Full-process data processing method and system oriented to fluid mechanics control equation

Abstract

The invention discloses a full-process data processing method and system oriented to a fluid mechanics control equation, and the method comprises the steps: initializing a path and an artificial intelligence agent related to the solution of the fluid mechanics control equation in a local server, so as to import and disassemble a parameter space of a fluid mechanics problem; identifying a control equation and batch matching example files corresponding to the hydromechanics problem through an artificial intelligence agent, and extracting core parameters related to the control equation; performing parameter configuration on the control equation through an artificial intelligence agent; converting the format of the example file and locally storing the example file to a corresponding path; and calling a solver of the control equation to carry out resolving processing, and verifying the result of the resolving processing so as to judge the effectiveness of the result. By constructing the exclusive link for solving the fluid mechanics control equation, an automatic full-process link from problem parameter disassembly, control equation identification, exclusive parameter configuration, format conversion and disintegration verification is realized, and the example processing efficiency and the solving accuracy are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of AI data processing, in particular to a full-process data processing method and system for fluid mechanics control equations. BACKGROUND

[0002] Computational fluid dynamics (CFD) solves fluid mechanics control equations (such as continuity equation, momentum equation, energy equation, etc.) by computer and numerical method, realizes simulation analysis of fluid motion, heat transfer, mass transfer, etc., and is widely used in aerospace, automobile engineering, energy power, etc. The fluid mechanics control equation has the characteristics of strong nonlinearity, multi-physical field coupling, boundary condition sensitivity, etc., and its solution needs to rely on accurate grid division, reasonable selection of turbulence model, and adaptive numerical discrete format, and different types of fluid problems (incompressible flow, compressible flow, multi-directional flow, etc.) have significant differences in the shape and parameter requirements of the control equation.

[0003] The traditional computational fluid dynamics (CFD) processing has the following two core problems: first, the contradiction between fluid mechanics special requirements and manual operation, the construction of the example needs to manually adjust the key parameters (such as the setting of the viscosity coefficient of the momentum equation, the configuration of the thermal conductivity coefficient of the energy equation, etc.) according to the characteristics of the control equation, and the grid density needs to match the accuracy requirement of the equation solution (i.e. the grid in the boundary layer area needs to be encrypted to ensure the accuracy of the gradient calculation), manual operation is easy to cause the mismatch between the parameters and the equation type, and then affect the convergence of the solution; second, the generality process is out of touch with the solution of fluid mechanics, the existing example processing (such as file import, solver calling, etc.) is mostly computer general operation, and no special link is designed for the solution logic of fluid mechanics control equation, for example, when solving compressible flow, the Mach number, specific heat capacity, etc. Parameters need to be configured additionally, and the traditional process cannot automatically identify the equation type and match the corresponding parameters, which needs manual secondary modification, resulting in low processing efficiency.

[0004] The existing AI technology and the combination mode of the automation workflow tool cannot design a special link for the solution requirements of the fluid mechanics control equation, and still stay at the general file processing level, which leads to the technical problem that the general process cannot adapt to the special requirements of fluid mechanics. SUMMARY

[0005] Considering that the existing fluid mechanics control equation processing process cannot identify the control equation and match the corresponding network and numerical parameters, cannot design a special link for the solution requirements of the fluid mechanics control equation, and cannot adapt to the special requirements of fluid mechanics, the present application is proposed to provide a full-process data processing method for fluid mechanics control equations to overcome the above problems or at least partially solve the above problems, which includes: initializing a path and an artificial intelligence agent related to fluid mechanics control equation solving on a local server, thereby importing and disassembling a parameter space of a fluid mechanics problem; identifying, by the artificial intelligence agent, a control equation corresponding to the fluid mechanics problem and a batch of matched example files, and extracting core parameters related to the control equation; configuring, by the artificial intelligence agent, parameters of the control equation, converting a format of the example files, and locally saving the example files to a corresponding path; calling a solver of the control equation to perform solving processing, and verifying a result of the solving processing, so as to determine validity of the result.

[0006] Optionally, initializing a path and an artificial intelligence agent related to fluid mechanics control equation solving on a local server, thereby importing and disassembling a parameter space of a fluid mechanics problem, includes: deploying an automatic workflow platform on the local server, and collecting an artificial intelligence agent and connection parameters of the artificial intelligence agent and a large language model in the automatic workflow platform; initializing, according to the automatic workflow platform, a path related to fluid mechanics control equation solving; wherein the path matches a node of the automatic workflow platform; importing, by the node of the automatic workflow platform, a parameter space of a fluid mechanics problem to be solved, and disassembling, by the artificial intelligence agent, the parameter space into a plurality of executable steps according to a preset fluid mechanics knowledge graph; wherein the plurality of executable steps include control equation selection, grid parameter configuration, boundary condition setting, and solving parameter definition.

[0007] Optionally, identifying, by the artificial intelligence agent, a control equation corresponding to the fluid mechanics problem and a batch of matched example files, and extracting core parameters related to the control equation, includes: identifying, by the artificial intelligence agent, a control equation type corresponding to the fluid mechanics problem, batch-matching, according to the control equation type, a corresponding example file in a local example warehouse through a file screening node of the automatic workflow platform, and extracting core parameters related to the control equation from the example file; configuring, by the artificial intelligence agent, parameters of the control equation, converting a format of the example files, and locally saving the example files to a corresponding path, includes: automatically modifying, by the artificial intelligence agent, the example files according to a solving requirement of the control equation, adjusting grid parameters according to a gradient requirement of the control equation, and configuring numerical parameters according to the control equation type; Converting the configured numerical parameters into a format supported by fluid mechanics solving software and saving to a corresponding path according to the control equation type through a file processing node of the automated workflow platform.

[0008] Optionally, adjusting a grid parameter according to a gradient requirement of the control equation type, including: Accessing an artificial intelligence agent to identify a control equation type corresponding to the obtained fluid mechanics problem; Analyzing a gradient source term corresponding to the control equation type according to the control equation type corresponding to the fluid mechanics problem, wherein the gradient source term refers to a physical quantity parameter term affecting gradient change; Normalizing the physical quantity parameter term corresponding to the gradient source term corresponding to the control equation type to obtain a normalized physical quantity parameter term; Forming a gradient correlation vector corresponding to the control equation type using the normalized physical quantity parameter term; Obtaining a gradient potential field Φ(x) using the gradient correlation vector corresponding to the control equation type; wherein the gradient potential field Φ(x) is obtained by the following formula: Wherein Φ(x) represents the gradient potential field; S(x) represents the relative intensity of the gradient source term, and S(x) =║X║2×(X0+║X║2) -1 , wherein║X║2 represents the L2 norm corresponding to the gradient correlation vector; X0 represents a reference value of the same dimension as the L2 norm corresponding to the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i represents the weight value corresponding to the i-th vector element; X i represents the numerical value corresponding to the i-th vector element; G(x) represents an intensification factor, wherein the intensification factor is used to enhance the grid configuration intensity of the gradient vector in the key area, and the intensification factor G(x) is obtained by the following formula: Wherein α represents an intensification intensity coefficient, and the value range is 0.5-1.3; β represents a stability period number, and the value range is 1-1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; F0 represents a preset divergence reference value; Adjusting the current grid size using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained by the following formula: Wherein Г represents the adjusted grid size, η represents an intensity adjustment coefficient, and the value is 0.7-1.5; Δ base represents the grid size before adjustment.

