Method, system, device and medium for representing instant deformation state of sewing material based on material performance parameters

Abstract

The application discloses a method, system, device and medium for representing the instantaneous deformation state of sewing materials based on material performance parameters, and belongs to the technical field of unmanned autonomous sewing. The method comprises the following steps: obtaining original data of fabric materials, forming a material parameter vector dataset through segmented fitting and feature extraction; constructing a unified coordinate system according to the material parameter vector dataset and a stitch cycle, and obtaining an equivalent model of the sewing process; solving the equivalent model of the sewing process according to a single needle cycle time sequence, and calculating corresponding sewing coefficients; obtaining sewing parameters, calibrating and correcting the sewing parameters based on the sewing coefficients, comparing the calibrated and corrected sewing parameters, and obtaining a parameter adjustment direction. The application realizes accurate simulation and quantitative evaluation of the instantaneous deformation state of fabrics in the sewing process from material constitutive to mechanism coupling constraint to quality indicators, and solves the problem that traditional experience trial-and-error methods cannot objectively predict and systematically optimize the sewing quality.

Description

Technical Field

[0001] This invention relates to the field of unmanned autonomous sewing technology, specifically to a method, system, device, and medium for characterizing the instantaneous deformation state of sewing fabric based on fabric performance parameters. Background Technology

[0002] With the development of automation, digitalization, and intelligent technologies, the flexible material sewing industry, represented by the garment industry, urgently needs technologies to achieve unmanned autonomous sewing. Real-time identification, sensing, monitoring, and control of sewing quality is a crucial but currently lacking technological gap in the sewing industry. This technology requires real-time sensing and prediction of the fabric's state under the action of the sewing equipment's ring-forming mechanism, combined with electronic control and mechanical adjustment technologies, to achieve "real-time prediction of fabric deformation, real-time adjustment of equipment parameters by electronic control, and early correction of deviations to avoid sewing defects." Since textile fabrics and threads are typical flexible materials, and the morphology prediction and control technology for flexible materials is a global challenge in automation and control, image recognition and prediction, and material morphology perception and characterization theory research, it lacks sufficiently effective theoretical models, testing, and characterization methods.

[0003] Existing technology proposes a method for detecting anomalies in sewing stitches. A sample of completed overlock stitches is placed within a designated area on a sewing workbench. An image acquisition device then captures an image of the overlock stitch sample, obtaining a stitch sample image. The region of interest containing the overlock stitches is located and cropped from this image as the image to be detected. Finally, the image to be detected is input into a pre-trained unsupervised anomaly detection model to calculate the degree of anomaly relative to a normal stitch image, thereby determining the type and value of the anomaly.

[0004] Currently, the technologies for monitoring and evaluating sewing stitches, whether manual or computer vision, are only at the stage of hindsight; once a defect is discovered, it is already a fait accompli, and the only option is to remove the stitches and resew them. They do not play a substantial role in preventing sewing defects in advance.

[0005] In summary, there is currently a lack of technology for identifying, sensing, monitoring, and controlling the instantaneous deformation state of sewing fabric during the sewing process. The underlying mechanism and reason is the lack of a theory, method, or model for characterizing the instantaneous stress state of sewing fabric under the combined action of the sewing mechanism. At the same time, there is a lack of a closed-loop technical route that combines fabric mechanical parameter data, finite element simulation, and anomaly prediction. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the present invention aims to solve the technical problem that it is difficult to quantitatively characterize and predict the instantaneous deformation state of fabrics during the sewing process.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, comprising, The process involves acquiring raw fabric data and forming a material parameter vector dataset through piecewise fitting and feature extraction. A unified coordinate system is then constructed based on the stitch cycle according to this material parameter vector dataset to obtain an equivalent sewing process model. This model is then solved according to the single-needle cycle sequence to calculate the corresponding sewing coefficients. Sewing parameters are then acquired, and these parameters are calibrated and corrected based on the sewing coefficients. After calibration and correction, the sewing parameters are compared to determine the optimal adjustment direction.

