Automated production line digital model hole filling method and device

Abstract

The embodiment of the application provides a kind of automated production line digital model hole filling method and device, accurately identify the region to be processed by multilevel grid analysis and curvature field calculation.Innovatively designed the generation mechanism of patch based on density clustering and neural network, combined with local geometric features to realize intelligent filling optimization.The system uses non-uniform rational basis spline surface reconstruction and Laplace grid smoothing algorithm to ensure the continuity and fairness of the filling area, and is closely combined with the motion control and path planning of automated production line.This method breaks through the limitations of traditional model repair and provides an efficient and reliable solution for the integrity reconstruction of industrial digital models.

Description

Technical Field

[0001] This application relates to the field of data processing, specifically to a method and apparatus for filling holes in a digital model of an automated production line. Background Technology

[0002] Traditional methods for filling holes in digital models mainly rely on simple geometric interpolation or surface fitting, which struggles to handle complex topologies and maintain model continuity. Existing techniques lack systematic methods for hole boundary feature extraction and surface reconstruction, and fail to achieve adaptive filling optimization.

[0003] Meanwhile, existing systems have significant shortcomings in curvature analysis and patch generation. Traditional methods often employ a uniform filling strategy, failing to fully consider the influence of local geometric features and topological constraints, and lack an intelligent evaluation mechanism for filling quality. The systems are also relatively simplistic in handling transition regions and mesh smoothing, failing to achieve seamless model repair.

[0004] Furthermore, existing technologies also have limitations in industrial application integration. The lack of deep integration with motion control and path planning in automated production lines results in insufficient usability of the repair model in practical applications. Solving these problems is crucial for improving the integrity of digital models and the effectiveness of industrial applications. Summary of the Invention

[0005] To address the problems in the existing technology, this application provides a method and apparatus for filling holes in the digital model of an automated production line, which can overcome the limitations of traditional model repair and provide an efficient and reliable solution for the integrity reconstruction of industrial digital models.

[0006] To solve at least one of the above problems, this application provides the following technical solution:

[0007] In a first aspect, this application provides a method for filling holes in a digital model of an automated production line, comprising:

[0008] The digital model of the automated production line is decomposed into a multi-level grid representation. The local curvature field distribution is calculated at each grid level. The curvature field is projected onto the finest level grid. The curvature gradient change is calculated based on the finest level grid. An adaptive threshold segmentation algorithm is used to mark the region to be processed. Boundary points are extracted from the region to be processed. The normal vector field of the boundary points is calculated. The position information of the boundary points and the normal vector field are combined to construct a boundary feature descriptor.

[0009] Density clustering analysis is performed on the boundary feature descriptors, and the density clustering results are mapped to three-dimensional space to form filling patches. The angle between the normal vector of the filling patch and the normal vector of the boundary point is calculated. A neural network prediction model based on local geometric features is constructed. The optimal angle threshold is calculated using the neural network prediction model. Patches with an angle smaller than the optimal angle threshold are marked as patches to be optimized. The boundary curvature information and topological connectivity of the patches to be optimized are calculated. Motion control commands for the automated production line are generated based on the filling patches.

[0010] The surface patch to be optimized is input into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0011] Further, the process of decomposing the digital model of the automated production line into a multi-level grid representation, calculating the local curvature field distribution at each grid level, projecting the curvature field onto the finest level grid, calculating the curvature gradient change based on the finest level grid, and using an adaptive threshold segmentation algorithm to mark the region to be processed includes:

[0012] The octree decomposition algorithm is used to divide the digital model of the automated production line into grid layers of different scales. A vertex adjacency graph is constructed for each grid layer. Based on the adjacency graph, the Gaussian curvature and average curvature of the grid vertices are calculated. The Gaussian curvature and average curvature are combined to form a local curvature field distribution.

[0013] An interpolation mapping algorithm between grid levels is used to project curvature fields at different levels onto the finest grid level to construct a curvature gradient tensor field. The principal direction and eigenvalues ​​of the curvature gradient tensor field are calculated, and an adaptive threshold segmentation function is constructed based on the eigenvalues. The output of the segmentation function is marked as the region to be processed.

[0014] Further, the step of extracting boundary points from the region to be processed, calculating the normal vector field of the boundary points, and combining the position information of the boundary points with the normal vector field to construct a boundary feature descriptor includes:

[0015] A boundary tracing algorithm for the region to be processed is constructed. Based on the mesh topology connection relationship, the connected boundaries of the region to be processed are searched. The mesh vertices on the connected boundaries are extracted into a set of boundary points. The normal vector field of the set of boundary points is calculated by the local surface fitting method.

[0016] A spatial coordinate transformation is performed on the set of boundary points to establish a local coordinate system centered on the boundary points. The three-dimensional coordinate information of the boundary points and the normal vector field are orthogonally decomposed in the local coordinate system to construct a boundary feature descriptor containing position coordinate components and normal vector components.

[0017] Further, the step of performing density clustering analysis on the boundary feature descriptors, mapping the density clustering results to three-dimensional space to form filling patches, calculating the angle between the normal vector of the filling patch and the normal vector of the boundary point, and constructing a neural network prediction model based on local geometric features includes:

[0018] A similarity metric function for boundary feature descriptors is constructed. Based on the similarity metric function, the distance matrix between feature descriptors is calculated. A density-based spatial clustering algorithm is used to divide the boundary feature descriptors into multiple clusters. For each cluster, the core point and boundary point are calculated. The spatial coordinates of the core point and boundary point are projected back into three-dimensional space to form a filling patch.

[0019] The normal vector of the patch is calculated based on the mesh vertices of the filled patch. An angle evaluation model is established between the normal vector of the filled patch and the normal vector of the boundary point. The angle evaluation model is used as the input feature of the neural network to construct a multilayer perceptron network structure. The local geometric features of the boundary points are used as training samples to optimize the neural network.

[0020] Further, the step of using the neural network prediction model to calculate the optimal included angle threshold, marking patches smaller than the optimal included angle threshold as patches to be optimized, calculating the boundary curvature information and topological connectivity of the patches to be optimized, and generating motion control commands for the automated production line based on the filled patches includes:

[0021] The trained neural network model is applied to fill the local geometric features of the patch, outputting the optimal angle threshold between the patch normal vector and the boundary point normal vector. Based on the optimal angle threshold, the patch is screened, an index set of patches to be optimized is constructed, the principal curvature direction and curvature value of the boundary of the patch to be optimized are calculated, and an adjacency graph between patches is established.

[0022] The boundary curvature information of the surface to be optimized is converted into a discrete sampling point sequence. A parameterized representation of the surface boundary is established based on the sampling point sequence. Transitional constraints between surfaces are constructed using topological connection relationships. The transitional constraints are used as constraints of control commands to generate a motion control command sequence that meets the continuity requirements.

[0023] Further, the surface to be optimized is input into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, and constructs an objective function considering surface smoothness, including:

[0024] The boundary curvature information of the patch to be optimized is converted into a sequence of control points. Based on the sequence of control points, a node vector of the NURBS surface is constructed. The values ​​of the NURBS basis functions on the node vectors are calculated. The basis functions are weighted and optimized to obtain the mathematical expression of the non-uniform rational basis spline surface. The mapping relationship between the surface parameter domain and the three-dimensional space is established.

[0025] Based on the topological connectivity of the patches to be optimized, positional continuity and tangential continuity constraints are constructed between adjacent patches. The continuity constraints are combined with the mean curvature and Gaussian curvature of the surface to construct a smoothness evaluation function, which is then used as the optimization objective function.

[0026] Further, the initial filling surface is obtained by iteratively optimizing the objective function; the transition region between the initial filling surface and the boundary of the original model is calculated; a Laplacian mesh smoothing algorithm is applied to the transition region for local adjustment to generate the final filling model; and the filling model is imported into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection, including:

[0027] The gradient descent method is used to numerically optimize the objective function. The control point positions and weight parameters of the NURBS surface are updated by iterative calculation until the objective function converges to obtain an initial filling surface that satisfies the continuity constraint. The distance field function between the initial filling surface and the boundary of the original model is constructed, and the range of the transition region is determined based on the contour lines of the distance field function.

