Physical wind tunnel pressure measurement test optimization method based on CFD-AI and storage medium

Abstract

The invention discloses a physical wind tunnel pressure measurement test optimization method based on CFD-AI and a storage medium. The method comprises the following steps: completing wind load measurement point arrangement after segmentation based on a parameterized modeling platform, and completing curved surface partitioning; establishing a CFD numerical wind tunnel calculation model, performing CFD full wind direction angle calculation, and extracting building surface measuring point wind pressure and local shape coefficients corresponding to all wind direction angles; in combination with the local shape coefficient and the three-dimensional building model, performing machine learning clustering analysis on the measuring points to form an optimized measuring point arrangement scheme; curved surface partitions are updated based on an optimized measuring point arrangement scheme and a Thiessen polygon, and a physical wind tunnel test is carried out; and integrating wind load analysis results of the physical wind tunnel and the CFD numerical wind tunnel, marking a wind pressure hyper-standard region, and calculating and outputting an overall shape coefficient in combination with a curved surface partition area and a local shape coefficient. The objective of the invention is to improve the problems of high pressure test cost, too long test data processing time and incapability of achieving engineering practical application of test efficiency and data accuracy in a physical wind tunnel test.

Description

Technical Field

[0001] The present invention belongs to the technical field of composite application of structural wind engineering and CFD technology, and specifically relates to a physical wind tunnel pressure test optimization method and storage medium based on CFD-AI. Background Art

[0002] Physical wind tunnel testing is an important means of evaluating the wind resistance safety performance of buildings under wind loads. By simulating the actual wind field environment, aerodynamic tests are performed on building models to obtain wind pressure distribution data on their surfaces.

[0003] Traditional physical wind tunnel tests often rely on engineers' experience or simple uniform layout strategies in the arrangement of wind pressure measurement points. This method has several significant limitations: 1) Low test efficiency. Too many measurement points will increase the workload of data collection and processing and extend the test cycle; while too few measurement points may miss important information and affect the accuracy of the test results. 2) High cost. Unreasonable measurement point arrangement will increase the equipment and labor costs of wind tunnel tests, especially in the test of large or complex building models, this cost issue is particularly prominent.

[0004] At present, computational fluid dynamics (CFD) simulation has been widely used in architectural wind tunnel simulation, but its application in combination with physical wind tunnel is relatively rare. The general computational fluid dynamics (CFD) measurement point arrangement scheme covers a large number of measurement points, which cannot solve the problem of the limited number of measurement points in the physical wind tunnel, resulting in the inability of physical wind tunnels to adopt CFD analysis schemes. How to effectively combine CFD technology with physical wind tunnels to enhance the accuracy and efficiency of measurement points in physical wind tunnel tests has become a new challenge that needs to be solved. Summary of the invention

[0005] The technical problem to be solved by this application is to provide a physical wind tunnel pressure test optimization method and storage medium based on CFD-AI, aiming to improve the problems of high pressure test cost, long test data processing time, and test efficiency and data accuracy that cannot meet actual engineering applications in physical wind tunnel tests.

[0006] Furthermore, the present invention aims to solve the problem that the measurement point arrangement scheme of computational fluid dynamics (CFD) covers a large number of measurement points, but cannot solve the problem that the number of measurement points arranged in a physical wind tunnel is limited.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: A physical wind tunnel pressure test optimization method based on CFD-AI, characterized by comprising the following steps: S1. Import the complex building model into the NURBS surface modeling software, complete the repair and adjustment of the building model, complete the arrangement of wind load measurement points after segmentation based on the parametric modeling platform, and complete the surface partition based on the Thiessen polygon; The CFD numerical wind tunnel calculation model is established based on the arrangement of wind load measurement points and surface partitions after segmentation. Based on the CFD numerical wind tunnel calculation model, the CFD full wind direction angle calculation is performed to obtain the CFD numerical wind tunnel results. S2. Extract the wind pressure at the building surface measurement points corresponding to all wind direction angles from the CFD numerical wind tunnel results, and convert the wind pressure at the building surface measurement points into local body coefficients; S3. Combine the local body coefficient with the three-dimensional building model to establish a data matrix of measuring points that includes the body coefficients of measuring points and the spatial geometry of measuring points for multiple wind direction angles. Based on the wind pressure results of a certain wind direction angle, different weights are assigned to the spatial coordinates, curvature, normal vector and wind pressure in the measuring point data matrix of the target building, and the weighted Euclidean distance between the two measuring points is calculated using the assigned weights: machine learning clustering analysis is performed on the weighted Euclidean distance of the measuring points, and after clustering at a single wind direction angle, a sparse measuring point matrix is ​​constructed based on the principle that the wind pressure extreme value area is dense and the non-extreme value is sparse. The sparse measuring point matrix of all wind direction angles is obtained by integrating each wind direction angle, forming an optimized measuring point layout plan that fully reflects the characteristics of extreme wind pressure. Update the surface partition based on the optimized measurement point arrangement and Thiessen polygons, and input them into the physical wind tunnel to carry out physical wind tunnel tests; S4. After completing the physical wind tunnel test, the body coefficient results of the measuring points are output. Based on the CFD numerical wind tunnel results in step S2, the wind pressure on the building surface is derived. The wind load analysis results of the physical wind tunnel and the numerical wind tunnel are integrated. The areas where the wind pressure exceeds the specification are marked in combination with the design specifications. The overall body coefficient is calculated and output in combination with the surface partition area and the local body coefficient.

[0008] In the above technical solution, the method for repairing and adjusting the model after importing the model in step S1 is specifically as follows: Based on the 3D model file imported into NURBS surface modeling software, combined with CAD drawings and project text data, the tool set of surface modeling software is used to perform "trim", "merge", "smooth" and other repair operations to address problems such as conversion damage, model damage, and incompleteness that occur when importing the model, ensuring that the 3D model is consistent with the project data.

[0009] In the above technical solution, in step S1, the curvature change of the model is determined through the "curvature analysis" and "surface segmentation" tools of the surface modeling software, and the segmentation strategy is selected according to the degree of curvature change. The fine segmentation and surface adjustment of complex geometric surfaces are completed through the plug-ins provided by the modeling software and the parametric modeling platform.

