A three-dimensional flow field simulation method and system based on clean air conditioning

Abstract

The application provides a three-dimensional flow field simulation method and system based on a clean air conditioner, a grid historical database of an electronic workshop is constructed; an AI prediction model is trained according to the grid historical database, the AI prediction model is based on a random forest algorithm and superimposes a space attention mechanism; dynamic scene features of the electronic workshop are acquired, and the dynamic scene features are input into the trained AI prediction model, and high-risk area coordinates and partition grid parameters are output; then, a macroscopic layer, a mesoscopic layer and a microscopic layer of three-layer multi-scale grids are generated, data is coupled and transmitted by using an overlapping grid technology, and a grid is obtained; the grid is verified for independence, and a final grid file is output; specifically, grid resources are allocated on demand by AI learning and multi-scale technology, so that the contradiction between waste of computing power caused by too dense traditional grids and insufficient accuracy caused by too sparse traditional grids is solved, and the correlation between micro air flow and macro air flow can be captured.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of three-dimensional flow field simulation, and particularly relates to a three-dimensional flow field simulation method and system based on a clean air conditioner. BACKGROUND

[0002] In an electronic factory, a clean air conditioner is usually installed to create and maintain a specific clean environment.

[0003] Generally, computational fluid dynamics simulation, i.e., three-dimensional flow field simulation, is performed on the clean area of the electronic factory. On the one hand, the three-dimensional flow field simulation results can be imported into a clean room digital twin platform to realize real-time linkage between CFD (computational fluid dynamics) and digital twin. On the other hand, AR visualization construction and operation guidance can be performed.

[0004] However, the clean area of the electronic factory has very high requirements for the accuracy of CFD simulation. Traditional grid division relies on a general scene database, which lacks feature data such as the size of a photolithography machine, the layout of a FFU (fan filter unit), and a micro-vibration source, resulting in blind grid densification in high-risk areas (such as the periphery of a photolithography machine workbench), insufficient accuracy, or waste of computing power. SUMMARY

[0005] Therefore, the present application provides a three-dimensional flow field simulation method and system based on a clean air conditioner, which aims to solve the problem of waste of computing power caused by traditional grid over-densification and insufficient accuracy due to reliance on experience in the prior art.

[0006] The first aspect of the present application provides a three-dimensional flow field simulation method based on a clean air conditioner, which comprises:

[0007] constructing a grid history database of an electronic factory, wherein the grid history database contains scene features, grid schemes, and error feedback of three types of scenes, i.e., a photolithography machine workshop, a wafer packaging workshop, and a FFU dense area;

[0008] training an AI prediction model based on the grid history database, wherein the AI prediction model is based on a random forest algorithm and superimposes a spatial attention mechanism;

[0009] obtaining dynamic scene features of the electronic factory and inputting the dynamic scene features into the trained AI prediction model to output high-risk area coordinates and partition grid parameters;

[0010] generating three-layer multi-scale grids, i.e., a macroscopic layer, a mesoscopic layer, and a microscopic layer, based on the high-risk area coordinates, the partition grid parameters, and the accuracy requirements, coupling and transferring data using overlapping grid technology to obtain a grid, and the microscopic layer covers a photolithography machine workbench, HEPA fiber gaps, and wafer surfaces;

[0011] Independence verification is performed on the grid, and a final grid file is output.

[0012] Further, the scene features include the number of lithography machines, the size of the lithography machines, the number of FFUs, the spacing of the FFUs, the air volume of the FFUs, the coordinates of the vacuum pumps, the vibration frequency of the vacuum pumps, the width of the wafer transport track, the coordinates of the VOCs pollution sources, the release rate of the VOCs pollution sources, the length, width, and height of the clean area;

[0013] The grid scheme includes the coordinates of high-risk areas, partition grid parameters, and vibration source adaptive grid layer number;

[0014] The error feedback includes the deviation between the simulated and measured values of the air speed on the workbench of the lithography machine, the simulated error of the VOCs concentration, and the time-consuming of micro-vibration coupling calculation.

[0015] Further, the macroscopic layer is the entire clean room, and the grid is generated by ANSYSMeshing;

[0016] The mesoscopic layer is the 10m area around the lithography machine and the FFU array area, and the grid is generated by ICEMCFD;

[0017] The microscopic layer is the 0.1-0.5m area around the workbench of the lithography machine and the HEPA fiber gap, and the grid is generated by Palabos+LAMMPS.

[0018] Further, in the step of generating the macroscopic layer, the mesoscopic layer, and the microscopic layer three-layer multi-scale grid according to the coordinates of the high-risk area, the partition grid parameters, and the precision requirement, coupling and data transmission are performed using the overlapping grid technology, the adjacent two layers of grids are cross-overlapped at the boundary to form a data transition zone, and the width of the cross-overlapping area is the product of the prediction multiple and the size of the outer grid.

