Skylight front and rear column foam automatic profiling attachment optimization method for data modeling

Abstract

The invention discloses a skylight front and rear column foam automatic profiling attachment optimization method based on data modeling, and relates to the technical field of column foam attachment, and the method comprises the steps: obtaining a three-dimensional shape data set of a target skylight front and rear column under multiple view angles, and carrying out the denoising processing and coordinate conversion, and obtaining a skylight front and rear column shape space data set; carrying out three-dimensional reconstruction and grading optimization, and building a skylight front and rear column space model; performing profiling attachment simulation on the skylight front and rear column space model based on foam material information and thickness information according to a skylight foam attachment standard to generate a front and rear column foam attachment model; surface feature recognition and attachment path planning are carried out, and a target foam attachment path is determined; and executing the target foam attachment path and performing foam attachment monitoring through the automatic attachment equipment to obtain an attachment monitoring data stream, and introducing a closed-loop feedback mechanism to perform foam attachment optimization. The technical problem that in the prior art, the foam attaching precision is low is solved, and the technical effect of improving the foam attaching precision is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of column foam attachment, and in particular to a data modeling-based automatic contour-profiling attachment optimization method for front and rear column foams of a skylight. Background Art

[0002] With the continuous development of automobile manufacturing technology, the requirements for vehicle sealing and sound insulation performance are increasing day by day. The precise attachment of the front and rear pillar foam of the sunroof has become a key link in improving the quality of the whole vehicle. However, with the complexity of automobile design and the improvement of production automation level, the precision control of the foam attachment process faces many challenges. The traditional foam attachment method mainly relies on manual operation or fixed mechanical attachment, which often has the problem of low attachment accuracy and is difficult to meet the requirements of modern automobile manufacturing for high precision and high consistency. Summary of the invention

[0003] The present application provides a data modeling-based optimization method for automatic contour-forming attachment of foam on the front and rear pillars of a sunroof, which is used to solve the technical problem of low foam attachment accuracy in the prior art.

[0004] In view of the above problems, the present application provides a data modeling method for optimizing the automatic contour-forming attachment of the front and rear pillars of a sunroof.

[0005] The present application provides a data modeling method for optimizing the automatic contour attachment of foam in the front and rear pillars of a sunroof, the method comprising: A three-dimensional scanning device is used to collect and obtain a three-dimensional shape data set of the front and rear pillars of the target sunroof under multiple viewing angles, and the three-dimensional shape data set is denoised and coordinate transformed to obtain a shape space data set of the front and rear pillars of the sunroof; three-dimensional reconstruction and score optimization are performed based on the shape space data set of the front and rear pillars of the sunroof, and a space model of the front and rear pillars of the sunroof is constructed; foam material information and thickness information are obtained, and a contour-like attachment simulation is performed on the space model of the front and rear pillars of the sunroof based on the foam material information and thickness information according to the sunroof foam attachment standard to generate a front and rear pillar foam attachment model; surface feature recognition and attachment path planning are performed based on the front and rear pillar foam attachment model to determine a target foam attachment path; foam attachment monitoring is performed on the target front and rear pillars of the sunroof by executing the target foam attachment path through an automatic attachment device to obtain an attachment monitoring data stream, and a closed-loop feedback mechanism is introduced to perform foam attachment optimization based on the attachment monitoring data stream.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application uses a three-dimensional scanning device to collect and obtain a three-dimensional shape data set of the front and rear pillars of a target sunroof under multiple viewing angles, performs denoising and coordinate transformation on the three-dimensional shape data set, and obtains a space data set of the front and rear pillars of the sunroof; performs three-dimensional reconstruction and score optimization based on the space data set of the front and rear pillars of the sunroof, and builds a space model of the front and rear pillars of the sunroof; obtains foam material information and thickness information, and performs a contour-like attachment simulation on the space model of the front and rear pillars of the sunroof based on the foam material information and thickness information in accordance with the sunroof foam attachment standard, and generates a front and rear pillar foam attachment model; performs surface feature recognition and attachment path planning based on the front and rear pillar foam attachment model, and determines a target foam attachment path; performs foam attachment monitoring on the front and rear pillars of the target sunroof by executing the target foam attachment path through an automatic attachment device, obtains an attachment monitoring data stream, and introduces a closed-loop feedback mechanism to perform foam attachment optimization based on the attachment monitoring data stream. The present invention solves the technical problem of low foam attachment accuracy in the prior art, and achieves the technical effect of improving foam attachment accuracy through three-dimensional scanning modeling, contour attachment simulation, automatic attachment execution and closed-loop feedback optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.

[0008] Figure 1 A schematic flow chart of a method for optimizing the automatic contour attachment of foam on the front and rear pillars of a sunroof based on data modeling provided in an embodiment of the present application; Figure 2 A schematic diagram of the process of building a spatial model of the front and rear pillars of a sunroof in a data modeling method for automatic contour-adhering optimization of the front and rear pillars of a sunroof provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The present application provides a data-modeled optimization method for automatic contour-forming attachment of foam on the front and rear pillars of a sunroof, which is used to solve the technical problem of low foam attachment accuracy in the prior art. Through three-dimensional scanning modeling, contour-forming attachment simulation, automatic attachment execution and closed-loop feedback optimization, the technical effect of improving the foam attachment accuracy is achieved.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0012] Examples, such as Figure 1 As shown, the present application provides a data modeling method for optimizing the automatic contour attachment of the front and rear pillar foam of the sunroof, the method comprising: Step S100: using a 3D scanning device to acquire a 3D shape dataset of the front and rear pillars of the target skylight from multiple viewing angles, performing denoising and coordinate transformation on the 3D shape dataset to obtain a spatial dataset of the front and rear pillars of the skylight.

