Three-dimensional finite element model generation and numerical simulation method and system for wading engineering composite material XCT digital image

Abstract

The invention discloses a three-dimensional finite element model generation and numerical simulation method and system for a wading engineering composite material XCT digital image, and belongs to the technical field of finite element analysis. Comprising the steps of collecting a composite material XCT image in an initial state and performing preprocessing; performing statistical analysis on the two-dimensional microstructure parameters; a virtual XCT image is generated based on the Pix2PixHD style migration network; the method comprises the following steps of: accurately segmenting each component region of a real XCT (X-ray computed tomography) image based on a Swinin-Transformer network; completing contour feature extraction and smoothing of the segmented image based on a mapping relation between pixels and nodes; constructing a space coordinate system and carrying out discrete derivation on all yarn center points of each segmented image; grid division is carried out based on a multi-material moving cube algorithm in a CGAL library, and a global cohesion unit is inserted; completing material attribute and local material direction distribution; and customizing proper boundary conditions, and carrying out numerical simulation based on a finite element method.

Description

Technical Field

[0001] The present invention belongs to the technical field of finite element analysis, and in particular relates to a three-dimensional finite element model generation and numerical simulation method and system for XCT digital images of composite materials for water-related engineering. Background Art

[0002] Basalt fiber reinforced composites (BFRP) are high-performance composite materials whose core reinforcing components are basalt fibers, and are carefully manufactured through advanced molding technologies such as resin transfer molding (RTM) processes. For the construction of infrastructure such as water-related projects, the requirements for materials are extremely strict, and multiple factors such as strength, durability, corrosion resistance and construction convenience must be taken into account. Basalt fiber reinforced composites can not only effectively reduce the weight of the structure and improve the overall bearing capacity, but also maintain stable performance in harsh hydrological environments, reduce maintenance costs, and extend service life. Therefore, BFRP has great application prospects in the hydropower industry, which is conducive to promoting the innovation and development of hydropower engineering technology, and provides strong technical support for the green and lightweight transformation of the hydropower industry. It is of great significance to promote the optimization and upgrading of my country's energy structure.

[0003] XCT (X-ray Computed Tomography) scanning is a non-destructive testing technology based on X-rays, which can provide high-resolution information about the internal structure of materials. Through XCT scanning, we can obtain the microstructure of basalt fiber composite materials. XCT scanning technology can be used to obtain the internal microstructure characterization of composite materials under non-destructive conditions. This provides an important means of image data acquisition for further characterizing the internal microstructure of composite materials.

[0004] However, due to the obvious anisotropy and inhomogeneity of composite materials, their macroscopic mechanical properties testing often requires more experimental samples, complex testing equipment, high testing costs and long test cycles. Therefore, for the deformation and damage of composite materials under external loads, traditional test methods only focus on characterizing the average mechanical properties at the macroscopic level, ignoring the mechanical properties and spatial distribution characteristics of each component inside the composite material, and failing to establish a cross-scale connection between the micro-macroscopic mechanical properties.

[0005] Therefore, in recent years, finite element numerical simulation methods have become a common means of studying the mechanical properties of composite materials. By qualitatively and quantitatively characterizing the microstructural parameters, a more realistic finite element model is constructed, material properties and boundary conditions are set, and the deformation and damage evolution of the material under real experimental conditions are simulated, so that the surface and internal fracture mechanisms of the material can be observed at a low cost. However, most composite material finite element models are often based on ideal models or parameterized models, ignoring the heterogeneity of the microscopic characteristic structure inside the material. It is difficult for a three-dimensional finite element model that only considers the idealization of the microscopic characteristics to accurately express the mechanical response characteristics. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes a three-dimensional finite element model generation and numerical simulation method and system for XCT digital images of water-related engineering composite materials, which can be used to accurately construct a three-dimensional finite element model of the composite material and study its mesoscopic structural damage evolution process and rupture state.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] A three-dimensional finite element model generation and numerical simulation method for XCT digital images of composite materials for water-related engineering, comprising the following steps:

[0009] S1: Collect the real XCT images of basalt fiber composite in the initial state and perform manual segmentation;

[0010] S2: Perform parametric statistical analysis on the manually segmented images, quantify the microstructural parameters of the yarn inside the material and perform two-dimensional parametric random modeling to obtain parametric random modeling images;

[0011] S3: learning the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image;

[0012] S4: Based on the Swin-Tranformer network and virtual XCT images, accurate segmentation of each component region of real XCT images is achieved;

[0013] S5: Based on the segmented real XCT image, the contour microscopic features are extracted and the local contours are smoothed to build a yarn and pore feature database;

[0014] S6: Based on the yarn and pore feature database, extract the contour feature of each yarn in each segmented real XCT image, calculate the coordinate value of the center of the yarn contour, establish a spatial coordinate system, and based on the spatial coordinate system, perform discrete derivation on the center of the contour of each yarn in each segmented image to construct a feature database;

[0015] S7: Based on the feature database, a three-dimensional voxel model is reconstructed, and meshing and cohesive force units are inserted based on a multi-material moving cube algorithm in the CGAL library to simulate the yarn separation and delamination phenomenon under load;

[0016] S8: Based on the divided grid, define the material properties of each component region and assign local material directions;

[0017] S9: Set boundary conditions and perform numerical simulation calculations.