[0019] Further, in the step of generating the macroscopic layer, the mesoscopic layer, and the microscopic layer three-layer multi-scale grid according to the coordinates of the high-risk area, the partition grid parameters, and the precision requirement, coupling and data transmission are performed using the overlapping grid technology, the adjacent two layers of grids are cross-overlapped at the boundary to form a data transition zone, and the width of the cross-overlapping area is the product of the prediction multiple and the size of the outer grid.

[0020] Further, the step of obtaining the prediction multiple includes:

[0021] A multiple influence feature library is constructed, the multiple influence feature library includes physical field gradient features, geometric complexity features and error sensitive features, the physical field gradient features include wind speed gradient and vibration frequency, the geometric complexity features include boundary curvature and grid orthogonality, and the error sensitive features include historical simulation error and cleanliness level;

[0022] A multiple prediction model is constructed based on a random forest regression algorithm, the multiple prediction model is used for inputting physical field gradient features, geometric complexity features and error sensitive features, and outputting an initial prediction multiple, and an optimization target is that a simulation error corresponding to a model prediction multiple is less than a preset value, wherein a wind speed deviation is less than 2%, and a HEPA efficiency deviation is less than 0.5%;

[0023] Actual physical field gradient features, geometric complexity features and error sensitive features are acquired, are input into the trained multiple prediction model, and an initial prediction multiple is output, and the multiple is dynamically corrected by real-time monitoring of coupling precision to obtain the prediction multiple, specifically, real-time monitoring indexes are monitored, the indexes include a wind speed deviation, a HEPA efficiency deviation and a vibration transmission error, a first mapping relationship between an index exceeding a standard and a multiple adjustment strategy is established, and a second mapping relationship between all indexes not exceeding a standard and a multiple adjustment strategy is established, and corresponding multiple adjustment strategies are output according to real-time monitoring indexes, the first mapping relationship and the second mapping relationship, so that multiple correction is completed.

[0024] Further, on the basis of the grid historical database, a process timing dimension is newly added, and a timing prediction model is constructed, the timing prediction model generates corresponding grid plans for each process stage in advance by learning the correlation law between process timing and grid demand.

[0025] A second aspect of the embodiment of the present application provides a three-dimensional flow field simulation system based on a clean air conditioner, which is used for implementing the three-dimensional flow field simulation method based on the clean air conditioner, and the system comprises:

[0026] A construction module is configured to construct a grid historical database of an electronic factory, wherein the grid historical database includes scene features, grid schemes and error feedback of three types of scenes, i.e., a lithography machine workshop, a wafer packaging workshop and an FFU dense area.

[0027] A training module is configured to train an AI prediction model based on the grid historical database, wherein the AI prediction model is based on a random forest algorithm and superimposes a spatial attention mechanism.

[0028] An input module is configured to acquire dynamic scene features of the electronic factory, and input the dynamic scene features into the trained AI prediction model to output high-risk area coordinates and partition grid parameters.

[0029] A coupling module is configured to generate macroscopic, mesoscopic and microscopic multi-scale grids according to the high-risk area coordinates, the partition grid parameters and the precision requirement, couple and transfer data by using the overlapping grid technology, and obtain a grid, and the microscopic layer covers the photolithography machine workbench, the HEPA fiber gap and the wafer surface.

[0030] An adjustment module is configured to verify the independence of the grid and output a final grid file.

[0031] The third aspect of the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the three-dimensional flow field simulation method based on a clean air conditioner provided in the first aspect.

[0032] The fourth aspect of the embodiment of the present application provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the three-dimensional flow field simulation method based on a clean air conditioner provided in the first aspect when executing the program.

[0033] The three-dimensional flow field simulation method and system based on a clean air conditioner provided in the embodiment of the present application, by constructing a grid historical database of an electronic factory, the grid historical database comprises scene characteristics, grid schemes and error feedback of three types of scenes of a photolithography machine workshop, a wafer packaging workshop and a FFU dense area; according to the grid historical database, an AI prediction model is trained, the AI prediction model is based on a random forest algorithm and superimposes a spatial attention mechanism; dynamic scene characteristics of the electronic factory are acquired, and the dynamic scene characteristics are input into the trained AI prediction model, and high-risk area coordinates and partition grid parameters are output; according to the high-risk area coordinates, the partition grid parameters and the precision requirement, macroscopic, mesoscopic and microscopic multi-scale grids are generated, data is coupled and transferred by using the overlapping grid technology, and a grid is obtained, and the microscopic layer covers the photolithography machine workbench, the HEPA fiber gap and the wafer surface; the independence of the grid is verified, and a final grid file is output, specifically, by AI learning and multi-scale technology, grid resources are allocated on demand, the contradiction between waste of computing power caused by too dense traditional grids and insufficient precision caused by too sparse traditional grids is solved, and the correlation between microscopic air flow and macroscopic air flow is captured. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 An implementation flowchart of the three-dimensional flow field simulation method based on a clean air conditioner provided in the first aspect of the embodiment of the present application is provided.