[0009] Optionally, a solver of the control equation is called to perform a solving process, and a result of the solving process is verified to determine validity of the result, including: A solving instruction is constructed according to the control equation type through a command line execution node of the automated workflow platform, so as to call a control equation solver to perform a solving process; The solving process is monitored in real time through the artificial intelligence agent, and the validity of the result of the solving process is determined according to the solving process log and the convergence characteristics of the control equation.

[0010] As an aspect of the present application, the embodiments of the present application also provide a full-process data processing system for fluid mechanics control equations, including: An initialization module is configured to initialize a path and an artificial intelligence agent related to a fluid mechanics control equation solving on a local server, so as to import and disassemble a parameter space of a fluid mechanics problem; An example file processing module is configured to identify a control equation corresponding to the fluid mechanics problem through the artificial intelligence agent, and to batch-match an example file, and to extract a core parameter related to the control equation; A parameter configuration module is configured to perform parameter configuration on the control equation through the artificial intelligence agent; A file conversion and saving module is configured to convert a format of the example file and to save locally to a corresponding path; A solving and verifying module is configured to call a solver of the control equation to perform a solving process, and to verify a result of the solving process, so as to determine validity of the result.

[0011] Optionally, the initialization module is configured to initialize a path and an artificial intelligence agent related to a fluid mechanics control equation solving on a local server, so as to import and disassemble a parameter space of a fluid mechanics problem, including: An automated workflow platform is deployed on a local server, and an artificial intelligence agent and a connection parameter of the artificial intelligence agent and a large language model are configured in the automated workflow platform; The path is initialized according to the automated workflow platform, and the path is matched with a node of the automated workflow platform; A parameter space of a fluid mechanics problem to be solved is imported through a node of the automated workflow platform, and the parameter space is disassembled into a plurality of executable steps according to a preset fluid mechanics knowledge graph through the artificial intelligence agent; the plurality of executable steps include control equation selection, grid parameter configuration, boundary condition setting, and solving parameter definition.

[0012] Optionally, the case file processing module is configured to identify a control equation corresponding to the fluid mechanics problem and batch-match a case file by the artificial intelligence agent, extract core parameters related to the control equation, including: By identifying the control equation type corresponding to the fluid mechanics problem by the artificial intelligence agent, batch-matching the corresponding case file in the local case warehouse according to the control equation type by the file screening node of the automatic workflow platform, and extracting the core parameters related to the control equation from the case file; The parameter configuration module is configured to configure parameters for the control equation by the artificial intelligence agent, including: By the artificial intelligence agent, the case file is automatically modified according to the solving requirement of the control equation; the grid parameters are adjusted according to the gradient requirement of the control equation; and the numerical parameters are configured according to the control equation type; The file conversion and saving module is configured to convert the format of the case file and save it locally to the corresponding path, including: By the file processing node of the automatic workflow platform, the configured numerical parameters are converted into a format supported by the fluid mechanics solving software, and saved to the corresponding path according to the control equation type.

[0013] Optionally, the grid parameters are adjusted according to the gradient requirement of the control equation, including: The control equation type corresponding to the fluid mechanics problem is obtained by calling the artificial intelligence agent; The gradient source term corresponding to the control equation type is analyzed according to the control equation type corresponding to the fluid mechanics problem, wherein the gradient source term refers to the physical quantity parameter term affecting the gradient change; The physical quantity parameter term corresponding to the gradient source term of the control equation type is normalized to obtain the normalized physical quantity parameter term; The normalized physical quantity parameter term is used to form a gradient correlation vector corresponding to the control equation type; The gradient potential field Φ(x) is obtained by using the gradient correlation vector corresponding to the control equation type; wherein the gradient potential field Φ(x) is obtained by the following formula: Wherein, Φ(x) represents the gradient potential field; S(x) represents the relative strength of the gradient source term, and S(x)=║X║2×(X0+║X║2) -1 ,║X║2 represents the L2 norm corresponding to the gradient correlation vector; X0 represents a reference value of the same dimension as the L2 norm corresponding to the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i represents the weight value corresponding to the i-th vector element; X irepresents the numerical value corresponding to the i-th vector element; G(x) represents a reinforcement factor, wherein the reinforcement factor is used to enhance the grid configuration intensity of the gradient vector in the key region, and the reinforcement factor G(x) is obtained by the following formula: Wherein, alpha represents the reinforcement intensity coefficient, the value range is 0.5-1.3; beta represents the stability period number, the value range is 1-1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; F0 represents the preset divergence reference value; The current grid size is adjusted by using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained by the following formula: Wherein, Г represents the adjusted grid size, eta represents the intensity adjustment coefficient, the value is 0.7-1.5; Delta base Represents the grid size before adjustment.

[0014] Optionally, the solving and verifying module is configured to call a solver of the control equation for solving processing, and verify the result of the solving processing to determine the validity of the result, including: Through the command line execution node of the automatic workflow platform, a special solving instruction is constructed according to the control equation type to call a control equation solver for solving processing; Through the artificial intelligence agent, the solving processing log is monitored in real time, and according to the solving processing log and the convergence characteristics of the control equation, the validity of the result of the solving processing is determined.

[0015] The beneficial effects of the above technical solutions provided in the embodiments of the application at least include: The embodiments of the application provide a fluid mechanics control equation oriented full-process data processing method and system, which initializes a path and an artificial intelligence agent related to fluid mechanics control equation solving in a local server, imports and disassembles the parameter space of a fluid mechanics problem, identifies the control equation corresponding to the fluid mechanics problem through the artificial intelligence agent, and batch matches the example file, extracts the core parameters related to the control equation, configures the parameters of the control equation through the artificial intelligence agent, converts the format of the example file and saves it locally to the corresponding path, calls a solver of the control equation for solving processing, and verifies the result of the solving processing to determine the validity of the result. By constructing a special link for fluid mechanics control equation solving, the automatic full-process link from problem parameter disassembly, control equation identification, special parameter configuration, format conversion and solution verification is realized, and the example processing efficiency and solving accuracy are improved.

[0016] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structures particularly pointed out in the written description and claims hereof as well as the appended drawings.

