A method for generating a feature grid of plastic parts based on machine learning

Abstract

The present invention discloses a method for generating feature meshes of plastic parts based on machine learning, which relates to the technical field of mesh generation. The method comprises the following steps: importing existing 3D model data of plastic parts of different categories into CloudCompare to obtain corresponding point cloud data; performing feature extraction and classification identification on the obtained point cloud data to obtain corresponding point cloud implicit geometric features and classification results; performing similarity matching between the obtained point cloud implicit geometric features and classification results and data samples in a retrieval database, and outputting the corresponding plastic part feature mesh according to the similarity matching result; obtaining point cloud data from a CAD file, outputting the point cloud implicit geometric features and classification results in combination with a deep learning network, searching in a retrieval database according to the point cloud implicit geometric features and classification results to output a mesh, thereby realizing the generation of plastic part meshes based on machine learning and improving the efficiency of plastic part mesh generation.

Description

Technical Field

[0001] The present invention relates to the technical field of grid generation, and in particular to a method for generating characteristic grids of plastic parts based on machine learning. Background Art

[0002] Plastic part simulation plays a crucial role in automotive R&D, providing strong technical support for lightweighting, material selection, structural design, molding process optimization, and performance testing. Plastic part simulation is a complex and time-consuming process, encompassing multiple steps: geometric preprocessing, mid-surface extraction, mesh generation, mesh optimization, material property assignment, boundary condition and load application, and finally, simulation analysis and result evaluation. Mesh generation is the most fundamental and critical preparatory step, representing a significant portion of R&D workload, and mesh quality significantly impacts simulation results. Therefore, improving the efficiency of plastic part mesh generation is an urgent need. For a long time, mesh generation for plastic parts has relied primarily on manual operations. Although the mid-surface mesh generation functions of current mainstream commercial software can provide preliminary meshing, the generated meshes often fail to fully meet analytical and computational requirements, and extensive manual optimization and adjustment are still required. Improving the efficiency of outputting mesh features for plastic parts is a challenge. To this end, we present a machine learning-based method for generating feature meshes for plastic parts. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for generating feature grids of plastic parts based on machine learning.

[0004] The object of the present invention can be achieved by the following technical solution: A method for generating a feature grid of a plastic part based on machine learning, comprising the following steps:

[0005] Step S1: Import existing 3D model data of plastic parts of different categories into CloudCompare to obtain corresponding point cloud data;

[0006] Step S2: performing feature extraction and classification recognition on the obtained point cloud data to obtain the corresponding point cloud implicit geometric features and classification results;

[0007] Step S3: performing similarity matching on the obtained implicit geometric features and classification results of the point cloud and the data samples in the retrieval database, and outputting the corresponding plastic part feature mesh according to the similarity matching results.

[0008] Furthermore, the plastic part 3D model data is a CAD file containing a 3D model of the plastic part, and each CAD file is associated with a corresponding plastic part category and mesh data, wherein the mesh data includes a mesh type and a mesh density;

[0009] After the CAD file is input into CloudCompare, the point density and point quantity of the point cloud data are set in CloudCompare to obtain point cloud data corresponding to different categories of plastic parts.

[0010] Furthermore, the process of performing feature extraction and classification recognition on the obtained point cloud data to obtain the corresponding point cloud implicit geometric features and classification results includes:

[0011] The point cloud data output by CloudCompare is classified and summarized according to the category of plastic parts to obtain the corresponding point cloud dataset;

[0012] The obtained point cloud dataset is divided into a base dataset and an incremental dataset;

[0013] Build a classification network model, set the base class task, train the classification network model with the base class data set, obtain the corresponding base class classification network model, input the test set into the trained base class classification network model, obtain the corresponding point cloud implicit geometric features and classification results, and complete the base class task;

[0014] Set a few-sample classification incremental learning task, and perform sample incremental learning on the set base class classification network model through the incremental data set according to the set few-sample classification incremental learning task.

