A shoe style design method based on digital three-dimensional model

Abstract

The present application relates to a method for designing footwear styles based on a digital three-dimensional model. The method comprises: obtaining three-dimensional point cloud data of protective shoes, extracting distribution features after noise reduction processing to construct a three-dimensional mesh model; dividing the model into the sole, upper, and anti-smashing head area, and obtaining a closed boundary point sequence for each area; extracting the sole thickness distribution value, anti-smashing head curvature value, and upper wrinkle value based on the boundary point sequence to generate a feature vector data set; using the feature vector data set to construct a finite element mechanics simulation model to generate a quantitative relationship data set for protective performance; combining the quantitative relationship data set to establish a multi-objective optimization model to generate an optimal structural parameter combination that meets the constraints of preset safety standards. This method can improve the efficiency and accuracy of protective shoe design, provide a data-driven standardized process for protective shoe structural design, effectively ensure that the product meets safety standards and optimizes comprehensive performance.

Description

Technical Field

[0001] The invention belongs to the field of computer graphics, and in particular relates to a shoe style design method based on a digital three-dimensional model. Background Art

[0002] With the advancement of computer graphics, footwear design techniques based on digital 3D models have emerged. Traditional design methods rely on manual surveying, physical modeling, and empirical trial and error, resulting in long design cycles, high costs, insufficient accuracy, and difficulty balancing functionality and comfort. With the advancement of digital technology, techniques such as 3D scanning, computer-aided design (CAD), and finite element analysis (FEA) have been gradually applied to product development. However, there remains a lack of systematic solutions for accurately modeling complex curved footwear structures (such as anti-smash curvature, sole thickness distribution, and upper wrinkle) and optimizing performance under the coupled effects of multiple physical fields (mechanical impact, electric field shielding, and plantar pressure distribution). Existing technologies are limited by noise interference in point cloud data processing, fuzzy regional boundaries in mesh model segmentation, and technical bottlenecks in balancing safety standards and ergonomics in multi-objective optimization. Summary of the Invention

[0003] Based on this, it is necessary to address the above technical problems and provide a shoe style design method based on digital three-dimensional models that can improve the design efficiency and comprehensive performance of footwear products and realize digital and precise modeling of protective shoes.

[0004] In a first aspect, the present application provides a method for designing shoe styles based on a digital three-dimensional model, comprising:

[0005] The three-dimensional point cloud data of the protective shoes is obtained, the noise of the three-dimensional point cloud data is reduced, and the distribution features are extracted to construct a three-dimensional grid model.

[0006] The vertex coordinate data and triangular facet topology data of the three-dimensional mesh model are obtained; the curvature characteristic parameters of each vertex are calculated based on the vertex coordinate data to obtain a curvature distribution map; high curvature areas are extracted based on the curvature distribution map, and adjacent triangular facets are merged in accordance with regional connectivity constraints to generate an initial segmentation area.

[0007] According to the preset segmentation threshold, the boundary of the initial segmented area is expanded and eroded to determine the boundary point sets of the sole area, upper area and anti-smashing area; the boundary point set is topologically analyzed, and after removing isolated points, it is matched with the triangular patch topology data to obtain the closed boundary point sequence of each area.

[0008] The sole thickness distribution value, anti-smashing curvature value and upper wrinkle value are extracted according to the closed boundary point sequence to generate a feature vector data set.

[0009] A finite element mesh model is constructed based on the material properties and geometric parameters in the eigenvector data set; the mechanical solver is called to calculate the stress distribution data of the finite element mesh model; and the electric field solver is synchronously called to calculate the potential gradient distribution of the finite element mesh model.

[0010] The stress distribution data is coupled with the electric potential gradient distribution to extract the anti-smashing performance index value; the anti-smashing performance index value includes the impact resistance coefficient and the electric field shielding rate; and a quantitative relationship data set of protection performance is generated based on the anti-smashing performance index value and geometric parameters.

[0011] A multi-objective optimization model is established based on the quantitative relationship data set to generate the optimal structural parameter combination that meets the preset safety standard constraints.

[0012] In one embodiment, obtaining three-dimensional point cloud data of protective shoes, performing noise reduction processing on the three-dimensional point cloud data, extracting distribution features and constructing a three-dimensional grid model include:

[0013] Acquire three-dimensional point cloud data of the protective shoes; the three-dimensional point cloud data includes point cloud density information.

[0014] The denoising parameter threshold for controlling the point cloud neighborhood search radius is determined based on the point cloud density information.

[0015] The outlier filtering is performed on the 3D point cloud data based on the noise reduction parameter threshold to obtain the denoised 3D point cloud data.

[0016] The surface normal vector distribution features of the denoised 3D point cloud data are extracted; the surface normal vector distribution features contain curvature continuity information.

[0017] The triangular patch topology structure is generated according to the curvature continuity information, and the denoised 3D point cloud data is reconstructed using Poisson method to obtain the initial 3D mesh model.

[0018] The vertex curvature gradient of the initial three-dimensional mesh model is calculated to perform subdivision optimization on the initial three-dimensional mesh model to generate a final three-dimensional mesh model.