[0028] In the transition region, the Laplacian operator of the mesh vertices is constructed, the displacement vector of the mesh vertices is calculated based on the Laplacian operator, the spatial position of the mesh vertices is iteratively updated to achieve local smoothing, the smoothed mesh is merged with the original model to form a complete filling model, and a spatial index structure of the filling model is established for path planning and collision detection.

[0029] Secondly, this application provides an automated production line digital model hole-filling device, comprising:

[0030] The boundary determination module is used to decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the region to be processed, extract boundary points from the region to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor.

[0031] The filling calculation module is used to perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches.

[0032] The surface filling module is used to input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0033] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the automated production line digital model hole filling method.

[0034] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the described method for filling holes in a digital model of an automated production line.

[0035] Fifthly, this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the described method for filling holes in a digital model of an automated production line.

[0036] As described above, this application provides a method and apparatus for filling holes in digital models of automated production lines. Through multi-level mesh analysis and curvature field calculation, it accurately identifies the areas to be processed. An innovative patch generation mechanism based on density clustering and neural networks is designed, combined with local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled area, and is closely integrated with the motion control and path planning of automated production lines. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is one of the flowcharts illustrating the method for filling holes in a digital model of an automated production line in this application embodiment;

[0039] Figure 2 This is the second schematic diagram of the process for filling holes in the digital model of an automated production line in the embodiments of this application;

[0040] Figure 3 This is the third flowchart illustrating the method for filling holes in the digital model of an automated production line in this application.

[0041] Figure 4 This is the fourth flowchart illustrating the method for filling holes in the digital model of an automated production line in this application.

[0042] Figure 5 This is the fifth flowchart illustrating the method for filling holes in the digital model of an automated production line in this application.

[0043] Figure 6 This is the sixth flowchart illustrating the method for filling holes in the digital model of an automated production line in this application.

[0044] Figure 7 This is the seventh flowchart illustrating the method for filling holes in the digital model of an automated production line in this application.

[0045] Figure 8 This is a structural diagram of the hole-filling device for the digital model of the automated production line in the embodiments of this application;

[0046] Figure 9This is a schematic diagram of the structure of the electronic device in the embodiments of this application.

[0047] Figure label:

[0048] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver storage unit 9144, antenna 9111, speaker 9131, microphone 9132. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0051] To address the problems existing in current technologies, this application provides a method and apparatus for filling holes in digital models of automated production lines. Through multi-level mesh analysis and curvature field calculation, the method accurately identifies the areas to be processed. An innovative patch generation mechanism based on density clustering and neural networks is designed, combined with local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled area, and is closely integrated with the motion control and path planning of the automated production line. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0052] To overcome the limitations of traditional model repair methods and provide an efficient and reliable solution for the complete reconstruction of industrial digital models, this application provides an embodiment of a method for filling holes in digital models of automated production lines. See [link to embodiment]. Figure 1 The method for filling holes in the digital model of the automated production line specifically includes the following:

[0053] Step S101: Decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the area to be processed, extract boundary points from the area to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor;

[0054] Optionally, this embodiment employs an adaptive octree structure for multi-level partitioning during the mesh decomposition process. During partitioning, a bounding box is first established for the entire automated production line model, and then the subspace partitioning is dynamically adjusted based on local geometric complexity. For complex areas such as turns in the conveyor system, joint structures of robotic arms, and equipment connection surfaces, a recursive subdivision strategy is used until the mesh size meets the preset accuracy requirements. For example, near the end effector of the robotic arm, where precise path planning and collision detection are required, the mesh size can reach the millimeter level; while in simpler areas such as large support frames, a centimeter-level mesh size is maintained, achieving optimized allocation of computational resources.

[0055] In this embodiment, an adaptive curvature estimation algorithm based on local fitting is implemented in the curvature field calculation stage. For each grid vertex, its topological neighborhood range is first determined, and the K-nearest neighbor search method is used to select sample points to participate in the fitting. Then, a local parameterized plane is constructed using the moving least squares method to establish a quadratic surface fitting model. In irregular surface areas of the production line, such as the transition fillets of the robot base and the guide grooves of the conveyor belt, the size of the fitting window is dynamically adjusted by analyzing the distribution characteristics of the local point cloud. For areas with drastic curvature changes, the fitting window is reduced to improve accuracy; for gradually transitioning areas, the fitting window is expanded to enhance stability.

[0056] In this embodiment, a feature-preserving hierarchical projection algorithm was developed during curvature field projection. First, the spatial correspondence between mesh levels was established, and the projection mapping was determined using the inclusion relationship of octree nodes. During projection calculation, a weighting function based on geodesic distance was introduced to ensure accurate transfer of feature information across different resolutions. For example, at the mounting interface of the control cabinet, a local feature decomposition strategy was used to accurately project the curvature information of higher-level meshes to the finest level, avoiding the loss of important features during multi-resolution conversion.

[0057] This embodiment employs a hybrid difference scheme for gradient estimation when calculating curvature gradients. Gradient calculation of the curvature field is achieved by constructing a difference operator on an irregular mesh. When dealing with characteristic boundaries of the production line model, such as mating surfaces between equipment and boundaries of functional units, a one-sided difference scheme is used to avoid numerical oscillations across these boundaries. For smooth transition regions, a central difference scheme is used to improve computational accuracy. Simultaneously, an adaptive step-size control mechanism is introduced to automatically reduce the computational step size where gradient changes drastically, ensuring numerical stability.

[0058] This embodiment implements an adaptive segmentation algorithm based on multi-scale feature analysis during threshold segmentation. First, statistical analysis of the curvature gradient field is performed to construct a local histogram, and an initial threshold is determined through peak detection. Then, a region growing strategy is introduced to dynamically adjust the threshold based on the spatial continuity of the gradient. In precision assembly areas of the production line, such as bearing housings and guide rails, a smaller threshold interval is used to capture subtle features; in areas with large structural components, a larger threshold interval is used to improve processing efficiency.

[0059] In this embodiment, a boundary tracing algorithm based on topological manifolds was developed for the boundary point extraction stage. By analyzing the connectivity of mesh cells, a half-edge data structure is constructed to automatically extract boundary loops. When processing characteristic transition regions of the production line model, such as the connection between the conveyor belt and the support, and the contact surface between the electrical control box and the base plate, curvature continuity constraints are used to ensure the smoothness of the boundary. For complex nodes with multiple connections, a branching mechanism is introduced to ensure the integrity of the boundary and the correctness of the topology.

[0060] This embodiment implements a robust estimation method based on tensor voting during the normal vector calculation process. First, principal direction analysis is performed on the local neighborhood of the boundary points to construct the covariance matrix. Then, the initial direction of the normal vector is determined through eigenvalue decomposition, and the direction is optimized using a tensor voting mechanism. Flatness constraints are added to key positioning surfaces on the production line, such as the mounting reference surface of the robotic arm and the mounting surface of sensors, to improve the accuracy of the normal vector. For curved transition regions, curvature weight adjustment ensures smooth changes in the normal vector.

[0061] This embodiment employs a multi-level feature encoding strategy when constructing feature descriptors. Geometric features such as the location information of boundary points, normal vector fields, and principal curvature directions are organized into a hierarchical descriptive structure. At the local feature encoding level, a geodesic distance-based feature aggregation method is used to ensure the descriptor's sensitivity to local geometric changes. At the global feature level, a feature propagation network captures long-range dependencies, enabling the descriptor to express the functional relationships between production line components.

[0062] This embodiment constructs a complete feature analysis system for production line digital models through the above implementation scheme. This scheme can accurately identify and characterize various feature structures in the model, providing a reliable feature foundation for subsequent hole filling. Practice shows that this scheme exhibits good adaptability and stability when dealing with complex automated production line digital models, effectively supporting the digital transformation and optimization of production lines.

[0063] Step S102: Perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches;

[0064] Optionally, this embodiment develops an adaptive density threshold clustering algorithm for density clustering analysis. The density threshold is dynamically adjusted to address different types of defects in automated production lines, such as mesh breaks at robotic arm joints or missing models in conveyor belt systems. The algorithm first calculates the local density of each boundary feature descriptor and determines the clustering core points by analyzing the gradient field of the density distribution. In precision-fitting areas of the production line, such as bearing housing contact surfaces and guide rail sliding surfaces, a higher density threshold is used to ensure accurate feature segmentation.

