A digital textile sweater modeling simulation method and system

Abstract

The present application relates to sweater model simulation technical field, especially a kind of digital textile sweater's model simulation method and system.The method includes the following steps: obtaining the user all-around image of design to be designed, textile raw material multiscale parameter and textile technology log;The geometric shape parameter analysis of user all-around image of design to be designed is carried out, and three-dimensional geometric point cloud modeling is carried out, and user three-dimensional form model is constructed;Textile raw material multiscale parameter is analyzed, and depth parameter feature is mined, to obtain textile raw material multiscale state feature;Based on textile raw material multiscale state feature, external mechanical deformation response analysis and internal fiber elastic response analysis are carried out, to generate textile raw material external mechanical deformation response data and textile raw material internal fiber elastic response feature.The present application realizes personalized, intuitive user try-on simulation by sweater model simulation, improves textile sweater production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sweater model simulation, and in particular to a digital textile sweater model simulation method and system. BACKGROUND

[0002] With the development of computer simulation technology, especially under the support of three-dimensional modeling, virtual reality and artificial intelligence algorithms, the digital textile sweater model simulation method has gradually become a research hotspot in the textile field. By establishing a virtual model of the sweater and performing multi-level and multi-physical field simulation, the physical properties and wearing effect of the sweater can be effectively predicted, such as the elasticity, air permeability, warmth retention of the fabric, and the physical stability of the fabric, etc. The widespread application of this technology not only improves the accuracy of design, but also allows for quick adjustments in the simulation of different materials, styles and sizes, significantly shortening the product development cycle, reducing production costs, and better meeting the growing personalized and customized needs of consumers.

[0003] However, the current digital textile sweater model simulation technology still faces certain challenges. Traditional textile modeling methods mainly rely on simple geometric modeling and physical parameter settings, which are difficult to truly restore the microstructure and mechanical properties of sweater fiber materials, and are even less able to accurately predict the complex mechanical behavior during the knitting process. This not only limits the innovation of sweater design, but also makes it difficult to support virtual try-on and production process optimization based on digital models. In addition, fabric in actual production is influenced by multiple factors such as yarn quality, weaving method and textile machine parameters, and how to accurately map these multi-dimensional factors in digital simulation is a key problem in current technology development. Therefore, there is an urgent need for a more accurate and efficient digital textile sweater model simulation method that can fully consider the influence of material performance, weaving process and external environment, so as to achieve more realistic and reliable virtual sample development and optimization. SUMMARY

[0004] To solve the above technical problems, the present application provides a digital textile sweater model simulation method and system to solve at least one of the above technical problems.

[0005] To achieve the above purpose, the present application provides a digital textile sweater model simulation method, comprising the following steps:

[0006] Step S1: obtaining the user's all-around image to be designed, the multi-scale parameters of the textile raw material and the textile process log; analyzing the geometric shape parameters of the user's all-around image to be designed, and performing three-dimensional geometric point cloud modeling to construct a user three-dimensional shape model;

[0007] Step S2: analyzing the physical characteristic parameters of the multi-scale parameters of the textile raw material, and performing deep parameter feature mining to obtain the multi-scale state features of the textile raw material;

[0008] Step S3: based on the multi-scale state characteristics of the textile raw material, external mechanical deformation response analysis and internal fiber elastic response analysis are performed to generate external mechanical deformation response data of the textile raw material and internal fiber elastic response characteristics of the textile raw material;

[0009] Step S4: according to the external mechanical deformation response data of the textile raw material and the internal fiber elastic response characteristics of the textile raw material, dynamic textile deformation mapping is performed on the textile process log to construct a digital twin model of the textile sweater;

[0010] Step S5: dye penetration interactive mining is performed on the digital twin model of the textile sweater, and then dynamic color rendering is performed to construct a dynamic rendering digital twin model;

[0011] Step S6: based on the dynamic rendering digital twin model, dynamic try-on simulation is performed on the user three-dimensional shape model, and intelligent sweater parameter optimization is performed to construct an intelligent parameter optimized sweater model.

[0012] The present application can accurately capture the user's body characteristics by analyzing the geometric shape parameters of the user's full image and constructing a three-dimensional point cloud model, providing accurate reference for subsequent design, and constructing a user three-dimensional shape model helps personalized customization of clothing, improves the accuracy and compliance of design, through physical characteristic parameter analysis and deep feature mining, the characteristics of the textile raw material can be fully understood, providing a basis for subsequent simulation and design, obtaining the multi-scale state characteristics of the textile raw material helps to select appropriate raw materials, improves the quality and comfort of the sweater, external mechanical deformation response analysis and internal fiber elastic response analysis can help understand the behavior of the textile raw material under different conditions, provide basis for subsequent simulation and optimization, generating these data helps to simulate the actual deformation and elastic properties of the textile, improves the reality of model simulation, through dynamic textile deformation mapping, the characteristics of the raw material can be mapped into the model to construct a real digital twin model, which helps to simulate the morphological change of the textile, constructing a digital twin model can provide reliable reference for subsequent design and production, improve the quality and compliance of the product, through dye penetration interactive mining and dynamic color rendering, different dyeing effects can be simulated to provide more choices and inspiration for designers, constructing a dynamic rendering digital twin model helps to show the sweater effect under different color schemes, improves the diversity and innovation of design, through dynamic try-on simulation and intelligent parameter optimization, personalized customization can be made according to the user's body characteristics and needs, improves the comfort and fit of the clothing, constructing an intelligent parameter optimized sweater model helps to improve production efficiency and customer satisfaction, realizes customized production and service.

[0013] Preferably, step S1 comprises the following steps:

[0014] Step S11: obtaining a user all-around image to be designed, textile raw material multi-scale parameters and a textile process log;

[0015] Step S12: image detail reconstruction is performed on the user all-around image to be designed, and a super-resolution reconstructed image is constructed;

[0016] Step S13: deep visual semantic segmentation is performed on the super-resolution reconstructed image, and user body part information is identified;

[0017] Step S14: user part key point identification is performed on the user body part information, and body part key points are marked;

[0018] Step S15: user skeleton structure analysis is performed based on the body part key points, so as to generate user skeleton structure features;

[0019] Step S16: geometric morphological parameter analysis is performed on the user skeleton structure features, so as to generate user geometric morphological parameters; three-dimensional geometric point cloud modeling is performed on the user geometric morphological parameters, and a user three-dimensional morphological model is constructed.

[0020] By obtaining the all-around image, the textile parameters and the process log, a comprehensive basic data set can be established, necessary information and background are provided for subsequent steps, comprehensive utilization of these data helps to ensure the accuracy and integrity of the design process, image detail reconstruction can improve the clarity and quality of the image, which helps to capture the user body detail features, and provides more accurate data for subsequent analysis and modeling, construction of the super-resolution reconstructed image helps to improve the detail display of the image, and provides a better basis for subsequent body part information identification, through key point identification, important feature points of the user body can be marked, which helps subsequent skeleton structure analysis and generation of geometric morphological parameters, marking of the body part key points can provide more accurate data for subsequent steps, and ensure the accuracy and authenticity of the model, through user skeleton structure analysis, the user's skeleton features and structure can be understood, which provides a basis for subsequent geometric morphological parameter analysis, generation of the user skeleton structure features helps to simulate the user's body morphology, and provides key information for subsequent model establishment, through geometric morphological parameter analysis, the user's geometric morphological parameters can be generated, which provides a basis and basis for establishing the user three-dimensional morphological model, and construction of the user three-dimensional morphological model can better understand the user's body structure, and provide an accurate basis for subsequent sweater design and fitting simulation.

[0021] Preferably, the step S12 comprises the following specific steps:

[0022] The user all-around image to be designed is subjected to image-by-image filtering and noise reduction processing, and a filtered and denoised all-around image is obtained;

[0023] Image global outlier scanning is performed on the filtered denoised all-around image, and image outliers are extracted;

[0024] Abnormal outliers are removed from the image outliers, and an outlier-optimized all-around image is obtained;

[0025] Image detail recognition is performed on the outlier-optimized all-around image, and image detail features are extracted;

[0026] Image magnification distortion analysis is performed on the image detail features, and image magnification distortion data is obtained;

[0027] Based on the image magnification distortion data, point cloud smoothing is performed on the outlier-optimized all-around image to obtain a detail part smoothing image;

[0028] Original resolution point cloud extraction is performed on the detail part smoothing image to obtain an original image point cloud resolution;

[0029] Depth convolution learning is performed according to the original image point cloud resolution to obtain point cloud resolution convolution features;

[0030] Based on the point cloud resolution convolution features, super-resolution reconstruction is performed on the detail part smoothing image to construct a super-resolution reconstructed image.

[0031] The present application reduces noise and interference in the image, improves image quality and clarity, helps to accurately extract image details, provides more accurate data for subsequent processing steps, finds abnormal points in the image, helps to identify errors or abnormal data, extracts outliers to further optimize the image, ensures the accuracy and integrity of the data, cleans up abnormal outliers in the image, reduces data interference and misleading, optimizes the all-around image to improve the accuracy and efficiency of subsequent processing steps, extracts image details to better understand image content, and the identification of detail features provides important information for subsequent analysis and processing. Understand the distortion that occurs during image magnification to provide a reference for maintaining image quality. This analysis helps to maintain the authenticity and clarity of image details in subsequent processing, reduces noise and discontinuity in the image through smoothing processing, and smoothing processing helps to improve the overall quality and visualization of the image. Extract the point cloud data of the original image to provide a basis for subsequent analysis and processing. This step helps to preserve the details and accuracy of the image. Through deep learning technology, feature information in the point cloud data is extracted, and the learned convolution features can be used for subsequent model construction and analysis. Construct a super-resolution reconstructed image to improve image clarity and detail display, and help generate more realistic and accurate images to provide a better visual basis for digital textile sweater model simulation.