[0013] In an embodiment of the present application, multi-view three-dimensional shape data of the front and rear pillars of the target skylight are collected by using a three-dimensional scanning device (such as a laser scanner or a structured light scanner). These devices acquire point cloud data of the target surface by emitting laser or structured light and receiving reflected signals, thereby forming a three-dimensional shape data set. Since the scanning process may be affected by ambient light, equipment errors or reflective characteristics of the target surface, the collected data will contain noise. Therefore, the three-dimensional shape data set is denoised, that is, by identifying the type of noise (such as random noise, system noise), intensity, distribution and change trend, a suitable data filter (such as a Gaussian filter or a median filter) is selected to filter the data, remove invalid or abnormal points, and obtain a usable three-dimensional shape data set.

[0014] Next, in order to unify the scanned data into a consistent coordinate system, a camera coordinate system is constructed based on the 3D scanning device, and the available 3D shape data set is mapped to the coordinate system to obtain the 3D coordinate set of the front and rear columns. However, since the demand for foam attachment may involve specific process requirements, the foam attachment coordinate system needs to be customized according to the actual application scenario. By converting the 3D coordinate set of the front and rear columns into the foam attachment coordinate system, the spatial shape data set of the front and rear columns of the sunroof is finally obtained.

[0015] Furthermore, in the method provided in the embodiment of the application, the obtaining of the spatial data set of the shapes of the front and rear columns of the skylight further includes: Perform noise change rules on the three-dimensional shape data set to obtain noise data characteristic information, wherein the noise data characteristic information includes noise type, noise intensity, noise distribution and noise change trend; select a data filter based on the noise data characteristic information, and use the data filter to perform denoising filtering on the three-dimensional shape data set to obtain a usable three-dimensional shape data set; construct a camera coordinate system based on the three-dimensional scanning device, map the usable three-dimensional shape data set to the camera coordinate system, and obtain a three-dimensional coordinate set of front and rear pillars; customize a foam attachment coordinate system according to foam attachment requirements, and perform coordinate transformation on the three-dimensional coordinate set of the front and rear pillars based on the foam attachment coordinate system to obtain the shape space data set of the front and rear pillars of the sunroof.

[0016] In the embodiment of the present application, the noise data characteristic information is first extracted by identifying the noise change law of the three-dimensional shape data set. This step uses a statistical analysis method to detect and analyze the distribution of outliers on the point cloud in the three-dimensional shape data set. By calculating the density distribution and outlier characteristics of the point cloud, the type of noise (such as random noise, system noise or environmental noise), noise intensity (the degree of influence of noise on the data), noise distribution (the spatial distribution of noise in the data set) and noise change trend (the change law of noise with scanning conditions or time) are identified. These characteristic information provides a scientific basis for subsequent denoising processing.

[0017] Next, based on the characteristic information of the noise data, a suitable data filter is selected to perform denoising filtering on the 3D shape data set. For example, for random noise, a Gaussian filter is used to calculate the weighted average of each point through the convolution kernel to smooth the noise; for impulse noise, a median filter is used to replace the current point with the median of the neighborhood points to remove isolated noise points; and for scenes that need to retain edge details, a bilateral filter is used to retain the target edge information while denoising. Through filtering processing, invalid or abnormal points in the data set are removed to obtain a usable 3D shape data set with higher accuracy and reliability.

[0018] Next, a camera coordinate system is constructed based on the 3D scanning device. This is the reference coordinate system used by the scanning device when collecting data. This step is achieved through camera calibration technology, which uses calibration plates or known geometric features to determine the camera's intrinsic parameters (such as focal length, principal point coordinates) and extrinsic parameters (such as camera position and attitude). Then, the point cloud coordinates in the available 3D shape data set are mapped to the camera coordinate system through matrix transformations (such as rotation matrices and translation vectors) to obtain the 3D coordinate set of the front and rear columns. This coordinate set describes the precise geometric position and shape information of the front and rear columns of the target skylight in the camera coordinate system.

[0019] Finally, according to the process requirements of foam attachment, customize the foam attachment coordinate system. This step is completed using a coordinate system definition tool (such as CAD software) to determine the origin, coordinate axis direction and scale of the foam attachment coordinate system to ensure that it is aligned with the attachment equipment or process requirements. Then, the three-dimensional coordinate set of the front and rear columns is converted from the camera coordinate system to the foam attachment coordinate system through coordinate transformation matrices (such as rotation, translation and scaling matrices), and finally the spatial data set of the shape of the front and rear columns of the skylight is obtained. This data set not only contains the precise geometric information of the front and rear columns of the target skylight, but also ensures the consistency of the coordinate system of the data with the subsequent attachment process, providing a basis for subsequent three-dimensional reconstruction and contour attachment.

[0020] Step S200: Perform three-dimensional reconstruction and score optimization based on the space data set of the shape of the front and rear pillars of the skylight, and build a space model of the front and rear pillars of the skylight.

[0021] In an embodiment of the present application, based on a spatial data set of the shapes of the front and rear pillars of a skylight, a set of feature points of the front and rear pillars of the skylight and a set of multidimensional description sub-descriptions of the feature points are first obtained through feature point extraction and multidimensional description, so as to provide key geometric information for three-dimensional reconstruction; then, the three-dimensional model of the data set is reconstructed using these feature information to generate an initial spatial model of the front and rear pillars; subsequently, a model generation adversarial network including a model generator and a model scorer is constructed by collecting the model spatial data set and performing alternating training based on it; finally, the network is used to iteratively score and optimize the initial spatial model of the front and rear pillars, so as to gradually improve the model accuracy, and finally a high-precision spatial model of the front and rear pillars of the skylight is constructed.