[0065] This embodiment implements a feature-preserving spatial reconstruction method during the clustering result mapping process. By establishing a mapping relationship between the feature descriptor space and three-dimensional Euclidean space, the cluster boundaries are converted into actual geometric patches. During the mapping process, a local coordinate system transformation mechanism is introduced to ensure that the orientation of the patches remains consistent with the original model surface. For example, when processing cylindrical holes in a robot base, the tangential continuity between the reconstructed patches and the cylindrical surface is guaranteed by analyzing local geometric features.

[0066] In this embodiment, a weighted geodesic distance evaluation method is used in the calculation of the normal vector angle. For each filled surface, a geodesic path is constructed between the normal vector and the boundary point, and the gradient relationship of the normal vector is calculated along the path. When dealing with the transition areas of production line equipment, such as the connection between the control cabinet and the bracket, and sensor mounting slots, curvature weights are introduced to ensure the smoothness of the normal vector transition.

[0067] In this embodiment, a multi-layered feature extraction structure is designed during the construction of the neural network model. The input layer receives local geometric features, including geometric quantities such as principal curvature values, Gaussian curvature, and mean curvature, as well as the topological relationships between adjacent regions. The hidden layer performs feature transformation through a multilayer perceptron, gradually extracting high-level semantic features. During training, typical samples from different parts of the production line are used, such as planar contact, arc transitions, and irregular surfaces, to ensure the model's generalization ability.

[0068] In this embodiment, feature aggregation based on an attention mechanism is implemented when predicting the optimal included angle threshold. The model dynamically adjusts the feature weights by analyzing the importance distribution of local geometric features. For key functional surfaces in the production line, such as positioning reference surfaces and assembly contact surfaces, the model assigns higher feature weights, thereby generating stricter included angle threshold constraints.

[0069] In this embodiment, a multi-level screening mechanism was developed during the marking of the surface patches to be optimized. First, preliminary screening is performed based on a predicted included angle threshold, followed by refined screening combining local curvature continuity and topological consistency. When processing precision-fitting components on the production line, such as the cylindrical surface of bearing housings and the sliding surface of guide rails, even stricter screening criteria are adopted to ensure the geometric accuracy of the filled surface patches.

[0070] In this embodiment, an adaptive mesh subdivision strategy is employed in the boundary curvature calculation stage. By analyzing the gradient of curvature changes, local subdivision is performed in regions of abrupt curvature changes to improve the accuracy of curvature estimation. For characteristic transition regions in the production line, such as rounded corners and chamfers, curvature tensor analysis is used to ensure the continuity of curvature information.

[0071] This embodiment implements an intelligent connection mechanism based on feature recognition when constructing topological connections. By analyzing the positional relationships and geometric features between the facets to be optimized, it automatically identifies functionally related facet combinations. When dealing with model defects in conveyor belt systems, it can accurately identify the direction of conveyor belt movement and the functional associations of adjacent components.

[0072] In this embodiment, a trajectory planning algorithm based on geometric constraints was developed during the motion control command generation process. By analyzing the geometric features and topological relationships of the filled surface, a motion trajectory that meets the continuity requirement is generated. For operations requiring precise positioning, such as the gripping point of a robotic arm or the detection position of a vision sensor, feature point extraction is used to ensure the accuracy of the control commands.

[0073] This embodiment constructs a complete model repair and control command generation system through the above implementation scheme. This scheme can effectively handle various defects in the digital model of automated production lines and generate precise motion control commands. Practice shows that this scheme exhibits good adaptability and reliability in actual production line operation and maintenance, and can effectively support the automated operation and precise control of the production line.

[0074] Step S103: Input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0075] Optionally, this embodiment develops an adaptive node vector generation algorithm during the construction of non-uniform rational basis spline surfaces. For different types of areas to be repaired in automated production lines, such as surface transitions at robotic arm joints and guide grooves in conveyor belt systems, the distribution of control points is dynamically adjusted. By analyzing the characteristics of boundary curvature distribution, the density of control points is increased where curvature changes drastically, ensuring the accurate representation of local geometric features on the reconstructed surface.

[0076] In this embodiment, a weight adjustment mechanism based on geometric features is implemented in the control point weight optimization stage. By analyzing the principal curvature direction and curvature value of the region to be repaired, an initial weight is assigned to each control point. Larger weight values ​​are used at critical locations on precision assembly surfaces of the production line, such as the mating surfaces of bearing housings and the sliding surfaces of guide rails, to improve the local control accuracy of the surface. Smaller weight values ​​are used for transition regions to achieve a smooth transition.

[0077] This embodiment employs a hierarchical constraint system when constructing continuity constraints. First, positional continuity constraints are established to ensure precise connection between the reconstructed surface and the boundary of the original model. Then, tangential continuity constraints are introduced to ensure smooth surface transitions. When processing functional surfaces of production line equipment, such as the mounting surface of vision sensors and the gripping surface of fixtures, normal continuity constraints must also be satisfied to ensure the accuracy of subsequent operations.

[0078] This embodiment implements a multi-objective trade-off mechanism in the design of the smoothness objective function. The objective function includes a geometric error term, a surface energy term, and a topological consistency term. The geometric error term ensures the fitting accuracy between the reconstructed surface and the boundary points, the surface energy term controls the smoothness of the surface, and the topological consistency term ensures a continuous transition between adjacent surfaces. During the optimization process, the weights of each term are dynamically adjusted according to the functional requirements of different parts of the production line.

[0079] In this embodiment, an adaptive step size control strategy was developed during the iterative optimization process. The optimization step size is dynamically adjusted by analyzing the gradient information of the objective function. A larger step size is used in the early stages of optimization to quickly approximate the solution space, and the step size is gradually reduced as the optimization process progresses to improve accuracy. For precision-fitting components in the production line, a more stringent convergence criterion is adopted to ensure the geometric accuracy of the reconstructed surface.

[0080] In this embodiment, a distance field analysis method is used in the transition region calculation stage. By constructing a distance field function between the initial filled surface and the boundary of the original model, the range of the transition region is determined based on contour line analysis. When determining the transition region, the functional characteristics of the production line equipment are considered, such as the clearance requirements of moving parts and the accuracy requirements of assembly datums, to reasonably set the range of the transition region.

[0081] This embodiment implements a feature-preserving Laplacian operator during mesh smoothing. A weighted Laplacian operator is constructed by analyzing the local geometric features of the mesh vertices. During smoothing, a smaller smoothing intensity is applied to functionally important feature edges and points, while a larger smoothing intensity is used for general transition regions, achieving selective smoothing.

[0082] In this embodiment, a mesh quality optimization algorithm was developed during the final model generation. By analyzing the shape quality indicators of mesh cells, such as aspect ratio and included angles, the mesh was locally optimized and adjusted. In key functional areas of the production line, such as the movement trajectory area of ​​the robotic arm and the detection area of ​​sensors, the mesh quality was ensured to meet the requirements of subsequent simulation analysis.

[0083] In this embodiment, an octree-based spatial index structure is implemented during the 3D visualization system integration phase. By establishing hierarchical spatial partitions for filling the model, the computational efficiency of collision detection and path planning is improved. When processing the motion planning of the robotic arm, potential collision areas can be quickly located, and the optimal motion trajectory can be generated.

[0084] This embodiment constructs a complete model reconstruction and optimization system through the above implementation scheme. This scheme is particularly suitable for the repair and optimization of digital models in automated production lines, accurately reconstructing various defect areas and ensuring the geometric accuracy and functional integrity of the repaired model. Practice has shown that this scheme reliably supports virtual debugging and motion planning of production lines, providing strong digital support for intelligent manufacturing.

[0085] As described above, the hole-filling method for automated production line digital models provided in this application can accurately identify the areas to be processed through multi-level mesh analysis and curvature field calculation. It innovatively designs a patch generation mechanism based on density clustering and neural networks, combining local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled area, and is closely integrated with the motion control and path planning of the automated production line. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0086] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 2 It can also specifically include the following:

[0087] Step S201: The octree decomposition algorithm is used to divide the digital model of the automated production line into grid layers of different scales. A vertex adjacency graph is constructed for each grid layer. The Gaussian curvature and average curvature of the grid vertices are calculated based on the adjacency graph. The Gaussian curvature and average curvature are combined to form a local curvature field distribution.