[0010] In the above technical solution, the method for completing the arrangement of wind load measurement points and surface partitioning in step S1 is specifically as follows: On the parametric modeling platform, the number and spacing of control measuring points are set in each surface, and the automatic arrangement of parametric measuring points is completed in combination with wind loads; partitioning is performed according to the geometric points and the geometric model adjusted after segmentation, so that one measuring point corresponds to a partition model, wherein the partition model is a geometric model obtained by segmenting the original model. When performing geometric partitioning, a three-dimensional Thiessen polygon crystal is first generated on the measuring point, and then the crystal is used to segment the geometric model to obtain the partition model corresponding to the measuring point.

[0011] In the above technical solution, the construction of the Thiessen polygon crystal in step S1 is mainly based on the following steps: First, prepare a set of discretely distributed data points, and construct a Delaunay triangulation based on the discrete data points. On the basis of the Delauany triangulation, draw the perpendicular bisectors of each triangle edge. These perpendicular bisectors divide the screen area into a series of polygons.

[0012] Among them, the Delaunay triangulation is a special triangulation, which has the empty circumscribed circle property and the maximized minimum angle property, and is the basis for constructing Thiessen polygons.

[0013] In the above technical solution, the method for establishing the CFD numerical wind tunnel calculation model in step S1 is specifically as follows: The characteristic dimensions of the target building are analyzed based on the three-dimensional model compiled in the NURBS surface modeling software and the parametric modeling platform. The height of the target building site is taken as the basic height. The distance between the target building and the urban building reaches the corresponding multiple of the basic height to determine the selection of the calculation domain height of the CFD numerical wind tunnel calculation model. The calculation domain layout of the CFD numerical wind tunnel is completed according to the characteristic length of the building and the dimensionless value recommended by the design specification.

[0014] In the above technical solution, in step S1, the pre-processing process of the CFD numerical wind tunnel calculation model is completed according to the climatic conditions of the project location and the physical orientation information provided by the project data.

[0015] In the above technical solution, the CFD numerical wind tunnel calculation model after the pre-processing process in step S1 can be used to calculate the full wind angle on the user's local server, or uploaded to the cloud server heterogeneous system according to demand to calculate the full wind angle. It should be noted that the CFD numerical wind tunnel calculation model is established based on the three-dimensional model and building size information provided by the project designer. The model contains refined building drawing information and is a three-dimensional expression of the plane drawing. It is widely used in the fields of building wind resistance design, wind resistance toughness assessment, etc. In the above technical solution, the local body coefficient in step S2 is the ratio of the average pressure or suction caused by the wind acting on a certain or set area of ​​the building surface to the velocity pressure of the incoming wind.

[0016] In the above technical solution, in step S3, the local body coefficients are downloaded and stored in the NURBS surface modeling software and the parametric modeling platform.

[0017] In the above technical solution, the measuring point data in step S3 includes the spatial coordinates of the measuring point, curvature information, the normal vector of the building surface where the measuring point is located, and the wind pressure coefficient and local shape coefficient of the measuring point at multiple wind direction angles.

[0018] In the above technical solution, the specific method of optimizing the measurement point arrangement by machine learning cluster analysis in step S3 is: firstly, preprocess the discrete measurement point data under all wind directions, including preprocessing the spatial coordinates (X, Y, Z) of the measurement points, curvature information (Curvature), the normal vector of the building surface where the measurement points are located, and the wind pressure coefficient (Pressure Coefficient) at multiple wind directions. This step covers the elimination of outliers, the filling of missing values, and the standardization of data, aiming to ensure the accuracy and consistency of the data and lay a solid foundation for subsequent analysis.

[0019] In the above technical solution, in step S3, the weighted Euclidean distance between the two measuring points is: ; In the formula d ij is the weighted Euclidean distance between two measuring points, w 1, w 2, w 3 and w 4 are the weight coefficients corresponding to the spatial coordinates, curvature, wind pressure and normal vector, x is and x js are the spatial coordinate components of the two measuring points; s=1, 2, 3 correspond to the X direction, Y direction and Z direction in space, i and j represent two different measuring points, p ik and p jk is the wind pressure information of the measuring point under the kth wind direction angle; i and j represent two different measuring points; n im and n jm is the normal vector component of the measuring point; m=1, 2, 3 corresponds to the X direction, Y direction and Z direction in space, and i and j represent two different measuring points.

[0020] In the present invention, the weight coefficients corresponding to the spatial coordinates, curvature, wind pressure and normal vector are preferably w 1, w 2, w 3 and w 4 are 0.5, 0.7, 1.0 and 0.9 respectively.

[0021] In the above technical solution, in step S3, the cluster center is selected, and the specific content is: 1) Randomly select a measurement point from the data set as the first cluster center point.

[0022] 2) For each measured point, calculate its weighted Euclidean distance to the selected cluster center, and calculate the probability of each data point being selected as the next cluster center based on these distances. Specifically, the farther a data point is from the selected cluster center, the greater its probability of being selected.

[0023] 3) Randomly select a data point as the next cluster center according to the calculated probability distribution, and repeat the cluster center selection process until K cluster centers are selected. Execute the machine learning clustering algorithm based on the selected K initial cluster centers.

[0024] In the above technical solution, in step S3, K=40 is preferably set.

[0025] In the above technical solution, the specific steps of the clustering algorithm in step S3 are: 1) For each measurement point in the data set and the obtained K cluster centers or cluster centers, use the weighted Euclidean distance to calculate its distance to each cluster center point and assign it to the cluster with the closest distance; 2) Recalculate the center point in each cluster. The new center point is the weighted average of all the measurement points in the cluster in the weighted feature space. Specifically, for each feature dimension (spatial coordinates, curvature, wind pressure and normal vector), weighted sum the data points according to the corresponding weight, and then divide by the sum of the weights to get the weighted average of the dimension. The weighted averages of all dimensions are combined to form the weighted average vector of the cluster center. 3) Repeat the steps of assigning measurement points to clusters and updating cluster centers until the cluster centers no longer change or the preset number of iterations is reached.