[0019] In one embodiment, the vertex curvature gradient is calculated using the following formula:

[0020] = ;

[0021] = ;

[0022] in, Indicates the The vertex curvature gradient of the mesh, Indicates the vertices in the mesh, Represents a vertex The first-order neighbor vertex set of represents the number of neighboring vertices, and Represents a vertex and vertices The principal curvature value of Indicates that from the vertex Point to the vertex The unit direction vector of represents the weighting coefficient, Represents a scaling parameter that controls the influence of curvature differences.

[0023] In one embodiment, the sole thickness distribution value, the anti-smashing curvature value, and the upper wrinkle value are extracted according to the closed boundary point sequence to generate a feature vector data set, including:

[0024] The boundary point curvature continuity parameters and thickness gradient change rate are extracted based on the closed boundary point sequence.

[0025] The curvature radius change rate of the anti-smashing head is calculated according to the curvature continuity parameter, and the curvature radius distribution matrix is ​​generated.

[0026] The thickness gradient change rate and the curvature radius distribution matrix are combined to generate a three-dimensional feature mapping table.

[0027] The density distribution parameters of the wrinkle area are extracted from the three-dimensional feature map, and the principal component analysis method is used to reduce the dimension of the density distribution parameters of the wrinkle area to obtain a low-dimensional feature vector set.

[0028] A feature vector similarity matrix is ​​constructed based on the low-dimensional feature vector set; the similarity matrix is ​​used to determine the correlation between the wrinkle degree of the shoe upper and the anti-smashing curvature.

[0029] If the correlation exceeds a preset threshold, the curvature radius distribution weight coefficient in the three-dimensional feature mapping table is updated.

[0030] The dimensional distribution of the low-dimensional feature vector set is adjusted according to the updated weight coefficient, and the optimized feature vector data set is output.

[0031] In one embodiment, a multi-objective optimization model is established based on a quantitative relationship data set to generate an optimal structural parameter combination that meets the preset safety standard constraints, including:

[0032] The plantar pressure distribution matrix and shear force gradient matrix are extracted based on the quantitative relationship data set; the pressure distribution matrix contains the pressure intensity data of each area; the shear force gradient matrix contains the dynamic shear change.

[0033] The safety assessment function value is calculated based on the weighted fusion of the pressure distribution matrix and the shear gradient matrix.

[0034] Determine whether the value of the security assessment function exceeds the preset threshold. If not, dynamically adjust the step size of the structural parameters based on the gradient descent algorithm.

[0035] The structural parameter combination is updated based on the structural parameter step size to generate a new parameter combination sequence.

[0036] The parameter combination sequence is input into the multi-objective optimization model to obtain the set of objective function values.

[0037] The optimal parameter identification number that meets the constraints is screened according to the objective function value set to obtain the optimal structural parameter combination; the optimal parameter identification number corresponds to the dual-objective balance point of pressure and shear force.

[0038] In one embodiment, the security assessment function value is calculated using the following formula:

[0039] ;

[0040] in, represents the value of the security assessment function, represents the plantar pressure distribution matrix, Indicates the first Rank The pressure intensity value of the column, represents the shear gradient matrix, represents the first Rank The dynamic shear variation of the column, represents the regional weight coefficient, and represents the weighting coefficient, A nonlinear mapping function representing pressure and shear forces.

[0041] In a second aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program.

[0042] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the above method when executed by a processor.

[0043] The above-mentioned footwear design method, computer device, and storage medium based on digital 3D models acquire 3D point cloud data of protective shoes, extract distribution features after noise reduction, and construct a 3D mesh model. The model is divided into the sole, upper, and anti-smash area, and a closed boundary point sequence is obtained for each area. Based on the boundary point sequence, the sole thickness distribution value, anti-smash curvature value, and upper wrinkle value are extracted to generate a feature vector dataset. The feature vector dataset is used to construct a finite element mechanical simulation model and generate a quantitative relationship dataset for protective performance. Combined with the quantitative relationship dataset, a multi-objective optimization model is established to generate the optimal structural parameter combination that meets the constraints of preset safety standards. The protective shoe is digitally modeled through 3D point cloud processing and mesh modeling. Region division and feature extraction are used to accurately analyze key structural parameters. Finite element simulation and multi-objective optimization are used to quantitatively evaluate protective performance and optimize structural parameters. This method solves the problem of traditional design relying on manual operation and empirical judgment, improves the efficiency and accuracy of protective shoe design, and provides a data-driven standardized process for protective shoe structural design, effectively ensuring product compliance with safety standards and optimizing overall performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flowchart of a shoe style design method based on a digital three-dimensional model provided by an embodiment of the present invention;

[0046] Figure 2 A flowchart of an embodiment of the present invention for obtaining three-dimensional point cloud data of protective shoes, performing noise reduction processing on the three-dimensional point cloud data, extracting distribution features, and constructing a three-dimensional mesh model;

[0047] Figure 3 A flowchart of an embodiment of the present invention for constructing a finite element mechanics simulation model based on a feature vector data set to generate a data set of quantitative relationships of protective performance. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] In one embodiment, Figure 1As shown, the present application provides a shoe style design method based on a digital three-dimensional model, which may include the following steps:

[0050] Step S101: Acquire three-dimensional point cloud data of protective shoes, perform noise reduction on the three-dimensional point cloud data, extract distribution features and construct a three-dimensional grid model.