[0022] Further, such as Figure 2 As shown, in the method provided in the embodiment of the application, the construction of the front and rear column space model of the skylight also includes: The method comprises the steps of: extracting feature points and performing multi-dimensional description on the shape space data set of the front and rear pillars of the skylight to obtain a feature point set of the front and rear pillars of the skylight and a multi-dimensional descriptor set of feature points; reconstructing a three-dimensional model of the shape space data set of the front and rear pillars of the skylight based on the feature point set of the front and rear pillars of the skylight and the multi-dimensional descriptor set of feature points to generate an initial space model of the front and rear pillars; acquiring a model space data set, performing alternating training based on the model space data set to obtain a model generation adversarial network, the model generation adversarial network comprising a model generator and a model scorer; iteratively scoring and optimizing the initial space model of the front and rear pillars of the skylight based on the model generator and the model scorer to build a space model of the front and rear pillars of the skylight.

[0023] In an embodiment of the present application, based on the spatial data set of the shape of the front and rear columns of the skylight, a feature point extraction algorithm (such as Harris corner detection or SIFT algorithm) is first used to identify the key geometric feature points in the data set. Specifically, Harris corner detection calculates the gradient changes of pixels or points in the image or point cloud to identify areas with significant curvature changes as feature points; the SIFT algorithm constructs a scale space and detects local extreme points as feature points. Then, a multidimensional descriptor (such as FPFH or SHOT) is used to describe each feature point. For example, FPFH (Fast Point Feature Histograms) generates a histogram describing the local geometric information of the feature point by calculating the difference in normal vectors of the neighborhood around the feature point; SHOT (Signature of Histograms of OrienTations) combines the local coordinate system and the histogram to describe the geometric distribution of the feature point. Finally, a set of feature points of the front and rear columns of the skylight and a set of multidimensional descriptors of the feature points are generated.

[0024] Next, based on the extracted feature point set of the front and rear columns of the skylight and the multidimensional descriptor set of the feature points, the similarity of the feature points is first calculated to generate a feature point similarity set. Specifically, the Euclidean distance or cosine similarity between the feature point descriptors is calculated to quantify the matching degree between the feature points. Then, the feature points are registered according to the feature point similarity set to generate a front and rear column matching feature point set. The registration process uses the nearest neighbor search algorithm to quickly find matching point pairs, and the RANSAC algorithm is used to eliminate mismatched points to ensure the registration accuracy. Then, the front and rear column matching feature point set is plane projected and meshed to generate a front and rear column triangular mesh. Specifically, the matching feature points are projected onto a two-dimensional plane, and a triangular mesh is generated using the Delaunay triangulation algorithm, and then the mesh is mapped back to three-dimensional space. Finally, the skylight front and rear column shape space data set mapping is applied to the front and rear column triangular mesh, and the mesh vertex information is filled in through interpolation or fitting algorithms to complete the three-dimensional model reconstruction and generate the initial front and rear column space model.

[0025] In order to optimize the initial model, the model space dataset is first collected. Specifically, the real geometric data of the front and rear columns of the skylight are obtained by a 3D scanner or high-precision measuring equipment to generate a high-precision point cloud or mesh model. Then, the initial model is compared with the real data, and information such as point cloud deviation and geometric error is calculated to generate a model space dataset. For example, the deviation of the model is quantified by calculating the Hausdorff distance or point cloud registration error between the initial model and the real data. Then, alternating training is performed based on the dataset to construct a model generative adversarial network (GAN). GAN consists of a model generator and a model scorer, in which the generator is responsible for generating an optimized model, and the scorer evaluates the similarity between the generated model and the real data. Specifically, the generator adopts a convolutional neural network (CNN) or a graph neural network (GNN) structure, inputs the initial model, and outputs the optimized model; the scorer evaluates the accuracy of the model by calculating the geometric error (such as Chamfer distance) between the generated model and the real data. Through alternating training, the generator continuously optimizes the model generation capability, and the scorer improves the model evaluation accuracy, and finally obtains a generative adversarial network that can efficiently generate high-quality models.

[0026] Finally, the trained model generator and model scorer are used to iteratively score and optimize the initial front and rear column space model. In each round of iteration, the generator optimizes the model according to the feedback of the scorer and corrects the defects in the model (such as uneven surface or feature loss), and the scorer re-evaluates the optimized model. Specifically, the generator reduces the geometric error between the real data by adjusting the vertex position or mesh structure of the model; the scorer generates a new scoring result by calculating the deviation between the optimized model and the real data. Through multiple iterations, the geometric accuracy and detail restoration of the model are gradually improved, and finally a high-precision skylight front and rear column space model is built. This process realizes the complete construction from data to high-quality 3D model through the combination of feature extraction, 3D reconstruction and generative adversarial network, providing reliable technical support for the precise design and manufacture of the front and rear columns of the skylight.

[0027] Furthermore, in the method provided in the embodiment of the application, the generating of the initial front and rear column space model further includes: Based on the feature point multidimensional descriptor set, similarity calculation is performed on the feature point set of the front and rear pillars of the sunroof to obtain a feature point similarity set; feature point alignment is performed on the feature point set of the front and rear pillars of the sunroof according to the feature point similarity set to obtain a front and rear pillar matching feature point set; plane projection and mesh conversion are performed on the front and rear pillar matching feature point set to obtain a front and rear pillar triangular mesh; the front and rear pillar shape space data set mapping of the sunroof is applied to the front and rear pillar triangular mesh to perform three-dimensional model reconstruction to generate the initial front and rear pillar space model.