[0026] After completing the clustering algorithm, the K clusters obtained contain a corresponding number of measurement points, and each cluster has similar weighted features (spatial coordinates, curvature, wind pressure and normal vector). After clustering the single wind direction angle, a sparse measurement point matrix is ​​constructed based on the principle that the wind pressure extreme value area is dense and the non-extreme value is sparse, and the sparse measurement point matrix of all wind direction angles is obtained by integrating each wind direction angle to fully reflect the extreme wind pressure characteristics.

[0027] In the above technical solution, in step S3, the retention ratio of the number of measurement points in each cluster under a certain wind direction angle is defined as R , analyze the mean and variance of wind pressure at each cluster measuring point, determine the extreme wind pressure value in combination with the numerical wind tunnel results, and analyze whether the mean wind pressure at the measuring points in the cluster satisfies the following conditions: ; In the formula p min and p max For minimum and maximum wind pressure, p mean is the mean wind pressure of the measuring points within the cluster, α and β It is the scaling ratio of minimum and maximum wind pressure, and the value can be adjusted according to actual cases and design requirements; When the wind pressure at the measuring point in the cluster satisfies the above formula, it can be considered that the wind pressure at the measuring point in the cluster is far away from the extreme wind pressure. Therefore, the number of measuring points can be appropriately reduced and a smaller retention ratio of measuring points can be set. R Otherwise, it can be considered that the wind pressure of the cluster measuring point is close to the extreme wind pressure, and a larger measurement point retention ratio can be set. R On this basis, the cluster with large wind pressure variance can be appropriately increased R The value of each cluster is based on R The value of modifies the number of optimized measuring points.

[0028] In this way, a sparse measurement point matrix under a certain wind direction angle is obtained, which accurately retains the extreme wind pressure characteristics and wind pressure gradient characteristics under the wind direction angle. By integrating the results of all wind direction angles, a sparse measurement point matrix of all wind direction angles covering the extreme wind pressure characteristics can be obtained.

[0029] In the above technical solution, in step S3, the surface partition is further optimized using the Thiessen polygon principle based on the modified measurement point distribution to ensure that the measurement points are evenly distributed throughout the monitoring area and fully cover all important wind pressure change areas, thereby achieving accurate and efficient wind pressure monitoring. Physical wind tunnel tests are carried out based on the optimized measurement point solution and surface partition information.

[0030] In the above technical solution, in step S4, the measuring point body coefficient is optimized based on the output of the physical wind tunnel test, and the wind pressure information of the building surface at all wind directions is derived based on the numerical wind tunnel test. In combination with the design specifications, the measuring point body coefficient, the building surface wind pressure information and the specification limit are compared, and the measuring points and areas where the wind pressure exceeds the specification requirements are accurately marked, and the measuring point body coefficient and the information of the wind pressure exceeding the specification area are imported into the three-dimensional building model.

[0031] In the present invention, the design specification may be a domestic specification, or a specification of a certain industry or a specific region.

[0032] In the above technical solution, in step S4, the overall shape coefficient is calculated by combining the surface partition area and the measuring point shape coefficient information through the surface partition weighted average analysis method, thereby obtaining the overall shape coefficient on each surface.

[0033] Specifically, each measuring point P i has its normal vector ( n x , n y , n z ), calculated wind pressure coefficient of the measuring point C pi 、 Local body shape coefficient μ si The corresponding surface partition area A i , which is obtained by updating the Thiessen polygon in step S3. For each independent surface, if the shape coefficient on the entire surface is averaged, then the overall shape coefficient can be obtained by weighting the partition area as follows: .

[0034] In the above technical solution, in step S4, taking a high-rise building as an example, for a certain height interval H For the building interface within the height range, if the density distribution of the measuring points is reasonable and the wind pressure magnitude and direction of the measuring points on the partition area remain unchanged, the overall shape coefficient of the building in the horizontal and vertical directions within the height range is: ; ; In the formula μ sa , μ sc is the overall shape coefficient of the horizontal longitudinal and lateral directions in this height range, μ z is the wind pressure height coefficient corresponding to the center height of the height interval, μ zr is the wind pressure height coefficient corresponding to the building reference point height, L a and L c The longitudinal and transverse reference lengths are taken as the longitudinal and transverse windward widths of the high-rise building within this height range. α i is the angle between the normal direction of the measuring point and the horizontal longitudinal direction, and the normal vector ( n x , n y , nz ) is calculated with the specified horizontal direction.

[0035] The overall shape coefficient thus calculated is a discrete function distributed along the height, and can be applied as the overall shape coefficient of different floors in actual projects.

[0036] In the above technical solution, in step S4, the wind pressure exceeding specification area, the measuring point body coefficient, and the building overall body coefficient are sorted and output, wherein the overall body coefficient is combined with the numerical wind tunnel building surface wind pressure cloud map information to ensure the rigor, accuracy and effectiveness of the wind load information, thereby providing data support and optimization suggestions for the structural wind resistance design.

[0037] The present application also provides a computer-readable storage medium or electronic device, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0038] Specifically include: 1) Importing complex building structure models, completing model repair and adjustment in NURBS surface modeling software based on project design data, analyzing its geometric modeling features, completing the layout of wind load measurement points after segmentation based on the parametric modeling platform, and completing surface partitioning based on Thiessen polygons. Establishing a CFD numerical wind tunnel calculation model, and sending the configured model to a local or cloud heterogeneous system for CFD full wind direction angle calculation; 2) Extracting the wind pressure at the measurement point from the calculated CFD numerical wind tunnel results, converting it into indicators of wind-resistant design such as surface wind pressure and body coefficient that are consistent with the specifications, and downloading and storing it on the parametric modeling platform; 3) Optimizing the measurement point layout by combining the measurement point body coefficient with the three-dimensional building model, performing machine learning clustering analysis on the measurement point body coefficient, and concentrating the measurement points on areas where the wind pressure is closer based on the clustering results. In the area of ​​extreme wind pressure, the surface partition is updated based on the optimized measurement point arrangement and Thiessen polygons to carry out physical wind tunnel tests; 4) After completing the physical wind tunnel test, the measurement point shape coefficient results are output, and the building surface wind pressure is derived based on the CFD numerical wind tunnel results in step S2. The wind load analysis results of the physical wind tunnel and the numerical wind tunnel are integrated, and the areas where the wind pressure exceeds the specification are marked in combination with domestic specifications. The overall shape coefficient is calculated and output in combination with the surface partition area and the measurement point shape coefficient to supplement the specification value, thereby providing data support and design suggestions for the wind-resistant design of the structure.