[0051] Specifically, to obtain three-dimensional point cloud data of protective shoes (including shoes with different functions such as anti-smashing, anti-puncture, insulation, anti-slip, oil resistance, acid and alkali resistance, etc.), laser scanning or structured light scanning technology can be used to collect spatial coordinate information of the shoe surface to form raw data containing a dense point set. When denoising this data, the neighborhood search radius threshold is calculated based on the point cloud density information, and the statistical outlier filtering algorithm is used to remove noise points and retain the true surface features. The normal vector distribution and curvature continuity characteristics of the point cloud are then extracted for subsequent mesh model construction to ensure that the model accurately represents the complex curved surfaces of the shoe (such as the arc surface of the sole and the bends of the upper).

[0052] Step S102, obtain the vertex coordinate data and triangular facet topology data of the three-dimensional mesh model; calculate the curvature characteristic parameters of each vertex based on the vertex coordinate data to obtain a curvature distribution map; extract high curvature areas based on the curvature distribution map, and merge adjacent triangular facets in accordance with regional connectivity constraints to generate an initial segmentation area.

[0053] In step S103, a dilation-erosion operation is performed on the boundary of the initial segmented area according to a preset segmentation threshold to determine the boundary point sets of the sole area, the upper area, and the anti-smashing area; a topological relationship analysis is performed on the boundary point set, and after removing isolated points, the set is matched with the triangular patch topology data to obtain a closed boundary point sequence for each area.

[0054] The preprocessed 3D mesh model is divided into the sole, upper, and anti-smashing area. Automatic segmentation is achieved using a region growing algorithm based on curvature distribution combined with connectivity constraints. First, the curvature characteristic parameters of the mesh vertices are calculated to generate a curvature distribution map, which is used to identify high-curvature boundary regions. Then, through region merging and boundary optimization, the closed boundary point sequence of each functional area is determined.

[0055] Step S104 , extracting the sole thickness distribution value, the anti-smashing curvature value, and the upper wrinkle value according to the closed boundary point sequence to generate a feature vector data set.

[0056] Specifically, key structural parameters are extracted based on a sequence of closed boundary points: the sole thickness distribution is calculated by calculating the distance between corresponding points on the upper and lower surfaces of the sole, the anti-smashing curvature value is derived by analyzing the continuous curvature parameters of the boundary points, and the upper wrinkle value is determined by identifying the density distribution parameters of local surface curvature variations. These parameters are integrated into a multidimensional feature vector, and after dimensionality reduction through principal component analysis, a feature vector dataset containing geometric and mechanical properties is generated.

[0057] Step S105, constructing a finite element mesh model based on the material properties and geometric parameters in the feature vector data set; calling a mechanical solver to calculate the stress distribution data of the finite element mesh model; and synchronously calling an electric field solver to calculate the potential gradient distribution of the finite element mesh model.

[0058] Step S106: Couple the stress distribution data with the electric potential gradient distribution to extract the anti-smashing performance index value; the anti-smashing performance index value includes the impact resistance coefficient and the electric field shielding rate; and generate a protection performance quantitative relationship data set based on the anti-smashing performance index value and the geometric parameters.

[0059] Furthermore, a finite element mesh model is constructed using the material properties and geometric parameters in the eigenvector dataset. The discretization of the model space is defined by setting node coordinates and element topology. A mechanical solver is used to calculate the stress distribution data of the model under impact loads. The electric field distribution characteristics are simultaneously analyzed, and protective performance indicators (such as impact resistance coefficient and electric field shielding ratio) are obtained through multi-physics field coupling calculations. These indicators are then correlated with geometric parameters to generate a quantitative dataset reflecting the relationship between structural parameters and protective performance.

[0060] Step S107 , establishing a multi-objective optimization model based on the quantitative relationship data set, and generating an optimal structural parameter combination that meets the preset safety standard constraints.

[0061] Specifically, a multi-objective optimization model was established based on a quantitative relationship dataset, with protective performance indicators, plantar pressure distribution, and shear force variations serving as objective functions, and pre-set safety standards serving as constraints. A gradient descent algorithm was used to dynamically adjust the structural parameter step size, generating a sequence of parameter combinations that were input into the optimization model. An iterative calculation sought the equilibrium point between the dual objectives of pressure and shear force. Ultimately, a parameter combination that met safety constraints and achieved optimal overall performance was selected, achieving quantitative optimization and standardized verification of the protective shoe's structural design.