[0017] The technical solutions of the present application are described in further detail below with reference to the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings are included to provide a further understanding of the present application and are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and are used to explain the present application, but do not constitute a limitation on the present application. In the drawings: Figure 1 A flowchart of a full-process data processing method for fluid mechanics control equations provided in an embodiment of the present application; Figure 2 A structural schematic diagram of a full-process data processing system for fluid mechanics control equations provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] Exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0020] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", "far", "near", "front", "back", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0021] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication between two elements inside. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0022] Referring to Figure 1 An embodiment of the present application provides a full-process data processing method for fluid mechanics control equations. The full-process data processing method for fluid mechanics control equations comprises: Initializing a path and an artificial intelligence agent related to fluid mechanics control equation solving on a local server to import and disassemble the parameter space of a fluid mechanics problem; the artificial intelligence agent is an AI agent that can realize corresponding task processing functions on the local server as an artificial intelligence intermediary; Identifying the control equation corresponding to the fluid mechanics problem and batch matching the example file through the artificial intelligence agent, and extracting the core parameters related to the control equation; Parameter configuration of the control equation through the artificial intelligence agent; conversion of the example file format and local saving to the corresponding path; Calling the solver of the control equation for solving processing and verifying the result of the solving processing to determine the validity of the result. The full-process data processing method for fluid mechanics control equations has the beneficial effects of the above-mentioned embodiment. By constructing a dedicated link for fluid mechanics control equation solving, the method realizes automatic full-process link from problem parameter disassembly, control equation identification, dedicated parameter configuration, format conversion, and solution verification, improves example processing efficiency and solving accuracy.

[0023] In another embodiment, a path and an artificial intelligence agent related to fluid mechanics control equation solving are initialized on a local server to import and disassemble the parameter space of a fluid mechanics problem, comprising: Deploying an automatic workflow platform on the local server, and collecting the artificial intelligence agent and the connection parameters of the artificial intelligence agent and the large language model on the automatic workflow platform; Initializing a path related to fluid mechanics control equation solving according to the automatic workflow platform; the path matches the nodes of the automatic workflow platform; Importing the parameter space of the fluid mechanics problem to be solved through the nodes of the automatic workflow platform, and disassembling the parameter space into several executable steps according to the preset fluid mechanics knowledge graph through the artificial intelligence agent; the several executable steps include control equation selection, grid parameter configuration, boundary condition setting, and solution parameter definition.

[0024] The automatic workflow platform may be implemented as an n8n workflow platform, for example.

[0025] The above embodiment has the beneficial effect that an automatic workflow platform is taken as an automatic workflow carrier, and the automatic workflow platform integrates an artificial intelligence agent function module capable of running a corresponding large language model LLM. In actual operation, the automatic workflow platform is first deployed on a local server, and the workflow platform integrates an artificial intelligence agent and configures connection parameters of the artificial intelligence agent and the large language model LLM, so that the artificial intelligence agent can connect and call the large language model. The automatic workflow platform includes a plurality of nodes matched with the workflow, and a plurality of process steps are involved in the solving process of the fluid mechanics control equation. In order to enable the workflow platform to adapt to the solving of the fluid mechanics control equation, a path related to the solving of the fluid mechanics control equation is initialized on the platform, and the path is ensured to be adapted to the nodes of the platform.

[0026] There are also fluid mechanics problems including solving and processing of different parameters. In order to enable all parameters to be adaptively processed, the parameter space of the fluid mechanics problem to be solved is imported through the nodes of the automatic workflow platform, so that the platform nodes correspondingly undertake all tasks of the processing parameter space. Specifically, according to the preset fluid mechanics knowledge graph, the parameter space is disassembled into executable steps such as control equation selection, grid parameter configuration, boundary condition setting, and solving parameter definition by the artificial intelligence agent, so as to ensure that the artificial intelligence agent processes each executable step independently.

[0027] In another embodiment, the grid parameters are adjusted according to the gradient requirements of the control equation, including: The artificial intelligence agent is called to identify the control equation type corresponding to the fluid mechanics problem; The gradient source term corresponding to the control equation type is analyzed according to the control equation type corresponding to the fluid mechanics problem, wherein the gradient source term refers to a physical quantity parameter term affecting the gradient change; The physical quantity parameter term corresponding to the gradient source term corresponding to the control equation type is normalized to obtain a normalized physical quantity parameter term; The normalized physical quantity parameter term is used to form a gradient correlation vector corresponding to the control equation type; The gradient potential field Φ(x) is obtained by using the gradient correlation vector corresponding to the control equation type; wherein the gradient potential field Φ(x) is obtained by the following formula: Wherein, Φ(x) represents the gradient potential field; S(x) represents the relative strength of the gradient source term, and S(x)=║X║2×(X0+║X║2) -1 , wherein ||X||2 represents the L2 norm corresponding to the gradient correlation vector; X0 represents a reference value of the same dimension as the L2 norm corresponding to the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i represents the weight value corresponding to the i-th vector element; Xi represents the numerical value corresponding to the i-th vector element; G(x) represents a reinforcement factor, wherein the reinforcement factor is used to enhance the grid configuration intensity of the key area where the gradient vector is located, and the reinforcement factor G(x) is obtained by the following formula: wherein a represents a reinforcement intensity coefficient, and the value range is 0.5-1.3; β represents a stability period number, and the value range is 1-1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; F0 represents a preset divergence reference value; The current grid size is adjusted by using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained by the following formula: wherein Г represents the adjusted grid size, and η represents an intensity adjustment coefficient, and the value is 0.7-1.5; Δ base represents the grid size before adjustment.

[0028] The above embodiment has the beneficial effects that through an intelligent pre-configuration method combining physical knowledge and mathematical model, an optimized grid highly consistent with specific flow physics and user demand is generated at the beginning of calculation, thereby realizing the coordinated leap of efficiency, precision and automation degree at the source, and breaking through the inherent limitations of traditional grid self-adaptive technology relying on solver feedback and artificial experience. At the same time, by identifying the control equation type and analyzing the gradient source term through AI, the physical quantities (such as flow gradient and pressure gradient) affecting the gradient change can be extracted, avoiding the problem of insufficient adaptability of "general grid" to different fluid problems, and making the grid adjustment more consistent with the physical nature of the specific problem. The L2 norm, divergence and other indicators of the gradient correlation vector will significantly increase in the "key area where the gradient changes dramatically"; at the same time, combined with the enhancement effect of the reinforcement factor, the gradient potential field will rise in these areas, and finally the grid size is reduced through the grid adjustment formula, the calculation resolution of the key area is improved, and the numerical error is reduced. At the same time, the grid parameters are directly mapped from the analytical formula, avoiding the repeated trial and error and global / local grid reconstruction operations based on error estimation or gradient threshold determination, significantly reducing the calculation resource consumption purely for grid adaptation process. Through the mechanisms of "gradient potential field" and "local aggregation degree", the key areas such as boundary layer, shock wave and shear layer where the physical quantity changes dramatically can be identified and strengthened in advance without relying on any instantaneous solution, and the resolution capability for complex flow phenomena is improved.