[0039] Compared with the existing wind pressure measurement point arrangement technology, the beneficial effects of the present invention are: (1) Significantly improve test efficiency and data accuracy. The general computational fluid dynamics (CFD) measurement point layout scheme covers a large number of measurement points, which cannot solve the problem of the limited number of measurement points in the physical wind tunnel layout, resulting in the inability of the physical wind tunnel to adopt the CFD analysis scheme. By combining CFD numerical simulation and machine learning cluster analysis, the present invention can accurately predict and evaluate the wind pressure distribution on the surface of the building before the physical wind tunnel test. This prediction capability makes the measurement point layout more scientific and reasonable, avoiding the blindness and redundancy of the measurement point layout in the traditional method. Therefore, in the physical wind tunnel test, the number of unnecessary measurement points can be significantly reduced, the time for data collection and processing can be shortened, and the test efficiency can be improved. At the same time, because the measurement point layout is more accurate, the wind pressure change characteristics on the surface of the building can be captured more comprehensively, improving the accuracy and reliability of the test data.

[0040] (2) Reduce test costs. Traditional physical wind tunnel tests are often conservative in the arrangement of measurement points, resulting in an excessive number of measurement points, which increases the test equipment and labor costs. The present invention reduces the number of unnecessary measurement points and the workload of data collection and processing by optimizing the measurement point arrangement. This not only reduces the investment in test equipment, but also reduces labor costs and time costs. In addition, due to the improvement in test efficiency, energy consumption and other related costs during the test process are also indirectly reduced. Therefore, this patent has a significant advantage in reducing test costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A physical wind tunnel pressure test optimization method based on CFD-AI and a storage medium schematic diagram in the implementation of this application.

[0043] Figure 2 This is a schematic diagram of a three-dimensional building model established in Rhino of a target building selected in an embodiment of the present invention.

[0044] Figure 3 The figure is a schematic diagram of an initial arrangement scheme of measuring points established based on the parametric modeling platform Grasshopper in an embodiment of the present invention.

[0045] Figure 4 It is a schematic diagram of the battery principle of completing surface partitioning based on the Thiessen polygon principle in an embodiment of the present invention.

[0046] Figure 5 This is a schematic diagram of the CFD numerical wind tunnel completed by the pre-processing software urbanFlow for the target building selected in the embodiment of the present invention.

[0047] Figure 6It is a schematic diagram of a certain wind direction angle measurement point arrangement scheme after optimization and modification by an adaptive clustering algorithm in an embodiment of the present invention.

[0048] Figure 7 It is a schematic diagram of measuring point partitioning under a certain unfavorable wind direction angle completed by clustering algorithm optimization and modification and combining Thiessen polygons in an embodiment of the present invention.

[0049] Figure 8 It is a schematic diagram of the surface local shape coefficient of the target building in an embodiment of the present invention obtained by numerical wind tunnel calculation under a certain unfavorable wind direction angle.

[0050] Fig. 9 This is a statistical diagram of the extreme values ​​of the body coefficient of the measuring points of the target building A considering all wind direction angles in an embodiment of the present invention.

[0051] Fig.10 This is a schematic diagram of the overall shape coefficient of the target building A according to the floor level under different wind directions in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0053] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0054] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0055] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the application is usually placed when in use. They are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0056] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0057] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] In the present application, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0059] The features and performance of the present application are further described in detail below in conjunction with the embodiments.

[0060] Example 1 According to the technical solution of the present invention, a physical wind tunnel pressure test optimization method and storage medium based on CFD-AI are implemented. The principle steps are as follows: Figure 1 As shown, a specific implementation case is given below: Taking a super high-rise building wind pressure numerical simulation project as an example, the specific implementation steps of the present invention are introduced as follows: Step (1): Based on the CAD drawings and model files provided by the project party, the complex architectural model is imported into the NURBS surface modeling software Rhino. In order to solve the problems of model damage, incorrect information expression, and excessive model details affecting calculation efficiency during model transmission, the model is repaired and simplified in combination with the CAD drawings. The obtained model diagram is as follows: Figure 2 As shown below. Figure 2 The super high-rise building on the left side of the middle is named Building A, and the high-rise building on the right side is named Building B.

[0061] Import the organized 3D building model into the parametric modeling software platform Grasshopper, set each surface of Building A and Building B as an analysis unit Brep, set the number and spacing of horizontal and vertical measuring points based on the individual surfaces, and set the overall spacing to about 3m in this project. The horizontal control spacing is maintained at 7 segments, and the vertical spacing is maintained at 30-50 segments according to the surface height. This completes the preliminary setting of the measuring points. Figure 3 As shown. Subsequently, with the help of the SplitGeo battery in the Grasshopper plug-in, the geometric model is partitioned according to the principle of the closest distance between the measuring points based on the Thiessen polygon principle, and the process of partitioning the case surface is as follows: Figure 4 shown.

[0062] Specifically, Figure 4 The partitioning principle is as follows: for each measuring point on the surface, a three-dimensional Thiessen polygon crystal is first generated. Any position in the crystal is closest to the measuring point in the crystal and farthest from the measuring point in the adjacent crystal. The surface is segmented using the crystal to obtain a partition model corresponding to the measuring point.