[0062] The above-mentioned footwear design method based on digital 3D models obtains 3D point cloud data of protective shoes, extracts distribution features after noise reduction, and constructs a 3D mesh model. The model is divided into the sole, upper, and anti-smash area, and a closed boundary point sequence is obtained for each area. Based on the boundary point sequence, the sole thickness distribution value, anti-smash curvature value, and upper wrinkle value are extracted to generate a feature vector dataset. The feature vector dataset is used to construct a finite element mechanical simulation model and generate a quantitative relationship dataset for protective performance. Combined with the quantitative relationship dataset, a multi-objective optimization model is established to generate the optimal structural parameter combination that meets the constraints of preset safety standards. The protective shoe is digitally modeled through 3D point cloud processing and mesh modeling. Region division and feature extraction are used to accurately analyze key structural parameters. Finite element simulation and multi-objective optimization are used to quantitatively evaluate protective performance and optimize structural parameters. This method solves the problem of traditional design relying on manual operation and empirical judgment, improves the efficiency and accuracy of protective shoe design, and provides a data-driven standardized process for protective shoe structural design, effectively ensuring product compliance with safety standards and optimizing overall performance.

[0063] In one embodiment, Figure 2 As shown, obtaining the three-dimensional point cloud data of the protective shoes, performing noise reduction on the three-dimensional point cloud data, extracting distribution features and constructing a three-dimensional grid model may include the following steps:

[0064] Step S201: Acquire three-dimensional point cloud data of protective shoes; the three-dimensional point cloud data includes point cloud density information.

[0065] Step S202 : determining a noise reduction parameter threshold for controlling a point cloud neighborhood search radius according to point cloud density information.

[0066] Step S203 : performing outlier filtering on the three-dimensional point cloud data based on a noise reduction parameter threshold to obtain noise-reduced three-dimensional point cloud data.

[0067] Step S204 , extracting surface normal vector distribution features of the denoised three-dimensional point cloud data; the surface normal vector distribution features include curvature continuity information.

[0068] Step S205 , generating a triangular patch topology structure based on the curvature continuity information, and performing Poisson reconstruction on the denoised three-dimensional point cloud data to obtain an initial three-dimensional mesh model.

[0069] Step S206 , calculating the vertex curvature gradient of the initial three-dimensional mesh model, performing subdivision optimization on the initial three-dimensional mesh model, and generating a final three-dimensional mesh model.

[0070] Specifically, the three-dimensional point cloud data of protective shoes containing point cloud density information is obtained, and the noise reduction parameter threshold used to control the point cloud neighborhood search radius is determined based on the point cloud density information. Based on the threshold, outlier filtering is performed on the three-dimensional point cloud data to obtain the denoised point cloud data; the surface normal vector distribution characteristics (including curvature continuity information) of the denoised point cloud data are extracted, and the triangular facet topology structure is generated according to the curvature continuity, and the initial three-dimensional mesh model is obtained through Poisson reconstruction; the vertex curvature gradient of the initial model is calculated and subdivided and optimized to generate the final three-dimensional mesh model.

[0071] This embodiment uses adaptive point cloud density to determine noise reduction parameters, achieving precise noise filtering of the protective shoe's three-dimensional point cloud data while preserving the true geometric features of the shoe's curved surface. Poisson reconstruction based on curvature continuity and vertex curvature gradient subdivision optimization enable the 3D mesh model to accurately reflect the details of the protective shoe's complex structure (such as the curvature of the anti-smashing surface and areas of varying sole thickness), avoiding facet breakage or blurred features in the model. This method improves the automation and modeling accuracy of point cloud processing, providing a high-quality 3D model foundation for subsequent regional segmentation and mechanical performance simulation of protective shoes, and enhancing the reliability and efficiency of the digital design process.

[0072] In one embodiment, the vertex curvature gradient can be calculated using the following formula:

[0073] = ;

[0074] = ;

[0075] in, Indicates the The vertex curvature gradient of the mesh, Indicates the vertices in the mesh, Represents a vertex The first-order neighbor vertex set of represents the number of neighboring vertices, and Represents a vertex and vertices The principal curvature value of Indicates that from the vertex Point to the vertex The unit direction vector of represents the weighting coefficient, Represents a scaling parameter that controls the influence of curvature differences.

[0076] Preferably, The principal curvature of a vertex can be calculated by the following steps:

[0077] Calculate vertices Neighborhood covariance matrix

[0078] = ;

[0079] in, Represents the centroid of the neighborhood vertex.

[0080] Covariance matrix Perform eigenvalue decomposition and obtain three eigenvalues , and its corresponding eigenvector , , .

[0081] The normal vector of the vertex is the eigenvector corresponding to the minimum eigenvalue .

[0082] The principal curvature of a vertex can be approximated as:

[0083] = ;

[0084] In this embodiment, in areas of drastic curvature changes (such as the junction between the anti-smashing arc of a protective shoe and the shoe upper), the curvature difference of neighboring vertices automatically reduces the influence of distant vertices with high curvature differences. This focuses on neighboring vertices with significant local features, driving the mesh subdivision algorithm to generate denser meshes in key areas and accurately depict surface transition details. Geometric distance weighting suppresses the ineffective participation of distant vertices, avoiding the waste of computational resources caused by global uniform subdivision. This reduces redundant meshes while maintaining model accuracy, improving the efficiency of subsequent mechanical simulation and optimization. This method addresses the issues of under-representation or over-subdivision of characteristic regions in traditional mesh optimization and provides theoretical support for high-precision modeling of three-dimensional protective shoe models.