[0029] In another embodiment, the control equation corresponding to the fluid mechanics problem is identified by an artificial intelligence agent, and a batch of example files are matched, and the core parameters related to the control equation are extracted, including: The type of control equation corresponding to the fluid mechanics problem is identified by an artificial intelligence agent, and according to the type of control equation, the corresponding example files are batch-matched in a local example warehouse through a file screening node of an automatic workflow platform, and the core parameters related to the control equation are extracted from the example files; The parameters of the control equation are configured by the artificial intelligence agent, and the example files are converted in format and saved locally to the corresponding path, including: The example files are automatically modified by the artificial intelligence agent according to the solving requirements of the control equation, the grid parameters are adjusted according to the gradient requirements of the control equation, and the numerical parameters are configured according to the type of control equation; The configured numerical parameters are converted into a format supported by the fluid mechanics solving software through the file processing node of the automatic workflow platform, and are saved to the corresponding path according to the type of control equation.

[0030] The fluid mechanics solving software may be implemented as VirtualFlow software.

[0031] The beneficial effects of the above embodiments are that the example files corresponding to the solving process of different types (forms) of fluid mechanics control equations are different. In order to enable each type of fluid mechanics control equation to obtain accurate example file support, the artificial intelligence agent batch-matches the corresponding example files in the local example warehouse based on the disassembled control equation type and the file screening node of the platform, and extracts the core parameters related to the control equation from the example files; wherein the core parameters corresponding to different types of control equations are different, such as the core parameter of the momentum equation is the viscosity coefficient, and the core parameter of the energy equation is the thermal conductivity coefficient. Through the above way of extracting core parameters, the solving requirements of different types of control equations can be met.

[0032] In addition, the example files required by different types of control equations are different. In order to ensure that the example files can be effectively processed, the artificial intelligence agent automatically modifies the example files according to the solving requirements of the control equation, adjusts the grid parameters according to the gradient requirements of the control equation, and configures the numerical parameters according to the type of control equation; and the configured numerical parameters are converted into a format supported by the fluid mechanics solving software through the file processing node of the automatic workflow platform, and are saved to the corresponding path according to the type of control equation. By converting the format of the example files, it can be ensured that the example files are compatible with the corresponding software, and the processing efficiency of the example files is improved.

[0033] In another embodiment, a solver of the control equation is called for solving processing, and the result of the solving processing is verified to determine the validity of the result, including: The dedicated solving instruction is constructed according to the control equation type through a command line execution node of the automated workflow platform, so as to call a control equation solver to perform solving processing; wherein, the control equation solver may be implemented as a transatmb solver, for example. The solving processing log is monitored in real time through the artificial intelligence agent, and the effectiveness of the result of the solving processing is judged according to the solving processing log and the convergence characteristics of the control equation.

[0034] The above-mentioned embodiments have the beneficial effects that, in actual operation, the command line execution node of the platform is used to construct a solving instruction matched with the control equation according to the control equation type, so as to ensure that the solving instruction can calculate and process each solving step of the control equation, and the control equation solver is called to perform solving processing, thereby realizing efficient solving of the control equation. In addition, the solving processing log is monitored in real time through the artificial intelligence agent, and the effectiveness of the result of the solving processing is judged according to the solving processing log and the convergence characteristics of the control equation. When the solving processing process of the control equation meets the convergence requirement, the result of the solving processing is judged to be effective; otherwise, the result of the solving processing is judged to be ineffective, and the control equation is solved again until the convergence requirement is met.

[0035] The embodiment of the present application takes the CFD example processing of the “two-dimensional cylindrical external incompressible flow problem” as an example, and the goal is to realize full automation from problem parameter input to solving verification, wherein the fluid mechanics control equation is the incompressible N-S equation (continuity equation + momentum equation, not including energy equation), and the core requirements include: Mesh: The surface boundary layer region mesh of the cylinder is encrypted (the minimum unit size is 0.005m), and the mesh of the far field region is sparse (the unit size is 0.1m); Numerical parameters: the finite volume method is used to discretize the equation, the SIMPLE algorithm is used to solve the pressure-velocity coupling, and the convergence criterion is that the residual is less than 1e-3; Boundary conditions: velocity inlet (incoming flow velocity 10m / s), pressure outlet (static pressure 0Pa), and no slip boundary on the surface of the cylinder.

[0036] The processing process of the “two-dimensional cylindrical external incompressible flow problem” is as follows: (1) Automated workflow platform deployment and environment configuration The n8n is installed on the local server through npminstall-gn8n, the platform is started through n8nstart--port5678, and the visual interface is accessed through http: / / server IP: 5678; Artificial intelligence agent integration and large language model LLM configuration: Add an "AI Agent" module to the automated workflow platform, configure the connection parameters with the target LLM (deepseek / deepseek-r1-0528-qwen3-8b); the API address is https: / / api.openrouter.ai / v1 / chat / completions, the API key is obtained through the OpenRouter platform, and the request timeout is set to 60 seconds; Path initialization: Local test case repository path: "C:\Users\18274\OneDrive\Desktop\CFD_Case\Incompressible"; Path to save the modified example file: "C:\Users\18274\OneDrive\Desktop\CFD_Case\Processed\Incompressible\Cylinder_Flow"; Solution result output path: The file is located at “C:\Users\18274\OneDrive\Desktop\CFD_Case\Result\Incompressible\Cylinder_Flow” and is stored in categories such as “Residual Files”, “Flow Field Data Files”, and “Convergence Reports”.

[0037] (2) Parametric space diagram and artificial intelligence agent decomposition of fluid mechanics problems Parameter space import: Add a "Form Input" node to the automated workflow platform and design a dedicated input interface for fluid mechanics problems. The association logic between the fields and the governing equations is shown in Table 1 below, ensuring that the input parameters directly serve the subsequent equation identification and configuration. Table 1; ; Once the above parameters are entered, the node automatically converts the parameter space into a JSON format data stream, as follows: json { "problem_type":"Flow around an external cylinder in two dimensions", "fluid_type":"Incompressible air", "governing_equation":"Incompressible Navier-Stokes equations", "physical_parameters": {"velocity_inlet": 10, "density": 1.225, "viscosity": 1.789e-5}, "solution_requirement": {"residual_criterion": 1e-6, "output_data": "velocity distribution"} } Artificial intelligence agent parameter space disintegration The artificial intelligence agent receives the above JSON data stream and disintegrates the parameter space into four executable steps strongly associated with the incompressible N-S equation, ensuring that each step serves the equation solving needs: json { "step1": "Control equation identification and matching: Confirm that the target equation is the incompressible N-S equation, and filter the.stt / .inp files containing "incompressible" or "2D_Cylinder" in the name", "step2": "Grid parameter configuration: According to the requirements of incompressible flow boundary layer, the minimal_cellsize of the cylinder surface grid is ≤0.005m, and the maximal_cellsize of the far field is ≥0.1m, to improve the stability of equation discretization", "step3": "Boundary conditions and numerical parameter settings: Velocity inlet (10m / s), pressure outlet (0Pa), use SIMPLE algorithm to solve pressure-velocity coupling, iteration steps ≥1000", "step4": "Solution verification rules: Monitor the continuity equation and x / y direction momentum equation residuals, which need to be reduced to 1e-6 below and stable for 10 steps, to ensure the effectiveness of the equation solution" } Disintegration logic: Through the identification of the "governing_equation" field, the artificial intelligence agent automatically matches the solving logic of the incompressible N-S equation.