[0088] Step S202: The curvature fields of different levels are projected onto the finest level grid using an interpolation mapping algorithm between grid levels to construct a curvature gradient tensor field. The principal direction and eigenvalues ​​of the curvature gradient tensor field are calculated. An adaptive threshold segmentation function is constructed based on the eigenvalues. The output of the segmentation function is marked as the region to be processed.

[0089] Optionally, this embodiment implements an adaptive partitioning strategy based on geometric features during the octree decomposition process. The mesh partitioning accuracy is dynamically adjusted for different functional units in the automated production line, such as the joint structure of a robotic arm, the guiding device of a conveyor belt, and the mounting surface of a control cabinet. In precision operation areas of the production line, such as the gripping position of a robot fixture and the detection area of ​​a vision sensor, a finer mesh partitioning is used to ensure accurate capture of geometric features.

[0090] This embodiment develops a multi-resolution topology maintenance mechanism during mesh hierarchy construction. By establishing parent-child relationships between octree nodes, ordered organization of the mesh hierarchy is achieved. For complex transitional areas in the production line, such as equipment connections and interfaces of functional components, geometric details are preserved through recursive subdivision, while balancing accuracy and efficiency within the limits of computational resources.

[0091] This embodiment employs a dynamically updated data structure during the construction of the vertex adjacency graph. For each mesh level, an efficient adjacency query mechanism is established by analyzing the topological connections between vertices. When dealing with complex curved surfaces of production line equipment, such as the outer shell structure of a robotic arm or the guide grooves of a conveyor belt, the integrity and correctness of adjacency relationships are ensured.

[0092] In this embodiment, a curvature estimation algorithm based on local fitting is implemented in the curvature calculation stage. By analyzing the neighborhood structure of each grid vertex, the moving least squares method is used to fit the local surface. In characteristic transition regions of the production line, such as fillet transitions and chamfers, the fitting window size is adaptively adjusted to ensure the accuracy of curvature calculation.

[0093] This embodiment develops a feature-preserving curvature synthesis method when constructing local curvature fields. By combining Gaussian curvature and mean curvature, a complete curvature descriptor is constructed. When dealing with irregular surfaces on production lines, such as the mounting surface of a robot base or the heat dissipation holes of a control cabinet, it can accurately express the variation patterns of local geometric features.

[0094] This embodiment implements a feature-preserving hierarchical mapping algorithm during curvature field projection. By constructing spatial correspondences between grids of different resolutions, a distance-weighted interpolation strategy is adopted to ensure the accurate transmission of curvature information during hierarchical transformation. For precision-fitting structures in the production line, such as the mating surfaces of bearing housings and the sliding surfaces of guide rails, special attention is paid to maintaining the continuity of geometric features.

[0095] This embodiment employs a robust numerical differentiation method for calculating the curvature gradient tensor field. By constructing a local coordinate system, the rate of change of curvature in different directions is analyzed to form a complete gradient tensor description. When dealing with characteristic boundaries of production line equipment, such as the motion limits of robotic arms and the guide edges of conveyor belts, an adaptive step size strategy is used to ensure the accuracy of gradient calculation.

[0096] In this embodiment, a direction extraction algorithm based on eigenvalue decomposition was developed during the main direction analysis process. By analyzing the characteristic structure of the gradient tensor, the main directions of local geometric changes are determined. When processing functional surfaces of a production line, such as the operating surfaces of robot tool ends and the detection surfaces of vision sensors, accurate identification of characteristic directions is of great significance for subsequent operation planning.

[0097] This embodiment implements a multi-scale feature analysis mechanism when constructing the threshold segmentation function. By comprehensively considering the feature value distribution of the curvature gradient, the segmentation threshold is dynamically adjusted. When dealing with different types of defects in the production line, such as model breakage and mesh missing, an adaptive threshold strategy is adopted to ensure the rationality of the segmentation results.

[0098] This embodiment establishes a complete geometric feature analysis system through the above implementation scheme. This scheme can accurately identify abnormal areas in the digital model of automated production lines, providing reliable feature basis for subsequent model repair. Practice shows that this scheme exhibits good adaptability and stability when dealing with complex industrial scenarios, and can effectively support the digital optimization and transformation of production lines.

[0099] In practical applications, the solution in this embodiment successfully addresses various types of production line model defects, such as mesh breaks at robotic arm joints and missing models of conveyor belt systems. It provides a reliable geometric basis for virtual debugging and motion planning of production lines, effectively improving the digitalization level of automated production lines.

[0100] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 3 It can also specifically include the following:

[0101] Step S301: Construct a boundary tracing algorithm for the region to be processed. Search for the connected boundaries of the region to be processed based on the mesh topology connection relationship. Extract the mesh vertices on the connected boundaries into a set of boundary points. Use the local surface fitting method to calculate the normal vector field of the set of boundary points.

[0102] Step S302: Perform spatial coordinate transformation on the set of boundary points, establish a local coordinate system centered on the boundary points, orthogonally decompose the three-dimensional coordinate information of the boundary points and the normal vector field in the local coordinate system, and construct a boundary feature descriptor containing position coordinate components and normal vector components.

[0103] Optionally, this embodiment implements a boundary recognition mechanism based on topological manifolds during the boundary tracking algorithm construction process. Adaptive boundary search strategies are developed for different types of defect areas in automated production lines, such as mesh breaks at robotic arm joints, missing models in conveyor belt systems, and deformation of control cabinet mounting surfaces. By analyzing the connection relationships between mesh cells, a half-edge data structure is constructed to achieve rapid boundary localization and tracking.

[0104] This embodiment employs a hierarchical, progressive search strategy during the connected boundary search process. First, the boundary starting point is identified based on the mesh's topological connectivity. Then, the search gradually expands along the boundary direction until a closed boundary is constructed. When dealing with complex boundaries of production line equipment, such as irregular surfaces on robot tool ends or the internal contours of sensor mounting slots, directional continuity constraints ensure the accuracy of boundary tracking.

[0105] In this embodiment, a feature-preserving sampling algorithm was developed for the boundary point extraction stage. By analyzing the boundary curvature distribution, the sampling density is increased in areas of drastic curvature change, while the sampling frequency is appropriately reduced in flat areas. For precision-fitting components in the production line, such as the cylindrical surface of bearing housings and the sliding surface of guide rails, a denser sampling strategy is adopted to ensure the complete preservation of geometric features.

[0106] This embodiment implements a robust estimation method based on local fitting during the normal vector calculation process. For each boundary point, a local neighborhood is constructed, and the local surface is fitted using the moving least squares method. When dealing with characteristic transition regions of the production line, such as rounded corners and chamfers, the fitting window size is adaptively adjusted to ensure the accuracy of the normal vector calculation.

[0107] In this embodiment, a principal direction analysis method is used to construct the local coordinate system. By analyzing the spatial distribution characteristics of the boundary point set, the main directions of change are determined as the coordinate axes. When processing functional surfaces of the production line, such as the motion reference surface of the robotic arm and the detection surface of the vision sensor, the appropriate selection of the coordinate system direction has a significant impact on subsequent feature description.

[0108] In this embodiment, a feature-preserving transformation algorithm was developed for coordinate transformation. By constructing a rigid body transformation matrix, boundary point information in the global coordinate system is mapped to the local coordinate system. During the transformation process, special attention is paid to preserving the invariance of geometric features to ensure that boundary features can be accurately represented in the local coordinate system.

[0109] In this embodiment, a multi-scale feature decomposition mechanism is implemented in the orthogonal decomposition stage. The positional information and normal vector information of boundary points are projected onto the orthogonal basis of the local coordinate system to form a complete feature representation. When processing different types of features in the production line, such as planes, cylindrical surfaces, and freeform surfaces, key geometric features are highlighted through reasonable component weight configuration.

[0110] This embodiment employs a hierarchical feature encoding strategy when constructing feature descriptors. The positional and normal vector components obtained from orthogonal decomposition are organized into structured description vectors. For critical functional components in the production line, such as positioning references and assembly interfaces, their importance is highlighted by increasing feature weights.