[0035] Figure 2 A structural block diagram of the three-dimensional flow field simulation system based on a clean air conditioner provided in the third aspect of the embodiment of the present application is provided.

[0036] Figure 3A structural block diagram of an electronic device is provided for Embodiment Four of the present application. DETAILED DESCRIPTION

[0037] For the purpose of promoting an understanding of the principles of the application, reference will now be made to the embodiments illustrated in the drawings. There is shown in the drawings several embodiments of the application. However, it should be understood that the application can be practiced in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It is therefore an object of the present application to provide a novel and improved method and apparatus for providing a three-dimensional flow field simulation.

[0038] It is to be understood that where an element is referred to as being "on" another element, it can be directly on the other element or intervening elements can also be present. Where an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements can also be present. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0040] Embodiment One

[0041] According to the embodiments of the present application, a three-dimensional flow field simulation method based on clean air conditioning is provided. It is to be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] The embodiment I provides a three-dimensional flow field simulation method based on a clean air conditioner, which can be used in electronic equipment such as a computer. In order to realize the simulation of the three-dimensional flow field, the overall steps are as follows: firstly, geometric modeling is performed, and a physical space is converted into a dynamic digital skeleton; then, mesh division is performed, and the digital skeleton is allocated with accurate calculation resources; a physical model is constructed, and the digital skeleton is injected with actual operation rules; boundary conditions are determined, and dynamic optimization iteration based on rules is solved; and finally, the iteration results are applied to the physical space, and the deviation of the digital space is corrected in reverse, so that the final simulation result is obtained. However, in the step of mesh division in the above process, the mesh encryption is often dependent on experience, and the traditional mesh encryption adopts fixed size for encryption. For example, for the area with large air flow gradient of the clean air conditioner, the mesh size is reduced to 1 / 3-1 / 5 of that of the conventional area, so that the waste of calculation power is caused.

[0043] Therefore, refer to Figure 1 , Figure 1 The embodiment I provides an implementation flowchart of the three-dimensional flow field simulation method based on the clean air conditioner, and specifically includes steps S01 to S05.

[0044] In step S01, a mesh history database of an electronic factory is constructed, and the mesh history database includes scene characteristics, mesh schemes and error feedback of three types of scenes of a photolithography machine workshop, a wafer packaging workshop and an FFU dense area.

[0045] Specifically, a plurality of groups of mesh data of clean areas of electronic factories are collected, covering three types of scenes, that is, a photolithography machine workshop scene, a wafer packaging workshop scene and an FFU dense area scene. For example, the photolithography machine workshop scene includes single / multiple photolithography machine layouts and wafer handling robot tracks; the wafer packaging workshop scene includes multi-station packaging equipment and local VOCs (volatile organic compounds) pollution sources; and the FFU dense area scene includes an ultra-clean area with more than 60 FFUs per square meter, such as a photoresist coating area. 2

[0046] Through each group of mesh data, scene characteristics, mesh schemes and error feedback are extracted. The scene characteristics include the number of photolithography machines, the size of photolithography machines, the number of FFUs, the spacing of FFUs, the air volume of FFUs, the coordinates of vacuum pumps, the vibration frequency of vacuum pumps, the width of wafer handling tracks, the coordinates of VOCs pollution sources, the release rate of VOCs pollution sources, the length, width and height of the clean area;

[0047] The mesh scheme includes the coordinates of high-risk areas, the partition mesh parameters and the vibration source adaptive mesh layer number;

[0048] ​The error feedback comprises a deviation between a simulated value and a measured value of a lithography machine workbench surface wind speed, a simulated error of VOCs concentration, and a micro-vibration coupling calculation time consumption.

[0049] In step S02, an AI prediction model is trained according to the grid history database, and the AI prediction model is based on a random forest algorithm and superimposes a spatial attention mechanism.

[0050] In the embodiment of the present application, the AI prediction model is built by using the PyTorch framework, the spatial feature weight of the equipment surrounding the electronic factory and the FFU area is set to 2 times that of the conventional area, and in addition, the input and output variables of the AI prediction model are defined.