[0018] Preferably, in S3, the method of learning the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image includes:

[0019] S31: generating a warp yarn random model based on warp yarn parameterized statistical analysis;

[0020] S32: Generate a random model of weft yarns according to the parameterized statistical analysis of weft yarns;

[0021] S33: generating an artificial synthetic label image based on the warp yarn random model and the weft yarn random model;

[0022] S34: Based on the artificially synthesized label image, an improved Pix2PixHD network is applied to generate a virtual image of a basalt fiber composite material similar to a real mesostructure, and a mixed data set, i.e., a real-virtual XCT image, is constructed.

[0023] Preferably, in S4, the method for realizing accurate segmentation of each component region of a real XCT image based on a Swin-Tranformer network comprises:

[0024] S41: Input the mixed data set to the Swin-Tranformer network to obtain training images;

[0025] S42: Divide the training image into different small blocks by pixels through a block division module, and then convert it into a one-dimensional feature vector image;

[0026] S43: Accurately segment each component region in the one-dimensional feature vector image to obtain a semantic segmentation result image;

[0027] S44: Based on the semantic segmentation result map, a watershed segmentation algorithm is used to complete region segmentation for each yarn.

[0028] Preferably, in S5, based on the segmented real XCT image, the method of extracting contour microscopic features and smoothing the local contour to construct a yarn and pore feature database includes:

[0029] S51: Selecting a resolution that meets preset requirements to downsample the segmented real XCT image;

[0030] S52: performing feature screening on the real XCT image after downsampling;

[0031] S53: based on the real XCT image after feature screening, extracting the image contour features of the pores and the yarn, and converting the coordinate values ​​according to the positional relationship between the pixels and the nodes to obtain the contour coordinate values;

[0032] S54: setting a convolution kernel that meets preset requirements, and using the operation between the convolution kernel and the contour coordinate value to achieve contour smoothing;

[0033] S55: Process all segmented images according to S51-S54, build a yarn and pore feature database, and store the contour coordinate values ​​of each component after the coordinate system is transformed.

[0034] Preferably, in S6, based on the yarn and pore feature database, the contour feature of each yarn in each segmented image is extracted, the coordinate value of the center of the yarn contour is calculated, a spatial coordinate system is established, and based on the spatial coordinate system, the method for performing discrete derivation of the center of the contour of each yarn in each segmented image includes:

[0035] S61: extracting the coordinate value of the center point of each yarn contour in each segmented image from the yarn and pore feature database, and establishing a spatial coordinate system in the order of the segmented images;

[0036] S62: Based on the spatial coordinate system, use the first-order intermediate differential law to perform discrete derivative on the center point of each yarn contour in each segmented image to obtain the tangent direction of the center point, that is, the 1 direction of the yarn;

[0037] S63: Obtain direction 2 from direction 1 obtained by calculation.

[0038] Preferably, in S7, based on the feature database, the three-dimensional voxel model is reconstructed, and the method for meshing based on the multi-material marching cube algorithm in the CGAL library includes:

[0039] S71: Based on the feature database, the segmented XCT image is imported into Avizo 2019.1 software to complete the three-dimensional voxel model reconstruction, and an inr file is exported;

[0040] S72: Mesh the reconstructed 3D voxel model using the multi-material marching cube algorithm based on the CGAL library to obtain a mesh file;

[0041] S73: Use a python script to convert the mesh file into an inp file that can be imported into Abaqus.

[0042] Preferably, in S72, the method of meshing the reconstructed three-dimensional voxel model based on the multi-material marching cube algorithm of the CGAL library to obtain the mesh file includes:

[0043] Downsample the reconstructed 3D voxel model and extract the intersection edges of different components, use the boundary features of the intersection edges as one-dimensional line features, and perform smoothing operations on the one-dimensional line features;

[0044] Delaunay triangulation is performed using the outer surfaces of voxels of different components to generate surface triangular meshes and then the surface triangular meshes are re-divided. The classic Laplacian smoothing algorithm is used to process non-manifold areas to avoid self-intersections and sharp dihedral angles.

[0045] The one-dimensional line feature is added to the re-divided surface triangular mesh, and the interior of the closed surface triangular mesh is divided into a tetrahedral mesh C3D4. According to the node sharing relationship of the surface triangular mesh generated on the intersecting edges of the mutually contacting components, the global zero-thickness cohesion unit COH3D6 is inserted, and finally the reconstructed three-dimensional voxel model is converted into a mesh model to obtain a mesh file.

[0046] Preferably, in S8, based on the divided grids, the material properties of the regional features of each component are defined, and the method for allocating the local material direction includes:

[0047] S81: Define the material properties and mechanical response characteristics of each component region;

[0048] S82: The calculated local material direction is gradually assigned to each unit of each yarn.