[0085] In one embodiment, dividing the three-dimensional mesh model into a sole area, a shoe upper area, and an anti-smashing area to obtain a closed boundary point sequence for each area may include the following steps:

[0086] Step S301: Acquire vertex coordinate data and triangle patch topology data of a three-dimensional mesh model.

[0087] Step S302 : Calculate the curvature characteristic parameters of each vertex according to the vertex coordinate data to obtain a curvature distribution map.

[0088] Preferably, the local curvature of the mesh surface is quantified through geometric calculations. Specifically, based on the vertex coordinate data of the three-dimensional mesh model, a local neighborhood of each vertex is first constructed (usually a first-order or second-order neighborhood is selected). The local tangent plane of the neighborhood point set is fitted using the least squares method, and the deviation of the vertex relative to the tangent plane is then calculated. Commonly used curvature calculation methods include mean curvature and Gaussian curvature. Mean curvature reflects the average curvature of the surface in the two principal curvature directions. After completing the curvature calculation by traversing all vertices, the curvature value of each vertex is mapped to the corresponding spatial coordinates to generate a visual curvature distribution map, providing a quantitative geometric feature basis for subsequent region segmentation. This calculation process does not rely on subjective judgment and objectively reflects the curvature characteristics of the mesh surface through mathematical methods, laying the foundation for the accurate identification of high-curvature areas such as the bends on the soles of protective shoes and the arc surface of anti-smashing head protection.

[0089] Step S303 : extracting high curvature regions based on the curvature distribution map, merging adjacent triangular facets based on regional connectivity constraints, and generating initial segmented regions.

[0090] Step S304: performing dilation and corrosion operations on the boundaries of the initial segmented areas according to a preset segmentation threshold, and determining a set of boundary points of the sole area, the upper area, and the anti-smashing head area.

[0091] Step S305 , performing a topological relationship analysis on the boundary point set, removing isolated points, and matching the result with the triangular patch topology data to obtain a closed boundary point sequence for each region.

[0092] Specifically, the vertex coordinate data and triangular facet topology data of the three-dimensional mesh model are obtained, and the curvature characteristic parameters of each vertex are calculated based on the vertex coordinates to generate a curvature distribution map; the high curvature area is extracted according to the curvature distribution map, and the adjacent triangular facets are merged in combination with the regional connectivity constraint to generate the initial segmentation area; the initial area boundary is expanded and eroded by a preset segmentation threshold to determine the boundary point set of the sole, upper and anti-head-smashing area; the boundary point set is subjected to topological relationship analysis, and after removing isolated points, it is matched with the triangular facet topology data to obtain a closed boundary point sequence for each area.

[0093] This example uses curvature feature parameters and a curvature distribution map to identify characteristic regions within a 3D mesh model of protective footwear. Regional connectivity constraints and topological analysis are employed to ensure the geometric integrity of the segmentation results. High-curvature region extraction, combined with dilation and erosion operations, precisely defines the boundaries of functional areas such as the sole, upper, and anti-smashing head, avoiding the subjectivity and errors of traditional manual segmentation. The generation of a closed boundary point sequence provides a precise geometric boundary basis for the subsequent extraction of structural parameters from each region (such as sole thickness and anti-smashing head curvature), improving the efficiency and accuracy of multi-region feature decoupling in the digital design of protective footwear.

[0094] In one embodiment, extracting the sole thickness distribution value, the anti-smashing curvature value, and the upper wrinkle value according to the closed boundary point sequence to generate a feature vector data set may include the following steps:

[0095] Step S401 : extracting boundary point curvature continuity parameters and thickness gradient change rates according to a closed boundary point sequence.

[0096] Step S402 : calculating the rate of change of the anti-smashing head curvature radius according to the curvature continuity parameter, and generating a curvature radius distribution matrix.

[0097] Step S403 : Combining the thickness gradient change rate with the curvature radius distribution matrix, a three-dimensional feature mapping table is generated.

[0098] Step S404: extracting wrinkle region density distribution parameters from the three-dimensional feature map, and performing dimensionality reduction processing on the wrinkle region density distribution parameters using a principal component analysis method to obtain a low-dimensional feature vector set.

[0099] Step S405: constructing a feature vector similarity matrix based on the low-dimensional feature vector set; the similarity matrix is ​​used to determine the correlation between the wrinkle degree of the shoe upper and the anti-smashing curvature.

[0100] Step S406: If the correlation exceeds a preset threshold, the curvature radius distribution weight coefficient in the three-dimensional feature mapping table is updated.

[0101] Step S407: adjusting the dimensional distribution of the low-dimensional feature vector set according to the updated weight coefficients, and outputting an optimized feature vector data set.