[0028] In an embodiment of the present application, based on the feature point set of the front and rear pillars of the skylight and the multi-dimensional descriptor set of the feature points, a feature point similarity set is first generated by similarity calculation. Specifically, a measurement method such as Euclidean distance or cosine similarity is used to calculate the similarity between feature point descriptors. For example, for the FPFH descriptor, a histogram is generated by calculating the difference in normal vectors of the neighborhood around the feature point, and the similarity calculation is achieved by comparing the distribution differences of the histograms. The Euclidean distance quantifies the similarity of feature points by calculating the geometric distance between descriptor vectors; the cosine similarity measures the directional consistency of the feature points by calculating the cosine value of the angle between the vectors. Through this process, the feature point similarity set is finally obtained, which provides a matching basis for the subsequent feature point registration.

[0029] Next, according to the feature point similarity set, the feature point set of the front and rear columns of the skylight is registered to generate a set of matching feature points of the front and rear columns. Specifically, a nearest neighbor search algorithm (such as KD-Tree) is used to quickly find matching point pairs. KD-Tree constructs a multidimensional spatial index to efficiently search for nearest neighbor points, significantly improving matching efficiency. Next, the RANSAC algorithm is used to remove mismatched points to ensure registration accuracy. The RANSAC algorithm selects the optimal matching point pairs through random sampling and consistency verification, effectively improving the robustness of the registration. Finally, the front and rear column matching feature point set is obtained, providing aligned point cloud data for subsequent mesh generation.

[0030] Then, the matching feature point sets of the front and rear columns are projected and meshed. Specifically, the matching feature points are projected onto a two-dimensional plane, and a triangular mesh is generated using the Delaunay triangulation algorithm. Delaunay triangulation generates uniform and non-overlapping triangular meshes by maximizing the minimum angle principle to ensure mesh quality. The projection process reduces the dimensionality of the three-dimensional point cloud data to a two-dimensional plane, which facilitates subsequent mesh generation. Finally, the front and rear column triangular meshes are obtained, providing a basic geometric framework for three-dimensional model reconstruction.

[0031] Finally, the spatial data set mapping of the front and rear columns of the skylight is applied to the front and rear column triangular meshes, and the mesh vertex information is filled in through bilinear interpolation to complete the 3D model reconstruction and generate the initial front and rear column spatial model. The interpolation algorithm combines the point cloud data with the mesh structure to ensure the integrity and continuity of the model's geometric information. The initial front and rear column spatial model finally obtained provides a basis for subsequent optimization and refinement.

[0032] Furthermore, in the method provided in the embodiment of the application, the construction of the skylight front and rear column space model also includes: The model scorer is used to score the effect of the initial front and rear pillar space model to obtain the front and rear pillar model effect score information; the front and rear pillar model effect score information is fed back to the input end of the model generator for optimization generation to obtain the front and rear pillar optimized space model; based on the model scorer and the model scorer, the front and rear pillar optimized space model is iteratively scored and tuned to build the front and rear pillar space model of the sunroof.

[0033] In the embodiment of the present application, the model scorer is first used to score the effect of the initial front and rear column space model, and the front and rear column model effect scoring information is generated. Specifically, the Hausdorff distance method is used to calculate the maximum deviation between the model surface and the original point cloud data to quantify the geometric error of the model. The Hausdorff distance evaluates the overall geometric accuracy of the model by calculating the farthest distance from each point on the model surface to the point cloud data. The front and rear column model effect scoring information is obtained through this process, which provides a quantitative basis for model optimization.

[0034] Next, the effect score information of the front and rear column models is fed back to the input end of the model generator for optimization and generation, and the front and rear column optimized spatial model is obtained. Specifically, the Laplacian smoothing algorithm is used to optimize the model surface. Laplacian smoothing adjusts the position of the mesh vertices to move them toward the average value of the surrounding vertices, thereby reducing surface noise and local distortion, and obtaining the front and rear column optimized spatial model.

[0035] Finally, the front and rear pillars are iteratively scored and tuned based on the model scorer to build a spatial model of the front and rear pillars of the skylight. Specifically, the iterative closest point algorithm (ICP) is used to further optimize the alignment accuracy of feature points. ICP gradually improves the matching degree of feature points by iteratively calculating the closest point pairs between the model and the point cloud data and minimizing the distance between them. After each iteration, the model scorer re-evaluates the optimization results and generates the latest scoring information to guide the next round of optimization. When the model score reaches the preset quality threshold (such as a geometric error of less than 0.1 mm), the iterative process terminates and the spatial model of the front and rear pillars of the skylight is obtained.

[0036] Step S300: Acquire foam material information and thickness information, perform contour attachment simulation on the front and rear pillar space model of the sunroof based on the foam material information and thickness information according to the sunroof foam attachment standard, and generate a front and rear pillar foam attachment model.

[0037] In the embodiment of the present application, the foam material information and thickness information are first obtained from a preset database, wherein the foam material information includes elastic modulus, Poisson's ratio and density.

[0038] After obtaining the foam material information and thickness information, determine the evaluation indicators (such as position deviation, overlap limit, void ratio and smoothness) according to the sunroof foam attachment standard, and set the contour attachment parameters. Map the foam material and thickness information to the sunroof front and rear pillar space model, perform contour attachment simulation optimization through finite element analysis, and generate a front and rear pillar foam attachment model that meets the standard.

[0039] Furthermore, in the method provided in the embodiment of the application, the generating of the front and rear column foam attachment model further includes: According to the sunroof foam attachment standard, foam attachment evaluation indicators are determined, and the foam attachment evaluation indicators include position deviation threshold, overlap limit, void ratio and smoothness; according to the foam attachment evaluation indicators, contour attachment parameters are set; the foam material information and thickness information are mapped to the sunroof front and rear pillar space model according to the contour attachment parameters to perform contour attachment simulation optimization, and generate the front and rear pillar foam attachment model.

[0040] In the embodiment of the present application, according to the sunroof foam attachment standard, the evaluation indicators are first clarified, including the position deviation threshold (the allowable deviation range between the foam attachment position and the target position), overlap limit (the maximum allowable value of the foam edge overlap), void ratio (the gap ratio between the foam and the model surface) and smoothness (the smoothness of the foam attachment surface). These indicators are determined by technical experts.