[0063] Based on the 3D model file provided by the project designer, the NURBS surface modeling software was imported. Combined with the CAD drawings and project text materials provided by the project designer, the toolset of the surface modeling software was used to perform "trim", "merge", "smooth" and other repair operations to solve the problems of conversion damage, model damage, defects and incompleteness when the model was imported, so as to ensure that the 3D model was consistent with the project materials. On this basis, the "curvature analysis" and "surface segmentation" tools of the surface modeling software were used to intuitively understand the curvature of the model, select the appropriate segmentation strategy according to the degree of curvature change, and complete the fine segmentation and surface adjustment of complex geometric surfaces through the plug-ins provided by the modeling software and the parametric modeling platform.

[0064] The specific method for completing the arrangement of wind load measurement points and surface partitioning is as follows: According to the visual programming capabilities of the parametric modeling platform based on nodes and links, the number of control points, spacing and other measurement point layout rules are set in each surface, and the automatic layout of parametric measurement points is completed in combination with the needs of wind load research. Subsequently, partitioning is performed based on the geometric points and the geometric model adjusted after segmentation. The result is that one measurement point corresponds to one partition model, where the partition model is a geometric model obtained by segmenting the original model. The partition mainly follows the principle of Thiessen polygons. When performing geometric partitioning, a three-dimensional Thiessen polygon crystal is first generated on the measurement point, and then the crystal is used to segment the geometric model to obtain the partition model corresponding to the measurement point.

[0065] Thiessen polygon is an effective spatial partitioning method, which is mainly used to calculate and analyze specific attribute values ​​in a spatial region based on discretely distributed data points. The distance between each point in a Thiessen polygon and its control point is the shortest, and the distance to the points in the adjacent polygon is far. This unique spatial partitioning feature makes it widely used in meteorology, geographic information systems, urban planning and ecology.

[0066] The definition of Thiessen polygons is briefly as follows: Suppose there is a set of discrete points ( x i , y j ) (i, j are the numbers of discrete points), if the area B is divided into k mutually adjacent polygons by a set of straight line ends, such that: 1) Each polygon has only one discrete point: 2) If any point on area B ( x , y ) is located in the polygon containing the discrete point, the following inequality always holds when i≠j: ; 3) If the point ( x , y ) is located on the common edge of the two polygons containing the discrete point, then the following equation holds: ; The polygons obtained in this way can be called Thiessen polygons.

[0067] The construction of Thiessen polygons is mainly based on the following steps: First, prepare a set of discretely distributed data points, and construct a Delaunay triangulation based on the discrete data points. The Delaunay triangulation is a special triangulation with the empty circumscribed circle property and the maximized minimum angle property, and is the basis for constructing Thiessen polygons. On the basis of the Delauany triangulation, draw the perpendicular bisectors of each triangle edge. These perpendicular bisectors divide the screen area into a series of polygons.

[0068] The specific method for establishing the CFD numerical wind tunnel calculation model is as follows: Based on the three-dimensional model organized in the NURBS surface modeling software and the parametric modeling platform, the characteristic dimensions of the target building are analyzed. Specifically, the height of the target building site is used as the basic height. The distance between the building in the city and the target building reaches the corresponding multiple of the basic height to determine the selection of the calculation domain height of the CFD numerical wind tunnel calculation model; the calculation domain layout of the CFD numerical wind tunnel is completed according to the characteristic length of the building and the dimensionless value recommended by the specification. The pre-processing process of the CFD numerical wind tunnel calculation model is completed according to the climatic conditions of the project location and the physical orientation and other information provided by the project data. After the pre-processing process, the CFD numerical wind tunnel calculation model can be used to carry out full wind angle calculation on the user's local server, or uploaded to the cloud server heterogeneous system according to the needs to carry out full wind angle calculation. It should be noted that the CFD numerical wind tunnel calculation model is established based on the three-dimensional model and building size information provided by the project designer. The model contains refined architectural drawing information and is a three-dimensional expression of the plane drawing. It is widely used in the fields of building wind resistance design and wind resistance toughness assessment.

[0069] Step (2): Store the processed three-dimensional building model, measurement points and partitions in the parametric modeling platform Grasshopper, and build a numerical wind tunnel based on the independently developed building numerical wind tunnel pre-processing software (abbreviated as: urbanFlow). Set Building A and Building B as the target buildings, set the height of Building A as the basic height H, and use this height as the reference height to set the inlet boundary condition. Combined with the "Standard for Wind Tunnel Test Methods for Building Engineering" (JGJ / T 338-2014), set the distance from the entrance of the calculation domain to the model to 10H, the distance from the model to the exit of the calculation domain to 15H, and control the distance from the model to both sides of the calculation domain to 5H to ensure that the geometric model blockage ratio of the building is not greater than 5%. Since the calculation area is large, it is necessary to reasonably partition the entire calculation area, and then generate grids for each area separately, mainly using structural grids, and using unstructured grids for some more complex parts. The grids around the main building group are denser, and the grids in the area away from the main building group are sparser. In the near-wall area and the area where the flow field changes more drastically, the grid is appropriately encrypted to ensure the reliability of the calculation. Under this principle, the grid scheme obtained after grid sensitivity analysis is consistent with the overall calculation domain as shown in Figure 2. Figure 5 shown.

[0070] It should be noted that this project and the numerical wind tunnel pre-processing software urbanFlow mainly use the open source finite volume method software OpenFOAM for numerical simulation. It is highly customizable and can achieve a high degree of liberalized parameter setting and secondary development. Therefore, the architectural numerical wind tunnel pre-processing software urbanFlow can be used to automatically establish a parametric numerical wind tunnel according to the OpenFOAM solution file writing format.

[0071] The velocity inlet boundary condition (velocity-inlet) in OpenFOAM is used to calculate the inlet of the flow. The boundary condition is used to define the flow velocity and other related scalar flow variables at the flow inlet. This boundary condition is applicable to incompressible flow. The atmospheric boundary condition corresponding to the representative ground roughness category is used as the incoming flow condition for calculation, simulating the exponential distribution of the wind speed profile in the atmospheric boundary layer, and its velocity changes with height obeys the exponential law: (1) Where Z0,U0 is the basic wind speed at 10m height and 10m height, and the ground roughness coefficient is .

