processes are grouped to obtain a plurality of group structure data of the global grids of the communication processes, wherein the group structure data of the global grid of each communication process includes a plurality of group node structure data of the global grids of the communication processes; Based on the grouped node structure data of the global grid of each communication process, the closed structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

2. The method for reconstructing a grid of a communication process according to claim 1, characterized in that: The initial structure data of the global grid of the communication process includes a plurality of initial node structure coordinates of the global grid of the communication process; Determining the boundary structure data of the global grid of the communication process from the initial structure data of the global grid of the communication process includes: From a plurality of initial node structure coordinates of the global grid of the communication process, taking the maximum and minimum initial node structure coordinates in each direction as the target node structure coordinates of the global grid of the communication process; The initial structural data of the edge where the structural coordinates of the target node of the global grid of the communication process are located is used as the boundary structural data of the global grid of the communication process.

3. The method for reconstructing a grid of a communication process according to claim 1, characterized in that: If the grouping structure data of the global grid of the communication process is a one-dimensional structure, the grouping node structure data of the global grid of each communication process includes the head and tail node structure data of the global grid of the communication process and the intermediate node structure data of the global grid of the communication process, and the intermediate node structure data of the global grid of the communication process is the grouping node structure data of the global grid of the communication process excluding the head and tail node structure data of the global grid of the communication process; The reconstructing the closed structure data of the global grid of each communication process based on the grouped node structure data of the global grid of each communication process to obtain the reconstructed structure data of the global grid of the communication process includes: For each of the grouping structure data of the global grid of the communication process, deleting the intermediate node structure data of the global grid of at least one of the communication processes to obtain the target intermediate node structure data of the global grid of the communication process; Based on the head and tail node structure data of the global grid of the communication process and the target intermediate node structure data of the global grid of the communication process, the boundary structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

4. The method for reconstructing a grid of a communication process according to claim 1, wherein: If the grouping structure data of the global grid of the communication process is a two-dimensional structure, the grouping node structure data of the global grid of each communication process includes the boundary node structure data of the global grid of the communication process and the internal node structure data of the global grid of the communication process, and the internal node structure data of the global grid of the communication process is the grouping node structure data of the global grid of the communication process excluding the boundary node structure data of the global grid of the communication process; The reconstructing the closed structure data of the global grid of each communication process based on the grouped node structure data of the global grid of each communication process to obtain the reconstructed structure data of the global grid of the communication process includes: For each of the grouping structure data of the global grid of the communication process, deleting the internal node structure data of the global grid of at least one of the communication processes to obtain target internal node structure data of the global grid of the communication process; Based on the boundary node structure data of the global grid of the communication process and the target internal node structure data of the global grid of the communication process, the boundary structure data of the global grid of the communication process is reconstructed to obtain the reconstructed structure data of the global grid of the communication process.

5. The method for reconstructing a grid of a communication process according to claim 1, characterized in that: Mapping the current physical field data of the local grid of each of the computing processes to the initial physical field data of the global grid of the communication process to obtain the reconstructed physical field data of the global grid of the communication process includes: Determining corresponding positions of the local grids of each of the computing processes in the global grid of the communication process using a geometric mapping method; The current physical field data of the local grid of each computing process is mapped to the corresponding position in the global grid of the communication process by using a spatial interpolation method to replace the initial physical field data of the global grid of the communication process.

6. The method for reconstructing a grid of a communication process according to claim 1, characterized in that: The method further comprises distributing the reconstructed structural data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process to each of the computing processes based on the unique identifiers of the communication processes and the unique identifiers of the computing processes, so that each of the computing processes updates the current structural data of the local grid of each of the computing processes and the current physical field data of the local grid of each of the computing processes. Based on the unique identifiers of the communication processes, the reconstructed structure data of the global grid of the communication process and the reconstructed physical field data of the global grid of the communication process are divided into a plurality of reconstructed sub-structure data of the global grid of the communication process and a plurality of reconstructed sub-physical field data of the global grid of the communication process, each reconstructed sub-structure data of the global grid of the communication process and each reconstructed sub-physical field data of the global grid of the communication process corresponding to a unique identifier of the communication process; The reconstructed substructure data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process are sent to the calculation process, so that each calculation process uses the reconstructed substructure data of the global grid of each communication process and the reconstructed sub-physical field data of the global grid of each communication process to update the current structure data of the local grid of each calculation process and the current physical field data of the local grid of each calculation process respectively, and the unique identifier of the communication process is consistent with the unique identifier of the calculation process.

7. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the method for reconstructing a grid of a communication process according to any one of claims 1 to 6.

8. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the method for reconstructing a grid of a communication process according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the method for reconstructing a grid of a communication process as described in any one of claims 1 to 6.

Images