[0032] Preferably, step S2 comprises the following steps:

[0033] Step S21: physical characteristic parameter analysis is performed on the textile raw material multi-scale parameters to extract the textile raw material physical characteristic parameters;

[0034] Step S22: fiber mechanics performance calculation is performed on the textile raw material physical characteristic parameters to obtain textile raw material fiber mechanics performance data;

[0035] Step S23: inter-fiber friction coefficient calculation is performed on the textile raw material physical characteristic parameters to obtain inter-fiber friction parameters;

[0036] Step S24: fiber bundle mechanics characteristic analysis is performed on the textile raw material physical characteristic parameters to obtain fiber bundle mechanics characteristic data;

[0037] Step S25: deep parameter feature mining is performed on the textile raw material fiber mechanics performance data, inter-fiber friction parameters and fiber bundle mechanics characteristic data to obtain textile raw material multi-scale state features.

[0038] The physical characteristic parameter analysis can deeply understand the physical properties of the textile raw material, provide a basis for subsequent performance calculation and characteristic analysis, and the extraction of the physical characteristic parameters of the textile raw material helps to determine the characteristics and attributes of the material and provide accurate input data for model simulation. The fiber mechanics performance calculation can reveal the performance of the textile raw material under stress, provide key information for further analysis and design, and the obtained fiber mechanics performance data are helpful for evaluating the strength, elasticity and other characteristics of the material, which are of great significance in model simulation. The calculation of the inter-fiber friction coefficient can help understand the interaction between the fibers of the textile raw material, affect the performance and characteristics of the textile, and the obtained inter-fiber friction parameters are helpful for simulating the performance of the textile under different conditions and providing more accurate data for model simulation. Through the fiber bundle mechanics characteristic analysis, the stress condition and performance characteristics of the fiber bundle of the textile raw material can be understood, which provides an important reference for design and simulation, and the obtained fiber bundle mechanics characteristic data are helpful for evaluating the performance of the textile in actual use and providing practical information for model simulation. Through deep parameter feature mining, the multi-scale state features of the textile raw material can be obtained by comprehensively analyzing the fiber mechanics performance, friction parameters and fiber constraint mechanics characteristics, which can fully exhibit the performance and characteristics of the textile raw material and provide comprehensive data support for model simulation of digital textile sweaters.

[0039] Preferably, step S3 comprises the following specific steps:

[0040] Step S31: external mechanical deformation response analysis is performed on the textile raw material multi-scale state features to generate textile raw material external mechanical deformation response data;

[0041] Step S32: internal fiber bundle discrete analysis modeling is performed based on the textile raw material multi-scale parameters to obtain textile raw material internal fiber discrete particles;

[0042] Step S33: simulate the external load action on the internal fiber discrete particles of the textile material to extract external load action simulation data of the fiber discrete particles;

[0043] Step S34: calculate the force balance of each particle based on the interaction simulation data of the fiber discrete particles to extract the force balance data of each fiber discrete particle;

[0044] Step S35: perform internal fiber elastic response analysis based on the force balance data of each fiber discrete particle to obtain the internal fiber elastic response characteristics of the textile material.

[0045] The present application can understand the deformation and response characteristics of the textile material under external force by analyzing the external mechanical deformation response, provide key data for model simulation, generate external mechanical deformation response data of the textile material, which helps to evaluate the deformation behavior and performance of the material, provide a basis for design and simulation, and through internal fiber bundle discrete analysis modeling, the structure and arrangement of the internal fibers of the textile material can be simulated, which provides a basis for subsequent simulation and analysis, and the internal fiber discrete particles of the textile material are obtained, which helps to understand the internal structure of the material, provides detailed information for model simulation, and through external load action simulation, the behavior of the fiber discrete particles under external load can be simulated, which provides basic data for further analysis, and the extraction of fiber discrete particle external load action simulation data helps to understand the response of the material under force, which provides necessary information for subsequent steps, and the force balance calculation of each particle can reveal the interaction and force condition between the fiber discrete particles, which provides a basis for simulating the internal mechanical properties of the textile material, and the extraction of the force balance data of each fiber discrete particle helps to understand the internal micro-mechanical behavior of the material, which provides key data for model simulation, and through internal fiber elastic response analysis, the elastic characteristics and response behavior of the internal fibers of the textile material under force can be understood, which provides important information for model simulation, and the internal fiber elastic response characteristics of the textile material are obtained, which helps to evaluate the elastic performance and deformation characteristics of the material, and provides support for design and simulation.

[0046] Preferably, the specific steps of step S31 are:

[0047] Based on the multi-scale state characteristics of the textile material, simulate the multi-frequency pressure application of the textile material to extract the pressure simulation response state parameters of the textile material;

[0048] Identify the fiber deformation characteristics based on the textile material pressure simulation response state parameters to generate fiber deformation characteristic data;

[0049] Perform stress-strain analysis on the fiber deformation characteristic data to obtain the stress-strain data of the textile material;

[0050] The strain response change curve is analyzed for external mechanical deformation response, and external mechanical deformation response data of the textile raw material is generated.

[0051] The strain response change curve is analyzed for external mechanical deformation response, and external mechanical deformation response data of the textile raw material is generated.

[0052] The present application can simulate the pressure response of textile raw materials under different frequencies through multi-frequency pressure simulation, understand the deformation and response of materials under different frequencies, extract the pressure simulation response state parameters of textile raw materials, help to evaluate the performance of materials under multi-frequency pressure, provide data basis for subsequent analysis, identify the deformation characteristics of fibers, help to understand the deformation mode and degree of textile raw materials under the action of pressure, provide key information for subsequent analysis, generate fiber deformation feature data, help to understand the internal structure change of materials, provide basis for stress-strain analysis, stress-strain analysis can help to determine the stress distribution and deformation of textile raw materials under the action of pressure, provide important data for material performance evaluation, obtain the stress-strain data of textile raw materials, help to understand the strength and deformation characteristics of materials, provide support for model simulation, strain response change analysis can reveal the deformation characteristics and response behavior of textile raw materials under different strains, provide key information for further analysis, obtain the strain response change curve, help to understand the performance change of materials under different strain conditions, provide data basis for subsequent steps, external mechanical deformation response analysis can help to understand the overall deformation characteristics of textile raw materials under different strain response change conditions, provide comprehensive understanding for model simulation, generate external mechanical deformation response data of textile raw materials, help to evaluate the deformation performance of materials under external mechanical action, and provide support for design and simulation.

[0053] Preferably, the specific steps of step S4 are:

[0054] Step S41: multi-stage textile process analysis is performed on the textile process log, and textile process data of each stage is extracted;

[0055] Step S42: process timing logic analysis is performed on the textile process data of each stage, and textile process timing logic is generated;

[0056] Step S43: process textile simulation is performed on the textile sweater based on the textile process timing logic, to obtain a textile sweater simulation model;

[0057] Step S44: dynamic textile deformation mapping is performed on the textile sweater simulation model based on the external mechanical deformation response data of the textile raw material and the internal fiber elastic response characteristics of the textile raw material, and a digital twin model of the textile sweater is constructed.

[0058] The application can deeply understand the manufacturing process of digital textile sweaters by analyzing the textile process log, extract process data at each stage, and extract textile process data at each stage to help understand the specific operation and parameters of each step, provide basic data for subsequent analysis, and establish the time sequence and logical relationship between textile processes through process timing logic analysis to ensure the smooth progress of the manufacturing process, generate textile process timing logic to help optimize production processes, improve efficiency and quality control, simulate the manufacturing process of digital textile sweaters through process textile simulation to obtain a simulation model for further analysis and optimization, and obtain a textile sweater simulation model to help understand the details and improvement points in the entire production process, improve production efficiency and product quality, and combine external mechanical deformation response data with internal fiber elastic response characteristics through dynamic textile deformation mapping to construct a digital twin model of the digital textile sweater, and the construction of the digital twin model helps to simulate the deformation and performance of the textile sweater under different conditions, providing an important reference for product design and optimization.

[0059] Preferably, the specific steps of step S5 are:

[0060] Step S51: performing preset dyeing demand analysis on the textile process log to extract preset process dyeing demand data;

[0061] Step S52: performing dye parameter calculation on the preset process dyeing demand data to extract dye characteristic parameters;

[0062] Step S53: performing dye penetration interaction mining on the dye characteristic parameters based on the multi-scale state characteristics of the textile raw materials to generate textile raw material dye penetration interaction data;

[0063] Step S54: performing dye diffusion evolution analysis on the textile raw material dye penetration interaction data to generate dynamic dye diffusion evolution data;

[0064] Step S55: performing dynamic color rendering on the digital twin model of the textile sweater according to the dynamic dye diffusion evolution data to construct a dynamic rendering digital twin model.

[0065] The application can determine the dyeing requirements and parameters of digital textile sweaters through dyeing demand analysis, extract the required process dyeing data, and extract the preset dyeing demand data to help ensure that the dyeing process meets the design requirements, provide basic data for subsequent steps, calculate the dye parameters to determine the characteristic parameters of the required dyes, so as to accurately dye the formula and control in the dyeing process, and extract the dye characteristic parameters to help ensure the accuracy and consistency of the dyeing process, improve the quality and stability of the dyeing effect, and through dye penetration interaction mining, the penetration and interaction of dyes in textile raw materials can be deeply understood, relevant data can be generated, and textile raw material dye penetration interaction data can be generated to help understand the behavior of dyes in textile materials and provide a basis for subsequent analysis and control. Through dye diffusion evolution analysis, the diffusion process of dyes in textile raw materials can be simulated, dynamic dye diffusion evolution data can be generated, and dynamic dye diffusion evolution data can be generated to help understand the propagation mode and speed of dyes in materials and provide support for the control and optimization of the dyeing process. Through dynamic color rendering, the digital twin model of the textile sweater can be color rendered according to the dynamic dye diffusion evolution data, the color change at different stages can be displayed, and the dynamic rendering digital twin model can be constructed to help visually display the change of the dyeing effect and provide visual support for design and display.