[0111] In this embodiment, an adaptive normalization method was developed during the descriptor normalization process. The normalization parameters are dynamically adjusted by analyzing the statistical distribution of the feature components. When dealing with production line components of different scales, such as large support frames and precision connectors, a hierarchical normalization strategy is adopted to ensure the balance of feature representation.

[0112] This embodiment establishes a complete boundary feature extraction and description system through the above implementation scheme. This scheme can accurately capture boundary features in the digital model of automated production lines, providing a reliable feature foundation for subsequent model repair and optimization. Practice shows that this scheme exhibits good adaptability and stability when handling complex industrial scenarios.

[0113] In practical applications, the solution in this embodiment has successfully handled various types of production line model defect boundary feature extraction problems, such as complex curved surfaces at robotic arm joints and guide grooves in conveyor belt systems, providing reliable geometric feature support for the digital optimization and transformation of production lines and effectively improving the digital twin level of automated production lines.

[0114] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 4 It can also specifically include the following:

[0115] Step S401: Construct a similarity measurement function for boundary feature descriptors, calculate the distance matrix between feature descriptors based on the similarity measurement function, use a density-based spatial clustering algorithm to divide the boundary feature descriptors into multiple clusters, calculate the core point and boundary point for each cluster, and project the spatial coordinates of the core point and boundary point back into three-dimensional space to form a filling patch.

[0116] Step S402: Calculate the normal vector of the filled patch based on the mesh vertices, establish an angle evaluation model between the normal vector of the filled patch and the normal vector of the boundary point, use the angle evaluation model as the input feature of the neural network, construct a multilayer perceptron network structure, and use the local geometric features of the boundary points as training samples to optimize the neural network.

[0117] Optionally, this embodiment develops a multi-feature fusion distance calculation mechanism during the construction of the similarity metric function. For different types of boundary features in automated production lines, such as the joint structure of a robotic arm, the guide groove of a conveyor belt, and the mounting surface of a control cabinet, a weighted Euclidean distance metric is constructed by comprehensively considering the differences between position coordinate components and normal vector components. When dealing with precision-fitting components in the production line, such as the cylindrical surface of a bearing housing and the sliding surface of a guide rail, the influence of key geometric features is highlighted by dynamically adjusting the feature weights.

[0118] This embodiment implements an efficient parallel computing strategy in the distance matrix calculation stage. By constructing a spatial index structure for feature descriptors, the search efficiency for distance calculation is optimized. When dealing with large-scale production line models, such as complex assembly line layouts and multi-robot collaborative workstations, it can efficiently handle the distance relationships between massive amounts of feature points.

[0119] In this embodiment, an adaptive density threshold clustering strategy is adopted in the density clustering algorithm implementation. Clustering parameters are dynamically determined by analyzing the point density distribution in the feature space. When processing characteristic regions of production line equipment, such as irregular surfaces of robot tool ends or the internal contours of sensor mounting slots, it can accurately identify combinations of regions with similar geometric features.

[0120] In this embodiment, a topological importance-based evaluation method was developed for the core point extraction stage. By analyzing the density distribution and connectivity within clusters, representative core feature points are identified. When processing critical functional surfaces of the production line, such as positioning reference surfaces and assembly contact surfaces, particular emphasis is placed on maintaining the representativeness of geometric features.

[0121] This embodiment implements a feature-preserving mapping algorithm during spatial projection. By constructing a mapping relationship between the feature space and the three-dimensional Euclidean space, it ensures that the projection result meets the geometric continuity requirements. When processing feature transition areas in the production line, such as fillet transitions and chamfers, curvature constraints are used to ensure the smoothness of the projected surface.

[0122] This embodiment employs a robust normal vector estimation method for calculating the normal vectors of facets. By analyzing the local distribution characteristics of the facet vertices, a weighted least-squares fitting plane is constructed to extract reliable normal vector information. When processing precision surfaces of production line equipment, such as the detection surfaces of vision sensors and the gripping surfaces of fixtures, particular emphasis is placed on the accuracy of normal vector calculation.

[0123] In this embodiment, a multi-scale feature analysis mechanism was developed during the construction of the angle evaluation model. By comprehensively considering multiple evaluation indicators such as the angle between normal vectors, curvature similarity, and positional continuity, a complete evaluation system is constructed. When dealing with complex curved surfaces in production lines, such as the shell structure of robotic arms and the guiding device of conveyor belts, the geometric rationality of the filling patch can be accurately evaluated.

[0124] In this embodiment, a deep learning model based on local geometric features is implemented in the neural network construction stage. The network input layer receives multi-dimensional features such as the angle between normal vectors, curvature features, and topological relationships, which are then transformed and fused through a multilayer perceptron. During training, typical samples from different parts of the production line, such as planar contact, arc transitions, and irregular surfaces, are used to ensure the model's generalization ability.

[0125] In this embodiment, a dynamic learning rate adjustment strategy is employed during network optimization. By analyzing the feature distribution of training samples, the optimization parameters are adaptively adjusted. For key functional components in the production line, such as positioning references and assembly interfaces, the model's sensitivity to key features is improved by increasing sample weights.

[0126] This embodiment establishes a complete feature clustering and evaluation system through the above implementation scheme. This scheme can accurately identify and evaluate the missing regions in the digital model of automated production lines, providing a reliable quality evaluation basis for subsequent model optimization. Practice shows that this scheme exhibits good adaptability and stability when dealing with complex industrial scenarios.

[0127] In practical applications, the solution in this embodiment has successfully addressed various types of production line model filling quality assessment problems, such as complex curved surfaces at robotic arm joints and guide grooves in conveyor belt systems. It provides reliable quality assurance for the digital optimization and transformation of production lines and effectively improves the accuracy of digital twins in automated production lines.

[0128] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 5 It can also specifically include the following:

[0129] Step S501: Apply the trained neural network model to the local geometric features of the fill patch, output the optimal angle threshold between the patch normal vector and the boundary point normal vector, filter the fill patches based on the optimal angle threshold, construct an index set of patches to be optimized, calculate the principal curvature direction and curvature value of the boundary of the patch to be optimized, and establish an adjacency graph between patches.

[0130] Step S502: Convert the boundary curvature information of the surface to be optimized into a discrete sampling point sequence, establish a parameterized representation of the surface boundary based on the sampling point sequence, construct transition constraints between surfaces using topological connection relationships, use the transition constraints as constraints of control commands, and generate a motion control command sequence that meets the continuity requirements.

[0131] Optionally, in this embodiment, a trained neural network is used for inference calculation during the optimal included angle threshold prediction process. The network input includes the local geometric features of the filled surface, such as principal curvature values, Gaussian curvature, and average curvature, as well as the positional relationship features between the surface and boundary points. When processing different functional components of an automated production line, such as the joint structure of a robotic arm or the guide groove of a conveyor belt, the model can dynamically adjust the threshold prediction strategy based on specific geometric features.

[0132] In this embodiment, a multi-level screening mechanism is implemented in the patch selection process. First, preliminary screening is performed based on a predicted included angle threshold. Then, refined screening is conducted by combining local curvature continuity and topological consistency. When processing precision-fitting components on the production line, such as the mating surfaces of bearing housings and the sliding surfaces of guide rails, even stricter screening criteria are adopted to ensure the geometric accuracy of the filled patches.

[0133] In this embodiment, a robust curvature estimation algorithm was developed during the principal curvature calculation process. By constructing a local quadratic surface fit, the curvature changes of the surface in different directions are analyzed. When processing characteristic transition areas of production line equipment, such as rounded corners and chamfers, the fitting window size is adaptively adjusted to ensure the accuracy of the curvature calculation.

[0134] This embodiment employs a feature-based intelligent connection mechanism when constructing the adjacency graph. By analyzing the positional relationships and geometric features between the faces to be optimized, it automatically identifies functionally related face combinations. When addressing model defects in a conveyor belt system, it can accurately identify the conveyor belt's movement direction and the functional associations of adjacent components.