[0038] (3) Control equation identification and batch matching of example files (exclusive screening) Add "custom code node (function1)" in the automated workflow platform, receive the disintegration results output by the artificial intelligence agent, extract "control equation type = incompressible N-S equation", and generate targeted screening rules: File type screening: Only.stt grid files and.inp solver input files are retained.

[0039] Name tag screening: File name should contain "incompressible" or "2D_Cylinder".

[0040] Grid parameter pre-check: Read the "minimal_cellsize" field in the.stt file, only keep files with ≤0.01m (preliminarily meet the requirement of incompressible boundary layer resolution, further optimization will be done later).

[0041] Batch case file reading and path processing Add a "File Read" node and configure the above screening rules. Scan the local case repository "C:\Users\18274\OneDrive\Desktop\CFD_Case\Incompressible" and enable batch reading mode to obtain all files that meet the conditions at one time.

[0042] Write a JS script to process file paths through "Custom Code Node (function1)". Path extraction: Detect the input data field, convert it to a string, split it by newline characters, filter out empty lines and invalid paths, and get the absolute path of the valid file. Standardization: Remove the double quotes at the beginning and end of the path through regular matching, replace the backslashes with forward slashes, remove the white spaces, and finally output in the format of "Item+key-value pair" (such as [Item0 {"Path":"C:\Users\18274\OneDrive\Desktop\CFD_Case\Incompressible\Cylinder_2D.incompressible.stt"},] ) to ensure that each case corresponds to a unique ID and path. Add a "LoopOverItems" node to execute recursive functions, iterate through all Item key-value pairs, extract "case file name" and "case path" information through the {{$json.source_dir}} built-in command, store them in data data form (as shown in Table 2), and extract text information from data through the "ExtractfromFile" node, set the input binary field to "data" and the target output field to "text", and pass it to the artificial intelligence agent node.

[0043] Table 2 ; (4) Artificial intelligence agent for exclusive parameter configuration of control equations Build exclusive prompt words for control equations: In the n8n workflow platform "Artificial Intelligence Agent" node, based on the disassembly results of step 2 and the file pre-extraction information of step 3, the parameter modification prompt words for the incompressible N-S equation are constructed, ensuring that each modification matches the equation solving requirements: {{$json.data}} The known target fluid mechanics control equation is "incompressible N-S equation (continuity + momentum)", and the processing example file is related to two-dimensional circular external flow (stt grid file and inp solver input file). Modify the parameters according to the following rules, and only return the modified complete file content, without adding explanations: 1..stt file modification (adapt to incompressible boundary layer solving requirements for flow around a cylinder): - Adjust "minimal_cellsize" under X_DIRECTION and Y_DIRECTION to 0.005m "maximal_cellsize" to 0.1m; - Increase "cornerpoint_number" of the cylinder surface grid cell by 20; - Keep the grid orthogonality parameter "orthogonality_ratio" unchanged; 2..inp file modification (match incompressible N-S equation solving logic): - Confirm "EQUATION_TYPE" field as "INCOMPRESSIBLE", add "ENERGY_EQUATION:OFF"; - Set "NUMERICAL_METHOD" field to "FINITE_VOLUME_SIMPLE"; - Configure "BOUNDARY_CONDITION" field: - Inlet boundary (INLET): "VELOCITY:1000"; - Outlet boundary (OUTLET): "PRESSURE:0"; - Cylinder surface (WALL): "NO_SLIP"; - Set "SOLVER_SETTING" field: - "ITERATION_STEPS:1500"; - "RESIDUAL_CRITERION:1e-6"; - "VISCOSITY:1.789e-5".

[0044] Among them, {{$json.data}} is a built-in command of the node, which is used to reference the transformed example text data in data to ensure that the prompt words are accurately associated with the file to be processed.

[0045] Data preprocessing and large language model LLM call: Add a "custom code node (function2)" to split the batch of case data into a single processing unit (such as the current processing of the "Cylinder_2D" case), and add a unique identifier: case_id:Cylinder_2D_Incompressible_20240520 and a control equation type label "equation_type:incompressible_NS" to facilitate the matching and traceability of subsequent solution results with equation types; The JSON.parse function parses the input string data, generates a structured data object, adds "caseId" and "equation_type" attributes and assigns values, and returns the processed object; The AI ​​agent node automatically combines the preprocessed example data with the above prompts and sends it to the target LLM interface via a POST request. An example request format is as follows: json { "model":"deepseek / deepseek-r1-0528-qwen3-8b", "messages":[ {"role":"system","content":"You are the expert in configuring parameters for the fluid dynamics control equations. You must strictly modify the example files according to the solution requirements of the incompressible Navier-Stokes equations to ensure that the parameters completely match the equation assumptions and physical scenarios."} {"role":"user","content":{"prompt":"[the above-mentioned specific prompt word]","file_data":"[the original text count of the Cylinder_2D.incompressible.stt and .inp files]"}} ], "timeout":60 } Results cleaning and data validation: Receive the response results returned by the Large Language Model (LLM). An example response is shown below: json [Item0{ "result":{ "stt_data":"[modified full.stt file content, minimal_cellsize=0.005m, cornerpoint_number increased by 20]", "inp_data":"[modified full.inp file content, ENERGY_EQUATION:OFF, ITERATION_STEPS=1500]" }, "note":"Parameters have been modified according to incompressible N-S equation requirements" ]] Adding "Custom Code Node (function3)" cleaning results: Text extraction: Extract "stt_data" and "inp_data" fields from structured data and assign them to temporary variables. Invalid information filtering: Match and remove explanatory text (such as "note" field content) using regular expressions (such as / ^note: / gm), and keep pure file data.

[0046] Fluid mechanics parameter verification: Check if the.inp file contains "ENERGY_EQUATION:OFF" and "EQUATION_TYPE:INCOMPRESSIBLE" to ensure compatibility with the incompressible N-S equation. Check if the.stt file "minimal_cellsize" is ≤ 0.005m and "cornerpoint_number" is increased as required to ensure that the grid parameters meet the equation discretization requirements. If the verification is passed, generate a standardized data stream; if not, return to the artificial intelligence agent for re-modification until it meets the control equation requirements.

[0047] (5) Example file format conversion and local saving Control equation adaptation format conversion: Add "ConverttoFile" node to receive the standardized data stream output by the artificial intelligence agent and convert it to the format required by the VirtualFlow software (core solver is transatmb) control equation solver: .stt file: Write modified grid parameters (such as "minimal_cellsize" and "cornerpoint_number") to "GRIDPROPERTIES", "X_DIRECTION", "Y_DIRECTION", and other specified modules.