[0051] It can be understood that the input variables are the number of lithography machines, the size of the lithography machine, the number of FFUs, the spacing of the FFUs, the air volume of the FFUs, the coordinates of the vacuum pumps, the vibration frequency of the vacuum pumps, the width of the wafer handling track, the coordinates of the VOCs pollution source, the release rate of the VOCs pollution source, the length, width and height of the clean area, and the output variables are the coordinates of the high-risk area, the partition grid parameters and the vibration source adaptive grid layer number.

[0052] For example, the high-risk area coordinates can include the 0.5-1m surrounding the lithography machine workbench, the FFU airflow intersection angle area, and the 1m range of the vacuum pump; the partition grid parameters are 5-10mm around the lithography machine, 20-30mm in the FFU area, 8mm around the vacuum pump, and 50-80mm in the conventional area; and the vibration source adaptive grid layer number is 8-12 layers around the vacuum pump.

[0053] In step S03, the dynamic scene features of the electronic factory are obtained, and the dynamic scene features are input into the trained AI prediction model to output the coordinates of the high-risk area and the partition grid parameters.

[0054] In the embodiment of the present application, the real-time position of the lithography machine and the running state of the FFU are obtained from the MES system of the electronic factory, the CAD drawing of the clean area is obtained from the geometric model, and the drawing is parsed and the scene features are extracted by using Python+OpenCV. The obtained scene features are input into the trained AI prediction model to output the coordinates of the high-risk area and the partition grid parameters, and the grid tool is selected based on the partition grid parameters.

[0055] It should be noted that the surrounding of the lithography machine is generated by ICECFD to generate unstructured tetrahedral mesh; the FFU area is generated by ANSYS Meshing to generate structured hexahedral mesh; and the vacuum pump vibration area is generated by ANSYS Meshing to generate prismatic layer mesh.

[0056] Step S04, according to the high-risk area coordinates, the partition grid parameters and the accuracy requirement, a three-layer multi-scale grid of macroscopic layer, mesoscopic layer and microscopic layer is generated, and the data is coupled and transmitted by using the overlapping grid technology to obtain a grid, and the microscopic layer covers the photolithography machine workbench, HEPA fiber gap and wafer surface.

[0057] Firstly, the macroscopic layer, mesoscopic layer and microscopic layer in the electronic factory are defined, the macroscopic layer is the whole clean workshop, and the structured grid is generated by using ANSYS MESHING;

[0058] The mesoscopic layer is the photolithography machine periphery 10m and the FFU array area, and the grid is generated by using ICEM CFD;

[0059] The microscopic layer is the photolithography machine workbench 0.1-0.5m and HEPA (High Efficiency Particulate Air Filter) fiber gap, and the grid is generated by using Palabos+LAMMPS, wherein the LBM grid is generated by using Palabos, the molecular dynamics grid is generated by using LAMMPS, and the wafer surface is provided with a slip boundary.

[0060] After the macroscopic layer, mesoscopic layer and microscopic layer are defined, according to the output of the previous AI prediction model, the corresponding grid is formed in the macroscopic layer, mesoscopic layer and microscopic layer, further, the data is coupled and transmitted by using the overlapping grid technology, specifically, the adjacent two layers of grids are cross-overlapped at the boundary to form a data transition zone, wherein the width of the cross-overlapping area is the product of the prediction multiple and the outer grid size.

[0061] It should be noted that the step of obtaining the prediction multiple comprises:

[0062] A multiple influence feature library is constructed, the multiple influence feature library comprises physical field gradient features, geometric complexity features and error sensitivity features, the physical field gradient features comprise wind speed gradient and vibration frequency, the geometric complexity features comprise boundary curvature and grid orthogonality, and the error sensitivity features comprise historical simulation error and cleanliness level, specifically, the vibration frequency refers to the vibration frequency of the vacuum pump / photolithography machine, the boundary curvature refers to the surface curvature radius of the equipment, the grid orthogonality refers to the grid twist degree at the boundary, the historical simulation error refers to the past wind speed deviation of the region, and the cleanliness level refers to ISO Class 3 / 5 / 6.

[0063] Based on the random forest regression algorithm, a multiple prediction model is constructed, the multiple prediction model is used to input physical field gradient features, geometric complexity features and error sensitive features, and output the initial prediction multiple, that is, the overlap multiple, and the optimization target is that the simulation error corresponding to the model prediction multiple is less than the preset value, wherein the wind speed deviation is less than 2%, and the HEPA efficiency deviation is less than 0.5%, in the embodiment of the present application, Python+Scikit-learn is adopted, the number of decision trees (100) is adjusted through 5-fold cross-validation, and the prediction accuracy is ensured to be greater than or equal to 92%;

[0064] The actual physical field gradient features, geometric complexity features and error sensitive features are obtained, input into the trained multiple prediction model, and the initial prediction multiple is output, and the coupling accuracy is monitored in real time, and the multiple is dynamically corrected to obtain the prediction multiple, specifically, real-time monitoring indexes are monitored, the indexes include wind speed deviation, HEPA efficiency deviation and vibration transmission error, a first mapping relationship between index exceeding and multiple adjustment strategy is established, and a second mapping relationship between all indexes not exceeding and multiple adjustment strategy is established, and according to the real-time monitoring indexes, the first mapping relationship and the second mapping relationship, the corresponding multiple adjustment strategy is output to complete the multiple correction.