[0041] Next, based on the determined foam attachment evaluation indicators, the contour attachment parameters such as attachment pressure, temperature and time are set through experimental testing and simulation verification. The setting of these parameters depends on material mechanical property tests (such as tensile tests and compression tests) and process parameter optimization technology to ensure that the foam can meet the requirements of position deviation, overlap limit, void ratio and smoothness during the attachment process.

[0042] The material information (such as elastic modulus, Poisson's ratio and density) and thickness information of the foam are then mapped to the spatial model of the front and rear columns of the skylight through the material property definition module in the computer-aided engineering (CAE) software. This step combines 3D scanning technology to obtain the precise geometric data of the front and rear columns of the skylight, and uses the meshing tool in finite element analysis (FEA) to discretize the model into multiple small units, providing a basis for subsequent contour attachment simulation.

[0043] Finite element analysis technology is used to accurately simulate the contact and deformation between the foam and the front and rear pillar models of the skylight. During the simulation process, contact algorithms (such as penalty function method) are used to deal with the contact problem between the foam and the model surface to ensure that the attachment effect conforms to the actual physical properties. Through the iterative optimization algorithm, the contour attachment parameters are adjusted to gradually optimize the position deviation, overlap limit, void ratio and smoothness of the foam until the evaluation indicators are met. After the simulation optimization is completed, the final front and rear pillar foam attachment model is generated using computer-aided design (CAD) software. This model not only accurately reflects the thickness and material properties of the foam, but also ensures that the attached geometry matches the height of the front and rear pillar space model of the skylight.

[0044] Step S400: performing surface feature recognition and attachment path planning based on the front and rear pillar foam attachment model to determine a target foam attachment path.

[0045] In the embodiment of the present application, based on the front and rear pillar foam attachment model, the key features such as shape contour, curvature change, depression and protrusion are first extracted through surface feature recognition to form a front and rear pillar foam surface feature set. Subsequently, the model is segmented into N attachment areas based on these features. Combined with the attachment path planning objectives (such as efficiency, accuracy and interference avoidance), the path optimization is performed for each area, and the target foam attachment path is finally determined.

[0046] Furthermore, in the method provided in the embodiment of the application, the step of determining the target foam attachment path further includes: Based on the front and rear pillar foam attachment model, surface feature recognition is performed to obtain a front and rear pillar foam surface feature set, wherein the front and rear pillar foam surface feature set includes shape contour, curvature change, depression and protrusion; the front and rear pillar foam attachment model is segmented into attachment areas according to the front and rear pillar foam surface feature set to obtain N front and rear pillar foam attachment areas; an attachment path planning target is obtained, and based on the attachment path planning target, an attachment path optimization is performed on the N front and rear pillar foam attachment areas to determine a target foam attachment path.

[0047] In the embodiment of the present application, based on the front and rear pillar foam attachment model, three-dimensional scanning technology (such as laser scanning or structured light scanning) is first used to collect high-precision data on the model surface to obtain point cloud data. Then, the point cloud data is processed using traditional geometric processing algorithms to extract key geometric features. The shape contour is identified by an edge detection algorithm (such as the Canny algorithm) to determine the outer shape boundary of the model; the curvature change is analyzed by a curvature calculation algorithm (such as a method based on local surface fitting) to reflect the degree of curvature of the surface; the depressions and protrusions are identified by a local surface fitting algorithm (such as least squares fitting) to mark the high and low undulating areas on the model surface. These features together constitute the surface feature set of the front and rear pillar foam.

[0048] Next, the model is segmented using a regional segmentation algorithm based on the surface feature set of the front and rear pillar foam. For example, a curvature-based region growing algorithm is used to gradually expand the region based on curvature similarity starting from a seed point; or a watershed algorithm based on edge detection is used to divide the region based on gradient information. By analyzing the shape contour, curvature change, and concavity and convexity features, the model is divided into N front and rear pillar foam attachment regions.

[0049] Then, the pre-set attachment path planning target is obtained, including the attachment efficiency, etc. Based on the attachment path planning target, a path optimization algorithm is used to optimize the path of N attachment areas. For example, the Dijkstra algorithm is used to search for the shortest path in the regional grid map; or a heuristic search algorithm (such as the simulated annealing algorithm) is used to find the optimal path in a complex area. During the optimization process, traditional collision detection techniques (such as detection methods based on bounding boxes or distance fields) are combined to ensure that the path does not interfere with other parts of the model. At the same time, kinematic simulation (such as a simulation tool based on a robot kinematic model) is used to verify the feasibility and efficiency of the path to ensure that the attachment tool (such as a robotic arm) can be smoothly executed along the planned path.

[0050] Through the above steps, a target foam attachment path that meets the attachment path planning target is generated.

[0051] Furthermore, in the method provided in the embodiment of the application, the step of determining the target foam attachment path further includes: Based on the attachment path planning target, the N front and rear pillar foam attachment areas are respectively optimized for attachment paths to obtain N front and rear pillar foam attachment paths; the distribution position information of the N front and rear pillar foam attachment areas is used as a constraint condition, and the N front and rear pillar foam attachment paths are optimized for regional connection paths to determine the target foam attachment path.

[0052] In the embodiment of the present application, for N front and rear pillar foam attachment areas, the attachment path planning target is used as the optimization direction, and the traditional path optimization algorithm (such as Dijkstra algorithm) is used for path planning. For example, in flat areas, straight path planning is prioritized to improve efficiency; in high curvature areas, segmented fitting curve paths are used to ensure accuracy; in complex concave and convex areas, collision detection technology (such as bounding box-based detection method) is combined to avoid interference. Through the above method, N front and rear pillar foam attachment paths are generated.