[0049] The present invention also provides a three-dimensional finite element model generation and numerical simulation system for XCT digital images of composite materials of water-related engineering, including: an acquisition module, a modeling module, a learning module, a precise segmentation module, a first database construction module, a second database construction module, a partitioning module, an allocation module, a simulation module and a calculation module;

[0050] The acquisition module is used to acquire the real XCT image of the basalt fiber composite material in the initial state and perform manual segmentation;

[0051] The modeling module is used to perform parametric statistical analysis on the manually segmented image, quantify the microscopic structural parameters of the yarn inside the material and perform two-dimensional parametric random modeling to obtain a parametric random modeling image;

[0052] The learning module is used to learn the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image;

[0053] The precise segmentation module is used to achieve precise segmentation of each component area of ​​the real XCT image based on the Swin-Tranformer network and the virtual XCT image;

[0054] The first database construction module is used to extract contour microscopic features and smooth local contours based on the segmented real XCT image to construct a yarn and pore feature database;

[0055] The second database construction module is used to extract the contour features of each yarn in each segmented real XCT image based on the yarn and pore feature database, calculate the coordinate value of the yarn contour center, establish a spatial coordinate system, and based on the spatial coordinate system, perform discrete derivation on the contour center of each yarn in each segmented image to construct a feature database;

[0056] The partitioning module is used to reconstruct a three-dimensional voxel model based on the feature database, perform meshing and insert cohesive force units based on a multi-material moving cube algorithm in the CGAL library, and simulate the separation and delamination of yarns under load;

[0057] The allocation module is used to define material properties for each component region feature based on the divided grid and allocate local material directions;

[0058] The calculation module is used to set boundary conditions and perform numerical simulation calculations.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The invention discloses a three-dimensional finite element model generation and numerical simulation method and system for XCT digital images of composite materials for water-related engineering, collects composite XCT images of initial state and preprocesses, performs statistical analysis on two-dimensional micro-structure parameters, generates virtual XCT images-virtual label images based on Pix2PixHD style transfer network to realize data enhancement, realizes accurate segmentation of each component inside the composite material based on Swin Transformer network, completes segmentation image contour feature extraction and smoothing based on the mapping relationship between pixels and nodes, constructs a spatial coordinate system and discretely derives all yarn center points of each segmented image, reconstructs the segmented three-dimensional model, performs grid division based on the multi-material moving cube algorithm of CGAL library, inserts global cohesion unit, defines material properties of each component, allocates local material direction, sets reasonable boundary conditions, and completes numerical simulation calculation. The invention can be used to accurately establish a three-dimensional finite element model of composite materials based on XCT images, helps to reduce the experimental cost in real situations, study its micro-structure damage evolution process and rupture state, master the mechanical properties of materials, and realize the rapid optimization design and application of material structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0062] Figure 1 A schematic diagram of a flow chart of a method for generating a three-dimensional finite element model and a numerical simulation method for XCT digital images of composite materials for water-related engineering according to an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of XCT image segmentation results based on deep learning according to an embodiment of the present invention;

[0064] Figure 3 A schematic diagram of a 3D finite element model generation process according to an embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of the size of the segmented sample and the mesh division results of each component inside it according to an embodiment of the present invention;

[0066] Figure 5 A schematic diagram of the generation results and boundary condition settings of a three-dimensional finite element model according to an embodiment of the present invention;

[0067] Figure 6 It is a schematic diagram of the simulation results of a three-dimensional finite element model of an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0070] Embodiment 1

[0071] like Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 and Figure 6 As shown, this embodiment provides a flow chart of a method for generating a three-dimensional finite element model and a numerical simulation method for XCT digital images of composite materials for water-related engineering, comprising the following steps:

[0072] S1: Acquire XCT images of basalt fiber composite materials in the initial state and perform manual segmentation;

[0073] S2: Perform parametric statistical analysis on the manually segmented images, quantify the microstructural parameters of the yarn inside the material and perform two-dimensional parametric random modeling to obtain parametric random modeling images;

[0074] S3: learning the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image;

[0075] S4: Accurate segmentation of each component region of real XCT images based on Swin-Tranformer network;

[0076] S5: Based on the segmented real XCT image, the contour microscopic features are extracted and the local contours are smoothed to build a yarn and pore feature database;

[0077] S6: Based on the yarn and pore feature database, extract the contour feature of each yarn in each segmented real XCT image, calculate the coordinate value of the yarn contour center, establish a spatial coordinate system, and based on the spatial coordinate system, perform discrete derivative of each yarn contour center of each segmented image to construct a feature database;

[0078] S7: Based on the feature database, a three-dimensional voxel model is reconstructed, and meshing and cohesive force units are inserted based on a multi-material moving cube algorithm in the CGAL library to simulate the yarn separation and delamination phenomenon under load;

[0079] S8: Based on the divided grid, define the material properties of each component region and assign local material directions;

[0080] S9: Set boundary conditions and perform numerical simulation calculations.

[0081] The specific implementation process of this embodiment is as follows:

[0082] S1, collecting an initial state XCT image of the composite material, and manually segmenting the image according to the internal component categories of the material based on the XCT image;

[0083] Specifically, the steps include:

[0084] Further preferably, S1 includes:

[0085] S11, acquiring complete XCT scan source image data, obtaining 1450 source images, appropriately cropping and filtering the source image data, and using a cropping tool to remove segmented images with blurred edge details;

[0086] S12, extracting one segmented image every 10 segmented images, manually marking each component in each extracted segmented image, and completely segmenting to obtain four components: resin base, warp yarn, weft yarn, and pores;

[0087] S13. Perform feature extraction on the annotated image set to obtain a true label set, which has 139 true label images in total.