[0065] For example, when the wind speed deviation is greater than 2%, the multiple adjustment strategy is multiple = current multiple x 1.2; when the HEPA efficiency deviation is greater than 0.5%, the multiple adjustment strategy is multiple = current multiple x 1.1; when the vibration transmission error is greater than 5%, the multiple adjustment strategy is multiple = current multiple x 1.3 (upper limit 5 times); when all indexes are less than the threshold value, and the multiple is greater than 2 times, the multiple adjustment strategy is multiple = current multiple x 0.9, it can be understood that the adjusted multiple should not exceed the preset upper and lower limits.

[0066] More specifically, the data transmission in the three-layer multi-scale grid is a bidirectional feedback, wherein the macroscopic layer transmits the main air pipe wind speed and the FFU inlet pressure to the mesoscopic layer, the mesoscopic layer transmits the lithography machine peripheral airflow velocity and the vacuum pump vibration frequency to the microscopic layer, and the microscopic layer transmits the wafer surface particle concentration and the HEPA interception efficiency to the mesoscopic layer.

[0067] It can be understood that the mesoscopic layer needs to calculate the FFU outlet velocity and the device peripheral airflow, and must know the input conditions of the FFU first, that is, the macroscopic layer transmits the main air pipe wind speed and the FFU inlet pressure to the mesoscopic layer; the microscopic layer needs to calculate the wafer surface micro airflow, and needs to obtain the lithography machine peripheral airflow velocity, which is the basic airflow of the wafer surface, and the vacuum pump vibration will disturb this airflow, so the vacuum pump vibration frequency is taken into account; since the mesoscopic layer needs to verify the overall cleanliness of the device periphery, the wafer surface particle concentration is the final index of whether the cleanliness meets the standard, and the HEPA interception efficiency determines the overall particle removal rate of the mesoscopic layer.

[0068] Furthermore, to verify the coupling effect and ensure that the inter-layer wind speed deviation is <2% and the simulated-measured deviation of HEPA interception efficiency is <0.5%, it is understandable that the cleanliness and thermal environment of electronic factories depend on airflow distribution. If the inter-layer wind speed transmission is inaccurate, all subsequent simulations will be distorted. HEPA is the cleanliness defense line of electronic factories. To achieve ISO Class 5, electronic factories rely on the interception efficiency of HEPA for 0.1-0.3μm particles (≥99.999%). If the interception efficiency simulation is inaccurate, the particle concentration calculation for the entire workshop will be wrong.

[0069] Step S05: Perform independence verification on the mesh and output the final mesh file.

[0070] Specifically, based on the current grid, three sets of fused grids with different densities are generated. The wind speed error between two adjacent grids is verified to be <2% and the particle concentration error is <1%. The grid with the middle density is selected as the final grid.

[0071] In summary, the three-dimensional flow field simulation method based on cleanroom air conditioning in the above embodiments of the present invention constructs a grid history database of an electronic factory, which includes scene features, grid schemes, and error feedback for three types of scenarios: lithography machine workshop, wafer packaging workshop, and FFU dense area. Based on the grid history database, an AI prediction model is trained, which is based on a random forest algorithm with a spatial attention mechanism. Dynamic scene features of the electronic factory are acquired and input into the trained AI prediction model, outputting high-risk area coordinates and partitioned grid parameters. Based on the high-risk area coordinates, the partitioned grid parameters, and accuracy requirements, a three-layer multi-scale grid (macro, meso, and micro) is generated. Overlapping grid technology is used to couple and transfer data to obtain the grid. The micro layer covers the lithography machine worktable, HEPA fiber gaps, and wafer surface. The grid is then validated for independence, and the final grid file is output. Specifically, through AI learning and multi-scale technology, grid resources are allocated on demand, resolving the contradiction between excessively dense grids wasting computing power and excessively sparse grids lacking accuracy, while also capturing the correlation between micro and macro airflow.