[0015] Furthermore, the classification network model is trained using the base class data set to obtain the corresponding base class classification network model. The process includes:

[0016] The obtained point cloud data is projected from multiple perspectives to obtain point cloud view images from different perspectives;

[0017] Input the multi-view point cloud view image into the visual encoder of the pre-trained model CLIP and output the initial encoding features;

[0018] The initial coding features corresponding to the obtained point cloud view images of different perspectives are spliced together, and the spliced initial coding features are input into a two-layer MLP network to obtain the corresponding global image features;

[0019] Input the point cloud data into the 3D network, map the output of the 3D network through a two-layer MLP network to obtain the corresponding 3D features;

[0020] Fusing the obtained 3D features with the global image features to obtain implicit geometric features of the point cloud and simultaneously obtain text features of the point cloud data;

[0021] Generate corresponding text prompts based on the plastic part category corresponding to the point cloud data, and extract features from the generated text prompts through the text encoder of the CLIP model to obtain corresponding text features;

[0022] Calculating similarity between the obtained implicit geometric features of the point cloud and the text features to obtain similarity values between the point cloud data and each plastic part category, and outputting the plastic part category corresponding to the maximum similarity value as the predicted classification result;

[0023] The corresponding loss function is obtained based on the predicted classification results and the actual plastic part category. The base class classification network model is updated based on the obtained loss function, and the above operation is repeated iteratively.

[0024] Furthermore, the process of sample incremental learning of the classification network model includes:

[0025] Setting a few-shot classification incremental learning task, wherein the few-shot classification incremental learning task includes n learning stages, and each learning stage is numbered as i, where i = 1, 2, ..., n;

[0026] Set corresponding training sets and test sets for each learning stage;

[0027] Training the classification network model in sequence using the training set corresponding to the learning stage according to the learning stage corresponding to the label sequence;

[0028] Input the training set of the learning stage corresponding to label i=1 into the trained base class classification network model, and then evaluate the training results of the base class classification network model using the test set corresponding to the learning stage, thus completing the learning process of the learning stage with label i=1;

[0029] Input the training set corresponding to the learning stage corresponding to label i=2 into the base class classification network model that has completed the learning process of the learning stage labeled i=1, and evaluate the training results of the base class classification network model using the test sets corresponding to the learning stages labeled i=1 and label i=2, thus completing the learning process of the learning stage labeled i=2;

[0030] The training set corresponding to the learning stage corresponding to label i=3 is input into the base class classification network model that completes the learning process of the learning stage labeled i=2, and the training results of the base class classification network model are evaluated through the test sets corresponding to the learning stages labeled i=1, i=2 and i=3, completing the learning process of the learning stage labeled i=3, and so on, until all learning stages are completed.

[0031] Furthermore, the obtained implicit geometric features and classification results of the point cloud are matched with the data samples in the retrieval database for similarity, and the process of outputting the corresponding plastic part feature mesh according to the similarity matching results includes:

[0032] Building a retrieval database and importing sample data of different plastic part categories into the retrieval database, wherein the sample data includes candidate categories, candidate features, and grid data;

[0033] Input the obtained implicit geometric features of the point cloud and the classification results into the retrieval database, match the classification results with the candidate categories, determine the corresponding retrieval range based on the matching results, and filter the sample data corresponding to the classification results based on the retrieval range;

[0034] The implicit geometric features of the point cloud are then compared with the candidate features in the screened sample data to obtain the corresponding cosine similarity. The candidate feature corresponding to the maximum value of the cosine similarity is used as the matching result, and the mesh data corresponding to the matched candidate feature is output as the plastic part feature mesh.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] By obtaining point cloud data from CAD files and combining it with the deep learning network to output the implicit geometric features and classification results of the point cloud, the mesh is output by searching in the retrieval database based on the implicit geometric features and classification results of the point cloud. This realizes a plastic part mesh generation solution based on machine learning and improves the efficiency of plastic part mesh generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0038] Figure 1 This is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0039] like Figure 1 As shown, a method for generating a feature mesh of a plastic part based on machine learning includes the following steps:

[0040] Step S1: Import existing 3D model data of plastic parts of different categories into CloudCompare to obtain corresponding point cloud data;

[0041] Step S2: performing feature extraction and classification recognition on the obtained point cloud data to obtain the corresponding point cloud implicit geometric features and classification results;

[0042] Step S3: performing similarity matching on the obtained implicit geometric features and classification results of the point cloud and the data samples in the retrieval database, and outputting the corresponding plastic part feature mesh according to the similarity matching results.