[0066] Preferably, the specific steps of step S6 are:

[0067] Step S61: dynamically fitting the user three-dimensional shape model based on the dynamic rendering digital twin model to obtain a textile sweater-user shape simulation model;

[0068] Step S62: analyzing the fit of the textile sweater-user shape simulation model to extract sweater fit data;

[0069] Step S63: calculating the tightness of the textile sweater-user shape simulation model to generate user sweater tightness;

[0070] Step S64: analyzing the individualized user fitting characteristics of the sweater fit data and user sweater tightness to extract individualized user fitting characteristic parameters;

[0071] Step S65: intelligently optimizing the sweater parameters based on the individualized user fitting characteristic parameters to obtain individualized sweater optimization parameters;

[0072] Step S66: individualized process simulation optimization of the textile sweater-user shape simulation model based on the individualized sweater optimization parameters to construct an intelligent parameter optimized sweater model.

[0073] The application can simulate the actual effect of the sweater on the user by dynamically fitting simulation of the user's three-dimensional shape model, obtain a textile sweater-user shape simulation model, and the obtained simulation model helps to evaluate the fitness and appearance effect of the sweater on different users, provides a reference for personalized design, through fit analysis, the fit of the sweater on the user can be evaluated, fit data can be extracted, and the extracted data helps to understand the fitting degree of the sweater and the user's body shape, provides a basis for subsequent adjustment and optimization, calculating the tightness of the user's sweater can determine the comfort and wearing feeling of the sweater, and better wearing experience is provided for the user, the generation of the tightness data helps to understand the comfort and adaptability of the sweater, and provides a reference for personalized design, through analysis of the personalized user fitting characteristic parameters, the dressing needs and preferences of different users can be deeply understood, and the extracted characteristic parameters help personalized design and customization, improve user satisfaction and wearing comfort, through intelligent parameter optimization, the sweater design can be optimized and adjusted according to the personalized user fitting characteristic parameters, improve the wearing effect and comfort, and the obtained personalized sweater optimization parameters help to meet the personalized needs of users and improve the market competitiveness of products, according to the personalized sweater optimization parameters, process simulation optimization is performed on the simulation model, an intelligent parameter optimized sweater model that meets the needs of users can be constructed, and the constructed model helps to improve the personalized degree of sweater design and wearing experience, and enhances the market appeal and user satisfaction of products.

[0074] In the present specification, a model simulation system of a digital textile sweater is provided for performing the model simulation method of the digital textile sweater as described above, comprising:

[0075] A three-dimensional shape module is configured to acquire a full-view image of a user to be designed, multi-scale parameters of a textile raw material, and a textile process log, analyze geometric shape parameters of the full-view image of the user to be designed, and perform three-dimensional geometric point cloud modeling to construct a three-dimensional shape model of the user.

[0076] A multi-scale state module is configured to analyze physical characteristic parameters of the multi-scale parameters of the textile raw material, and perform deep parameter feature mining to obtain multi-scale state features of the textile raw material.

[0077] A mechanical deformation module is configured to perform external mechanical deformation response analysis and internal fiber elastic response analysis based on the multi-scale state features of the textile raw material to generate external mechanical deformation response data of the textile raw material and internal fiber elastic response features of the textile raw material.

[0078] A textile deformation module is configured to perform dynamic textile deformation mapping on the textile process log according to the external mechanical deformation response data of the textile raw material and the internal fiber elastic response features of the textile raw material to construct a digital twin model of the textile sweater.

[0079] A dynamic color rendering module is used to perform dye penetration interaction mining on the digital twin model of the textile sweater, and then perform dynamic color rendering to construct a dynamic rendering digital twin model.

[0080] A dynamic try-on simulation module is used to perform dynamic try-on simulation on the user three-dimensional form model based on the dynamic rendering digital twin model, and perform intelligent sweater parameter optimization to construct an intelligent parameter optimized sweater model.

[0081] The present application constructs a user three-dimensional form model through geometric form parameter analysis and three-dimensional geometric point cloud modeling of the user's full range of images, better understands the user's body features and form, and provides a basis for subsequent design and simulation. Through physical characteristic parameter analysis and deep parameter feature mining of the multi-scale parameters of the textile raw material, the multi-scale state features of the textile raw material are obtained, which helps to better understand the characteristics and state of the textile raw material and provides more accurate data support in the design and production process. Based on the multi-scale state features of the textile raw material, external mechanical deformation response analysis and internal fiber elastic response analysis are performed to generate deformation and elastic response data of the textile raw material, which helps to understand the deformation of the textile material under external mechanical action and provides a basis for subsequent simulation and optimization. According to the external deformation response data and internal fiber elastic response features of the textile raw material, dynamic textile deformation mapping is performed on the textile process log to construct a digital twin model of the textile sweater, which makes it possible to more accurately simulate the performance of the textile under different deformation conditions and provides a reference for the design and production process. Through dye penetration interaction mining and dynamic color rendering, a dynamic rendering digital twin model is constructed, which enables the design team to better preview and adjust the color effect of the sweater and more intuitively understand the appearance of the sweater, improving design efficiency and product quality. Through try-on simulation and intelligent parameter optimization of the dynamic rendering digital twin model on the user three-dimensional form model, an intelligent parameter optimized sweater model is constructed, which helps to personalized design and production, improves the fit and comfort of the sweater, and enhances user experience and product competitiveness. BRIEF DESCRIPTION OF DRAWINGS

[0082] Figure 1 A step flowchart of a model simulation method of a digital textile sweater of the present application;

[0083] Figure 2 A detailed implementation step flowchart of step S1;

[0084] Figure 3 A detailed implementation step flowchart of step S2;

[0085] Figure 4 A detailed implementation step flowchart of step S3. DETAILED DESCRIPTION

[0086] It is to be understood that the specific embodiments described herein are merely illustrative of the present application and should not be used to limit the present application in any manner.

[0087] The present application provides a digital textile sweater model simulation method and system. The execution subject of the digital textile sweater model simulation method and system includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. which can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: audio image management system, information management system, cloud data management system at least one.

[0088] Please refer to Figures 1 to 4 The present application provides a digital textile sweater model simulation method, which includes the following steps:

[0089] Step S1: obtaining the user's all-around image to be designed, textile raw material multi-scale parameters and textile process log; analyzing the geometric shape parameters of the user's all-around image to be designed, and performing three-dimensional geometric point cloud modeling to construct a user three-dimensional shape model;

[0090] Step S2: analyzing the physical characteristic parameters of the textile raw material multi-scale parameters, and performing deep parameter feature mining to obtain the textile raw material multi-scale state characteristics;

[0091] Step S3: based on the textile raw material multi-scale state characteristics, performing external mechanical deformation response analysis and internal fiber elastic response analysis to generate textile raw material external mechanical deformation response data and textile raw material internal fiber elastic response characteristics;

[0092] Step S4: dynamically mapping the textile process log according to the textile raw material external mechanical deformation response data and the textile raw material internal fiber elastic response characteristics to construct a digital twin model of the textile sweater;

[0093] Step S5: dye penetration interaction mining is performed on the digital twin model of the textile sweater, and then dynamic color rendering is performed to construct a dynamic rendering digital twin model;

[0094] Step S6: based on the dynamic rendering digital twin model, dynamic try-on simulation is performed on the user three-dimensional shape model, and intelligent sweater parameter optimization is performed to construct an intelligent parameter optimized sweater model.

[0095] The application can accurately capture the body features of the user by analyzing the geometric parameters of the user's full-view image and modeling the three-dimensional point cloud, providing accurate reference for subsequent design, and constructing the three-dimensional shape model of the user, which helps to customize the clothing, improves the accuracy and compliance of the design, and through the analysis of physical characteristic parameters and deep feature mining, the characteristics of the textile raw material can be fully understood, providing a basis for subsequent simulation and design, and obtaining the multi-scale state characteristics of the textile raw material helps to select the appropriate raw material, improve the quality and comfort of the sweater, and the analysis of external mechanical deformation response and internal fiber elastic response can help to understand the behavior of the textile raw material under different conditions, providing a basis for subsequent simulation and optimization, and generating these data helps to simulate the actual deformation and elastic properties of the textile, improves the reality of model simulation, and through dynamic textile deformation mapping, the characteristics of the raw material can be mapped into the model, constructing a real digital twin model, which helps to simulate the morphological changes of the textile, and constructing the digital twin model can provide reliable reference for subsequent design and production, improve the quality and compliance of the product, and through dye penetration interaction mining and dynamic color rendering, different dyeing effects can be simulated, providing more choices and inspiration for designers, and constructing a dynamic rendering digital twin model helps to show the sweater effect under different color schemes, improves the diversity and innovation of design, and through dynamic try-on simulation and intelligent parameter optimization, personalized customization can be carried out according to the body characteristics and needs of the user, improving the comfort and fit of the clothing, and constructing an intelligent parameter optimization sweater model helps to improve production efficiency and customer satisfaction, realizing customized production and service.