[0135] This embodiment implements an adaptive sampling strategy during the curvature information discretization process. By analyzing the gradient of curvature changes, the sampling density is increased in regions of abrupt curvature changes, while the sampling frequency is appropriately reduced in regions of gentle curvature. For characteristic transition regions in the production line, such as irregular surfaces of robot tool ends and mounting slots in control cabinets, it ensures that the sequence of sampling points can accurately represent geometric features.

[0136] In this embodiment, a feature-preserving parameterization method was developed during the parameterization representation construction stage. By analyzing the spatial distribution characteristics of the sampling point sequence, suitable parameterization basis functions are constructed. When dealing with complex curved surfaces in production lines, such as the shell structure of a robotic arm or the mounting surface of a sensor, curvature constraints are used to ensure the geometric accuracy of the parameterization representation.

[0137] This embodiment employs a hierarchical constraint system when constructing transition constraints. First, positional continuity constraints are established to ensure precise connection between adjacent surfaces. Then, tangential continuity constraints are introduced to guarantee a smooth transition. When processing functional surfaces of production line equipment, such as the detection surfaces of vision sensors and the gripping surfaces of fixtures, normal continuity constraints must also be satisfied.

[0138] This embodiment implements a trajectory planning algorithm based on geometric constraints during the motion control command generation process. By analyzing the geometric features and topological relationships of the patches, a motion trajectory that meets the continuity requirement is generated. For operations requiring precise positioning, such as the gripping point of a robotic arm or the detection position of a vision sensor, feature point extraction ensures the accuracy of the control commands.

[0139] In this embodiment, an optimization strategy considering dynamic constraints was developed during the instruction sequence optimization stage. By analyzing the acceleration and velocity limits of moving parts, control commands are dynamically adjusted. When processing the robot's motion planning, particular emphasis is placed on maintaining the smoothness and continuity of the motion.

[0140] This embodiment constructs a complete geometry optimization and motion control system through the above implementation scheme. This scheme can accurately identify and optimize problem areas in the digital model of automated production lines and generate reliable motion control commands. Practice shows that this scheme exhibits good adaptability and stability when handling complex industrial scenarios.

[0141] In practical applications, the solution in this embodiment has successfully handled various types of production line motion control problems, such as precise positioning of robotic arms and speed control of conveyor belts, providing a reliable control foundation for the automated operation of production lines and effectively improving the operating efficiency and accuracy of automated production lines.

[0142] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 6 It can also specifically include the following:

[0143] Step S601: Convert the boundary curvature information of the patch to be optimized into a control point sequence, construct the node vector of the NURBS surface based on the control point sequence, calculate the value of the NURBS basis function on the node vector, perform weight optimization on the basis function to obtain the mathematical expression of the non-uniform rational basis spline surface, and establish the mapping relationship between the surface parameter domain and the three-dimensional space.

[0144] Step S602: Construct positional continuity and tangential continuity constraints between adjacent patches based on the topological connection relationship of the patches to be optimized. Combine the continuity constraints with the mean curvature and Gaussian curvature of the surface to construct a smoothness evaluation function. Use the smoothness evaluation function as the optimization objective function.

[0145] Optionally, this embodiment employs an adaptive sampling strategy based on curvature features during the control point sequence generation process. For different types of functional surfaces in automated production lines, such as the joint structure of a robotic arm, the guide groove of a conveyor belt, and the mounting surface of a control cabinet, the density of control points is dynamically adjusted by analyzing the boundary curvature distribution. The number of control points is increased where curvature changes drastically to ensure accurate capture of local geometric features.

[0146] In this embodiment, a node distribution algorithm based on geometric features is implemented in the node vector construction stage. By analyzing the spatial distribution characteristics of the control point sequence, the node positions are determined using the cumulative chord length parameterization method. When processing precision-fitting components on the production line, such as the cylindrical surface of a bearing housing or the sliding surface of a guide rail, the local control accuracy of the curved surface is improved by refining the node distribution.

[0147] In this embodiment, a numerically stable recursive algorithm was developed during the basis function calculation process. By constructing the recursive relationship of the basis functions, computational stability is ensured even when the node vector repetition is high. When processing characteristic transition regions of production line equipment, such as rounded corners and chamfers, the order of the basis functions is adjusted to balance accuracy and smoothness.

[0148] In this embodiment, an optimization strategy that considers geometric features is adopted in the weight optimization stage. By analyzing the local geometric features of the control points, an initial weight value is assigned to each control point. Larger weight values ​​are used at critical locations such as the precision operation surface of the robot tool end and the detection surface of the vision sensor to improve local control accuracy.

[0149] This embodiment implements a feature-preserving parameterization method during the mapping relationship construction. By constructing a bidirectional mapping relationship between the parameter domain and three-dimensional space, the uniformity and stability of surface parameterization are ensured. When dealing with complex surfaces in production lines, such as the shell structure of a robotic arm or the guiding device of a conveyor belt, the uniform distribution of geometric features is maintained through equidistant mapping.

[0150] This embodiment employs a hierarchical constraint system during the construction of continuity constraints. First, positional continuity constraints are established to ensure precise connection between adjacent surfaces. Then, tangential continuity constraints are introduced to guarantee smooth transitions. When handling functional surfaces of the production line, such as positioning reference surfaces and assembly contact surfaces, geometric continuity requirements are ensured through constraint conditions.

[0151] In this embodiment, a curvature estimation algorithm based on local fitting was developed for the mean curvature calculation stage. By constructing a local parametric surface, the algorithm analyzes the changes in principal curvature of the surface in different directions. When processing characteristic areas of production line equipment, such as the mounting surface of a robot base and the heat dissipation holes of a control cabinet, the algorithm accurately calculates the local geometric features of the surface.

[0152] This embodiment implements a robust numerical calculation method in the Gaussian curvature calculation process. By analyzing the basic shape characteristics of the surface, an appropriate calculation window size is constructed. When dealing with irregularly shaped surfaces in the production line, such as sensor mounting slots and fixture gripping surfaces, the accuracy and stability of the curvature calculation are ensured.

[0153] This embodiment employs a multi-objective trade-off evaluation mechanism when constructing the smoothness evaluation function. A complete evaluation system is built by comprehensively considering continuity constraints, mean curvature, and Gaussian curvature. During the optimization process, the weights of each factor are dynamically adjusted according to the functional requirements of different parts of the production line to achieve balanced optimization of geometric features.

[0154] This embodiment establishes a complete surface reconstruction and optimization system through the above implementation scheme. This scheme can accurately reconstruct problem areas in the digital model of automated production lines and ensure the geometric quality of the reconstructed surfaces. Practice shows that this scheme exhibits good adaptability and stability when handling complex industrial scenarios.

[0155] In practical applications, the solution in this embodiment has successfully handled various types of production line model reconstruction problems, such as complex curved surfaces at the joints of robotic arms and guide grooves in conveyor belt systems, providing a reliable geometric basis for the digital optimization and transformation of production lines and effectively improving the digital twin accuracy of automated production lines.

[0156] In one embodiment of the hole-filling method for the digital model of an automated production line in this application, see [link to relevant documentation]. Figure 7 It can also specifically include the following:

[0157] Step S701: Numerically optimize the objective function using gradient descent. Iteratively calculate and update the control point positions and weight parameters of the NURBS surface until the objective function converges to obtain an initial filling surface that satisfies the continuity constraint. Construct the distance field function between the initial filling surface and the boundary of the original model. Determine the range of the transition region based on the contour lines of the distance field function.

[0158] Step S702: Construct the Laplacian operator for the mesh vertices in the transition region, calculate the displacement vector of the mesh vertices based on the Laplacian operator, iteratively update the spatial position of the mesh vertices to achieve local smoothing, merge the smoothed mesh with the original model to form a complete filling model, and establish the spatial index structure of the filling model for path planning and collision detection.

[0159] Optionally, this embodiment employs an iterative strategy with an adaptive step size during the gradient descent optimization process. For different functional surfaces in an automated production line, such as the joint structure of a robotic arm, the guide groove of a conveyor belt, and the mounting surface of a control cabinet, the optimization step size is dynamically adjusted by analyzing the gradient changes of the objective function. The step size is increased in regions with slow convergence and decreased in sensitive regions to ensure the stability of the optimization process.