[0048] .inp file: arrange numerical parameters and boundary conditions in the format of transatmb instruction, such as writing "BOUNDARY_CONDITION" module in the order of "boundary name-type-parameter" to avoid solver parsing errors.

[0049] Save by control equation classification: Add a "file write" node and configure the save path as "C:\Users\18274\OneDrive\Desktop\CFD_Case\Processed\Incompressible\Cylinder_Flow" set in step (1) above; Set the file naming rule: "case_id_equation type_modification time_file suffix", the generated file in this embodiment is: "Cylinder_2D_Incompressible_20240520_incompressible_NS.stt" and "Cylinder_2D_Incompressible_20240520_incompressible_NS.inp", ensure that the file is strongly associated with the control equation type and case ID, and avoid overwriting; The node automatically generates a save log to record the file save path, file name, modification information, and save time.

[0050] (6) Solver calling and solution verification of control equation Control equation specific environment variable configuration: Add a "command line execution" node (cmd1) to set the environment variables related to VirtualFlow software to ensure that the solver can recognize the solution dependency of the incompressible N-S equation: cmd setVIRTUALFLOW_HOME=D:\VirtualFlow\v3.0 Solver installation directory, which includes transatmbDP.exe (solver program) and VirtualFlowCmd.exe (command line calling program) setPATH=%PATH%;%VIRTUALFLOW_HOME%\bin Add the solver executable file directory to the system PATH to ensure that it can be called from any directory. Specialized solution instructions are built and executed: Add a "Command Line Execution" node (cmd2) to extract the full path of the modified.inp file from the saved log in step 5 ("C:\Users\18274\OneDrive\Desktop\CFD_Case\Processed\Incompressible\Cylinder_Flow\Cylinder_2D_Incompressible_20240520_incompressible_NS.inp") and construct the transatmb solver call instruction based on the incompressible N-S equation solving requirements: cmd "D:\VirtualFlow\v3.0\bin\VirtualFlowCmd.exe"^ -log"C:\Users\18274\OneDrive\Desktop\CFD_Case\Result\Incompressible\Cylinder_Flow\convergence.log"^ Output residual convergence log for subsequent verification -PArgs="-n2"^ Set the number of solver cores to 2 to adapt to the incompressible flow parallel computing requirements and balance efficiency and resource occupation -PFile"C:\Users\18274\OneDrive\Desktop\CFD_Case\Processed\Incompressible\Cylinder_Flow\Cylinder_2D_Incompressible_20240520_incompressible_NS.inp"^ input file path.

[0051] Solving verification and result processing: Node execution of the above instructions to start the transatmb solver and capture console output and log files in real time.

[0052] Add a "Custom Code Node (function4)" to write fluid mechanics solving verification logic: Residual extraction: extract residual data of continuity equation (Continuity) and x, y direction momentum equation (Momentum-X, Momentum-Y) from the log; Convergence criterion: when the residuals of the three equations are all ≤1e-6, and remain stable for 10 consecutive iterations, it is determined that the "solution is successful", and the output is "Solution converged successfully"; otherwise, go back to step four to reconfigure.

[0053] After the solution is successful, the result file is stored in "C:\Users\18274\OneDrive\Desktop\CFD_Case\Result\Incompressible\Cylinder_Flow" according to "control equation type + problem type", and the artificial intelligence agent generates "incompressible N-S equation example processing report", including parameter modification record, solution convergence curve, etc.

[0054] If there are batch example files, the "LoopOverItems" node repeats the above steps (3)-(6) in order of "case_id" until all incompressible flow example files are processed, realizing the closed loop of the whole process.

[0055] Please refer to Figure 2 An embodiment of the present application provides a whole-process data processing system for fluid mechanics control equations. The whole-process data processing system for fluid mechanics control equations comprises: An initialization module for initializing paths and artificial intelligence agents related to fluid mechanics control equation solving on a local server, so as to import and disassemble the parameter space of fluid mechanics problems; An example file processing module for identifying the control equation corresponding to the fluid mechanics problem and batch matching the example file through the artificial intelligence agent, and extracting the core parameters related to the control equation; A parameter configuration module for parameter configuration of the control equation through the artificial intelligence agent; A file conversion and saving module for converting the format of the example file and saving it locally to the corresponding path; A solving and verifying module for calling the solver of the control equation for solving processing, and verifying the results of the solving processing, so as to judge the effectiveness of the results.

[0056] The above embodiment has the beneficial effect that the whole-process data processing system for fluid mechanics control equations realizes the automatic whole-process link from problem parameter disassembly, control equation identification, special parameter configuration, format conversion, and solution verification by constructing a special link for fluid mechanics control equation solving, improves the example processing efficiency and solving accuracy.

[0057] In another embodiment, the initialization module is configured to initialize a path and an artificial intelligence agent related to solving a control equation of fluid mechanics on a local server, so as to import a parameter space of a fluid mechanics problem and decompose the parameter space, including: deploying an automatic workflow platform on the local server, the automatic workflow platform comprising an artificial intelligence agent and a connection parameter of the artificial intelligence agent and a large language model; initializing the path related to solving the control equation of fluid mechanics according to the automatic workflow platform, wherein the path matches a node of the automatic workflow platform; importing the parameter space of the fluid mechanics problem to be solved through the node of the automatic workflow platform, and decomposing the parameter space into a plurality of executable steps according to a preset knowledge graph of fluid mechanics by the artificial intelligence agent, wherein the plurality of executable steps comprise control equation selection, grid parameter configuration, boundary condition setting, and solution parameter definition.

[0058] In another embodiment, the case file processing module is configured to identify a control equation corresponding to a fluid mechanics problem by an artificial intelligence agent and batch match a case file, and extract core parameters related to the control equation, including: identifying a control equation type corresponding to the fluid mechanics problem by the artificial intelligence agent, batch matching a corresponding case file in a local case warehouse through a file screening node of the automatic workflow platform according to the control equation type, and extracting core parameters related to the control equation from the case file; The parameter configuration module is configured to configure parameters for the control equation by the artificial intelligence agent, including: automatically modifying the case file according to a solution requirement of the control equation by the artificial intelligence agent; adjusting grid parameters according to a gradient requirement of the control equation; and configuring numerical parameters according to the control equation type; The file conversion and saving module is configured to convert the case file to a format and save it to a corresponding path locally, including: converting the configured numerical parameters to a format supported by fluid mechanics solving software through a file processing node of the automatic workflow platform, and saving the converted numerical parameters to a corresponding path according to the control equation type.