[0096] In the embodiment of the application, reference is made to Figure 1 The step flow diagram of the model simulation method of the digital textile sweater of the application is shown in the example, and the steps of the model simulation method of the digital textile sweater include:

[0097] Step S1: obtaining the full-view image of the user to be designed, the multi-scale parameters of the textile raw material and the textile process log; analyzing the geometric shape parameters of the full-view image of the user to be designed, and modeling the three-dimensional geometric point cloud, constructing the three-dimensional shape model of the user;

[0098] In this embodiment, high-resolution cameras or 3D scanners are used to acquire full-view images of the user to be designed, which should cover various angles of the user, including front, side and back, ensuring that the images are taken under uniform lighting conditions to reduce the impact of shadows and reflections on post-processing, collecting relevant textile raw material multi-scale parameter data, including fiber diameter, density, strength, elongation, etc., which can be measured through experiments or obtained from material databases, collecting relevant textile process logs related to the designed sweater, recording information including textile process, process parameters, dyeing requirements, etc., using image processing software (such as OpenCV or MATLAB) to preprocess the acquired user images, these steps include denoising, contrast enhancement and edge detection, etc., by analyzing the images, extracting the user's geometric parameters, such as height, shoulder width, chest circumference, waist circumference, hip circumference, etc., which can be achieved through manual measurement or automated tools (such as deep learning models), using three-dimensional reconstruction algorithms (such as Structure from Motion (SfM) or Multi-View Stereo (MVS)) to convert the processed images into point cloud data, these algorithms can generate dense three-dimensional point clouds by combining the information of multiple images, using point cloud processing software (such as CloudCompare or PCL) to filter and denoise the generated point cloud, remove outliers, and register the point cloud to ensure its integrity and accuracy, using 3D modeling software (such as Blender, MeshLab or 3dsMax) to convert the processed point cloud data into a three-dimensional geometric model, algorithms such as Delaunay triangulation or Poisson reconstruction can be used to create mesh models, optimizing the generated three-dimensional model, including simplifying the mesh, smoothing the surface and filling the holes, to improve the model quality and ensure its suitability for subsequent textile design and simulation, saving the final three-dimensional geometric model in a standard format (such as OBJ, STL or FBX) for subsequent processing and application, verifying the consistency of the generated user three-dimensional morphology model with the actual user morphology, adjusting and optimizing according to user feedback.

[0099] Step S2: Physical characteristic parameter analysis and deep parameter feature mining are performed on the multi-scale parameters of the textile raw materials, thereby obtaining the multi-scale state features of the textile raw materials;

[0100] In this embodiment, the multi-scale parameter data of the textile raw material is collected, including but not limited to fiber diameter, density, strength, elongation, specific gravity, thermal conductivity, etc. These data can be obtained by experimental measurement, literature review or material database. The collected multi-scale parameters are arranged in a structured format (such as Excel table or database) to ensure the integrity, accuracy and consistency of the data, determine the units and ranges of each parameter for subsequent analysis, define the physical characteristic parameters including elastic modulus, tensile strength, compressive strength, stiffness, etc. These parameters are important indicators for evaluating the performance of textile raw materials. According to the characteristics of the textile raw material, select the appropriate calculation method, the commonly used methods include: Hooke's law: used to calculate the elastic modulus, stress-strain curve analysis: used to calculate the tensile strength and elongation, according to the defined characteristic parameters and selected calculation method, calculate the physical characteristic parameters, record the calculation results, and compare with the known standard to ensure the reasonableness and effectiveness of the results, standardize or normalize the physical characteristic parameters for subsequent analysis and mining, remove outliers and noise to ensure the clarity and accuracy of the data, select appropriate deep feature mining methods, such as: principal component analysis (PCA): used to reduce data dimensionality and extract main features, clustering analysis: used to identify patterns and groups in the data, machine learning algorithms such as random forest or support vector machine, perform feature importance evaluation, apply the selected feature mining method to the sorted physical characteristic data, extract key deep parameter features, generate multi-scale state features of the textile raw material, including its performance under different conditions, record the mined multi-scale state features in the database or document to ensure the traceability and usability of the data, use data visualization tools (such as Matplotlib, Tableau or PowerBI) to visualize the analysis results, help understand the relationship between parameters, verify whether the results of deep feature mining are consistent with the actual material performance, if necessary, adjust and optimize the model, apply the obtained multi-scale state features of the textile raw material to subsequent product design and process optimization to ensure that the performance of the material meets the design requirements, collect user feedback in actual application to evaluate the effectiveness of the extracted features and provide reference for future feature extraction and analysis.

[0101] Step S3: Based on the multi-scale state features of the textile raw material, external mechanical deformation response analysis and internal fiber elastic response analysis are performed to generate external mechanical deformation response data of the textile raw material and internal fiber elastic response features of the textile raw material.

[0102] In this embodiment, ensure that the existing textile raw material multi-scale state feature data is complete, including physical properties, geometric properties and material parameters, determine the experimental conditions of external mechanical deformation response analysis and internal fiber elastic response analysis, including loading method (such as tension, compression, shear), load size, temperature and humidity, etc., use finite element analysis (FEA) software (such as ANSYS, ABAQUS or COMSOL) to establish the mechanical model of textile raw material, this model should consider the anisotropy and nonlinearity of the material, set appropriate boundary conditions, simulate the constraint conditions in actual use, apply external load on the model, record the load type, size and application method (static or dynamic), run finite element analysis, monitor the response of the model under external mechanics, including stress, strain, displacement, etc. Data, generate external mechanical deformation response data of textile raw material, record the stress and strain distribution of each node, based on the multi-scale characteristics of textile raw material, construct the discrete model of internal fiber bundle, use discrete element method (DEM) or fiber-based model, set the corresponding physical parameters for each fiber particle in the model, such as elastic modulus, Poisson's ratio and strength, etc. Apply appropriate external load to the internal fiber model to simulate the stress condition of the fiber bundle in actual use, use numerical simulation method (such as finite element method or molecular dynamics simulation) to analyze the elastic response of internal fiber, extract the stress and strain response of each fiber, record the obtained internal fiber elastic response feature data of textile raw material, including the stress, strain and interaction of each fiber, integrate the external mechanical deformation response data and internal fiber elastic response feature data to form a comprehensive data set, which is convenient for subsequent analysis, use data analysis software (such as MATLAB, Python or R) to analyze the response data, including statistical description and visualization display, draw stress-strain curve, displacement distribution map and fiber response map, help to understand the performance of the material under external mechanics.

[0103] Step S4: According to the external mechanical deformation response data of the textile raw material and the internal fiber elastic response characteristics of the textile raw material, dynamically map the textile process log to the textile deformation, and construct a digital twin model of the textile sweater.

[0104] In this embodiment, the external mechanical deformation response data and internal fiber elastic response characteristic data of the textile raw material are ensured to be complete and uniform in format. These data should include stress, strain, displacement, and fiber response information. Relevant textile process logs are collected to record important parameters and steps in the textile process, including weaving method, machine used, operating conditions, etc. Based on the collected external mechanical deformation response data, a dynamic mapping model is constructed to determine how to combine the mechanical response with the actual textile process. Suitable interpolation methods (such as linear interpolation, spline interpolation, or Kriging interpolation) are selected to process and map the mechanical response data, so as to combine it with the time series data in the process log. The external mechanical deformation response data and internal fiber elastic response characteristic data are mapped with each stage in the process log to generate a dynamic deformation model for each process stage. In the mapping process, the effects of time, temperature, humidity, and other environmental factors on the performance of the textile material are considered. The framework of the digital twin model is designed, and its structure, function, and required input and output parameters are determined. This model should be able to reflect the dynamic behavior of the textile sweater under different process conditions in real time. Suitable modeling tools or software (such as MATLAB Simulink, AnyLogic, Unity, or other simulation software) are selected to construct the digital twin model. In the selected software, the digital twin model of the textile sweater is constructed based on the dynamic mapping results and process log information. The mechanical response data and process information are input into the model to ensure that it can update and display the performance of the sweater under different process conditions in real time.

[0105] Step S5: dye penetration interaction mining is performed on the textile sweater digital twin model, and dynamic color rendering is performed to construct a dynamic rendering digital twin model.

[0106] In this embodiment, collect data related to dye properties such as chemical composition, molecular size, solubility, diffusion coefficient, and interaction characteristics with textile materials, organize experimental data of dyes under different conditions including temperature, pH value, time, etc. affecting factors, establish a dye penetration model, consider the multi-scale characteristics of textile materials and their influence on dye penetration, use mathematical models (such as Fick's law) to describe the diffusion process of dyes, use numerical simulation software (such as COMSOL Multiphysics, ANSYS Fluent) or custom algorithms to simulate the penetration process of dyes in the textile sweater, record the penetration depth, diffusion speed and concentration changes of dyes in the fiber, generate dye penetration interaction data, design a color mapping model based on dye penetration interaction data, determine how to correspond dye concentration to color change, use color space models (such as HSV or RGB) to map dye concentration to visual color, select appropriate rendering tools or engines (such as Unity, UnrealEngine or Blender) for dynamic color rendering, these tools should support real-time rendering and dynamic updating, implement dynamic color rendering in the selected rendering tools, update the color performance of the textile sweater in real time combined with dye penetration interaction data, set rendering parameters such as lighting, reflection and material properties to enhance visual effects and ensure the realism of rendering results, compare the rendering results with actual dyeing samples to verify the accuracy and authenticity of the dynamic rendering model, collect user feedback to evaluate the effect of color rendering and ensure it meets design requirements, optimize the rendering model based on verification results and user feedback, adjust mapping algorithms and rendering parameters to improve rendering effect.

[0107] Step S6: Dynamic fitting simulation of the user's three-dimensional shape model based on the dynamic rendering digital twin model, intelligent sweater parameter optimization, and construction of an intelligent parameter-optimized sweater model.