[0160] In this embodiment, a constraint-based position adjustment mechanism is implemented in the control point update stage. By analyzing continuity constraints, update rules for control point positions are constructed. When dealing with precision-fitted components on the production line, such as the cylindrical surface of a bearing housing or the sliding surface of a guide rail, special attention is paid to maintaining the continuity of geometric features.

[0161] In this embodiment, a weight adjustment strategy that considers local features was developed during the weight parameter optimization process. By analyzing the local geometric features of the surface, the weight values ​​of the control points are dynamically adjusted. When dealing with characteristic transition areas of production line equipment, such as rounded corners and chamfers, weight optimization ensures a smooth transition of the surface.

[0162] In this embodiment, a fast traversal algorithm is used to calculate the distance field when constructing the distance field function. By establishing a distance mapping relationship between the initial filled surface and the original model boundary, the shortest distance from any point in space to the boundary is calculated efficiently. This ensures the accuracy of the distance field calculation at critical locations such as the precision operating surface of the robot tool end and the detection surface of the vision sensor.

[0163] In this embodiment, an adaptive region division strategy is implemented in the transition region determination stage. The range of the transition region is dynamically determined by analyzing the contour distribution of the distance field. When dealing with complex curved surfaces in the production line, such as the outer shell structure of a robotic arm or the guiding device of a conveyor belt, the size of the transition region is adjusted based on local geometric features.

[0164] In this embodiment, a weight configuration method based on geometric features is used during the construction of the Laplacian operator. By analyzing the local neighborhood structure of mesh vertices, a Laplacian matrix considering geometric features is constructed. When processing functional surfaces of the production line, such as positioning reference surfaces and assembly contact surfaces, key features are preserved through weight adjustments.

[0165] In this embodiment, a feature-preserving smoothing algorithm was developed for the displacement vector calculation stage. By analyzing the characteristic structure of the Laplacian operator, the optimal displacement direction of the mesh vertices is calculated. When processing characteristic areas of production line equipment, such as the mounting surface of the robot base and the heat dissipation holes of the control cabinet, it is ensured that the smoothing process does not destroy the original geometric features.

[0166] This embodiment implements an iterative position optimization strategy during the mesh vertex update process. By gradually adjusting the spatial position of the mesh vertices, a smooth transition in local areas is achieved. When dealing with irregularly shaped surfaces in the production line, such as sensor mounting slots and fixture gripping surfaces, multiple iterations ensure a smooth effect.

[0167] In this embodiment, a topological consistency merging strategy is adopted in the model merging stage. Reliable model connections are constructed by analyzing and filling the boundary relationships between the merged and original models. During the optimization process, special attention is paid to maintaining the topological integrity of the models to ensure the geometric continuity of the merged models.

[0168] This embodiment develops a multi-level index structure during spatial index construction. By establishing a spatial partitioning tree for the filling model, efficient spatial query operations are supported. During path planning and collision detection, such as robot trajectory planning and equipment layout optimization, potential collision areas can be quickly located.

[0169] This embodiment establishes a complete model optimization and indexing system through the above implementation scheme. This scheme can accurately optimize problem areas in the digital model of automated production lines and provide efficient spatial retrieval support. Practice shows that this scheme exhibits good adaptability and stability when handling complex industrial scenarios.

[0170] In practical applications, the solution in this embodiment has successfully handled various types of production line model optimization problems, such as complex curved surfaces at the joints of robotic arms and guide grooves in conveyor belt systems. It provides a reliable geometric basis for the motion planning and layout optimization of production lines, effectively improving the operating efficiency and safety of automated production lines.

[0171] To overcome the limitations of traditional model repair methods and provide an efficient and reliable solution for the complete reconstruction of industrial digital models, this application provides an embodiment of an automated production line digital model hole-filling device for implementing all or part of the aforementioned automated production line digital model hole-filling method. See [link to embodiment]. Figure 8 The automated production line digital model hole filling device specifically includes the following components:

[0172] The boundary determination module 10 is used to decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the area to be processed, extract boundary points from the area to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor.

[0173] The filling calculation module 20 is used to perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connection relationship of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches.

[0174] The surface filling module 30 is used to input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0175] As described above, the hole-filling device for automated production line digital models provided in this application can accurately identify the area to be processed through multi-level mesh analysis and curvature field calculation. It innovatively designs a patch generation mechanism based on density clustering and neural networks, combining local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled area, and is closely integrated with the motion control and path planning of the automated production line. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0176] From a hardware perspective, in order to overcome the limitations of traditional model repair and provide an efficient and reliable solution for the complete reconstruction of industrial digital models, this application provides an embodiment of an electronic device for implementing all or part of the hole-filling method for the digital model of the automated production line. The electronic device specifically includes the following components:

[0177] The system comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between the automated production line digital model hole filling device and core business systems, user terminals, and related databases and other related equipment; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the automated production line digital model hole filling method and the automated production line digital model hole filling device, the contents of which are incorporated herein by reference, and repeated details will not be described again.

[0178] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0179] In practical applications, the hole-filling method for the digital model of an automated production line can be partially executed on the electronic device side as described above, or all operations can be completed in the client device. The choice can be made based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed in the client device, the client device may further include a processor.

[0180] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0181] Figure 9 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 9 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 9 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0182] In one embodiment, the function of the automated production line digital model hole-filling method can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0183] Step S101: Decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the area to be processed, extract boundary points from the area to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor;

[0184] Step S102: Perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches;

[0185] Step S103: Input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0186] As described above, the electronic device provided in this application accurately identifies the region to be processed through multi-level mesh analysis and curvature field calculation. It innovatively designs a patch generation mechanism based on density clustering and neural networks, combining local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled region, and is closely integrated with the motion control and path planning of automated production lines. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0187] In another embodiment, the automated production line digital model hole filling device can be configured separately from the central processing unit 9100. For example, the automated production line digital model hole filling device can be configured as a chip connected to the central processing unit 9100, and the automated production line digital model hole filling method function can be realized through the control of the central processing unit.

[0188] like Figure 9 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 9 All components shown; in addition, the electronic device 9600 may also include Figure 9 For components not shown, please refer to existing technologies.

[0189] like Figure 9 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0190] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0191] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0192] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0193] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0194] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processing unit 9100 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0195] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored audio via the speaker 9131.

[0196] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the automated production line digital model hole-filling method with a server or client as the execution subject in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the automated production line digital model hole-filling method with a server or client as the execution subject in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0197] Step S101: Decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the area to be processed, extract boundary points from the area to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor;

[0198] Step S102: Perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches;

[0199] Step S103: Input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0200] As described above, the computer-readable storage medium provided in this application accurately identifies the region to be processed through multi-level mesh analysis and curvature field calculation. It innovatively designs a patch generation mechanism based on density clustering and neural networks, combining local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplacian mesh smoothing algorithm to ensure the continuity and smoothness of the filled region, and is closely integrated with the motion control and path planning of automated production lines. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0201] Embodiments of this application also provide a computer program product capable of implementing all steps in the automated production line digital model hole filling method with the execution subject being a server or client as described in the above embodiments. When executed by a processor, this computer program / instruction implements the steps of the automated production line digital model hole filling method. For example, the computer program / instruction implements the following steps:

[0202] Step S101: Decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the area to be processed, extract boundary points from the area to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor;

[0203] Step S102: Perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches;

[0204] Step S103: Input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

[0205] As described above, the computer program product provided in this application accurately identifies the region to be processed through multi-level mesh analysis and curvature field calculation. It innovatively designs a patch generation mechanism based on density clustering and neural networks, combining local geometric features to achieve intelligent filling optimization. The system employs non-uniform rational basis spline surface reconstruction and a Laplace mesh smoothing algorithm to ensure the continuity and smoothness of the filled region, and is closely integrated with the motion control and path planning of automated production lines. This method overcomes the limitations of traditional model repair, providing an efficient and reliable solution for the complete reconstruction of industrial digital models.