[0102] Specifically, the curvature continuity parameters and thickness gradient change rates of the boundary points are first extracted from the closed boundary point sequence, and the curvature radius change rate of the anti-smashing head is calculated using the curvature continuity parameters to form a curvature radius distribution matrix; then the thickness gradient change rate is combined with the curvature radius distribution matrix to generate a three-dimensional feature mapping table; then the wrinkle area density distribution parameters are extracted from the mapping table, and the dimensionality is reduced through principal component analysis to obtain a low-dimensional feature vector set; then, a similarity matrix is ​​constructed based on the low-dimensional feature vector set to determine the correlation between the wrinkle degree of the shoe upper and the anti-smashing head curvature; if the correlation exceeds the preset threshold, the curvature radius distribution weight coefficient of the three-dimensional feature mapping table is updated, and the dimensional distribution of the low-dimensional feature vector set is adjusted accordingly, and the optimized feature vector data set is output.

[0103] This embodiment quantitatively analyzes the curvature and thickness characteristics of each region of the protective shoe boundary to systematically extract and integrate the curvature variation of the anti-smashing head protection, the thickness distribution of the sole, and the wrinkle characteristics of the upper. Dimensionality reduction through principal component analysis and feature correlation analysis removes redundant information and optimizes the feature vector structure, ensuring that the data fully reflects the product's geometric and mechanical properties while reducing the computational complexity of subsequent finite element simulation and multi-objective optimization. This method provides accurate and efficient feature data support for protective shoe design, helping to improve the accuracy and efficiency of product performance analysis and structural optimization.

[0104] In one embodiment, Figure 3 As shown, building a finite element mechanics simulation model based on the characteristic vector data set and generating a quantitative relationship data set of protection performance can include the following steps:

[0105] Step S501 : constructing a finite element mesh model based on the material properties and geometric parameters in the feature vector data set; the finite element mesh model includes node coordinates and element topology relationships.

[0106] Preferably, the material properties of each part of the protective shoe (such as elastic modulus, Poisson's ratio, and electrical conductivity) are extracted from the feature vector data set, as well as geometric parameters (such as sole thickness and anti-smashing head curvature radius) obtained based on the three-dimensional mesh model. Finite element pre-processing technology is then used to discretize the protective shoe solid model into a finite element mesh containing node coordinates and element topology relationships. The node coordinates accurately describe the position of the mesh in three-dimensional space, while the element topology defines the connection method between nodes (such as tetrahedral and hexahedral elements), ensuring that the model can accurately reflect the geometric shape and structural characteristics of the protective shoe. This process requires a balance between mesh density and computational efficiency. A dense mesh is used in key areas (such as the connection between the anti-smashing head and the sole) to capture stress concentration phenomena, while a sparse mesh is used in flat areas to reduce the amount of computation.

[0107] Step S502: calling a mechanical solver to calculate stress distribution data of a finite element mesh model.

[0108] Step S503: synchronously call the electric field solver to calculate the potential gradient distribution of the finite element mesh model.

[0109] Step S504 , coupling analysis is performed on the stress distribution data and the electric potential gradient distribution to extract an anti-smashing performance index value; the anti-smashing performance index value includes an impact resistance coefficient and an electric field shielding rate.

[0110] Step S505: generating a protection performance quantitative relationship data set according to the anti-smashing performance index value and the geometric parameters.

[0111] Specifically, a finite element mesh model is constructed based on the material properties and geometric parameters in the eigenvector data set. The model contains node coordinates and unit topological relationships. The mechanical solver is called to calculate the stress distribution data of the model, and the electric field solver is synchronously called to calculate the potential gradient distribution. The stress distribution and the potential gradient distribution are coupled and analyzed to extract anti-smashing performance index values ​​such as the impact resistance coefficient and the electric field shielding rate. A quantitative relationship data set of protection performance is generated based on the performance index values ​​and geometric parameters.

[0112] This embodiment integrates the material and geometric features of protective shoes through a finite element mesh model, achieving multi-physics coupling simulation of mechanics and electric fields, and accurately quantifying anti-smash performance indicators. The coupled analysis of stress and electric potential distribution breaks through the limitations of single physical field evaluation and can comprehensively reflect the structural strength and electric field protection capabilities of protective shoes under impact loads. The generated quantitative relationship data set provides data support for subsequent multi-objective optimization, shifting the design process from experience-driven to data-driven, improving the scientific nature and optimization efficiency of protective shoe performance evaluation, ensuring that the product meets safety standards and achieves multi-dimensional performance balance.

[0113] In one embodiment, establishing a multi-objective optimization model based on a quantitative relationship data set to generate an optimal structural parameter combination that meets preset safety standard constraints may include the following steps:

[0114] Step S601 , extracting a plantar pressure distribution matrix and a shear force gradient matrix based on the quantitative relationship data set; the pressure distribution matrix includes pressure intensity data of each region; and the shear force gradient matrix includes dynamic shear variation.

[0115] Step S602 : Calculate the safety assessment function value based on the weighted fusion of the pressure distribution matrix and the shear gradient matrix.