[0072] Example 2

[0073] Embodiment 2 of the present invention also provides a three-dimensional flow field simulation method based on cleanroom air conditioning. The difference from Embodiment 1 of the present invention is that, based on the grid historical database, a process sequence dimension is added, and a timing prediction model is constructed. The timing prediction model learns the correlation between process sequence and grid requirements, and generates corresponding grid plans in advance for each process stage. It is understood that the processes in electronic factories have a clear sequence. For example, in the photolithography process: wafer loading → coating → exposure → development → inspection, the pollution sources, airflow requirements, and equipment status are different in each stage. The solution in Embodiment 2 of the present invention can avoid simulation interruptions caused by temporary grid adjustments during process switching.

[0074] Specifically, based on existing historical data, complete timing data of the photolithography / packaging process is collected, and key parameters of each stage are marked. For example, in the coating stage, the photoresist solvent evaporation rate and coating machine rotation speed are included, and the corresponding grid in the 0.3m area around the coating machine needs to be densified.

[0075] Furthermore, based on the original random forest and spatial attention mechanisms, an LSTM time series prediction module is superimposed. The current process stage and remaining time are input. For example, in the glue application stage, there are 5 minutes left. The output is the high-risk area change and grid adjustment plan for the next stage. In addition, the process execution module of the electronic factory MES system is connected through the OPCUA protocol to obtain the current process progress in real time. The AI ​​prediction model with the LSTM time series prediction module updates the grid plan every 30 seconds. When the process is switched, the pre-generated grid parameters are directly called.

[0076] Furthermore, when the AI ​​prediction model predicts the grid plan for the next process stage, it directly triggers the adjustment of the multi-scale meso-level elastic grid. Specifically, the grid around the meso-level equipment (such as a 10m range around the lithography machine) is defined as an elastic cell. The grid nodes can move with the change of equipment position. Understandably, when the wafer handling robot moves, the corresponding grid nodes change accordingly. It should be noted that when the wafer handling robot approaches the preset area (such as 1m away from the FFU), the elastic cells are automatically densified; when the wafer handling robot moves away, the elastic cells are automatically sparsed to avoid wasting computing power.

[0077] Meanwhile, as the elastic grid cells move, the interlayer overlap area automatically adjusts its size. For example, when the robot moves from point A to point B, the meso-layer elastic grid moves with the wafer handling robot, and the overlap area between the macro-layer and the meso-layer automatically expands from 30mm to 40mm (ensuring uninterrupted data transmission). The micro-layer (the area around the wafer carried by the wafer handling robot) grid moves synchronously with the meso-layer.

[0078] Example 3

[0079] Please see Figure 2 ,Figure 2 This is a structural block diagram of a three-dimensional flow field simulation system based on cleanroom air conditioning, provided in Embodiment 3 of the present invention. This three-dimensional flow field simulation system 200 based on cleanroom air conditioning is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0080] Specifically, the three-dimensional flow field simulation system 200 based on cleanroom air conditioning includes: a construction module 21, a training module 22, an input module 23, a coupling module 24, and an adjustment module 25, wherein:

[0081] Module 21 is used to build a grid history database for electronic factories. The grid history database includes scene characteristics, grid schemes, and error feedback for three types of scenarios: lithography machine workshop, wafer packaging workshop, and FFU dense area. The scene characteristics include the number of lithography machines, lithography machine size, number of FFUs, FFU spacing, FFU air volume, vacuum pump coordinates, vacuum pump vibration frequency, wafer handling track width, VOCs pollution source coordinates, VOCs pollution source release rate, clean area length, width, and floor height.

[0082] The grid scheme includes the coordinates of high-risk areas, partitioned grid parameters, and the number of grid layers adapted to the vibration source.

[0083] The error feedback includes the deviation between the simulated and measured wind speed on the lithography machine table, the simulation error of VOCs concentration, and the calculation time for micro-vibration coupling.

[0084] Training module 22 is used to train an AI prediction model based on the grid historical database. The AI ​​prediction model is based on the random forest algorithm with spatial attention mechanism.

[0085] Input module 23 is used to acquire dynamic scene features of the electronic factory, input the dynamic scene features into the trained AI prediction model, and output the coordinates of high-risk areas and partition grid parameters.

[0086] The coupling module 24 is used to generate a three-layer multi-scale mesh of macroscopic, mesoscopic and microscopic layers according to the coordinates of the high-risk area, the partition mesh parameters and the accuracy requirements. The overlapping mesh technology is used to couple and transfer data to obtain the mesh. The microscopic layer covers the lithography machine table surface, HEPA fiber gaps and wafer surface. The macroscopic layer is the entire clean room and the mesh is generated using ANSYS Meshing.

[0087] The meso-layer consists of the 10m perimeter of the lithography machine and the FFU array area, with the mesh generated using ICEMCFD.