[0072] The turbulence intensity at the inlet varies with height as follows: (2) In the formula is the nominal turbulence constant at 10m height. This project is located in Class A landform. Take 0.12 as the nominal turbulence = 0.12. The distribution of velocity and turbulence intensity is implemented in the boundary conditions based on the automatic OpenFOAM text file writing function of urbanFlow.

[0073] The outlet uses the fully developed outflow boundary condition (Outflow). The Outflow boundary condition is used when the pressure or velocity on the outflow boundary is unknown, and is suitable for the case where the flow at the outlet is fully developed. The so-called fully developed means that the flow on the outflow surface is extrapolated from the interior of the region and has no effect on the upstream flow.

[0074] When modeling this project, the outlet boundary is located behind the building and is much larger than 10 times the height of the building, which ensures that the flow is fully developed, so the fully developed outflow boundary condition can be used. Symmetric boundary conditions (symmetry) are used on the top and both sides of the calculation domain, which are suitable for the case of symmetric flow, that is, they have mirror symmetry characteristics and can be used to describe the free slip wall in viscous flow. No-slip wall conditions (wall) are used on the surface of the building and the ground. Wall is a boundary condition used to limit the fluid and solid areas. The velocity of the no-slip wall is zero, and the fluid velocity at the wall is zero. Set the total calculation time and the exchange time step of the coupling area, and determine the range of iterations and convergence residuals for different types of areas within the exchange time step. In this case, the calculation step size is 0.1s, and the total calculation time is 500s, that is, the converged solution of the steady-state calculation within 5000 calculation time steps.

[0075] After completing the numerical wind tunnel CFD simulation pre-processing settings in urbanFlow, the working conditions of different wind direction angles can be set by rotating the building model. The minimum step length of the rotation angle is determined according to the dominant wind direction type of the project and the wind direction time course of meteorological data. In this project, the dominant wind direction in summer is south wind S, the dominant wind direction in winter is northeast by east ENE, and the dominant wind direction throughout the year is southeast by east ESE. The wind direction changes by 22.5°, so the east wind direction E of the project is set to 0°, and the minimum step length of the rotation angle is ensured to be 22.5°, thus completing the setting of 16 working conditions from 0° to 360°. According to the arranged measuring points, sampling points are set at the spatial coordinate positions in the calculation domain to effectively monitor the change time course of the field variables under the total calculation time, such as wind speed time course, wind pressure change time course, etc., and the sampling point output data interval is adjusted independently according to the calculation needs. After completing all the above pre-processing settings, the full wind direction angle simulation calculation of the OpenFOAM numerical wind tunnel can be carried out in the local system or cloud heterogeneous system.

[0076] It should be noted that in conventional solution calculations, each open source OpenFOAM solver case file must contain three folders: 0, system, and constant, including the initial and boundary conditions of the calculation domain (0 folder), mesh partition files (blockMeshDict, snappyHexMeshDict, and surfaceFeatureExtractDict), and solution control files (controlDict, fvSchemes, and fvSolution). The urbanFlow pre-processing software for building numerical wind tunnels is developed in the form of secondary development in the C# language, which can automatically complete the writing of OpenFOAM text files in the parametric modeling platform Grasshopper, thereby completing the automatic construction function of the CFD numerical wind tunnel.

[0077] Step (3): Download the wind pressure at the measuring point and convert it into local body coefficient data, and import the results into the NURBS surface modeling software Rhino and the parametric modeling platform Grasshopper. According to actual needs, based on the wind pressure results at a certain wind direction angle, different weights are assigned to the spatial coordinates, curvature, normal vector and wind pressure of the measuring points A and B, and the assigned weights are used to calculate the two points. P i and P j The weighted Euclidean distance between them is as follows: (3) In the formula d ij is the weighted Euclidean distance between two measuring points, w 1, w 2, w 3 and w4 are the weight coefficients corresponding to the spatial coordinates, curvature, wind pressure and normal vector, which are 0.5, 0.7, 1.0 and 0.9 respectively in this case. x is and x js are the spatial coordinate components of the two measuring points (s=1, 2, 3 correspond to the X direction, Y direction and Z direction in space, i and j represent two different measuring points), p ik and p jk is the wind pressure information of the measuring point under the kth wind direction angle (i and j represent two different measuring points), n im and n jm is the normal vector component of the measuring point (m=1, 2, 3 corresponds to the X direction, Y direction and Z direction in space, i and j represent two different measuring points); Then the cluster center is selected, the specific contents are as follows: 1) Randomly select a measurement point from the data set as the first cluster center point.

[0078] 2) For each measured point, calculate its weighted Euclidean distance to the selected cluster center, and calculate the probability of each data point being selected as the next cluster center based on these distances. Specifically, the farther a data point is from the selected cluster center, the greater its probability of being selected.

[0079] 3) Randomly select a data point as the next cluster center according to the calculated probability distribution, and repeat the cluster center selection process until K cluster centers are selected. Perform a machine learning clustering algorithm based on the selected K initial cluster centers, in this case K=40.

[0080] The specific steps of the clustering algorithm are: 1) For each measurement point in the data set and the 40 cluster centers obtained, use the weighted Euclidean distance to calculate its distance to each cluster center point and assign it to the cluster with the closest distance; 2) Recalculate the center point in each cluster. The new center point is the weighted average of all the measurement points in the cluster in the weighted feature space. Specifically, for each feature dimension (spatial coordinates, curvature, wind pressure and normal vector), weighted sum the data points according to the corresponding weight, and then divide by the sum of the weights to get the weighted average of the dimension. The weighted averages of all dimensions are combined to form the weighted average vector of the cluster center. 3) Repeat the steps of assigning measurement points to clusters and updating cluster centers until the cluster centers no longer change or the preset number of iterations is reached.