[0088] S2. Perform parametric statistical analysis on the completed manually segmented images, quantify the microstructural parameters of the yarn inside the material and perform two-dimensional parametric random modeling;

[0089] Further preferably, S2 includes:

[0090] S21, extracting the meso-structural parameters such as yarn length and average width of each yarn in each segmented image based on the meso-structural features of the manually annotated dataset;

[0091] S22, qualitatively and quantitatively express the mesostructure characteristics, and use statistical methods to analyze the statistical results;

[0092] S23, based on the results of the parametric statistical analysis, the data set is expanded by parametric random modeling to generate a virtual data set;

[0093] The statistical analysis includes: statistical analysis of warp yarn geometric parameters and statistical analysis of weft yarn geometric parameters.

[0094] The method for statistical analysis of warp yarn geometric parameters is: to count the average width, width standard deviation, length and other information of the marked warp yarn area, calculate the centroid of each warp yarn, and read the distance between the centroids of each warp yarn to generate multiple warp yarns.

[0095] The method for statistical analysis of weft yarn geometric parameters is as follows: the ellipse is fitted by the fitellipse function in the OpenCV library, the weft yarn inclination angle is calculated, the farthest distance of each weft yarn in the image is manually marked and used as the long axis, the two intersection points of the straight line perpendicular to the long axis are calculated to calculate the length of the short axis, and the ratio of the long axis to the short axis is obtained. The collected data of each weft yarn is substituted into the ellipse representation equation with the same center, and the ratio of the actual radius of the pixel at each angle to the ideal radius is calculated to achieve the irregularity of the ellipse.

[0096] Statistical analysis of warp yarn geometric parameters and weft yarn geometric parameters: Use the fitter library to automatically search for the distribution supported by the scipy library for fitting, and automatically fit the mean width, standard deviation, length, etc. of the warp yarn, the major diameter, aspect ratio, inclination angle and other data of the weft yarn.

[0097] S3, the adversarial learning style transfer network Pix2PixHD learns the parameterized random modeling image to generate a virtual XCT image;

[0098] Further preferably, S3 includes:

[0099] S31, generating a warp yarn random model according to warp yarn parameterized statistical analysis;

[0100] S32, generating a weft yarn random model according to the weft yarn parameterized statistical analysis;

[0101] S33, generating an artificial synthetic label image based on the warp random model and the weft random model;

[0102] S34. Apply the improved Pix2PixHD network to generate basalt fiber composite images similar to the real mesostructure and construct a hybrid dataset.

[0103] The specific implementation method of S31 is:

[0104] First, a straight line is generated as its center line, and then the width of the center line is filled. The center line is divided equally by selecting 4 to 6 nodes in a straight line, including the upper and lower endpoints, and the nodes in the middle part are randomly offset. The maximum offset is selected by experience, and the generated points are fitted into a curve by spline interpolation, which is used as the center line. According to the length of the generated center line, a corresponding number of widths are generated, and 1-3 nodes are randomly selected from them. The generated widths are sorted according to the nodes, and the shape of the uneven width of the real warp yarn is approached in an ascending and descending staggered manner. At the same time, the tip part required by other categories is generated in this way. The generated curved irregular rectangle is subjected to random elastic deformation. Random elastic deformation randomly generates two matrices of the same size as the image, representing the horizontal and vertical position offsets of the coordinates of each pixel point, and smoothed by Gaussian filtering to make the matrix continuous, forming a coordinate offset matrix in two directions. The original coordinates of the image are applied with offsets in two different directions, and the grayscale values ​​of the original image coordinates are obtained by interpolation of the offset pixels, and an image is reconstructed to achieve the effect of random elastic deformation. In addition, the median filter method is used to remove the burrs generated during the width sorting process. Different types of warp yarns are arranged at a certain interval.

[0105] The specific implementation method of S32 is:

[0106] A basic elliptical shape is generated with the fitted minor axis length and major-minor axis ratio. Nodes are set with equal lengths on the circumference of the ellipse, and then offsets are generated for all nodes according to the fitted weft offsets, which are applied to the lengths of all nodes. Here, 720 nodes are collected during generation, and a special smoothing method is used to take the midpoints of adjacent nodes of the ellipse. After multiple smoothings, the entire ellipse is median filtered to eliminate burrs, and finally the ellipse is tilted according to the inclination angle generated by the fitting.

[0107] The specific implementation method of S33 is:

[0108] The original image size is used as the generated image size, and the upper and lower boundaries of the resin area are artificially limited. The warp yarn is generated first, and the warp yarn is arranged in position according to the generated spacing until the remaining width in the image cannot accommodate the next generated spacing and the warp yarn width. After that, the two ends of the warp yarn are selected as the lateral boundaries of the resin area. Then the weft yarn is generated, and the weft yarn is randomly selected for placement. The placement area is expanded upward and downward, and in this way, the shape of the truncated weft yarn on the boundary of the original image is generated. Then the overlap rate with the already placed fibers is calculated to decide whether to place the weft yarn. Finally, the placement of the weft yarn stops when the placement fails a certain number of times or the total fiber area of ​​the image reaches a certain level.

[0109] The specific implementation method of S34 is:

[0110] The Pix2PixHD network is a conditional generative adversarial network (cGAN). Through supervised learning, the generated image is more accurately similar to the input target image in grayscale distribution. Its main purpose is to train a generator G, pass the original image x through the generator network G to obtain a fake image G(x), and train a discriminator D at the same time. The generated fake image G(x) and the real image are input into the discriminator D. Through training, the features of the original image are similar to those of the generated image, so that the discriminator D cannot distinguish whether the image is forged. By changing the generation part of the Pix2PixHD network, the generation part can simultaneously train two generator models at different scales, and fuse the features of the two generator models at different scales. Based on the generator model after feature fusion, a fiber composite image with the same mesoscopic structure as the real one is generated. 120 pictures with good synthesis effects were manually selected from the 200 synthetic data sets to form a synthetic data set, and together with the original data set consisting of 139 pictures, they constitute the final data set. We randomly selected 15 images from the 139 original datasets as the validation set, and used the remaining 124 original datasets and 120 synthetic datasets to form the training set.