[0043] It should be further explained that, in a specific implementation process, the 3D model data of the plastic part is a CAD file containing a 3D model of the plastic part, and each CAD file is associated with a corresponding plastic part category. For CAD files of different plastic part categories, corresponding mesh types and mesh densities are set according to requirements to obtain corresponding mesh data;

[0044] After setting the point density and number of points in CloudCompare, the point cloud data corresponding to different categories of plastic parts is output.

[0045] It should be further explained that, in the specific implementation process, the process of extracting features and classifying the obtained point cloud data to obtain the corresponding point cloud implicit geometric features and classification results includes:

[0046] The point cloud data output by CloudCompare is classified and summarized according to the category of plastic parts to obtain the corresponding point cloud dataset;

[0047] The obtained point cloud dataset is divided into a base class dataset and an incremental dataset. It should be further explained that, in the specific implementation process, a data volume threshold is set. If the number of point cloud data in the point cloud dataset reaches the data volume threshold, the point cloud dataset is recorded as the base class dataset. Otherwise, the point cloud dataset is recorded as the incremental dataset.

[0048] Build a classification network model, set base class tasks and few-sample classification incremental learning tasks for the classification network model, and use the incremental dataset to perform sample incremental learning on the classification network model through the set few-sample classification incremental learning tasks;

[0049] The classification network model is trained by the set base class task and the base class dataset to obtain the corresponding base class classification network model. The test set is input into the trained base class classification network model to obtain the corresponding point cloud implicit geometric features and classification results, thus completing the base class task.

[0050] It should be further explained that, in the specific implementation process, the classification network model that completes the sample incremental learning task is trained using the base class dataset to obtain the corresponding base class classification network model. The process includes:

[0051] The obtained point cloud data is projected from multiple perspectives to obtain point cloud view images from different perspectives. The point cloud view images from different perspectives are aggregated to obtain the corresponding global image features. The specific process is as follows:

[0052] Input the multi-view point cloud view image into the visual encoder of the pre-trained model CLIP and output the initial encoding feature, denoted as F 2D ;

[0053] The initial coding features corresponding to the point cloud view images obtained from different perspectives are spliced together, and the spliced initial coding features are input into the two-layer MLP network to obtain the corresponding global image features, which are recorded as f d ;

[0054]

[0055] in, Represent the first-layer MLP network and the second-layer MLP network respectively;

[0056] The point cloud data is input into the 3D network and mapped through the two-layer MLP network to obtain the corresponding 3D features. The specific process includes:

[0057] Input the point cloud data into the 3D network and record the output of the 3D network as f 3D ;

[0058] The output of the 3D network is mapped through a two-layer MLP network to obtain the corresponding 3D features, and the 3D features obtained by the MLP network mapping are recorded as f p ;

[0059] in,

[0060] in Represent the first-layer MLP network and the second-layer MLP network respectively;

[0061] The obtained 3D features are fused with the global image features to obtain the implicit geometric features of the point cloud, and the text features of the point cloud data are obtained at the same time. The obtained implicit geometric features of the point cloud are recorded as f g ;

[0062] in,

[0063] Among them, max() means finding the maximum value, and avg() means finding the average value;

[0064] Generate corresponding text prompts according to the plastic part category corresponding to the point cloud data, and extract features of the generated text prompts through the text encoder of the CLIP model to obtain the corresponding text features, which are recorded as F t ;

[0065] Calculating similarity between the obtained implicit geometric features of the point cloud and the text features to obtain similarity values between the point cloud data and each plastic part category, outputting the plastic part category corresponding to the maximum similarity value as the predicted classification result, and recording the similarity value as L;

[0066] Where, L = cos(fg , F t );

[0067] The maximum value of the obtained similarity values is used as the output of the plastic part category, and the output result is recorded as p;

[0068] Where p = softmax([L]);

[0069] The corresponding loss function is obtained based on the predicted classification results and the actual plastic part category. The base class classification network model is updated based on the obtained loss function. The above operation is repeated iteratively, where the number of iterations is 100.