[0053] After completing the path optimization of N areas, the distribution position information of the N front and rear column foam attachment areas is extracted, including the boundary coordinates, center position and spatial relationship of adjacent areas of each area. First, an edge detection algorithm (such as the Canny algorithm) is used to extract the boundary contour of each area from the point cloud data. Then, the geometric center point of each area is calculated by the geometric center calculation algorithm, for example, the average value of the point cloud data is used as the center point. Finally, a spatial index structure (such as a KD tree or a quadtree) is used to analyze the spatial relationship of adjacent areas and determine the connection order and transition path between areas. Through this process, the distribution position information of the N front and rear column foam attachment areas is obtained.

[0054] Then, the distribution position information of N attached areas is used as a constraint condition, and the A* algorithm or heuristic search algorithm is used to optimize the regional connection path. First, the starting point and end point of the connection path are generated based on the center point and boundary information of the adjacent areas. Next, the A* algorithm or heuristic search algorithm is used to search for the connection path in the global grid map, for example, by calculating the shortest path or optimal transition path between adjacent areas to ensure that the connection path avoids interference while meeting the attachment efficiency. During the path search process, the distance field-based collision detection method is combined to ensure that the path does not interfere with other parts of the model, for example, by calculating the minimum distance between the path and the model surface, excluding paths that may cause collisions. Finally, the spline curve fitting is used to smooth the connection path to ensure that the attachment tool (such as a robotic arm) can be executed smoothly, and finally a regional connection path that meets the constraints is generated.

[0055] Through the above steps, the N front and rear column foam attachment paths are integrated with the regional connection path to generate a complete target foam attachment path.

[0056] Step S500: The target foam attachment path is executed by an automatic attachment device to monitor the foam attachment of the front and rear pillars of the target sunroof, to obtain an attachment monitoring data stream, and a closed-loop feedback mechanism is introduced to optimize the foam attachment based on the attachment monitoring data stream.

[0057] In an embodiment of the present application, the target foam attachment path is executed by an automatic attachment device to monitor the foam attachment of the front and rear pillars of the target sunroof, to obtain an attachment monitoring data stream, and a closed-loop feedback mechanism is introduced to optimize the foam attachment based on the attachment monitoring data stream.

[0058] Specifically, first, a sensor group, including displacement sensors, pressure sensors, and visual sensors, is installed on the front and rear pillars of the target sunroof to monitor the key parameters in the attachment process in real time. Next, the control parameters of the automatic attachment equipment are parsed based on the target foam attachment path, and a device attachment control parameter set is generated to guide the device to perform the attachment operation. During the attachment process, the sensor group collects data such as the fitting accuracy, attachment pressure, and path deviation between the foam and the sunroof surface in real time to form an attachment monitoring data stream. Subsequently, the monitoring data is analyzed through attachment quality analysis to determine the amount of attachment quality deviation, such as inaccurate fitting or uneven pressure. Based on the deviation, simulation optimization analysis is used to optimize the device attachment control parameter set and the target foam attachment path to generate foam optimized attachment parameters.

[0059] Finally, the optimized parameters are applied to the automatic attachment equipment to achieve the optimal control of foam attachment to the front and rear pillars of the target sunroof. Through this closed-loop feedback mechanism, the high precision, high quality and high efficiency of the foam attachment process are ensured, and the deviations and defects that may occur during the attachment process are solved.

[0060] Furthermore, in the method provided in the embodiment of the application, the step of obtaining the attached monitoring data stream further includes: A sensor group is installed on the front and rear pillars of the target sunroof, wherein the sensor group includes a displacement sensor, a pressure sensor and a visual sensor; control parameters of the automatic attachment device are parsed based on the target foam attachment path to obtain a device attachment control parameter set; the automatic attachment device executes the device attachment control parameter set to automatically attach foam to the front and rear pillars of the target sunroof, and the sensor group is used to monitor the foam attachment process in real time to obtain the attachment monitoring data stream.

[0061] In the embodiment of the present application, a sensor group is installed at predetermined positions on the front and rear pillars of the target sunroof, specifically including a displacement sensor (such as a laser displacement sensor or a linear encoder), a pressure sensor (such as a piezoelectric sensor or a strain gauge sensor), and a visual sensor (such as an industrial camera or a 3D visual scanner). The displacement sensor monitors the position deviation between the foam and the sunroof surface in real time through laser ranging or encoder feedback; the pressure sensor measures the pressure applied during the attachment process through the piezoelectric effect or strain gauge; the visual sensor collects the foam surface image through a high-resolution industrial camera or a 3D scanner.

[0062] Next, according to the target foam attachment path (including regional attachment path and connection path), the control parameters of the automatic attachment equipment (such as a six-axis robot or CNC attachment machine) are analyzed. The path information is converted into a set of device attachment control parameters that can be executed by the device through a kinematic model (such as a forward and inverse kinematic model), including parameters such as motion speed, acceleration, attachment pressure, and tool posture. Specifically, first, the joint angle or motion trajectory of the device is calculated based on the path coordinate points; secondly, a smooth motion instruction is generated in combination with the motion characteristics of the device (such as maximum speed and acceleration limit); finally, the attachment pressure parameters are integrated with the motion instructions to form a complete set of device attachment control parameters.

[0063] Then, the automatic attachment device executes the device attachment control parameter set to automatically attach foam to the front and rear pillars of the target sunroof. The automatic attachment device uses a motion control system (such as a servo motor and encoder) to attach foam according to the device attachment control parameter set. During the attachment process, the sensor group collects the attachment data of the foam and the sunroof surface in real time to form an attachment monitoring data stream.