[0111] S4, based on the Swin-Tranformer network, accurate segmentation of XCT images is achieved, and the contour features between each component are clear;

[0112] Further preferably, S4 includes:

[0113] S41, input the mixed data set to the Swin-Tranformer network;

[0114] S42, dividing the image into different small blocks by pixels through a block division module, and then converting them into a one-dimensional feature vector;

[0115] S43, network model training, segmenting each component region in the image;

[0116] S44, completing region segmentation for each yarn based on a watershed segmentation algorithm;

[0117] The specific implementation method of S41 is:

[0118] The image with the size of 1119×1431 is randomly cropped to 448×448, and the image is horizontally flipped, vertically flipped, and rotated for data enhancement. The image is randomly cropped because the original image size is large. In order to reduce the amount of calculation and adapt to the Swin Transformer, the training speed is accelerated. Effective data enhancement can enhance the robustness of the model and prevent overfitting. Finally, the obtained image is input into the network for training.

[0119] The specific implementation method of S42 is:

[0120] The training images in the mixed data set are input into the network and processed by the block partitioning module to obtain pictures. The pictures are divided into different small blocks by pixels, the pixels of the small blocks on all channels are stretched into one-dimensional feature vectors, and all one-dimensional feature vectors are combined into a feature vector map.

[0121] The specific implementation method of S43 is:

[0122] The feature vector graph is processed in four stages to obtain four feature vector graphs at different scales, where each stage consists of block merging and Swin-Transformer Block. Swin-Transformer Block includes layer normalization layer, window multi-head self-attention layer, and multi-layer perception layer. Finally, the normalized category prediction probability of length 2 is obtained through the softmax function, which corresponds to pores, resin base, weft yarn, and warp yarn in the four channels. The channel with the highest prediction probability is determined as the corresponding category, thereby obtaining the semantic segmentation result map of the entire input image.

[0123] The specific implementation method of S44 is:

[0124] Based on the above semantic segmentation results, such as Figure 2 As shown in (a), the XCT image segmentation results are extracted along the warp and weft directions respectively, and the yarn is binarized, and the binarization result is used as the labeled image; secondly, the distance transform operation is performed on the binary image to obtain a distance transform map; finally, watershed segmentation is performed based on the map, the maximum value of the distance transform is used as the water injection point, and the binary image of the yarn is used as a mask to limit the segmentation area. Considering that the watershed segmentation effect of the long strip yarn is not ideal, the binary image of the weft needs to be extracted and processed along the weft laying direction. After the segmentation is completed, a small number of misclassified areas are manually corrected to obtain an example segmentation result, such as Figure 2 As shown in (b) in .

[0125] S5, based on the segmented XCT image, extract the contour microscopic features and smooth the local contour;

[0126] Further preferably, S5 includes:

[0127] S51, select a suitable resolution to downsample the image, retain the microscopic structural details as much as possible, and reduce the computing resource cost and the amount of calculation;

[0128] S52, performing feature screening on the downsampled image, filtering out a small portion of non-interested areas, and retaining necessary feature areas such as pores and yarns;

[0129] S53, extracting the image contour features of the pores and the yarns, and establishing a coordinate value conversion based on the positional relationship between pixels and nodes.

[0130] S54, setting a suitable convolution kernel, and utilizing the operation between the convolution kernel and the extracted contour coordinate values ​​to achieve contour smoothing, thereby avoiding stress concentration and error interruption that may occur during finite element numerical calculations.

[0131] S55. Process all segmented images according to the steps of S51-S54, construct a yarn and pore feature database, and store the contour coordinate values ​​of each component after the coordinate system transformation.

[0132] The specific implementation method of S51 is:

[0133] Based on the image that has completed the task of segmenting each component region, a secondary cropping is performed to remove the surrounding non-interested areas, and an image with a length and width of 1350×1725×1725 pixels and a resolution of 4.9819um is obtained. On the premise of retaining the detailed features of the microscopic structure as much as possible, the image is downsampled by taking one pixel every 5 pixels along the length, width and thickness directions, and an image of 270×345×345 pixels and a resolution of 24.9095um is obtained by integration, thereby reducing the number of pixels that can be processed and reducing the cost of computing resources.

[0134] The specific implementation method of S52 is:

[0135] Due to the geometric characteristics of the yarn itself, it is inevitable that the yarn itself has a high degree of discreteness in the segmented image. In a single image, the characteristics of a single yarn are distributed in multiple areas. Therefore, the contourArea function in the OpenCV library is used to filter small areas composed of multiple fibers. By setting the screening threshold to 10, the area smaller than the fixed threshold will not be considered, and only the regional features of the yarn with a larger area will be retained.