[0088] The microlayer consists of the 0.1-0.5m gap between the lithography machine stage and HEPA fibers, and the mesh is generated using Palabos+LAMMPS.

[0089] Adjacent mesh layers are overlapped at the boundary to form a data transition region. The width of the overlapped region is the product of the prediction factor and the size of the outer mesh layer. Specifically, the steps for obtaining the prediction factor include:

[0090] A feature library for the impact of multiples is constructed. The feature library includes physical field gradient features, geometric complexity features, and error-sensitive features. The physical field gradient features include wind speed gradient and vibration frequency. The geometric complexity features include boundary curvature and mesh orthogonality. The error-sensitive features include historical simulation errors and cleanliness level.

[0091] A multiple prediction model is constructed based on the random forest regression algorithm. The multiple prediction model is used to input the physical field gradient characteristics, geometric complexity characteristics, and error sensitivity characteristics, and outputs an initial prediction multiple. The optimization objective is to make the simulation error corresponding to the model prediction multiple less than a preset value, wherein the wind speed deviation is less than 2% and the HEPA efficiency deviation is less than 0.5%.

[0092] The actual physical field gradient characteristics, geometric complexity characteristics, and error sensitivity characteristics are obtained and input into the trained multiple prediction model. The initial prediction multiple is output, and the multiple is dynamically corrected by real-time monitoring of coupling accuracy to obtain the predicted multiple. Specifically, real-time monitoring indicators include wind speed deviation, HEPA efficiency deviation, and vibration transmission error. A first mapping relationship between the condition of indicators exceeding the standard and the multiple adjustment strategy, and a second mapping relationship between the condition of indicators not exceeding the standard and the multiple adjustment strategy are established. Based on the real-time monitoring indicators, the first mapping relationship, and the second mapping relationship, the corresponding multiple adjustment strategy is output to complete the multiple correction.

[0093] Data transmission in the three-layer multi-scale grid is bidirectional feedback. The macro layer transmits the main duct wind speed and FFU inlet pressure to the meso layer, the meso layer transmits the airflow velocity around the lithography machine and the vacuum pump vibration frequency to the micro layer, and the micro layer transmits the wafer surface particle concentration and HEPA interception efficiency to the meso layer.

[0094] Adjustment module 25 is used to perform independence verification on the mesh and output the final mesh file.

[0095] Furthermore, in some optional embodiments of the present invention, the construction module 21 adds a process timing dimension to the grid historical database and constructs a timing prediction model. The timing prediction model learns the correlation between process timing and grid requirements and generates corresponding grid plans for each process stage in advance.

[0096] Example 4

[0097] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 3 The image shows an electronic device according to Embodiment 4 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the three-dimensional flow field simulation method based on cleanroom air conditioning as described above.

[0098] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0099] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0100] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0101] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the three-dimensional flow field simulation method based on cleanroom air conditioning as described above.

[0102] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0103] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0104] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0105] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0106] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A three-dimensional flow field simulation method based on cleanroom air conditioning, characterized in that, The method includes: Construct a grid history database for electronic manufacturing plants. The grid history database includes scene characteristics, grid schemes, and error feedback for three types of scenarios: lithography machine workshop, wafer packaging workshop, and FFU dense area. Based on the grid historical database, an AI prediction model is trained, which is based on the random forest algorithm with spatial attention mechanism; The dynamic scene features of the electronic factory are obtained and input into the trained AI prediction model to output the coordinates of the high-risk area and the partition grid parameters. Based on the coordinates of the high-risk area, the partitioned grid parameters, and the accuracy requirements, a three-layer multi-scale grid of macroscopic, mesoscopic, and microscopic layers is generated. Overlapping grid technology is used to couple and transfer data to obtain the grid. The microscopic layer covers the lithography machine table surface, HEPA fiber gaps, and wafer surface. The independence of the mesh is verified, and the final mesh file is output. The macroscopic layer refers to the entire cleanroom, and the mesh is generated using ANSYS Meshing. The meso-layer consists of the 10m perimeter of the lithography machine and the FFU array area, with the mesh generated using ICEMCFD. The microlayer consists of the 0.1-0.5m gap between the lithography machine stage and the HEPA fiber, and the mesh is generated using Palabos+LAMMPS.

2. The three-dimensional flow field simulation method based on cleanroom air conditioning according to claim 1, characterized in that, The scene features include the number of lithography machines, the size of the lithography machines, the number of FFUs, the spacing between FFUs, the air volume of FFUs, the coordinates of the vacuum pumps, the vibration frequency of the vacuum pumps, the width of the wafer transport track, the coordinates of the VOCs pollution sources, the release rate of the VOCs pollution sources, the length and width of the clean area, and the floor height. The grid scheme includes the coordinates of high-risk areas, partitioned grid parameters, and the number of grid layers adapted to the vibration source. The error feedback includes the deviation between the simulated and measured wind speed on the lithography machine's worktable, the simulation error of VOCs concentration, and the time consumed in micro-vibration coupling calculation.