[0059] In another embodiment, the grid parameters are adjusted according to the gradient requirement of the control equation, including: accessing the control equation type corresponding to the fluid mechanics problem by the artificial intelligence agent; analyzing a gradient source term corresponding to the control equation type according to the control equation type corresponding to the fluid mechanics problem, wherein the gradient source term refers to a physical quantity parameter term affecting the gradient change; Normalizing a physical quantity parameter item corresponding to a gradient source item of the control equation type to obtain a normalized physical quantity parameter item; Forming a gradient correlation vector corresponding to the control equation type by using the normalized physical quantity parameter item; Obtaining a gradient potential field Φ(x) by using the gradient correlation vector corresponding to the control equation type; wherein the gradient potential field Φ(x) is obtained by the following formula: Wherein Φ(x) represents the gradient potential field; S(x) represents the relative strength of the gradient source item, and S(x) =║X║2×(X0+║X║2) -1 , wherein║X║2 represents the L2 norm corresponding to the gradient correlation vector; X0 represents a reference value of the same dimension as the L2 norm corresponding to the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i represents the weight value corresponding to the ith vector element; X i represents the numerical value corresponding to the ith vector element; G(x) represents an intensification factor, wherein the intensification factor is used to enhance the grid configuration strength of the gradient vector in the key area, and the intensification factor G(x) is obtained by the following formula: Wherein α represents the intensification intensity coefficient, and the value range is 0.5-1.3; β represents the stability period number, and the value range is 1-1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; F0 represents the preset divergence reference value; Adjusting the current grid size by using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained by the following formula: Wherein Г represents the adjusted grid size, η represents the intensity adjustment coefficient, and the value is 0.7-1.5; Δ base represents the grid size before adjustment.

[0060] The beneficial effects of the above embodiments are that, through an intelligent pre-configuration method combining physical knowledge and mathematical models, an optimized grid highly consistent with specific flow physics and user requirements is generated at the beginning of calculation, thereby realizing a synergistic leap in efficiency, accuracy, and automation level at the source, breaking through the inherent limitations of traditional grid self-adaptive technology relying on solver feedback and artificial experience. At the same time, by identifying the type of control equation and analyzing the gradient source term through AI, the physical quantities affecting the gradient change (such as flow velocity gradient, pressure gradient, etc.) can be extracted specifically, avoiding the problem of insufficient adaptability of "universal grid" to different fluid problems, and making the grid adjustment more consistent with the physical nature of the specific problem. The L2 norm, divergence, and other indicators of the gradient correlation vector will significantly increase in the "key areas with dramatic changes in gradients"; at the same time, combined with the enhancement effect of the reinforcement factor, the gradient potential field will rise in these areas, ultimately reducing the grid size through the grid adjustment formula, improving the calculation resolution of key areas, and reducing numerical errors. At the same time, the grid parameters are directly mapped from the analytical formula, avoiding the repeated trial and error and global / local grid reconstruction operations based on error estimation or gradient threshold determination, significantly reducing the consumption of computing resources purely for grid adaptation process. Through mechanisms such as "gradient potential field" and "local clustering degree", the key areas with dramatic changes in physical quantities such as boundary layer, shock wave, shear layer, etc. can be identified and strengthened in advance without relying on any instantaneous solution, improving the resolution capability for complex flow phenomena.

[0061] In another embodiment, the solving and verifying module is configured to call a solver of the control equation to perform a solving process, and verify the result of the solving process to determine the validity of the result, including: Through the command line execution node of the automated workflow platform, a dedicated solving instruction is constructed according to the type of the control equation to call the solver of the control equation to perform the solving process; Through the artificial intelligence agent, the solving process log is monitored in real time, and the validity of the result of the solving process is determined according to the solving process log and the convergence characteristics of the control equation.

[0062] The fluid mechanics control equation-oriented full-process data processing system of the present application corresponds to the operation and effect of the above-mentioned fluid mechanics control equation-oriented full-process data processing method. Therefore, the fluid mechanics control equation-oriented full-process data processing system will not be repeated here.

[0063] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. The present disclosure is not limited to the precise construction described above and shown in the accompanying drawings and various modifications and changes can be effected therein by those skilled in the art without departing from the scope of the application. The scope of the present disclosure is limited only by the claims appended hereto. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A full-process data processing method for fluid dynamics control equations, characterized in that, include: Initialize the paths and AI agents related to the solution of fluid dynamics control equations on the local server to import and decompose the parameter space of the fluid dynamics problem. The AI ​​agent identifies the control equations and batch matching example files corresponding to the fluid mechanics problem, and extracts the core parameters related to the control equations. The AI ​​agent configures the parameters of the control equations; converts the format of the example file and saves it locally to the corresponding path; The solver of the governing equations is invoked to perform the solution process, and the results of the solution process are verified to determine the validity of the results.

2. The full-process data processing method for fluid dynamics control equations as described in claim 1, characterized in that: Initialize the paths and AI agents related to solving the fluid dynamics governing equations on the local server to import and decompose the parameter space of the fluid dynamics problem, including: Deploy an automated workflow platform on a local server, and integrate an artificial intelligence agent into the automated workflow platform and configure the connection parameters between the artificial intelligence agent and the large language model; Based on the automated workflow platform, initialize the path related to solving the fluid dynamics control equations; wherein the path matches the nodes of the automated workflow platform; The parameter space of the fluid mechanics problem to be solved is imported through the nodes of the automated workflow platform. The artificial intelligence agent decomposes the parameter space into several executable steps according to the preset fluid mechanics knowledge graph. The several executable steps include the selection of control equations, configuration of mesh parameters, setting of boundary conditions, and definition of solution parameters.

3. The full-process data processing method for fluid dynamics control equations as described in claim 2, characterized in that: The AI ​​agent identifies the governing equations and batch-matched example files corresponding to the fluid mechanics problem, and extracts the core parameters related to the governing equations, including: The AI ​​agent identifies the type of control equations corresponding to the fluid mechanics problem. Based on the type of control equations, the AI ​​workflow platform uses a file filtering node to batch match the corresponding case files in the local case repository and extracts the core parameters related to the control equations from the case files. The AI ​​agent configures the parameters of the control equations; the example file is converted to a different format and saved locally to the corresponding path, including: The AI ​​agent automatically modifies the example file according to the solution requirements of the control equations; adjusts the mesh parameters according to the gradient requirements of the control equations; and configures numerical parameters according to the type of control equation. The configured numerical parameters are converted into a format supported by the fluid dynamics solution software through the file processing node of the automated workflow platform, and saved to the corresponding path according to the type of the governing equation.