[0116] Specifically, based on the pressure intensity data of each region in the plantar pressure distribution matrix in the quantitative relationship data set, and the dynamic shear change in the shear gradient matrix, regional weight coefficients and weighting coefficients are introduced for comprehensive calculation. The regional weight coefficients are set differently according to the sensitivity of different parts of the plantar (such as the arch, heel, and toes) to pressure and shear force, reflecting the importance of each region in the safety assessment; the weighting coefficients are used to adjust the relative proportion of pressure and shear force in the assessment. At the same time, the original pressure and shear force data are normalized using a nonlinear mapping function, converting them into comparable values ​​to eliminate the influence of dimensional differences. Through weighted summation, the pressure and shear force data are fused into a single safety assessment function value, which can comprehensively and objectively reflect the adaptability and safety of protective shoes to the plantar mechanical environment in actual use.

[0117] Step S603: determine whether the value of the security assessment function exceeds a preset threshold. If not, dynamically adjust the step size of the structural parameters based on the gradient descent algorithm.

[0118] Step S604: updating the structural parameter combination based on the structural parameter step size to generate a new parameter combination sequence.

[0119] Step S605: input the parameter combination sequence into the multi-objective optimization model to obtain a set of objective function values.

[0120] Step S606 , screening the optimal parameter identification number that meets the constraints according to the objective function value set to obtain the optimal structural parameter combination; the optimal parameter identification number corresponds to the dual-objective balance point of pressure and shear force.

[0121] Furthermore, the plantar pressure distribution matrix containing the pressure intensity data of each area and the shear force gradient matrix containing the dynamic shear change are obtained, and the safety assessment function value is calculated through weighted fusion; it is judged whether the function value exceeds the preset threshold. If not, the structural parameter step size is dynamically adjusted based on the gradient descent algorithm, and the parameter combination is updated to generate a new sequence; the new sequence is input into the multi-objective optimization model to obtain the objective function value set, from which the optimal parameter identification number that meets the constraints is screened, corresponding to the optimal structural parameter combination of the dual-objective balance point of pressure and shear force.

[0122] This embodiment builds a safety assessment system by integrating plantar pressure and shear force data to achieve a quantitative assessment of the ergonomic performance of protective shoes. Based on gradient descent parameter adjustment and multi-objective optimization models, it can automatically search for a balanced solution of pressure and shear force under preset safety standards, avoiding the blindness of subjective parameter adjustment in traditional designs. This method incorporates protective performance and wearing comfort into a unified optimization framework. The generated optimal parameter combination can not only meet safety indicators such as anti-smashing and electrical insulation, but also optimize the force distribution on the plantar surface, improve the comprehensive performance and market adaptability of the product, and promote the development of protective shoe design towards intelligence and precision.

[0123] In one embodiment, the security assessment function value can be calculated using the following formula:

[0124] ;

[0125] in, represents the value of the security assessment function, represents the plantar pressure distribution matrix, Indicates the first Rank The pressure intensity value of the column, represents the shear gradient matrix, represents the first Rank The dynamic shear variation of the column, represents the regional weight coefficient, and represents the weighting coefficient, A nonlinear mapping function representing pressure and shear forces.

[0126] Preferably, The nonlinear mapping function of pressure and shear force can be expressed by the following formula:

[0127] =exp( );

[0128] =( );

[0129] in, and represent the optimal values ​​of pressure and shear force, respectively. and Represents the parameters that control the shape of the function.

[0130] This embodiment constructs a systematic safety assessment system by quantitatively integrating plantar pressure and shear force data, avoiding the one-sidedness of single-indicator evaluation. The introduction of nonlinear mapping and weighting mechanisms can accurately reflect the differential impact of pressure intensity and dynamic shear changes in different plantar regions on safety, making the assessment results more in line with actual usage scenarios. This data-driven assessment method provides a scientific quantitative basis for the multi-objective optimization of protective shoes, helps to quickly identify the relationship between structural parameters and safety performance during the design phase, improve the efficiency and reliability of product design, and promote the development of protective shoe safety performance assessment towards standardization and precision.

[0131] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0132] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the aforementioned method for designing shoe styles based on a digitized three-dimensional model are implemented.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0134] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0135] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A shoe style design method based on a digital three-dimensional model, characterized in that: The method comprises: Acquire three-dimensional point cloud data of the protective shoe, perform noise reduction on the three-dimensional point cloud data, extract distribution features and construct a three-dimensional grid model; Acquiring vertex coordinate data and triangular facet topology data of the three-dimensional mesh model; calculating curvature characteristic parameters of each vertex based on the vertex coordinate data to obtain a curvature distribution map; extracting high curvature regions based on the curvature distribution map, and merging adjacent triangular facets in accordance with regional connectivity constraints to generate initial segmentation regions; Performing dilation and erosion operations on the boundaries of the initial segmented areas according to a preset segmentation threshold to determine the boundary point sets of the sole area, the upper area, and the anti-smashing area; performing topological relationship analysis on the boundary point sets, removing isolated points, and matching them with the triangular facet topology data to obtain a closed boundary point sequence for each area; Extracting the sole thickness distribution value, the anti-smashing curvature value and the upper wrinkle value according to the closed boundary point sequence to generate a feature vector data set; Constructing a finite element mesh model based on the material properties and geometric parameters in the feature vector data set; calling a mechanical solver to calculate stress distribution data of the finite element mesh model; and synchronously calling an electric field solver to calculate the electric potential gradient distribution of the finite element mesh model; The stress distribution data is coupled with the potential gradient distribution to analyze and extract an anti-smashing performance index value; the anti-smashing performance index value includes an impact resistance coefficient and an electric field shielding rate; and a protection performance quantitative relationship data set is generated based on the anti-smashing performance index value and the geometric parameters; A multi-objective optimization model is established based on the quantitative relationship data set to generate an optimal structural parameter combination that meets the preset safety standard constraints.