3. The three-dimensional flow field simulation method based on cleanroom air conditioning according to claim 2, characterized in that, In the step of generating a three-layer multi-scale grid (macro, meso, and micro) based on the coordinates of the high-risk area, the partitioned grid parameters, and accuracy requirements, and coupling and transmitting data using overlapping grid technology to obtain the grid, adjacent grid layers are intersected at the boundary to form a data transition zone. The width of the intersecting region is the product of the prediction multiple and the size of the outer grid.

4. The three-dimensional flow field simulation method based on cleanroom air conditioning according to claim 3, characterized in that, In the step of generating a three-layer multi-scale grid (macro, meso, and micro) based on the coordinates of the high-risk area, the partitioned grid parameters, and accuracy requirements, and coupling and transmitting data using overlapping grid technology to obtain the grid, the data transmission in the three-layer multi-scale grid is bidirectional feedback. Specifically, the macro layer transmits the main duct wind speed and FFU inlet pressure to the meso layer, the meso layer transmits the airflow velocity around the lithography machine and the vacuum pump vibration frequency to the micro layer, and the micro layer transmits the wafer surface particle concentration and HEPA interception efficiency to the meso layer.

5. The three-dimensional flow field simulation method based on cleanroom air conditioning according to claim 4, characterized in that, The steps for obtaining the predicted multiple include: A feature library for the impact of multiples is constructed. The feature library includes physical field gradient features, geometric complexity features, and error-sensitive features. The physical field gradient features include wind speed gradient and vibration frequency. The geometric complexity features include boundary curvature and mesh orthogonality. The error-sensitive features include historical simulation errors and cleanliness level. A multiple prediction model is constructed based on the random forest regression algorithm. The multiple prediction model is used to input the physical field gradient characteristics, geometric complexity characteristics, and error sensitivity characteristics, and outputs an initial prediction multiple. The optimization objective is to make the simulation error corresponding to the model prediction multiple less than a preset value, wherein the wind speed deviation is less than 2% and the HEPA efficiency deviation is less than 0.5%. The actual physical field gradient characteristics, geometric complexity characteristics, and error sensitivity characteristics are obtained and input into the trained multiple prediction model. The initial prediction multiple is output, and the multiple is dynamically corrected by real-time monitoring of coupling accuracy to obtain the predicted multiple. Specifically, real-time monitoring indicators include wind speed deviation, HEPA efficiency deviation, and vibration transmission error. A first mapping relationship is established between the condition of indicators exceeding the standard and the multiple adjustment strategy, and a second mapping relationship is established between the condition of indicators not exceeding the standard and the multiple adjustment strategy. Based on the real-time monitoring indicators, the first mapping relationship, and the second mapping relationship, the corresponding multiple adjustment strategy is output to complete the multiple correction.

6. The three-dimensional flow field simulation method based on cleanroom air conditioning according to claim 5, characterized in that, Based on the historical grid database, a new process timing dimension is added, and a timing prediction model is constructed. The timing prediction model learns the correlation between process timing and grid requirements, and generates corresponding grid plans in advance for each process stage.

7. A three-dimensional flow field simulation system based on cleanroom air conditioning, characterized in that, For implementing the three-dimensional flow field simulation method based on cleanroom air conditioning as described in any one of claims 1-6, the system comprises: The construction module is used to build a grid history database for electronic factories. The grid history database includes scene characteristics, grid schemes, and error feedback for three types of scenarios: lithography machine workshop, wafer packaging workshop, and FFU dense area. The training module is used to train an AI prediction model based on the grid historical database. The AI ​​prediction model is based on a random forest algorithm with a spatial attention mechanism. The input module is used to acquire the dynamic scene features of the electronic factory and input the dynamic scene features into the trained AI prediction model, and output the coordinates of the high-risk area and the partition grid parameters. The coupling module is used to generate a three-layer multi-scale mesh of macroscopic, mesoscopic and microscopic layers according to the coordinates of the high-risk area, the partition mesh parameters and the accuracy requirements. The overlapping mesh technology is used to couple and transmit data to obtain the mesh. The microscopic layer covers the lithography machine table surface, HEPA fiber gaps and wafer surface. The adjustment module is used to perform independence verification on the mesh and output the final mesh file.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the three-dimensional flow field simulation method based on cleanroom air conditioning as described in any one of claims 1-6.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the three-dimensional flow field simulation method based on cleanroom air conditioning as described in any one of claims 1-6.

Images