4. The full-process data processing method for fluid dynamics control equations as described in claim 3, characterized in that: Adjusting the mesh parameters according to the gradient requirements of the governing equations includes: Retrieve the type of control equations corresponding to the fluid mechanics problem identified by the artificial intelligence agent; Based on the type of governing equations corresponding to the fluid mechanics problem, the gradient source terms corresponding to the type of governing equations are analyzed, where the gradient source terms refer to the physical quantity parameter terms that affect the gradient change; Normalize the physical quantity parameter terms corresponding to the gradient source terms of the control equation type to obtain the normalized physical quantity parameter terms. The normalized physical quantity parameter terms are used to form a gradient correlation vector corresponding to the type of the governing equation; The gradient potential field Φ(x) is obtained using the gradient correlation vector corresponding to the type of the governing equation; wherein, the gradient potential field Φ(x) is obtained by the following formula: Where Φ(x) represents the gradient potential field; S(x) represents the relative intensity of the gradient source term, and S(x) = ║X║2×(X0+║X║2) -1 ║X║2 represents the L2 norm of the gradient correlation vector; X0 represents a reference value with the same dimensions as the L2 norm of the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i X represents the weight value corresponding to the i-th vector element; i Let G(x) represent the numerical value corresponding to the i-th vector element; G(x) represents the enhancement factor, which is used to enhance the grid configuration strength of the gradient vector in the key region, and the enhancement factor G(x) is obtained by the following formula: Where α represents the strengthening intensity coefficient, with a value ranging from 0.5 to 1.3; β represents the stability period, with a value ranging from 1 to 1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; and F0 represents the preset divergence reference value. The current mesh size is adjusted using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained using the following formula: Where Г represents the adjusted mesh size, η represents the strength adjustment coefficient, and its value ranges from 0.7 to 1.5; Δ base This indicates the grid size before adjustment.

5. The full-process data processing method for fluid dynamics control equations as described in claim 3, characterized in that: The solver of the governing equations is invoked for solution processing, and the results of the solution processing are verified to determine the validity of the results, including: Through the command line execution node of the automated workflow platform, a dedicated solution instruction is constructed according to the type of the control equation, thereby calling the control equation solver for solution processing; The AI ​​agent monitors the solution processing log in real time, and judges the validity of the solution processing result based on the solution processing log and the convergence characteristics of the control equation.

6. A full-process data processing system for fluid dynamics control equations, characterized in that, include: The initialization module is used to initialize the paths and artificial intelligence agents related to the solution of fluid dynamics control equations on the local server, thereby importing and decomposing the parameter space of fluid dynamics problems. The example file processing module is used to identify the control equations corresponding to the fluid mechanics problem and batch match example files through the artificial intelligence agent, and extract the core parameters related to the control equations; The parameter configuration module is used to configure the parameters of the control equations through the artificial intelligence agent; The file conversion and saving module is used to convert the format of the example file and save it locally to the corresponding path. The solution and verification module is used to call the solver of the governing equations to perform solution processing and verify the results of the solution processing to determine the validity of the results.

7. The full-process data processing system for fluid dynamics control equations as described in claim 6, characterized in that: The initialization module is used to initialize the paths and AI agents related to the solution of fluid dynamics control equations on the local server, thereby importing and decomposing the parameter space of the fluid dynamics problem, including: Deploy an automated workflow platform on a local server, and integrate an artificial intelligence agent into the automated workflow platform and configure the connection parameters between the artificial intelligence agent and the large language model; Based on the automated workflow platform, initialize the path related to solving the fluid dynamics control equations; wherein the path matches the nodes of the automated workflow platform; The parameter space of the fluid mechanics problem to be solved is imported through the nodes of the automated workflow platform. The artificial intelligence agent decomposes the parameter space into several executable steps according to the preset fluid mechanics knowledge graph. The several executable steps include the selection of control equations, configuration of mesh parameters, setting of boundary conditions, and definition of solution parameters.

8. The full-process data processing system for fluid dynamics control equations as described in claim 7, characterized in that: The example file processing module is used to identify the governing equations corresponding to the fluid mechanics problem and batch match example files through the artificial intelligence agent, and extract the core parameters related to the governing equations, including: The AI ​​agent identifies the type of control equations corresponding to the fluid mechanics problem. Based on the type of control equations, the AI ​​workflow platform uses a file filtering node to batch match the corresponding case files in the local case repository and extracts the core parameters related to the control equations from the case files. The parameter configuration module is used to configure the parameters of the control equations through the artificial intelligence agent, including: The AI ​​agent automatically modifies the example file according to the solution requirements of the control equations; adjusts the mesh parameters according to the gradient requirements of the control equations; and configures numerical parameters according to the type of control equation. The file conversion and saving module is used to convert the format of the example file and save it locally to the corresponding path, including: The configured numerical parameters are converted into a format supported by the fluid dynamics solution software through the file processing node of the automated workflow platform, and saved to the corresponding path according to the type of the governing equation.

9. The full-process data processing system for fluid dynamics control equations as described in claim 8, characterized in that: Adjusting the mesh parameters according to the gradient requirements of the governing equations includes: Retrieve the type of control equations corresponding to the fluid mechanics problem identified by the artificial intelligence agent; Based on the type of governing equations corresponding to the fluid mechanics problem, the gradient source terms corresponding to the type of governing equations are analyzed, where the gradient source terms refer to the physical quantity parameter terms that affect the gradient change; Normalize the physical quantity parameter terms corresponding to the gradient source terms of the control equation type to obtain the normalized physical quantity parameter terms. The normalized physical quantity parameter terms are used to form a gradient correlation vector corresponding to the type of the governing equation; The gradient potential field Φ(x) is obtained using the gradient correlation vector corresponding to the type of the governing equation; wherein, the gradient potential field Φ(x) is obtained by the following formula: Where Φ(x) represents the gradient potential field; S(x) represents the relative intensity of the gradient source term, and S(x) = ║X║2×(X0+║X║2) -1 ║X║2 represents the L2 norm of the gradient correlation vector; X0 represents a reference value with the same dimensions as the L2 norm of the gradient correlation vector; n represents the number of vector elements contained in the gradient correlation vector; λ i X represents the weight value corresponding to the i-th vector element; i Let G(x) represent the numerical value corresponding to the i-th vector element; G(x) represents the enhancement factor, which is used to enhance the grid configuration strength of the gradient vector in the key region, and the enhancement factor G(x) is obtained by the following formula: Where α represents the strengthening intensity coefficient, with a value ranging from 0.5 to 1.3; β represents the stability period, with a value ranging from 1 to 1.14; F(x) represents the divergence corresponding to the gradient correlation vector field; and F0 represents the preset divergence reference value. The current mesh size is adjusted using the gradient potential field Φ(x), and the adjusted gradient potential field Φ(x) is obtained using the following formula: Where Г represents the adjusted mesh size, η represents the strength adjustment coefficient, and its value ranges from 0.7 to 1.5; Δ base This indicates the grid size before adjustment.

10. The full-process data processing system for fluid dynamics control equations as described in claim 8, characterized in that: The solution and verification module is used to call the solver of the governing equations to perform solution processing and to verify the results of the solution processing, thereby determining the validity of the results, including: Through the command line execution node of the automated workflow platform, a dedicated solution instruction is constructed according to the type of the control equation, thereby calling the control equation solver for solution processing; The AI ​​agent monitors the solution processing log in real time, and judges the validity of the solution processing result based on the solution processing log and the convergence characteristics of the control equation.

Images