[0070] The loss function is recorded as Loss cls =L ce (p, y);

[0071] Among them, L ce () represents the cross entropy loss function, and y is the true category corresponding to the point cloud data.

[0072] It should be further explained that, in the specific implementation process, the process of sample incremental learning of the classification network model includes:

[0073] Setting a few-shot classification incremental learning task, wherein the few-shot classification incremental learning task includes n learning stages, and each learning stage is numbered as i, where i = 1, 2, ..., n;

[0074] For each learning stage, set the corresponding training set and test set. The training set and test set corresponding to the learning stage labeled i are respectively recorded as and

[0075] Training the classification network model in sequence using the training set corresponding to the learning stage according to the learning stage corresponding to the label sequence;

[0076] Input the training set of the learning stage corresponding to label i=1 into the trained base class classification network model, and then evaluate the training results of the base class classification network model using the test set corresponding to the learning stage, thus completing the learning process of the learning stage with label i=1;

[0077] Input the training set corresponding to the learning stage corresponding to label i=2 into the classification network model that completes the learning process of the learning stage labeled i=1, and evaluate the training results of the classification network model using the test sets corresponding to the learning stages labeled i=1 and label i=2, thereby completing the learning process of the learning stage labeled i=2;

[0078] The training set corresponding to the learning stage corresponding to label i=3 is input into the classification network model that completes the learning process of the learning stage labeled i=2, and the training results of the classification network model are evaluated through the test sets corresponding to the learning stages labeled i=1, i=2 and i=3, completing the learning process of the learning stage labeled i=3, and so on, until all learning stages are completed.

[0079] It should be further explained that, in the specific implementation process, the obtained implicit geometric features and classification results of the point cloud are matched with the data samples in the retrieval database for similarity, and the process of outputting the corresponding plastic part feature mesh based on the similarity matching results includes:

[0080] Building a retrieval database and importing sample data of different plastic part categories into the retrieval database, wherein the sample data includes candidate categories and candidate features;

[0081] Input the obtained implicit geometric features of the point cloud and the classification results into the retrieval database, match the classification results with the candidate categories, determine the corresponding retrieval range based on the matching results, and filter the sample data corresponding to the classification results based on the retrieval range;

[0082] The implicit geometric features of the point cloud are then compared with the candidate features in the screened sample data to obtain the corresponding cosine similarity. The candidate feature corresponding to the maximum value of the cosine similarity is used as the matching result, and the mesh data corresponding to the matched candidate feature is output as the plastic part feature mesh.