[0108] In this embodiment, it is ensured that the user's three-dimensional shape model and the dynamically rendered digital twin model have been constructed and can be operated in the same environment. The compatibility of the model is ensured using 3D modeling software (such as Blender, Unity or Maya), a virtual fitting environment is built in the selected 3D software, the lighting, material and physical properties are ensured to be consistent with the actual situation to achieve a real visual effect, the user's three-dimensional shape model is combined with the dynamically rendered digital twin model, the dynamic fitting effect is realized through a physical simulation engine (such as the physical engine of Unity or the physical simulation of Blender), simulation parameters such as gravity and friction are set to realistically simulate the performance of the sweater on the user's body, the contact between the sweater and the user's body is recorded, including fit, deformation and motion range data, the optimization target of the smart sweater is determined, such as improving fit, increasing comfort and optimizing appearance, quantitative indicators are set for each target, such as contact area, pressure distribution and tightness, suitable optimization algorithms are selected, such as genetic algorithm, particle swarm optimization or Bayesian optimization, which can automatically adjust parameters according to the objective function to achieve the best design, the data of dynamic fitting simulation is input into the optimization algorithm, the algorithm is run to identify and adjust the key parameters of the sweater (such as size, shape, material properties, etc.), the model performance is evaluated and the results are recorded in each iteration until the set optimization target is reached.

[0109] In this embodiment, reference is made to Figure 2 The detailed implementation steps of step S1 include:

[0110] Step S11: obtaining the user's all-around image to be designed, the multi-scale parameters of the textile raw materials and the textile process log;

[0111] Step S12: image detail reconstruction is performed on the user's all-around image to be designed to construct a super-resolution reconstructed image;

[0112] Step S13: depth vision semantic segmentation is performed on the super-resolution reconstructed image to identify user body part information;

[0113] Step S14: user part key point identification is performed on the user body part information to mark the body part key points;

[0114] Step S15: user skeleton structure analysis is performed based on the body part key points to generate user skeleton structure features;

[0115] Step S16: geometric shape parameter analysis is performed on the user skeleton structure features to generate user geometric shape parameters; three-dimensional geometric point cloud modeling is performed on the user geometric shape parameters to construct a user three-dimensional shape model.

[0116] In this embodiment, the user's full-body image is collected, which can be achieved through multi-angle shooting (such as 360-degree photography), ensuring that the image covers all body parts of the user, obtaining multi-scale parameters of the textile material, including the thickness, elasticity, texture, etc. of the material, which can be obtained through laboratory tests or information provided by the supplier, collecting the textile process log, recording the key parameters and operation steps in the textile process for subsequent analysis, organizing the collected images, parameters and log data into the designated database or file system, ensuring the integrity and accessibility of the data, selecting a suitable super-resolution reconstruction algorithm, such as SRCNN (Super-Resolution Convolutional Neural Network), ESPCN (Efficient Subpixel Convolutional Neural Network), etc., preprocessing the user's full-body image to be designed, including normalization, denoising and adjusting the size, etc. to improve the reconstruction effect, using the selected super-resolution algorithm to process the preprocessed image to generate a higher resolution reconstructed image, evaluating the quality of the reconstructed image to ensure that the details are effectively improved, selecting a suitable deep learning model for semantic segmentation, such as U-Net, DeepLab or MaskR-CNN, if there is no ready-made model, collecting labeled data for model training, using data augmentation techniques to improve the generalization ability of the model, verifying the segmentation effect of the model, adjusting the hyperparameters to optimize the performance, inputting the super-resolution reconstructed image into the trained deep learning model for deep visual semantic segmentation, identifying the user's body part information, saving the segmentation result as a binary image or label map for subsequent processing, selecting a suitable key point detection algorithm, such as OpenPose, PoseNet or HRNet, inputting the segmented image into the key point detection model to identify the user's body part key points (such as head, shoulder, elbow, knee, etc.), recording the identified key point coordinates in a data structure (such as an array or dictionary), marking the identified body part key points on the image to verify the accuracy of the identification, determining the model for user skeletal structure analysis, which is usually based on human anatomy models, constructing the user's skeletal structure according to the identified body part key points, using connection lines or three-dimensional models to represent the skeleton, extracting features of the skeletal structure, such as joint angles, limb proportions, etc., recording in a data structure for subsequent analysis, defining the types of user geometric morphological parameters, such as body width, length, volume, etc., calculating the user's geometric morphological parameters using the previously extracted skeletal structure features, converting the user's geometric morphological parameters into a three-dimensional point cloud model using three-dimensional modeling software (such as Blender, MeshLab) or point cloud processing libraries (such as PCL), processing the point cloud (such as denoising, resampling), generating a three-dimensional morphological model of the user, verifying the accuracy and completeness of the generated three-dimensional morphological model, storing the three-dimensional model in a suitable format (such as OBJ, PLY) for subsequent visualization and analysis.

[0117] In this embodiment, step S12 specifically comprises the following steps:

[0118] Filter and denoise each image of the all-around image of the user to be designed to obtain a filtered and denoised all-around image;

[0119] Scan the filtered and denoised all-around image for image global outliers to extract image outliers;

[0120] Perform outlier elimination on the image outliers to obtain an outlier-optimized all-around image;

[0121] Identify image details from the outlier-optimized all-around image to extract image detail features;

[0122] Perform magnification distortion analysis on the image detail features to obtain image magnification distortion data;

[0123] Smooth the outlier-optimized all-around image based on the image magnification distortion data to obtain a detail part smooth image;

[0124] Extract original resolution point clouds from the detail part smooth image to obtain an original image point cloud resolution;

[0125] Perform deep convolution learning according to the original image point cloud resolution to obtain point cloud resolution convolution features;

[0126] Reconstruct the detail part smooth image based on the point cloud resolution convolution features to construct a super-resolution reconstructed image.

[0127] In this embodiment, a suitable image filtering algorithm such as Gaussian filtering, median filtering or bilateral filtering is selected to reduce image noise. The selected filtering algorithm is applied to each user's full-view image to be designed, and image noise reduction processing is performed on each image. The filtering parameters (such as window size, standard deviation, etc.) are adjusted according to the image characteristics to obtain the best noise reduction effect. The filtered and noise-reduced full-view image is stored in a designated data structure for subsequent processing. A suitable outlier detection algorithm such as Local Outlier Factor (LOF), Isolation Forest or threshold-based method is selected to scan the filtered and noise-reduced full-view image for global outliers. The outliers with large differences from other pixel values in the image are identified, and their positions and characteristics are recorded for subsequent processing. The criteria for removing abnormal outliers, such as outlier degree threshold or limit on the number of outliers, are determined. According to the set criteria, the outliers are removed to generate an outlier-optimized full-view image, ensuring the integrity and effectiveness of the image after removal. The outlier-optimized full-view image is stored in a data structure for use in subsequent steps. A suitable image detail extraction algorithm such as edge detection (Canny, Sobel) or texture analysis (LBP, Gabor filtering) is selected to extract the key detail features of the outlier-optimized full-view image. The extracted detail features are stored in a data structure. A suitable magnification distortion analysis method such as Peak Signal-to-Noise Ratio (PSNR) or Structural Similarity (SSIM) is selected to evaluate the distortion degree when the details are magnified. The extracted image detail features are subjected to magnification distortion analysis to generate image magnification distortion data, which is recorded for subsequent smoothing processing. A suitable point cloud smoothing algorithm such as Gaussian smoothing, bilateral smoothing or MLS (Moving Least Squares) is selected to perform point cloud smoothing processing on the outlier-optimized full-view image based on the image magnification distortion data, resulting in a detail part smoothing image that ensures important details are not lost during smoothing. A suitable point cloud extraction method such as depth image-based point cloud reconstruction or three-dimensional reconstruction algorithm is selected to extract the original resolution point cloud from the detail part smoothing image, ensuring that the point cloud contains sufficient detail information. The extracted point cloud is stored in a suitable data structure. A suitable super-resolution reconstruction algorithm such as SRCNN, ESPCN or GAN (Generative Adversarial Network) is selected to perform super-resolution reconstruction on the detail part smoothing image based on the point cloud resolution convolution features, generating a super-resolution reconstructed image that ensures the details and clarity of the reconstructed image are improved. The generated super-resolution reconstructed image is stored in a suitable format and subjected to quality evaluation to ensure that it meets the design requirements.

[0128] In this embodiment, referring to Figure 3 The detailed implementation steps of step S2 include:

[0129] Step S21: physical characteristic parameter analysis is performed on the multi-scale parameters of the textile raw material to extract the physical characteristic parameters of the textile raw material;

[0130] Step S22: fiber mechanics performance calculation is performed on the physical characteristic parameters of the textile raw material to obtain fiber mechanics performance data of the textile raw material;

[0131] Step S23: inter-fiber friction coefficient calculation is performed on the physical characteristic parameters of the textile raw material to obtain inter-fiber friction parameters;

[0132] Step S24: fiber bundle mechanics performance analysis is performed on the physical characteristic parameters of the textile raw material to obtain fiber bundle mechanics performance data;

[0133] Step S25: deep parameter characteristic mining is performed on the fiber mechanics performance data, inter-fiber friction parameters and fiber bundle mechanics performance data of the textile raw material to obtain multi-scale state characteristics of the textile raw material.