[0136] The specific implementation method of S53 is:

[0137] The findContours function in the OpenCV library is used to extract the pixel coordinate value information of the contour of each yarn and pore, and the information is converted according to the positional relationship between the pixel and the node. In addition, considering that the coordinate system in the OpenCV library is different from the coordinate system of Abaqus2021, the node coordinate values ​​converted from the pixel contour coordinate values ​​need to be converted into a coordinate system to ensure that the segmented image and the constructed two-dimensional finite element model are highly consistent in the microstructure.

[0138] The specific implementation method of S54 is:

[0139] The extracted contour feature information of each component is processed twice, and a suitable convolution kernel is set. When the local contour coordinate values ​​vary greatly, contour smoothing is achieved by creating additional nodes.

[0140] The specific implementation method of S55 is:

[0141] The contour coordinate value information of each yarn and pore in each segmented image is obtained along the X-axis and Y-axis directions respectively, and the S51-S54 operations are repeated. For each segmented image, a corresponding json file is created to store the information in a dictionary form in the python language to build a feature database.

[0142] S6, extracting contour features of each yarn in each segmented image, calculating the coordinate value of the center of the yarn contour, establishing a spatial coordinate system, and performing discrete derivation of the center of the contour of each yarn in each segmented image;

[0143] Further preferably, S6 includes:

[0144] S61. Extract the coordinate value of the center point of each yarn contour in each segmented image from the feature database, and establish a spatial coordinate system in the order of the segmented images.

[0145] S62. Use the first-order intermediate differential law to perform discrete differentiation on the center point of each yarn contour in each segmented image to obtain the tangent direction of the center point, that is, the 1 direction of the yarn.

[0146] S63. Direction 2 can be obtained from direction 1 obtained by calculation.

[0147] The specific implementation method of S61 is:

[0148] Considering that the segmented image is converted into a finite element model and a single yarn is transversely isotropic, a local material orientation allocation algorithm is proposed to consider the influence of fiber orientation on mechanical properties. The contour feature coordinate value information of each yarn is extracted from the feature database along the X-axis and Y-axis directions respectively, and a spatial coordinate system is established in the order of the segmented images. Assuming that the distance between adjacent segmented images is i*4.9819um, the contour feature coordinate value information of all yarns is mapped to the constructed spatial coordinate system.

[0149] The specific implementation method of S62 is:

[0150] Statistical calculation of the center point of the i-th yarn section Statistical analysis is performed on the warp or weft center points of each cross-sectional image in different directions, and then the discrete derivative of each center point is solved to obtain the value of each cross-sectional image. or direction.

[0151]

[0152] Where i is the segmented image number, v represents the XCT image resolution, T is the pixel length on the Y or Z axis, and p it is the corresponding grayscale value of pixel t on the i-th yarn cross section, and are the corresponding Y-axis and Z-axis coordinates of pixel t on the i-th yarn cross section, It corresponds to The partial derivative solution on the yarn cross section, h is the corresponding solution step size.

[0153] The specific implementation method of S63 is:

[0154] Since the yarn is transversely anisotropic, the main direction is direction 1, and directions 2 and 3 can meet the requirements as long as they are perpendicular to direction 1, that is, the sum of the products of the corresponding components in each direction is equal to 0. Therefore, the component of direction 2 on the X-axis is defined as 0, and the component of direction 2 can be calculated. At the same time, the calculated discrete derivative value results are stored in the feature database.

[0155]

[0156] S7, meshing and inserting cohesive elements based on the multi-material moving cube algorithm in the CGAL library;

[0157] Further preferably, S7 includes:

[0158] S71. Based on S52, the preprocessed XCT image is imported into Avizo software to complete the three-dimensional voxel model reconstruction, and an inr file is exported;

[0159] S72. Use the multi-material moving cube algorithm based on the CGAL library to perform mesh division and insert cohesive force units to obtain a mesh file.

[0160] S73. Use python script to convert into inp file that can be imported by Abaqus.

[0161] The specific implementation method of S72 is:

[0162] First, the 3D model is downsampled to a resolution of 24.9095um to reduce the amount of calculation. By extracting the intersection edges of different components in the 3D reconstruction results, the boundary features of the intersection edges are used as one-dimensional line features, and the line features are smoothed. Secondly, based on the voxel model, the voxel outer surfaces of different components are used for Delaunay triangulation to generate surface triangular meshes and re-divide the surface mesh. The classic Laplacian smoothing algorithm is used to process non-manifold areas to avoid self-intersection and sharp dihedral angles. Finally, the line features are added to the re-divided surface mesh, and the closed surface triangular mesh is divided into a tetrahedral mesh (C3D4). According to the node sharing relationship of the surface triangular mesh generated on the intersection edges of the mutually contacting components, the global zero-thickness cohesion unit (COH3D6) is inserted. Finally, the voxel 3D model is converted into a mesh model to obtain a mesh file, such as Figure 4 shown.

[0163] The specific implementation method of S73 is:

[0164] The mesh file contains various information such as nodes and node coordinates of the divided units. However, this file format cannot be directly imported into Abaqus software for further processing. By analyzing the data format files between the mesh file and the inp file, a python script is written to read the relevant information of each unit in the mesh file and convert it according to the format of the inp file.

[0165] S8, define material properties for each component region feature and assign local material directions;

[0166] Further preferably, S8 includes:

[0167] S81. Define the material properties and mechanical response characteristics of each component region.

[0168] S82. The local material direction calculated by S6 is gradually assigned to each unit of each yarn.