[0081] After completing the clustering algorithm, the 40 clusters obtained contain a corresponding number of measurement points. Each cluster has similar weighted features (spatial coordinates, curvature, wind pressure and normal vector). After clustering the single wind direction angle, a sparse measurement point matrix is ​​constructed based on the principle of dense wind pressure extreme areas and sparse non-extreme areas. The sparse measurement point matrix of all wind direction angles is obtained by integrating each wind direction angle to fully reflect the characteristics of extreme wind pressure.

[0082] Specifically, the retention ratio of the number of measurement points in each cluster under a certain wind direction angle is defined as R , analyze the mean and variance of wind pressure at each cluster measuring point, determine the extreme wind pressure value in combination with the numerical wind tunnel results, and analyze whether the mean wind pressure at the measuring points in the cluster satisfies the following conditions: (4) In the formula p min and p max The minimum and maximum wind pressures, among which the minimum wind pressure is the maximum negative pressure. p mean is the mean wind pressure of the measuring points within the cluster, α and β is the scaling ratio of the minimum and maximum wind pressures, and in this case the value is uniformly taken as 0.9.

[0083] When the wind pressure at the measuring point in the cluster satisfies formula (4), it can be considered that the wind pressure at the measuring point in the cluster is far away from the extreme wind pressure. Therefore, the number of measuring points can be appropriately reduced and a smaller retention ratio of measuring points can be set. R Otherwise, it can be considered that the wind pressure of the cluster measuring point is close to the extreme wind pressure, and a larger measurement point retention ratio can be set. R On this basis, the cluster with large wind pressure variance can be appropriately increased. R Each cluster is based on R The value of is modified to optimize the number of measurement points. In this case, the clusters that satisfy formula (4) have a uniform value of R of 0.1, and the clusters that do not satisfy formula (4) have a uniform value of R of 0.5. For clusters with large variance, the value of R is appropriately increased.

[0084] Thus, the simplified measurement points under a certain wind direction angle are obtained as follows Figure 6 As shown in the figure, this measurement point scheme accurately retains the extreme wind pressure characteristics and wind pressure gradient characteristics under the wind direction angle, and the optimized measurement point layout scheme can be obtained by integrating the simplified measurement points under all wind directions. Figure 3 The initial measurement point plan reduces the number of measurement points by about 45%.

[0085] Based on the modified measurement point distribution, the Thiessen polygon principle is used to further optimize the surface partitioning. Figure 7 As shown, Figure 7 The measurement points used for surface partitioning are Figure 6The measurement points are streamlined to ensure that they are evenly distributed throughout the monitoring area and fully cover all important wind pressure change areas, achieving accurate and efficient wind pressure monitoring. Physical wind tunnel tests are carried out based on the optimized measurement point plan and surface partition information.

[0086] (4) After completing the physical wind tunnel test, the local shape coefficient results of the measuring points on the surface of the physical wind tunnel building and the wind pressure information on the surface of the numerical wind tunnel building are output. The local shape coefficient results of the measuring points can be output as a text file containing the spatial coordinate information of the measuring points and the shape coefficient value, or can be imported into the NURBS surface modeling software Rhino, and the measuring point information can be saved in the form of point cloud and color map combined with the three-dimensional building model. The color of the measuring point represents the shape coefficient value, and the measuring points where the wind pressure exceeds the specification are marked in combination with the existing specifications. On this basis, all direction angles can be comprehensively counted to obtain the extreme values ​​of the local shape coefficient of the measuring points under all wind direction angles. The surface wind pressure results at a certain wind direction angle and the local shape coefficient mechanism results of the measuring point A at all wind direction angles are as follows: Figure 8 and Fig. 9 As shown, Figure 8 Areas where negative pressure exceeds the standard are clearly marked. Fig. 9 This is a statistical diagram of the extreme values ​​of the body coefficient of the measuring points of the target building A considering all wind direction angles in an embodiment of the present invention.

[0087] The overall building shape coefficient can be calculated by combining the local shape coefficient results with the surface partitions corresponding to the measuring points. The surface partitions determined based on the Thiessen polygon principle can calculate the area of ​​each partition, thereby obtaining the corresponding relationship between the measuring point and its partition area. Combined with the measuring point shape coefficient, the surface partition area weighted average method is used to calculate the overall shape coefficient of different surfaces, and it is organized into a floor shape coefficient distribution diagram according to actual needs, as shown below. Fig.10 This result, combined with the building surface wind pressure cloud map information from the numerical wind tunnel, can ensure the rigor, accuracy and effectiveness of the wind load information.

[0088] Specifically, each measuring point P i has its normal vector ( n x , n y , n z ), calculated wind pressure coefficient of the measuring point C pi 、 Local body shape coefficient μ si The corresponding surface partition area A i, which is obtained by updating the Thiessen polygon in step S3. For each independent surface, if the shape coefficient on the entire surface is averaged, then the overall shape coefficient can be obtained by weighting the partition area as follows: .

[0089] The above example requires further analysis of the overall building shape coefficients of different floors according to demand. Here is a brief description: For a certain height range H If the density of the measuring points is reasonably distributed, combined with the Thiessen polygon partitioning, it can be considered that the wind pressure magnitude and direction of the measuring point in its partition area remain unchanged. In this example, the height interval is represented by the height interval of different floors. The overall shape coefficient of the building in the horizontal and vertical directions within the interval is: .

[0090] .

[0091] In the formula μ sa , μ sc is the overall shape coefficient of the horizontal longitudinal and lateral directions in this height range, μ z is the wind pressure height coefficient corresponding to the center height of the height interval, μ zr is the wind pressure height coefficient corresponding to the building reference point height, L a and L c As the reference length in the longitudinal and transverse directions, the longitudinal and transverse windward width of the high-rise building within this height range can be taken as α i is the angle between the normal direction of the measuring point and the horizontal longitudinal direction, and the normal vector ( n x , n y , n z ) is calculated with the specified horizontal direction.

[0092] The overall shape coefficient calculated in this way is a discrete function distributed along the height. In this example, it is the overall shape coefficient of different floors, such as Fig.10 shown.