[0134] In this embodiment, the multi-scale parameters of the textile raw material are collected, including fiber diameter, density, strength, elongation, etc. These data are sorted to ensure their integrity and accuracy for subsequent analysis to determine the physical characteristic parameters that need to be analyzed, such as the elastic modulus, tensile strength, and specific gravity of the fiber. The appropriate analysis method is selected, including statistical analysis, regression analysis, or multivariate analysis method. The selected method is used to analyze the multi-scale parameters of the textile raw material, and the physical characteristic parameters are extracted. The extracted physical characteristic parameters are recorded in the database or table for subsequent use. The key indicators of the fiber mechanical properties, such as tensile strength, shear modulus, and elastic modulus, are determined. The appropriate calculation formula and model are selected based on the theory of material mechanics (such as Hooke's law and stress-strain relationship). The fiber mechanical property data of the textile raw material are calculated based on the physical characteristic parameters and the selected formula. The calculation results are stored in the data structure to ensure their convenience for subsequent analysis. The calculation method of the inter-fiber friction coefficient is determined, which is usually based on experimental data or theoretical models. If necessary, experiments can be designed to measure the inter-fiber friction. The experimental data are collected, and the relevant formula (such as Coulomb's friction law) is used to calculate the friction coefficient of the textile raw material. The inter-fiber friction parameters are obtained. The mechanical properties of the fiber bundle, such as tensile strength, compressive strength, and stiffness, are determined. The appropriate analysis and calculation method is selected, such as finite element analysis (FEA) or macroscopic mechanics model. The mechanical properties of the fiber bundle are analyzed based on the physical characteristic parameters of the fiber and the selected method. The fiber bundle mechanical property data are generated. The fiber mechanical property data, inter-fiber friction parameters, and fiber bundle mechanical property data of the textile raw material are integrated into a unified data set. The appropriate deep feature mining method is selected, such as principal component analysis (PCA), factor analysis, or machine learning algorithm (such as random forest and support vector machine). The integrated data set is subjected to deep parameter feature mining to extract the multi-scale state features of the textile raw material. The mined features are recorded and visualized to ensure their convenience for understanding and analysis. The mined features are analyzed to verify their relevance and effectiveness to the actual textile performance. The results are sorted into a report or summary for subsequent application and research.

[0135] In this embodiment, reference is made to Figure 4 The detailed implementation steps of step S3 include:

[0136] Step S31: Perform external mechanical deformation response analysis on the multi-scale state features of the textile raw material to generate textile raw material external mechanical deformation response data.

[0137] Step S32: Perform internal fiber bundle dispersion analysis modeling based on the multi-scale parameters of the textile raw material to obtain the internal fiber dispersion particles of the textile raw material.

[0138] Step S33: Perform external load action simulation on the internal fiber discrete particles of the textile material to extract external load action simulation data of the fiber discrete particles;

[0139] Step S34: Perform force balance calculation on the fiber discrete particle interaction simulation data to extract force balance data of each fiber discrete particle;

[0140] Step S35: Perform internal fiber elastic response analysis based on the force balance data of each fiber discrete particle to obtain the internal fiber elastic response characteristics of the textile material.

[0141] In this embodiment, the multi-scale state characteristic data of the textile material is collected, including physical characteristics and mechanical property parameters, and a suitable mechanical model (such as an elastic model or a plastic model) is constructed to simulate the deformation response of the textile material under external force. A predefined external load (such as tension, compression, or shear) is applied to the model to simulate the mechanical response under actual use conditions. Finite element analysis (FEA) software (such as ANSYS or ABAQUS) is used to perform external mechanical deformation response analysis, and external mechanical deformation response data of the textile material is generated. The response data, including stress, strain, and deformation, are recorded. The multi-scale parameters of the textile material are integrated, with particular attention paid to parameters related to the internal structure, such as fiber diameter, arrangement, and relative position. A discrete analysis modeling method is selected, such as a discrete element method (DEM) or a particle system modeling. A modeling software (such as MATLAB or a specific DEM software) is used to construct a discrete model of the internal fiber bundle of the textile material, obtaining the internal fiber discrete particles of the textile material. The type and size of the external load applied to the fiber discrete particles are defined, such as uniform load or concentrated load. The external load is applied in the discrete model, and a numerical simulation method (such as finite element analysis or particle mechanics simulation) is used to perform external load action simulation. The external load action simulation data of the fiber discrete particles, including stress distribution and deformation within the particles, are extracted. A force balance calculation method is determined, typically based on Newtonian mechanics and statics principles. The force balance of each fiber discrete particle is calculated, taking into account the interaction forces with surrounding particles and the applied external load. The forces acting on each particle, including tension, pressure, and friction, are calculated. The force balance data of each fiber discrete particle are extracted and recorded in a data structure for subsequent analysis. A suitable elastic response model is selected, typically based on Hooke's law or other material behavior models. Based on the force balance data of each fiber discrete particle, internal fiber elastic response analysis is performed to calculate elastic deformation and stress response. The elastic response characteristics of each particle, including strain and stress distribution, are recorded. The obtained internal fiber elastic response characteristics of the textile material are organized into a report and stored in a database for subsequent research and application.

[0142] In this embodiment, the specific steps of step S31 are as follows:

[0143] Based on the multi-scale state characteristics of textile raw materials, multi-frequency pressure simulation is performed on the textile raw materials, and the pressure simulation response state parameters of the textile raw materials are extracted;

[0144] The fiber deformation feature recognition is performed on the textile raw material pressure simulation response state parameters, and the fiber deformation feature data is generated;

[0145] The stress-strain analysis is performed on the fiber deformation feature data, and the textile raw material stress-strain data is obtained;

[0146] The strain response change analysis is performed on the textile raw material stress-strain data, and the strain response change curve is obtained;

[0147] The external mechanical deformation response analysis is performed on the strain response change curve, and the textile raw material external mechanical deformation response data is generated.

[0148] In this embodiment, based on the multi-scale state characteristics of textile raw materials, a corresponding three-dimensional mechanical model is established, and a software such as ANSYS or ABAQUS is used to define the multi-frequency pressure conditions applied on the model, including different frequency, amplitude pressure waveforms (such as sine wave, pulse wave, etc.), these pressure conditions are applied in the model to simulate the pressure action in the real use environment, run the simulation, record the response of the textile raw material under the multi-frequency pressure, including stress, strain and displacement data, extract the pressure simulation response state parameters of the textile raw material, and store them in the database, preprocess the pressure response data obtained by simulation, remove noise and outliers, select suitable image processing or machine learning algorithms, such as edge detection, feature extraction algorithms (such as SIFT or SURF), identify fiber deformation features, apply the selected algorithm on the simulated deformation data, extract fiber deformation feature data such as deformation amount and deformation direction, record and organize the identified fiber deformation features, collect stress and strain data obtained by pressure simulation, ensure the integrity of the data, select a suitable stress-strain analysis method, usually based on the theory of materials mechanics, perform stress-strain analysis on the fiber deformation feature data, calculate the stress-strain curve, extract the corresponding data points, record the obtained textile raw material stress-strain data, including parameters such as elastic modulus and yield strength, integrate the stress-strain data, prepare for strain response change analysis, select a suitable analysis method, such as trend analysis or statistical regression analysis, analyze the change of strain under different pressure conditions, generate the strain response change curve, record the strain value and the corresponding pressure value of each point, based on the strain response change curve, prepare for external mechanical deformation response analysis, select to use finite element analysis or other numerical simulation methods, evaluate the external mechanical deformation response, run the analysis, generate the deformation response data of the textile raw material under the external mechanical action, including maximum strain, stress distribution and deformation mode, record and summarize the obtained external mechanical deformation response data to support subsequent application or research.

[0149] In this embodiment, step S4 includes the following steps:

[0150] Step S41: Multi-stage textile process analysis is performed on the textile process log to extract textile process data for each stage;

[0151] Step S42: Process timing logic analysis is performed on the textile process data for each stage to generate textile process timing logic;

[0152] Step S43: Process textile simulation is performed on the textile sweater based on the textile process timing logic to obtain a textile sweater simulation model;

[0153] Step S44: Dynamic textile deformation mapping is performed on the textile sweater simulation model based on the external mechanical deformation response data of the textile raw materials and the internal fiber elastic response characteristics of the textile raw materials to construct a digital twin model of the textile sweater.

[0154] In this embodiment, the textile process log is collected to ensure that the data includes operation records, timestamps, and related parameters for each stage. According to the timestamps and operation content in the process log, different textile process stages (such as spinning, weaving, dyeing, etc.) are identified, and the textile process data for each stage is extracted, including operation type, equipment used, material characteristics, and time, etc. The extracted data is organized into a structured format (such as a table or database) for subsequent analysis. The basic elements of the process timing logic are defined, including process sequence, parallel operation conditions, and dependency relationships. Suitable logic analysis tools and methods are selected, such as Petri nets, finite state machines, or flowchart tools. The extracted process data is converted into a timing logic model, and the relationship and sequence between different processes are analyzed using the selected method. The generated textile process timing logic is recorded and visualized for understanding and communication. Based on the textile process timing logic, the input parameters of the simulation model are defined, including process time, equipment characteristics, and material characteristics. Suitable simulation software (such as AnyLogic, Arena, or MATLAB) is selected to establish the process simulation model of the textile sweater. In the selected simulation software, the process simulation model of the textile sweater is constructed, the timing and logical relationship of the process are set, the simulation is run, and various dynamic changes in the textile process are observed. The simulation results are recorded, and the external mechanical deformation response data and internal fiber elastic response characteristics of the textile raw materials are collected to ensure data completeness. The dynamic textile deformation mapping model is defined to determine how to map external and internal response data to the simulation model of the textile sweater. Using the simulation model combined with response data, dynamic textile deformation mapping is performed to generate deformation characteristics of the textile sweater under different mechanical conditions. The constructed digital twin model of the textile sweater is recorded to ensure that it can reflect the dynamic changes in actual production. The generated digital twin model is verified to ensure that it is consistent with the actual process. According to the verification results, the model parameters and mapping relationships are adjusted to improve the accuracy and reliability of the model.