[0083] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any modification or equivalent replacement of the above embodiments made according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A method for generating feature meshes for plastic parts based on machine learning, characterized in that: The following steps are involved: Step S1: Import existing 3D model data of plastic parts of different categories into CloudCompare to obtain corresponding point cloud data; Step S2: Extract features and classify the obtained point cloud data to obtain the corresponding point cloud implicit geometric features and classification results. The process includes: The point cloud data output by CloudCompare is classified and summarized according to the category of plastic parts to obtain the corresponding point cloud dataset; The obtained point cloud dataset is divided into a base dataset and an incremental dataset; Build a classification network model, set the base class task, train the classification network model with the base class data set, obtain the corresponding base class classification network model, input the test set into the trained base class classification network model, obtain the corresponding point cloud implicit geometric features and classification results, and complete the base class task; Set a few-sample classification incremental learning task, and perform sample incremental learning on the set base class classification network model through the incremental dataset according to the set few-sample classification incremental learning task; The process of training the classification network model through the base class dataset to obtain the corresponding base class classification network model includes: The obtained point cloud data is projected from multiple perspectives to obtain point cloud view images from different perspectives; Input the multi-view point cloud view image into the visual encoder of the pre-trained model CLIP and output the initial encoding features; The initial coding features corresponding to the obtained point cloud view images of different perspectives are spliced together, and the spliced initial coding features are input into a two-layer MLP network to obtain the corresponding global image features; Input the point cloud data into the 3D network, map the output of the 3D network through a two-layer MLP network to obtain the corresponding 3D features; Fusing the obtained 3D features with the global image features to obtain implicit geometric features of the point cloud and simultaneously obtain text features of the point cloud data; Generate corresponding text prompts based on the plastic part category corresponding to the point cloud data, and extract features from the generated text prompts through the text encoder of the CLIP model to obtain corresponding text features; Calculating similarity between the obtained implicit geometric features of the point cloud and the text features to obtain similarity values between the point cloud data and each plastic part category, and outputting the plastic part category corresponding to the maximum similarity value as the predicted classification result; Obtain the corresponding loss function based on the predicted classification results and the actual plastic part category, update the base class classification network model based on the obtained loss function, and iterate and repeat the above operations Step S3: performing similarity matching on the obtained implicit geometric features and classification results of the point cloud and the data samples in the retrieval database, and outputting the corresponding plastic part feature mesh according to the similarity matching results.

2. The method for generating feature mesh of plastic parts based on machine learning according to claim 1, characterized in that: The plastic part 3D model data is a CAD file containing a 3D model of the plastic part, and each CAD file is associated with a corresponding plastic part category and mesh data, wherein the mesh data includes a mesh type and a mesh density; After the CAD file is input into CloudCompare, the point density and point quantity of the point cloud data are set in CloudCompare to obtain point cloud data corresponding to different categories of plastic parts.

3. The method for generating feature mesh of plastic parts based on machine learning according to claim 2, characterized in that: The process of sample incremental learning of the classification network model includes: Setting a few-shot classification incremental learning task, wherein the few-shot classification incremental learning task includes n learning stages, and each learning stage is numbered as i, where i=1, 2, ..., n; Set corresponding training sets and test sets for each learning stage; Training the classification network model in sequence using the training set corresponding to the learning stage according to the learning stage corresponding to the label sequence; The training set of the learning stage corresponding to label i=1 is input into the trained base class classification network model, and then the training results of the base class classification network model are evaluated using the test set corresponding to the learning stage, completing the learning process of the learning stage with label i=1; Input the training set corresponding to the learning stage corresponding to label i=2 into the base class classification network model that has completed the learning process of the learning stage labeled i=1, and evaluate the training results of the base class classification network model using the test sets corresponding to the learning stages labeled i=1 and i=2, thus completing the learning process of the learning stage labeled i=2; The training set corresponding to the learning stage corresponding to label i=3 is input into the base class classification network model that completes the learning process of the learning stage labeled i=2, and the training results of the base class classification network model are evaluated through the test sets corresponding to the learning stages labeled i=1, i=2 and i=3, completing the learning process of the learning stage labeled i=3, and so on, until all learning stages are completed.

4. The method for generating feature mesh of plastic parts based on machine learning according to claim 3, characterized in that: The process of performing similarity matching on the obtained implicit geometric features and classification results of the point cloud and the data samples in the retrieval database and outputting the corresponding plastic part feature mesh according to the similarity matching results includes: Building a retrieval database and importing sample data of different plastic part categories into the retrieval database, wherein the sample data includes candidate categories, candidate features, and grid data; Input the obtained implicit geometric features of the point cloud and the classification results into the retrieval database, match the classification results with the candidate categories, determine the corresponding retrieval range based on the matching results, and filter the sample data corresponding to the classification results based on the retrieval range; The implicit geometric features of the point cloud are then compared with the candidate features in the screened sample data to obtain the corresponding cosine similarity. The candidate feature corresponding to the maximum value of the cosine similarity is used as the matching result, and the mesh data corresponding to the matched candidate feature is output as the plastic part feature mesh.

Images