2. The method according to claim 1, characterized in that The step of obtaining three-dimensional point cloud data of the protective shoe, performing noise reduction processing on the three-dimensional point cloud data, extracting distribution features and constructing a three-dimensional grid model includes: Acquire three-dimensional point cloud data of the protective shoe; the three-dimensional point cloud data includes point cloud density information; Determining a noise reduction parameter threshold for controlling a point cloud neighborhood search radius according to the point cloud density information; Performing outlier filtering on the three-dimensional point cloud data based on the noise reduction parameter threshold to obtain noise-reduced three-dimensional point cloud data; Extracting surface normal vector distribution features of the denoised three-dimensional point cloud data; the surface normal vector distribution features include curvature continuity information; generating a triangular facet topology structure according to the curvature continuity information, and performing Poisson reconstruction on the denoised three-dimensional point cloud data to obtain an initial three-dimensional mesh model; The vertex curvature gradient of the initial three-dimensional mesh model is calculated to perform subdivision optimization on the initial three-dimensional mesh model to generate a final three-dimensional mesh model.

3. The method according to claim 2, characterized in that The vertex curvature gradient is calculated by the following formula: = ； = ； in, Indicates the The vertex curvature gradient of the mesh, Indicates the vertices in the mesh, Represents a vertex The first-order neighbor vertex set of represents the number of neighboring vertices, and Represents a vertex and vertices The principal curvature value of Indicates that from the vertex Point to the vertex The unit direction vector of represents the weighting coefficient, Represents a scaling parameter that controls the influence of curvature differences.

4. The method according to claim 1, wherein The extracting of the sole thickness distribution value, the anti-smashing curvature value and the upper wrinkle value according to the closed boundary point sequence to generate a feature vector data set includes: Extracting boundary point curvature continuity parameters and thickness gradient change rate according to the closed boundary point sequence; Calculate the rate of change of the anti-smashing head curvature radius according to the curvature continuity parameter to generate a curvature radius distribution matrix; Combining the thickness gradient change rate with the curvature radius distribution matrix to generate a three-dimensional feature mapping table; Extracting wrinkle region density distribution parameters from the three-dimensional feature map, and performing dimensionality reduction processing on the wrinkle region density distribution parameters using a principal component analysis method to obtain a low-dimensional feature vector set; Constructing a feature vector similarity matrix based on the low-dimensional feature vector set; the similarity matrix is ​​used to determine the correlation between the wrinkle degree of the shoe upper and the anti-smashing curvature; If the correlation exceeds a preset threshold, updating the curvature radius distribution weight coefficient in the three-dimensional feature mapping table; The dimensional distribution of the low-dimensional feature vector set is adjusted according to the updated weight coefficient, and an optimized feature vector data set is output.

5. The method according to claim 1, wherein The multi-objective optimization model is established based on the quantitative relationship data set to generate an optimal structural parameter combination that meets the preset safety standard constraints, including: Extracting a plantar pressure distribution matrix and a shear force gradient matrix based on the quantitative relationship data set; the pressure distribution matrix includes pressure intensity data of each region; the shear force gradient matrix includes dynamic shear variation; Calculating a safety assessment function value based on a weighted fusion of the pressure distribution matrix and the shear gradient matrix; Determine whether the value of the security assessment function exceeds a preset threshold, and if not, dynamically adjust the step size of the structural parameters based on a gradient descent algorithm; Update the structural parameter combination based on the structural parameter step size to generate a new parameter combination sequence; Inputting the parameter combination sequence into the multi-objective optimization model to obtain a set of objective function values; The optimal parameter identification number that meets the constraints is screened according to the objective function value set to obtain the optimal structural parameter combination; the optimal parameter identification number corresponds to the dual-objective balance point of pressure and shear force.

6. The method according to claim 5, characterized in that The security assessment function value is calculated by the following formula: ； in, represents the value of the security assessment function, represents the plantar pressure distribution matrix, Indicates the first Rank The pressure intensity value of the column, represents the shear gradient matrix, represents the first Rank The dynamic shear variation of the column, represents the regional weight coefficient, and represents the weighting coefficient, A nonlinear mapping function representing pressure and shear forces.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images