[0169] Accurately define material properties, such as density of each component material, material modulus, and Poisson's ratio, and select appropriate material damage constitutive model. For each yarn in the model, obtain the corresponding discrete derivative results from the S63 feature database, calculate the distance from the centroid of each unit to the discrete points on all segmented images, and select the directional derivative component on the discrete points with the shortest distance as the local material directional property of the unit.

[0170]

[0171] Among them, x ijk ,y ijk 、z ijkThey correspond to the X-axis, Y-axis, and Z-axis coordinate values ​​of the k-th node of the j-th unit on the ith yarn, respectively. They correspond to the X-axis, Y-axis, and Z-axis coordinate values ​​of the center of mass of the j-th unit on the ith yarn, respectively.

[0172] S9. Set reasonable boundary conditions and perform numerical simulation calculations;

[0173] The specific implementation method of S9 is:

[0174] Abaqus2021 software was used to apply displacement conditions (U1=0, U2=-0.24, U3=0, UR1=0, UR2=0, UR3=0) to the upper movable platform to simulate the continuous loading process of the sample in the vertical direction. At the same time, full constraint conditions (U1=0, U2=0, U3=0, UR1=0, UR2=0, UR3=0) were applied to the fixed platform below to ensure that the sample was subjected to compression effects, such as Figure 5 The numerical simulation results of the three-dimensional finite element model of composite materials generated by this algorithm are shown in Figure 6 shown.

[0175] Embodiment 2

[0176] The present invention also discloses a three-dimensional finite element model generation and numerical simulation method system for XCT digital images of composite materials of water-related engineering, which is characterized by comprising: an acquisition module, a modeling module, a learning module, a precise segmentation module, a first database construction module, a second database construction module, a partitioning module, an allocation module, a simulation module and a calculation module;

[0177] The acquisition module is used to acquire XCT images of basalt fiber composite materials in the initial state and perform manual segmentation;

[0178] The modeling module is used to perform parametric statistical analysis on the manually segmented images, quantify the microscopic structural parameters of the yarn inside the material, and perform two-dimensional parametric random modeling to obtain parametric random modeling images;

[0179] The learning module is used to learn the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image;

[0180] The precise segmentation module is used to achieve precise segmentation of each component area of ​​real XCT images based on the Swin-Tranformer network;

[0181] The first database construction module is used to extract contour microscopic features and smooth local contours based on the segmented real XCT image to build a yarn and pore feature database;

[0182] The second database construction module is used to extract the contour features of each yarn in each segmented image based on the yarn and pore feature database, calculate the coordinate value of the center of the yarn contour, establish a spatial coordinate system, and perform discrete derivative of the center of the yarn contour in each segmented image based on the spatial coordinate system to construct a feature database;

[0183] The partitioning module is used to reconstruct the three-dimensional voxel model based on the feature database and perform mesh partitioning based on the multi-material marching cube algorithm in the CGAL library;

[0184] The allocation module is used to define the material properties of each component region feature and allocate local material directions based on the divided grid;

[0185] The simulation module is used to insert cohesion elements based on the assigned local material direction to simulate the yarn separation and delamination phenomenon under load;

[0186] The calculation module is used to set boundary conditions and perform numerical simulation based on the simulated yarn load separation and delamination phenomena.

[0187] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A three-dimensional finite element model generation and numerical simulation method for XCT digital images of composite materials in water-related engineering, characterized in that: The following steps are involved: S1: Collect the real XCT images of basalt fiber composite in the initial state and perform manual segmentation; S2: Perform parametric statistical analysis on the manually segmented images, quantify the microstructural parameters of the yarn inside the material and perform two-dimensional parametric random modeling to obtain parametric random modeling images; S3: learning the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image; S4: Based on the Swin-Tranformer network and virtual XCT images, accurate segmentation of each component region of real XCT images is achieved; S5: Based on the segmented real XCT image, the contour microscopic features are extracted and the local contours are smoothed to build a yarn and pore feature database; S6: Based on the yarn and pore feature database, extract the contour feature of each yarn in each segmented real XCT image, calculate the coordinate value of the center of the yarn contour, establish a spatial coordinate system, and based on the spatial coordinate system, perform discrete derivation on the center of the contour of each yarn in each segmented image to construct a feature database; S7: Based on the feature database, a three-dimensional voxel model is reconstructed, and meshing and cohesive force units are inserted based on a multi-material moving cube algorithm in the CGAL library to simulate the separation and delamination of yarns under load; S8: Based on the divided grid, define the material properties of each component region and assign local material directions; S9: Set boundary conditions and perform numerical simulation calculations.

2. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S3, the method of learning the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image includes: S31: generating a warp yarn random model based on warp yarn parameterized statistical analysis; S32: Generate a weft yarn random model based on weft yarn parameterized statistical analysis; S33: generating an artificial synthetic label image based on the warp yarn random model and the weft yarn random model; S34: Based on the artificially synthesized label image, an improved Pix2PixHD network is applied to generate a virtual image of a basalt fiber composite material similar to a real mesostructure, and a mixed data set, i.e., a real-virtual XCT image, is constructed.

3. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S4, the method for realizing accurate segmentation of each component region of a real XCT image based on a Swin-Tranformer network includes: S41: Input the mixed data set to the Swin-Tranformer network to obtain training images; S42: dividing the training image into different small blocks by pixels through a block division module, and then converting the training image into a one-dimensional feature vector image; S43: Accurately segment each component region in the one-dimensional feature vector image to obtain a semantic segmentation result image; S44: Based on the semantic segmentation result map, a watershed segmentation algorithm is used to complete region segmentation for each yarn.

4. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S5, based on the segmented real XCT image, the method of extracting contour microscopic features and smoothing the local contour to construct a yarn and pore feature database includes: S51: Selecting a resolution that meets preset requirements to downsample the segmented real XCT image; S52: performing feature screening on the real XCT image after downsampling; S53: based on the real XCT image after feature screening, extracting the image contour features of the pores and the yarn, and converting the coordinate values ​​according to the positional relationship between the pixels and the nodes to obtain the contour coordinate values; S54: setting a convolution kernel that meets preset requirements, and realizing contour smoothing by using an operation between the convolution kernel and the contour coordinate value; S55: Process all segmented images according to S51-S54, build a yarn and pore feature database, and store the contour coordinate values ​​of each component after the coordinate system is transformed.

5. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S6, based on the yarn and pore feature database, the contour feature of each yarn in each segmented image is extracted, the coordinate value of the center of the yarn contour is calculated, a spatial coordinate system is established, and based on the spatial coordinate system, the method for performing discrete derivation of the center of the contour of each yarn in each segmented image includes: S61: extracting the coordinate value of the center point of each yarn contour in each segmented image from the yarn and pore feature database, and establishing a spatial coordinate system in the order of the segmented images; S62: Based on the spatial coordinate system, use the first-order intermediate differential law to perform discrete derivative on the center point of each yarn contour in each segmented image to obtain the tangent direction of the center point, that is, the 1 direction of the yarn; S63: Obtain direction 2 from direction 1 obtained by calculation.

6. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S7, based on the feature database, a three-dimensional voxel model is reconstructed, and a method for meshing based on a multi-material marching cube algorithm in a CGAL library includes: S71: Based on the feature database, the segmented XCT image is imported into Avizo 2019.1 software to complete the three-dimensional voxel model reconstruction, and an inr file is exported; S72: Mesh the reconstructed 3D voxel model using the multi-material marching cube algorithm based on the CGAL library to obtain a mesh file; S73: Use a python script to convert the mesh file into an inp file that can be imported into Abaqus.

7. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S72, the method of meshing the reconstructed three-dimensional voxel model based on the multi-material marching cube algorithm of the CGAL library to obtain the mesh file includes: Downsample the reconstructed 3D voxel model and extract the intersection edges of different components, use the boundary features of the intersection edges as one-dimensional line features, and perform smoothing operations on the one-dimensional line features; Delaunay triangulation is performed using the outer surfaces of voxels of different components to generate surface triangular meshes and then the surface triangular meshes are re-divided. The classic Laplacian smoothing algorithm is used to process non-manifold areas to avoid self-intersections and sharp dihedral angles. The one-dimensional line feature is added to the re-divided surface triangular mesh, and the interior of the closed surface triangular mesh is divided into a tetrahedral mesh C3D4. According to the node sharing relationship of the surface triangular mesh generated on the intersecting edges of the mutually contacting components, the global zero-thickness cohesion unit COH3D6 is inserted, and finally the reconstructed three-dimensional voxel model is converted into a mesh model to obtain a mesh file.

8. The method for generating a three-dimensional finite element model and numerical simulation of XCT digital images of composite materials for water-related engineering according to claim 1 is characterized in that: In S8, based on the divided grids, the material properties of each component region feature are defined, and the method for allocating the local material direction includes: S81: Define the material properties and mechanical response characteristics of each component region; S82: The calculated local material direction is gradually assigned to each unit of each yarn.

9. A three-dimensional finite element model generation and numerical simulation system for XCT digital images of composite materials in water-related engineering, characterized in that: include: An acquisition module, a modeling module, a learning module, a precise segmentation module, a first database construction module, a second database construction module, a partitioning module, an allocation module, a simulation module, and a calculation module; The acquisition module is used to acquire the real XCT image of the basalt fiber composite material in the initial state and perform manual segmentation; The modeling module is used to perform parametric statistical analysis on the manually segmented image, quantify the microscopic structural parameters of the yarn inside the material and perform two-dimensional parametric random modeling to obtain a parametric random modeling image; The learning module is used to learn the parameterized random modeling image based on the adversarial learning style transfer network Pix2PixHD to generate a virtual XCT image; The precise segmentation module is used to achieve precise segmentation of each component region of a real XCT image based on a Swin-Tranformer network and a virtual XCT image; The first database construction module is used to extract contour microscopic features and smooth local contours based on the segmented real XCT image to construct a yarn and pore feature database; The second database construction module is used to extract the contour features of each yarn in each segmented real XCT image based on the yarn and pore feature database, calculate the coordinate value of the yarn contour center, establish a spatial coordinate system, and based on the spatial coordinate system, perform discrete derivation on the contour center of each yarn in each segmented image to construct a feature database; The partitioning module is used to reconstruct a three-dimensional voxel model based on the feature database, perform meshing and insert cohesive force units based on a multi-material moving cube algorithm in the CGAL library, and simulate the separation and delamination of yarns under load; The allocation module is used to define material properties for each component region feature based on the divided grid and allocate local material directions; The calculation module is used to set boundary conditions and perform numerical simulation calculations.

Images