[0206] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0207] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0208] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0209] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0210] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for filling holes in a digital model of an automated production line, characterized in that, The method includes: The digital model of the automated production line is decomposed into a multi-level grid representation. The local curvature field distribution is calculated at each grid level. The curvature field is projected onto the finest level grid. The curvature gradient change is calculated based on the finest level grid. An adaptive threshold segmentation algorithm is used to mark the region to be processed. Boundary points are extracted from the region to be processed. The normal vector field of the boundary points is calculated. The position information of the boundary points and the normal vector field are combined to construct a boundary feature descriptor. Density clustering analysis is performed on the boundary feature descriptors, and the density clustering results are mapped to three-dimensional space to form filling patches. The angle between the normal vector of the filling patch and the normal vector of the boundary point is calculated. A neural network prediction model based on local geometric features is constructed. The optimal angle threshold is calculated using the neural network prediction model. Patches with an angle smaller than the optimal angle threshold are marked as patches to be optimized. The boundary curvature information and topological connectivity of the patches to be optimized are calculated. Motion control commands for the automated production line are generated based on the filling patches. The surface patch to be optimized is input into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

2. The method for filling holes in the digital model of an automated production line according to claim 1, characterized in that, The process involves decomposing the digital model of the automated production line into a multi-level grid representation, calculating the local curvature field distribution at each grid level, projecting the curvature field onto the finest level grid, calculating the curvature gradient change based on the finest level grid, and using an adaptive threshold segmentation algorithm to mark the region to be processed, including: The octree decomposition algorithm is used to divide the digital model of the automated production line into grid layers of different scales. A vertex adjacency graph is constructed for each grid layer. Based on the adjacency graph, the Gaussian curvature and average curvature of the grid vertices are calculated. The Gaussian curvature and average curvature are combined to form a local curvature field distribution. An interpolation mapping algorithm between grid levels is used to project curvature fields at different levels onto the finest grid level to construct a curvature gradient tensor field. The principal direction and eigenvalues ​​of the curvature gradient tensor field are calculated, and an adaptive threshold segmentation function is constructed based on the eigenvalues. The output of the segmentation function is marked as the region to be processed.

3. The method for filling holes in the digital model of an automated production line according to claim 1, characterized in that, The step of extracting boundary points from the region to be processed, calculating the normal vector field of the boundary points, and combining the position information of the boundary points with the normal vector field to construct a boundary feature descriptor includes: A boundary tracing algorithm for the region to be processed is constructed. Based on the mesh topology connection relationship, the connected boundaries of the region to be processed are searched. The mesh vertices on the connected boundaries are extracted into a set of boundary points. The normal vector field of the set of boundary points is calculated by the local surface fitting method. A spatial coordinate transformation is performed on the set of boundary points to establish a local coordinate system centered on the boundary points. The three-dimensional coordinate information of the boundary points and the normal vector field are orthogonally decomposed in the local coordinate system to construct a boundary feature descriptor containing position coordinate components and normal vector components.

4. The method for filling holes in the digital model of an automated production line according to claim 1, characterized in that, The process of performing density clustering analysis on the boundary feature descriptors, mapping the density clustering results to three-dimensional space to form filling patches, calculating the angle between the normal vector of the filling patch and the normal vector of the boundary point, and constructing a neural network prediction model based on local geometric features includes: A similarity metric function for boundary feature descriptors is constructed. Based on the similarity metric function, the distance matrix between feature descriptors is calculated. A density-based spatial clustering algorithm is used to divide the boundary feature descriptors into multiple clusters. For each cluster, the core point and boundary point are calculated. The spatial coordinates of the core point and boundary point are projected back into three-dimensional space to form a filling patch. The normal vector of the patch is calculated based on the mesh vertices of the filled patch. An angle evaluation model is established between the normal vector of the filled patch and the normal vector of the boundary point. The angle evaluation model is used as the input feature of the neural network to construct a multilayer perceptron network structure. The local geometric features of the boundary points are used as training samples to optimize the neural network.

5. The method for filling holes in a digital model of an automated production line according to claim 1, characterized in that, The process involves using the neural network prediction model to calculate the optimal included angle threshold, marking patches smaller than the optimal included angle threshold as patches to be optimized, calculating the boundary curvature information and topological connectivity of the patches to be optimized, and generating motion control commands for the automated production line based on the filled patches, including: The trained neural network model is applied to fill the local geometric features of the patch, outputting the optimal angle threshold between the patch normal vector and the boundary point normal vector. Based on the optimal angle threshold, the patch is screened, an index set of patches to be optimized is constructed, the principal curvature direction and curvature value of the boundary of the patch to be optimized are calculated, and an adjacency graph between patches is established. The boundary curvature information of the surface to be optimized is converted into a discrete sampling point sequence. A parameterized representation of the surface boundary is established based on the sampling point sequence. Transitional constraints between surfaces are constructed using topological connection relationships. The transitional constraints are used as constraints of control commands to generate a motion control command sequence that meets the continuity requirements.

6. The method for filling holes in the digital model of an automated production line according to claim 1, characterized in that, The process involves inputting the surface patch to be optimized into a surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational base spline surface based on the boundary curvature information, applies continuity constraints to the base spline surface using the topological connectivity relationship, and constructs an objective function considering surface smoothness, including: The boundary curvature information of the patch to be optimized is converted into a sequence of control points. Based on the sequence of control points, a node vector of the NURBS surface is constructed. The values ​​of the NURBS basis functions on the node vectors are calculated. The basis functions are weighted and optimized to obtain the mathematical expression of the non-uniform rational basis spline surface. The mapping relationship between the surface parameter domain and the three-dimensional space is established. Based on the topological connectivity of the patches to be optimized, positional continuity and tangential continuity constraints are constructed between adjacent patches. The continuity constraints are combined with the mean curvature and Gaussian curvature of the surface to construct a smoothness evaluation function, which is then used as the optimization objective function.

7. The method for filling holes in a digital model of an automated production line according to claim 1, characterized in that, The process involves iteratively optimizing the objective function to obtain an initial filling surface, calculating the transition region between the initial filling surface and the boundary of the original model, applying a Laplacian mesh smoothing algorithm to locally adjust the transition region, generating the final filling model, and importing the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection, including: The gradient descent method is used to numerically optimize the objective function. The control point positions and weight parameters of the NURBS surface are updated by iterative calculation until the objective function converges to obtain an initial filling surface that satisfies the continuity constraint. The distance field function between the initial filling surface and the boundary of the original model is constructed, and the range of the transition region is determined based on the contour lines of the distance field function. In the transition region, the Laplacian operator of the mesh vertices is constructed, the displacement vector of the mesh vertices is calculated based on the Laplacian operator, the spatial position of the mesh vertices is iteratively updated to achieve local smoothing, the smoothed mesh is merged with the original model to form a complete filling model, and a spatial index structure of the filling model is established for path planning and collision detection.

8. A device for filling holes in a digital model of an automated production line, characterized in that, The device includes: The boundary determination module is used to decompose the digital model of the automated production line into a multi-level grid representation, calculate the local curvature field distribution at each grid level, project the curvature field onto the finest level grid, calculate the curvature gradient change based on the finest level grid, use an adaptive threshold segmentation algorithm to mark the region to be processed, extract boundary points from the region to be processed, calculate the normal vector field of the boundary points, and combine the position information of the boundary points with the normal vector field to construct a boundary feature descriptor. The filling calculation module is used to perform density clustering analysis on the boundary feature descriptor, map the density clustering results to three-dimensional space to form filling patches, calculate the angle between the normal vector of the filling patch and the normal vector of the boundary point, construct a neural network prediction model based on local geometric features, use the neural network prediction model to calculate the optimal angle threshold, mark patches smaller than the optimal angle threshold as patches to be optimized, calculate the boundary curvature information and topological connectivity of the patches to be optimized, and generate motion control commands for the automated production line based on the filling patches. The surface filling module is used to input the surface patch to be optimized into the surface reconstruction module. The surface reconstruction module first constructs a non-uniform rational basis spline surface based on the boundary curvature information, applies continuity constraints to the basis spline surface using the topological connectivity relationship, constructs an objective function considering surface smoothness, iteratively optimizes the objective function to obtain an initial filling surface, calculates the transition region between the initial filling surface and the boundary of the original model, applies the Laplacian mesh smoothing algorithm to the transition region for local adjustment, generates the final filling model, and imports the filling model into the 3D visualization system of the automated production line for material handling path planning and equipment collision detection.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for filling holes in the digital model of an automated production line as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the automated production line digital model hole filling method according to any one of claims 1 to 7.

Images