[0093] The wind pressure cloud map information of the building surface under all wind directions, the local body coefficient measurement points, the overall body coefficient of the building and other results are sorted and output to provide important data support and optimization suggestions for the wind-resistant design of the structure. By analyzing and comparing the data under different wind directions, the stress characteristics and laws of the building under the influence of different wind loads can be found, providing a more scientific and digital basis for structural design and optimization.

[0094] Example 2 The present invention also provides a computer-readable storage medium or electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the physical wind tunnel pressure test optimization method based on CFD-AI as described in any one of the above items are implemented.

[0095] The embodiments described above are part of the embodiments of the present application, rather than all of the embodiments. The detailed description of the embodiments of the present application is not intended to limit the scope of the present application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

Claims

1. A physical wind tunnel pressure test optimization method based on CFD-AI, characterized in that The following steps are involved: S1. Import the 3D building model into the NURBS surface modeling software, complete the repair and adjustment of the building model, complete the layout of the wind load measurement points after segmentation based on the parametric modeling platform, and complete the surface partitioning based on the Thiessen polygons; establish a CFD numerical wind tunnel calculation model based on the layout of the wind load measurement points after segmentation and the surface partitioning, perform CFD full wind direction angle calculation based on the CFD numerical wind tunnel calculation model, and obtain the CFD numerical wind tunnel results; S2. Extract the wind pressure at the building surface measurement points corresponding to all wind direction angles from the CFD numerical wind tunnel results, and convert the wind pressure at the building surface measurement points into local body coefficients; S3. Combine the local body coefficient with the three-dimensional building model to establish a measurement point data matrix containing the measurement point body coefficients and the measurement point spatial geometry of multiple wind direction conditions; based on the wind pressure results of a certain wind direction angle, assign different weights to the spatial coordinates, curvature, normal vector and wind pressure in the measurement point data matrix of the target building, and calculate the weighted Euclidean distance between the two measurement points: perform machine learning clustering analysis on the weighted Euclidean distance of the measurement points, construct a sparse measurement point matrix and integrate it to obtain a sparse measurement point matrix of all wind direction angles, forming an optimized measurement point layout scheme that fully reflects the characteristics of extreme wind pressure; update the surface partition based on the optimized measurement point layout scheme and Thiessen polygons, and conduct physical wind tunnel tests; S4. After completing the physical wind tunnel test, the body coefficient results of the measuring points are output. Based on the CFD numerical wind tunnel results in step S2, the wind pressure on the building surface is derived. The wind load analysis results of the physical wind tunnel and the numerical wind tunnel are integrated, and the areas where the wind pressure exceeds the specification are marked. The overall body coefficient is calculated and output by combining the surface partition area and the local body coefficient.

2. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that Based on the 3D architectural model file imported into NURBS surface modeling software, combined with CAD drawings and project text data, the tool set of surface modeling software is used to perform "trim", "merge" and "smooth" repair operations to address conversion damage, model damage defects and incompleteness that occur when importing the model, ensuring that the 3D model is consistent with the project data.

3. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that In step S1, the curvature change of the model is determined by the "curvature analysis" and "surface segmentation" tools of the surface modeling software, and the segmentation strategy is selected according to the degree of curvature change. The fine segmentation and surface adjustment of the complex geometric surface are completed through the plug-ins provided by the modeling software and the parametric modeling platform.

4. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that: The method for completing the arrangement of wind load measuring points and surface partitioning in step S1 is specifically as follows: on a parametric modeling platform, the number and spacing of control measuring points are set in each surface, and the automatic arrangement of parametric measuring points is completed in combination with wind loads; partitioning is performed according to the geometric points and the geometric model adjusted after segmentation, so that one measuring point corresponds to one partition model, wherein the partition model is a geometric model obtained by segmenting the original model, and when performing geometric partitioning, a three-dimensional Thiessen polygon crystal is first generated on the measuring point, and then the crystal is used to segment the geometric model to obtain a partition model corresponding to the measuring point.

5. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that: The construction of the Thiessen polygon crystal in step S1 is mainly based on the following steps: first, prepare a set of discretely distributed data points, construct a Delaunay triangulation based on the discrete data points, and on the basis of the Delaunay triangulation, draw the perpendicular bisectors of each triangle edge, and these perpendicular bisectors divide the screen area into a series of polygons.

6. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that: The local shape coefficient in step S2 is the ratio of the average pressure or suction caused by the wind acting on the set area of ​​the building surface to the velocity pressure of the incoming wind.

7. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that: The measuring point data in step S3 include the spatial coordinates of the measuring point, curvature information, the normal vector of the building surface where the measuring point is located, and the wind pressure coefficient and local shape coefficient of the measuring point at multiple wind direction angles.

8. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1 is characterized in that: In step S3, the retention ratio of the number of measurement points in each cluster under a certain wind direction angle is defined as R , analyze the mean and variance of wind pressure at each cluster measuring point, determine the extreme wind pressure value in combination with the numerical wind tunnel results, and analyze whether the mean wind pressure at the measuring points in the cluster satisfies the following conditions: ； In the formula p min and p max For minimum and maximum wind pressure, p mean is the mean wind pressure of the measuring points within the cluster, α and β is the scaling ratio of minimum and maximum wind pressure; When the wind pressure of the measuring points in the cluster satisfies the above formula, it is considered that the wind pressure of the measuring points in the cluster is far away from the extreme wind pressure. The number of measuring points is appropriately reduced and a smaller retention ratio of measuring points is set. R Otherwise, the wind pressure of the cluster measuring point is considered to be close to the extreme wind pressure, and a larger measurement point retention ratio is set. R On this basis, the cluster with larger wind pressure variance is appropriately increased. R The value of each cluster is based on R The value of modifies the number of optimized measuring points.

9. The physical wind tunnel pressure test optimization method based on CFD-AI according to claim 1, characterized in that: In step S4, the overall shape coefficient is calculated by combining the surface partition area and the measuring point shape coefficient information through the surface partition weighted average analysis method, thereby obtaining the overall shape coefficient on each surface.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the physical wind tunnel pressure test optimization method based on CFD-AI as described in any one of claims 1 to 9 are implemented.

Images