[0155] In this embodiment, the specific steps of step S5 are:

[0156] Step S51: Perform a preset dyeing demand analysis on the textile process log to extract preset process dyeing demand data;

[0157] Step S52: Perform dye parameter calculation on the preset process dyeing demand data to extract dye characteristic parameters;

[0158] Step S53: Perform dye penetration interaction mining on the dye characteristic parameters based on the multi-scale state characteristics of the textile raw materials to generate textile raw material dye penetration interaction data;

[0159] Step S54: Perform dye diffusion evolution analysis on the textile raw material dye penetration interaction data to generate dynamic dye diffusion evolution data;

[0160] Step S55: Dynamic color rendering of the textile sweater digital twin model according to the dynamic dye diffusion evolution data, constructing a dynamic rendering digital twin model.

[0161] In this embodiment, records related to dyeing in the textile process log are collected, including dyeing time, temperature, dye type and other process parameters. According to the process log, the preset dyeing requirements such as the required color, dyeing depth and uniformity requirements are identified, the data related to the preset dyeing requirement is extracted, and the structured format (such as table or database) is arranged to ensure the accuracy and traceability of the data. The key characteristic parameters of the dye are determined, such as solubility, molecular weight, pH adaptability, and durability. The appropriate calculation method is selected, such as statistical analysis based on experimental data or theoretical model, and the dye parameter calculation is performed on the preset process dyeing requirement data. The dye characteristic parameters are extracted, and the calculation results are recorded to ensure their subsequent use. The multi-scale state characteristic data of the textile raw material, including fiber structure and physical properties, are integrated, and the interaction model between the dye and the textile raw material is constructed. The processes of penetration, adsorption and diffusion are considered, and the numerical simulation method (such as finite element analysis or molecular dynamics simulation) is used to interactively mine the dye characteristic parameters and multi-scale state characteristics. The dye penetration interaction data is generated, and the generated data is recorded and arranged for subsequent analysis. The appropriate dye diffusion model is selected, such as Fick's diffusion law or other related dynamic models, and the dye diffusion evolution analysis is performed on the dye penetration interaction data. The diffusion process of the dye under different conditions is simulated, and the dynamic dye diffusion evolution data is generated. The diffusion rate, concentration change and uniformity information are recorded, and the rationality of the analysis results is verified. The analysis results are compared with the actual dyeing experimental data. If inconsistencies are found, the model parameters are adjusted to ensure that the existing textile sweater digital twin model has the necessary geometric and physical properties. The appropriate dynamic color rendering algorithm is selected, including physically based rendering (PBR) or real-time rendering technology. According to the dynamic dye diffusion evolution data, the dynamic color rendering of the textile sweater digital twin model is performed, the distribution and change of the dye on the fiber are simulated, and the visual rendering result with dynamic effect is generated, which can reflect the real-time changes in the dyeing process. The rendering result is evaluated to ensure its consistency with the actual dyeing effect. If necessary, the rendering parameters are adjusted to improve the accuracy.

[0162] In this embodiment, the specific steps of step S6 are:

[0163] Step S61: Dynamic try-on simulation of the user three-dimensional shape model based on the dynamic rendering digital twin model, thereby obtaining a textile sweater-user shape simulation model;

[0164] Step S62: Fitting analysis of the textile sweater-user shape simulation model, and extracting sweater fitting data;

[0165] Step S63: Calculate the tightness of the textile sweater-user shape simulation model to generate the user sweater tightness;

[0166] Step S64: Perform personalized user fitting feature analysis on the sweater fit data and the user sweater tightness to extract personalized user fitting feature parameters;

[0167] Step S65: Perform intelligent sweater parameter optimization on the personalized user fitting feature parameters to obtain personalized sweater optimization parameters;

[0168] Step S66: Perform personalized process simulation optimization on the textile sweater-user shape simulation model according to the personalized sweater optimization parameters to construct an intelligent parameter optimized sweater model.

[0169] In this embodiment, the existing dynamic rendering digital twin model and the user's three-dimensional form model (such as user body data obtained through 3D scanning) are ensured, a 3D modeling and animation software (such as Blender, Maya or Unity) is used to build a virtual fitting environment, the digital twin model of the textile sweater is combined with the user's form model, a dynamic virtual fitting simulation is run, the performance of the sweater on the user's three-dimensional form is observed, the areas of the sweater in contact with the user's body during the simulation are recorded, a textile sweater-user form simulation model is obtained, the simulation results are saved for subsequent analysis, key parameters for fit analysis are determined, such as contact area, gap, pressure distribution, etc., suitable analysis tools and methods are selected, such as finite element analysis (FEA) or contact analysis software, the textile sweater-user form simulation model is subjected to fit analysis, the fit data of the sweater is extracted, the contact situation, pressure distribution and potential friction problems are recorded, key indicators of tightness are determined, such as elastic coefficient, deformation amount and applied external force, etc., suitable calculation methods are selected, based on material mechanics or statistical analysis, the tightness of the user's sweater is calculated based on the geometric and mechanical data of the textile sweater-user form simulation model, the calculation results are recorded, the sweater fit data and user tightness results are integrated to form a comprehensive data set, suitable feature extraction methods are selected, such as principal component analysis (PCA) or cluster analysis, the integrated data is subjected to personalized user fitting feature analysis, personalized user fitting feature parameters are extracted, such as optimal fit degree, tightness preference, smart sweater parameters that need to be optimized are determined, such as size, shape, material selection, etc., suitable optimization algorithms are selected, such as genetic algorithm, particle swarm optimization or other machine learning methods, based on the personalized user fitting feature parameters, the optimization algorithm is run to intelligently optimize the sweater parameters, personalized sweater optimization parameters are generated, the personalized sweater optimization parameters are used to update the textile sweater-user form simulation model, suitable process simulation software (such as AnyLogic, MATLAB or other industrial simulation tools) is selected, personalized process simulation optimization is run, the performance changes of the sweater and the improvement of the user's fit under the new parameters are observed, the simulation results are recorded, the smart parameter optimized sweater model is constructed to ensure that it meets the user's personalized needs, the consistency of the optimized model with the actual user fitting experience is verified, if inconsistencies are found, adjustments and optimizations are made to ensure that the final model is highly adaptable and comfortable.

[0170] In this embodiment, a model simulation system for digital textile sweaters is provided for performing the model simulation method of the digital textile sweater as described above, comprising:

[0171] A three-dimensional form module is configured to obtain all-around images of a user to be designed, multi-scale parameters of textile raw materials, and a textile process log; analyze the geometric form parameters of the all-around images of the user to be designed, and perform three-dimensional geometric point cloud modeling to construct a three-dimensional form model of the user.

[0172] A multi-scale state module is configured to analyze physical characteristic parameters of multi-scale parameters of the textile raw material and perform deep parameter feature mining, so as to obtain multi-scale state features of the textile raw material;

[0173] A mechanical deformation module is configured to perform external mechanical deformation response analysis and internal fiber elastic response analysis based on the multi-scale state features of the textile raw material, so as to generate external mechanical deformation response data of the textile raw material and internal fiber elastic response features of the textile raw material;

[0174] A textile deformation module is configured to perform dynamic textile deformation mapping on a textile process log according to the external mechanical deformation response data of the textile raw material and the internal fiber elastic response features of the textile raw material, so as to construct a digital twin model of the textile sweater.

[0175] A dynamic color rendering module is configured to perform dye penetration interaction mining on the digital twin model of the textile sweater, and then perform dynamic color rendering, so as to construct a dynamic rendering digital twin model.

[0176] A dynamic try-on simulation module is configured to perform dynamic try-on simulation on a user three-dimensional shape model based on the dynamic rendering digital twin model, and perform intelligent sweater parameter optimization, so as to construct an intelligent parameter optimized sweater model.

[0177] The present application constructs a user three-dimensional shape model through geometric shape parameter analysis and three-dimensional geometric point cloud modeling of the user's full image, which helps better understand the user's body features and shape, and provides a basis for subsequent design and simulation. Through physical characteristic parameter analysis and deep parameter feature mining of the multi-scale parameters of the textile raw material, the multi-scale state features of the textile raw material are obtained, which helps to better understand the characteristics and state of the textile raw material and provides more accurate data support in the design and production process. Based on the multi-scale state features of the textile raw material, external mechanical deformation response analysis and internal fiber elastic response analysis are performed, and deformation and elastic response data of the textile raw material are generated, which helps to understand the deformation of the textile material under external mechanical action and provides a basis for subsequent simulation and optimization. According to the external deformation response data and internal fiber elastic response features of the textile raw material, dynamic textile deformation mapping is performed on the textile process log, and a digital twin model of the textile sweater is constructed, which makes it possible to more accurately simulate the performance of the textile under different deformation conditions and provides a reference for the design and production process. Through dye penetration interaction mining and dynamic color rendering, a dynamic rendering digital twin model is constructed, which enables the design team to better preview and adjust the color effect of the sweater and more intuitively understand the appearance of the sweater, improving design efficiency and product quality. Through try-on simulation and intelligent parameter optimization of the user three-dimensional shape model based on the dynamic rendering digital twin model, an intelligent parameter optimized sweater model is constructed, which helps personalized design and production, improves the fit and comfort of the sweater, and enhances user experience and product competitiveness.

[0178] Thus, the embodiments should be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the description given above, and all changes which come within the meaning and range of equivalency of the claims are intended to be embraced therein.

[0179] The foregoing merely illustrates the principles of the application and applies only to the particular cases described and illustrated herein. Numerous modifications in the embodiments described herein will be readily apparent to those skilled in the art, and the principles defined herein can be applied to other embodiments without departing from the spirit or scope of the underlying inventive concept. Accordingly, the disclosure is not intended to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the claims, the principles and the novel features disclosed herein.