[0064] Furthermore, in the method provided in the embodiment of the application, the closed-loop feedback mechanism is introduced to optimize the foam attachment based on the attachment monitoring data stream, and further includes: The attachment monitoring data stream is analyzed for attachment quality to determine the attachment quality deviation; based on the attachment quality deviation, the device attachment control parameter set and the target foam attachment path are simulated and optimized to obtain foam optimization attachment parameters, and the foam optimization attachment parameters are used to perform foam optimization control on the front and rear pillars of the target sunroof.

[0065] In the embodiment of the present application, the attachment quality analysis is first performed on the attachment monitoring data stream, wherein the attachment monitoring data stream includes data collected by the displacement sensor, the pressure sensor, and the visual sensor. First, the data collected by the displacement sensor is analyzed to calculate the position deviation between the foam and the front and rear pillars of the sunroof during the attachment process, and the position deviation amount is obtained, specifically, the offset distance between the actual attachment position of the foam and the target position; secondly, the data collected by the pressure sensor is processed to evaluate whether the attachment pressure is evenly distributed, whether there is too much or too little pressure, and the pressure deviation amount is obtained. The specific evaluation method is as follows: the pressure value at different positions during the attachment process is collected by the pressure sensor, and the standard deviation and average value of the pressure distribution are calculated. If the standard deviation exceeds the preset threshold (for example, ±10%), the pressure distribution is determined to be uneven. At the same time, check whether there is a situation where the local pressure is too high or too low, and record the pressure deviation to avoid foam deformation or loose adhesion; finally, the image data collected by the visual sensor is processed, and traditional image processing technology (such as graying, edge detection and threshold segmentation) is used to identify defects such as bubbles and wrinkles on the foam surface, and the area and position of the defect are calculated to obtain the defect deviation, which is specifically the percentage of the defect area to the total area of ​​the foam and the offset distance between the defect position and the target position. Through this process, the attachment quality deviation is obtained.

[0066] Next, the attachment quality deviation is input into the finite element analysis (FEA) simulation model, and the equipment attachment control parameter set (including motion speed, acceleration, attachment pressure and tool posture) and the target foam attachment path are optimized and analyzed. The specific steps include establishing a geometric model of the foam and the front and rear pillars of the sunroof in the FEA software, defining material properties (such as the elastic modulus, Poisson's ratio and density of the foam, and the rigidity and surface properties of the front and rear pillars of the sunroof), inputting the current equipment attachment control parameters and the target foam attachment path into the simulation model, running the simulation to simulate the foam attachment process under different parameters, analyzing the stress distribution, deformation and attachment effect of the foam, and evaluating whether the attachment quality meets the requirements based on the simulation results, focusing on whether the stress distribution is uniform, whether the foam is excessively deformed, and whether there are fitting defects. The attachment process is optimized by iteratively adjusting parameters such as motion speed, attachment pressure and tool posture to ensure uniform stress distribution during the foam attachment process and reduce deformation and defects. Finally, the optimized equipment attachment control parameters and target foam attachment path are output as foam optimization attachment parameters.

[0067] Load the optimized foam attachment parameters into the control system of the automatic attachment equipment, and use the motion control system (such as servo motors and encoders) to attach the foam to the front and rear pillars of the target sunroof according to the optimized parameters and paths. First, input the optimized motion speed, attachment pressure, and tool posture parameters into the servo controller, configure the equipment operating parameters, and start the equipment to perform the attachment operation according to the optimized attachment path and parameters to ensure the precise fit of the foam to the front and rear pillars of the sunroof. At the same time, the displacement sensor, pressure sensor, and visual sensor are used to collect data in the attachment process in real time to form a new attachment monitoring data stream, and the monitoring data is fed back to the data processing unit for comparison with the target value. If deviations are found, the equipment parameters are further fine-tuned to ensure continuous optimization of the attachment quality.

[0068] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application uses a three-dimensional scanning device to collect and obtain a three-dimensional shape data set of the front and rear pillars of a target sunroof under multiple viewing angles, performs denoising and coordinate transformation on the three-dimensional shape data set, and obtains a space data set of the front and rear pillars of the sunroof; performs three-dimensional reconstruction and score optimization based on the space data set of the front and rear pillars of the sunroof, and builds a space model of the front and rear pillars of the sunroof; obtains foam material information and thickness information, and performs a contour-like attachment simulation on the space model of the front and rear pillars of the sunroof based on the foam material information and thickness information in accordance with the sunroof foam attachment standard, and generates a front and rear pillar foam attachment model; performs surface feature recognition and attachment path planning based on the front and rear pillar foam attachment model, and determines a target foam attachment path; performs foam attachment monitoring on the front and rear pillars of the target sunroof by executing the target foam attachment path through an automatic attachment device, obtains an attachment monitoring data stream, and introduces a closed-loop feedback mechanism to perform foam attachment optimization based on the attachment monitoring data stream. The present invention solves the technical problem of low foam attachment accuracy in the prior art, and achieves the technical effect of improving foam attachment accuracy through three-dimensional scanning modeling, contour attachment simulation, automatic attachment execution and closed-loop feedback optimization.

[0069] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0071] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A data modeling method for optimizing the automatic contour attachment of the front and rear pillars of a sunroof, characterized in that: The method comprises: Using a three-dimensional scanning device to acquire a three-dimensional shape data set of the front and rear pillars of the target skylight from multiple viewing angles, performing denoising and coordinate transformation on the three-dimensional shape data set to obtain a spatial data set of the front and rear pillar shapes of the skylight; Based on the spatial data set of the shape of the front and rear columns of the skylight, three-dimensional reconstruction and score optimization are performed to build a spatial model of the front and rear columns of the skylight; Acquire foam material information and thickness information, perform contour attachment simulation on the front and rear pillar space model of the sunroof based on the foam material information and thickness information according to the sunroof foam attachment standard, and generate the front and rear pillar foam attachment model; Based on the front and rear pillar foam attachment model, surface feature recognition and attachment path planning are performed to determine a target foam attachment path; The target foam attachment path is executed by automatic attachment equipment to monitor the foam attachment of the front and rear pillars of the target sunroof, to obtain an attachment monitoring data stream, and a closed-loop feedback mechanism is introduced to optimize the foam attachment based on the attachment monitoring data stream.

2. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 1, characterized in that: The obtaining of the spatial data set of the shapes of the front and rear columns of the skylight comprises: Identifying noise variation rules of the three-dimensional shape data set to obtain noise data characteristic information, wherein the noise data characteristic information includes noise type, noise intensity, noise distribution and noise variation trend; Selecting a data filter according to the noise data characteristic information, and using the data filter to perform denoising filtering on the three-dimensional shape data set to obtain a usable three-dimensional shape data set; Constructing a camera coordinate system based on the three-dimensional scanning device, mapping the available three-dimensional shape data set to the camera coordinate system, and obtaining a three-dimensional coordinate set of the front and rear columns; A foam attachment coordinate system is customized according to the foam attachment requirements, and the three-dimensional coordinate sets of the front and rear pillars are transformed based on the foam attachment coordinate system to obtain the shape space data set of the front and rear pillars of the sunroof.

3. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 1, characterized in that: The method of constructing the space model of the front and rear columns of the skylight includes: Extracting feature points and performing multi-dimensional description on the shape spatial data set of the front and rear columns of the skylight to obtain a feature point set of the front and rear columns of the skylight and a feature point multi-dimensional description sub-set; Reconstructing the three-dimensional model of the skylight front and rear pillar shape space data set based on the skylight front and rear pillar feature point set and the feature point multidimensional descriptor set to generate an initial front and rear pillar space model; Acquire a model space data set, perform alternating training based on the model space data set, and obtain a model generation adversarial network, wherein the model generation adversarial network includes a model generator and a model scorer; Based on the model generator and the model scorer, the initial front and rear pillar space model is iteratively scored and optimized to build a skylight front and rear pillar space model.

4. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 3, characterized in that: The generating of the initial front and rear column space model comprises: Based on the feature point multidimensional descriptor set, similarity calculation is performed on the feature point set of the front and rear pillars of the skylight to obtain a feature point similarity set; Performing feature point registration on the front and rear pillar feature point set of the sunroof according to the feature point similarity set to obtain a front and rear pillar matching feature point set; Performing plane projection and mesh conversion on the front and rear column matching feature point set to obtain a front and rear column triangular mesh; The three-dimensional model is reconstructed by mapping the shape space data set of the front and rear columns of the skylight to the front and rear column triangle meshes to generate the initial front and rear column space model.

5. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 3, characterized in that: The method of constructing the space model of the front and rear columns of the skylight includes: Using the model scorer to score the effect of the initial front and rear column space model to obtain front and rear column model effect score information; Feeding back the front and rear column model effect score information to the input end of the model generator for optimization generation to obtain the front and rear column optimized space model; Based on the model scorer and the model scorer, the front and rear pillar optimization space model is iteratively scored and tuned to build the front and rear pillar space model of the sunroof.

6. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 1, characterized in that: The method of generating the front and rear column foam attachment model comprises: Determining foam attachment evaluation indicators according to the sunroof foam attachment standard, wherein the foam attachment evaluation indicators include position deviation threshold, overlap limit, void ratio, and smoothness; According to the foam attachment evaluation index, setting contour attachment parameters; The foam material information and thickness information are mapped to the front and rear pillar space model of the sunroof according to the contour attachment parameters to perform contour attachment simulation optimization to generate the front and rear pillar foam attachment model.

7. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 1, characterized in that: The step of determining the target foam attachment path includes: Performing surface feature recognition based on the front and rear pillar foam attachment model to obtain a front and rear pillar foam surface feature set, wherein the front and rear pillar foam surface feature set includes shape contour, curvature change, and concavity and convexity; Segmenting the front and rear pillar foam attachment model into attachment regions according to the front and rear pillar foam surface feature set to obtain N front and rear pillar foam attachment regions; An attachment path planning target is obtained, and based on the attachment path planning target, an attachment path optimization is performed on the N front and rear pillar foam attachment areas to determine a target foam attachment path.

8. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 7, characterized in that: The step of determining the target foam attachment path includes: Based on the attachment path planning target, respectively optimizing the attachment paths of the N front and rear pillar foam attachment areas to obtain N front and rear pillar foam attachment paths; The distribution position information of the N front and rear pillar foam attachment areas is used as a constraint condition, and the regional connection path optimization is performed on the N front and rear pillar foam attachment paths to determine the target foam attachment path.

9. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 1, characterized in that: The step of obtaining the attached monitoring data stream includes: Installing a sensor group on the front and rear pillars of the target sunroof, wherein the sensor group includes a displacement sensor, a pressure sensor and a visual sensor; Based on the target foam attachment path, the control parameters of the automatic attachment device are analyzed to obtain a device attachment control parameter set; The automatic attaching device executes the device attaching control parameter set to automatically attach foam to the front and rear pillars of the target sunroof, and the sensor group is used to monitor the foam attaching process in real time to obtain the attachment monitoring data stream.

10. The data modeling optimization method for automatic contour attachment of front and rear pillars of a sunroof according to claim 9, characterized in that: The closed-loop feedback mechanism is introduced to optimize the foam attachment based on the attachment monitoring data stream, including: Performing an attachment quality analysis on the attachment monitoring data stream to determine an attachment quality deviation; Based on the attachment quality deviation, the device attachment control parameter set and the target foam attachment path are simulated and optimized to obtain foam optimization attachment parameters, and the foam optimization attachment parameters are used to perform foam attachment optimization control on the front and rear pillars of the target sunroof.

Images