Claims

1. A method of model simulation of a digital textile sweater, characterized in that, The method comprises the following steps: Step S1: obtaining a user's all-around image to be designed, textile raw material multi-scale parameters and a textile process log; analyzing geometric shape parameters of the user's all-around image to be designed, and performing three-dimensional geometric point cloud modeling to construct a user's three-dimensional shape model; Step S2: performing physical characteristic parameter analysis on the textile raw material multi-scale parameters, and performing deep parameter feature mining to obtain textile raw material multi-scale state features; Step S3: performing external mechanical deformation response analysis and internal fiber elastic response analysis based on the textile raw material multi-scale state features to generate textile raw material external mechanical deformation response data and textile raw material internal fiber elastic response features; Step S4: performing dynamic textile deformation mapping on the textile process log according to the textile raw material external mechanical deformation response data and the textile raw material internal fiber elastic response features to construct a textile sweater digital twin model; Step S5: performing dye penetration interactive mining on the textile sweater digital twin model, and then performing dynamic color rendering to construct a dynamic rendering digital twin model; the dye penetration interactive mining specifically comprises: simulating a dye penetration process in the textile sweater, and recording a penetration depth, a diffusion speed and a concentration change of the dye in the fiber; Step S6: performing dynamic try-on simulation on the user's three-dimensional shape model based on the dynamic rendering digital twin model, and performing intelligent sweater parameter optimization to construct an intelligent parameter optimized sweater model.

2. The digital textile sweater modeling method of claim 1, wherein, Step S1 specifically comprises the following steps: Step S11: obtaining a user's all-around image to be designed, textile raw material multi-scale parameters and a textile process log; Step S12: performing image detail reconstruction on the user's all-around image to be designed to construct a super-resolution reconstructed image; Step S13: performing deep visual semantic segmentation on the super-resolution reconstructed image to identify user body part information; Step S14: performing user part key point identification on the user body part information to mark body part key points; Step S15: performing user skeleton structure analysis based on the body part key points to generate user skeleton structure features; Step S16: performing geometric shape parameter analysis on the user skeleton structure features to generate user geometric shape parameters; performing three-dimensional geometric point cloud modeling on the user geometric shape parameters to construct a user's three-dimensional shape model.

3. The method of modeling a digital textile sweater according to claim 2, wherein, Step S12 specifically comprises the following steps: performing image-by-image filtering and noise reduction processing on the user's all-around image to be designed to obtain a filtered and denoised all-around image; performing image global outlier scanning on the filtered and denoised all-around image to extract image outliers; performing abnormal outlier elimination processing on the image outliers to obtain an outlier-optimized all-around image; performing image detail identification on the outlier-optimized all-around image to extract image detail features; performing magnification distortion analysis on the image detail features to obtain image magnification distortion data; performing point cloud smoothing on the outlier-optimized all-around image based on the image magnification distortion data to obtain a detail part smoothed image; performing original resolution point cloud extraction on the detail part smoothed image to obtain an original image point cloud resolution; performing deep convolution learning according to the original image point cloud resolution to obtain a point cloud resolution convolution feature; The point cloud resolution convolution feature is used for super-resolution reconstruction of the smooth image of the detail part, and a super-resolution reconstructed image is constructed.

4. The digital textile sweater modeling method of claim 1, wherein, The specific steps of step S2 are as follows: Step S21: physical characteristic parameter analysis is performed on the multi-scale parameters of the textile raw material, and the physical characteristic parameters of the textile raw material are extracted; Step S22: fiber mechanics performance calculation is performed on the physical characteristic parameters of the textile raw material, so as to obtain the fiber mechanics performance data of the textile raw material; Step S23: inter-fiber friction coefficient calculation is performed on the physical characteristic parameters of the textile raw material, so as to obtain the inter-fiber friction parameters; Step S24: fiber bundle mechanics characteristic analysis is performed on the physical characteristic parameters of the textile raw material, so as to obtain the fiber bundle mechanics characteristic data; Step S25: deep parameter feature mining is performed on the fiber mechanics performance data, inter-fiber friction parameters and fiber bundle mechanics characteristic data of the textile raw material, so as to obtain the multi-scale state characteristics of the textile raw material.

5. The digital textile sweater modeling method of claim 1, wherein, The specific steps of step S3 are as follows: Step S31: external mechanics deformation response analysis is performed on the multi-scale state characteristics of the textile raw material, so as to generate the external mechanics deformation response data of the textile raw material; Step S32: internal fiber bundle discrete analysis modeling is performed based on the multi-scale parameters of the textile raw material, so as to obtain the internal fiber discrete particles of the textile raw material; Step S33: external load action simulation is performed on the internal fiber discrete particles of the textile raw material, so as to extract the external load action simulation data of the fiber discrete particles; Step S34: force balance calculation is performed on the interaction simulation data of the fiber discrete particles one by one, so as to extract the force balance data of each fiber discrete particle; Step S35: internal fiber elastic response analysis is performed based on the force balance data of each fiber discrete particle, so as to obtain the internal fiber elastic response characteristics of the textile raw material.

6. The method of modeling a digital textile sweater according to claim 5, wherein, The specific steps of step S31 are as follows: Multi-frequency pressure simulation is performed on the textile raw material based on the multi-scale state characteristics of the textile raw material, so as to extract the textile raw material pressure simulation response state parameters; Fiber deformation feature recognition is performed on the textile raw material pressure simulation response state parameters, so as to generate fiber deformation feature data; Stress-strain analysis is performed on the fiber deformation feature data, so as to obtain the stress-strain data of the textile raw material; Strain response change analysis is performed on the stress-strain data of the textile raw material, so as to obtain the strain response change curve; External mechanics deformation response analysis is performed on the strain response change curve, so as to generate the external mechanics deformation response data of the textile raw material.

7. The digital textile sweater modeling method of claim 1, wherein, The specific steps of step S4 are as follows: Step S41: multi-stage textile process analysis is performed on the textile process log, so as to extract the textile process data of each stage; Step S42: process timing logic analysis is performed on the textile process data of each stage, so as to generate the textile process timing logic; Step S43: process textile simulation is performed on the textile sweater based on the textile process timing logic, so as to obtain the textile sweater simulation model; Step S44: dynamic textile deformation mapping is performed on the textile sweater simulation model based on the external mechanics deformation response data of the textile raw material and the internal fiber elastic response characteristics of the textile raw material, so as to construct the digital twin model of the textile sweater.

8. The digital textile sweater modeling method of claim 1, wherein, The specific steps of step S5 are as follows: Step S51: preset dyeing requirement analysis is performed on the textile process log, so as to extract the preset process dyeing requirement data; Step S52: dye parameter calculation is performed on the preset process dyeing requirement data, and dye characteristic parameters are extracted; Step S53: dye penetration interaction data of the textile raw material is generated by dye penetration interaction mining of the dye characteristic parameters based on the multi-scale state characteristics of the textile raw material; Step S54: dynamic dye diffusion evolution data is generated by dye diffusion evolution analysis on the textile raw material dye penetration interaction data; Step S55: dynamic color rendering is performed on the textile sweater digital twin model according to the dynamic dye diffusion evolution data, and a dynamic rendering digital twin model is constructed.

9. The digital textile sweater modeling method of claim 1, wherein, The specific steps of step S6 are: Step S61: dynamic fitting simulation is performed on the user three-dimensional shape model based on the dynamic rendering digital twin model, so as to obtain a textile sweater-user shape simulation model; Step S62: fit data of the sweater is extracted by fit analysis on the textile sweater-user shape simulation model; Step S63: user sweater tightness is generated by tightness calculation on the textile sweater-user shape simulation model; Step S64: personalized user fitting feature parameters are extracted by personalized user fitting feature analysis on the sweater fit data and user sweater tightness; Step S65: intelligent sweater parameter optimization is performed on the personalized user fitting feature parameters, so as to obtain personalized sweater optimization parameters; Step S66: personalized process simulation optimization is performed on the textile sweater-user shape simulation model according to the personalized sweater optimization parameters, and an intelligent parameter optimized sweater model is constructed.

10. A system for model simulation of a digital textile sweater, characterized by, A model simulation method for a digital textile sweater as claimed in claim 1, comprising: a three-dimensional shape module for acquiring a user all-around image to be designed, multi-scale parameters of a textile raw material, and a textile process log; performing geometric shape parameter analysis on the user all-around image to be designed, and performing three-dimensional geometric point cloud modeling to construct a user three-dimensional shape model; a multi-scale state module for performing physical characteristic parameter analysis on the multi-scale parameters of the textile raw material, and performing deep parameter feature mining, so as to obtain multi-scale state characteristics of the textile raw material; a mechanical deformation module for performing external mechanical deformation response analysis and internal fiber elastic response analysis based on the multi-scale state characteristics of the textile raw material, so as to generate external mechanical deformation response data of the textile raw material and internal fiber elastic response characteristics of the textile raw material; a textile deformation module for performing dynamic textile deformation mapping on the textile process log according to the external mechanical deformation response data of the textile raw material and the internal fiber elastic response characteristics of the textile raw material, and constructing a textile sweater digital twin model; a dynamic color rendering module for performing dye penetration interaction mining on the textile sweater digital twin model, and then performing dynamic color rendering to construct a dynamic rendering digital twin model; a dynamic fitting simulation module for performing dynamic fitting simulation on a user three-dimensional shape model based on the dynamic rendering digital twin model, and performing intelligent sweater parameter optimization to construct an intelligent parameter optimized sweater model.

Images