[0009] As a preferred embodiment of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters according to the present invention, wherein: the process of forming a material parameter vector dataset through piecewise fitting and feature extraction includes: The original data of the initial fabric were obtained by conducting warp and weft tensile and compression recovery tests on the fabric material. The stiffness and friction coefficient of the fabric material are tested to obtain the fabric stiffness and the fabric friction coefficient. The original data undergoes a first preprocessing step through logical judgment, followed by a second preprocessing step using a moving average filter. Divide the data into segments, perform segmented fitting, perform local linear fitting for each segment and judge the fitting effect, and extract the features of the fitted data. A material parameter vector dataset is formed based on the fitted data features, the fabric stiffness, and the fabric friction coefficient.

[0010] As a preferred embodiment of the method for characterizing the instantaneous deformation state of sewing fabric based on fabric performance parameters according to the present invention, wherein obtaining an equivalent model of the sewing process includes: By setting the fabric as an orthogonal anisotropic nonlinear material and establishing a unified coordinate system, a stitch cycle is divided into different analysis stages. For each of the different analysis stages, different fabric material points are selected as tracking points, and the actual displacement component of each tracking point along the feeding direction is calculated within one stitch cycle. The actual displacement components of all tracking points are averaged to obtain the actual displacement corresponding to the difference between the theoretical feed amount and the actual feed amount.

[0011] As a preferred embodiment of the method for characterizing the instantaneous deformation state of sewing fabric based on fabric performance parameters according to the present invention, the method for obtaining an equivalent model of the sewing process further includes: The interaction between the needle and the stitch is equivalent to the constraint points generated stitch by stitch along the sewing path. The first cycle of feeding is performed, and the displacement field of the fabric at the end of the first cycle of feeding is solved. The fabric material point directly below the needle axis in the displacement field is located to obtain the stitch point, and the constraint corresponding to the stitch point is activated. Define a reference point position, couple the reference point to the fabric, lock the current point displacement at the moment of needle insertion, release the constraint after needle insertion, retain the coupling relationship, and perform the next cycle of feeding, and repeat the generation of stitch points and corresponding constraints in sequence.

[0012] As a preferred embodiment of the method for characterizing the instantaneous deformation state of sewing fabric based on fabric performance parameters according to the present invention, wherein: the step of solving the equivalent model of the sewing process according to the single-needle cycle sequence includes: The material parameter vector is input into the virtual simulation software for the different analysis stages, and the needle point coordinates are output. Import the stitch point coordinates into virtual simulation software to obtain the sewing coefficient; The sewing coefficient includes the wrinkle amplitude value. The height value of the fitted plane is obtained by fitting a local reference plane of the fabric using the least squares method. The normal undulation relative to the reference plane is calculated using the height value of the fitted plane.

[0013] As a preferred embodiment of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters according to the present invention, the seam coefficient further includes seam edge offset. The initial principal direction of the seam edge is extracted and a normal vector is constructed based on singular value decomposition. For each actual stitch point, select a fabric edge node, fit a local fabric edge straight line, and calculate the vertical distance from the current stitch point to the local fabric edge fitted line. Set the target seam allowance, calculate the seam offset of the current needle, and calculate the average seam offset for the stitch point. Based on the coordinates of the initial main direction projection stitch points of the seam edge, the projection distance between adjacent points is calculated as the actual stitch distance.

[0014] As a preferred embodiment of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters according to the present invention, the calibration correction includes: The fitting data features are combined with the sewing parameters for calibration, and all parameters are jointly corrected and verified using the coefficient of determination. After calibration, a comparative analysis is performed, which includes a comparison of multiple sewing parameters. An orthogonal experiment is used, and the average value of each parameter and the difference between the maximum and minimum values ​​are calculated through range analysis.

[0015] This invention provides a characterization system for the instantaneous deformation state of sewing fabric based on fabric performance parameters.

[0016] As a preferred embodiment of the characterization system for the instantaneous deformation state of seam fabric based on fabric performance parameters according to the present invention, it includes: a data acquisition module, an equivalent module, a solution module, and a calibration module. The data acquisition module acquires the original data of the fabric material and forms a material parameter vector dataset through segmented fitting and feature extraction. The equivalent module constructs a unified coordinate system based on the stitch period according to the material parameter vector dataset to obtain an equivalent model of the sewing process. The solution module solves the equivalent model of the sewing process according to the single-needle cycle sequence and calculates the corresponding sewing coefficient; The calibration module acquires sewing parameters, calibrates and corrects the sewing parameters based on the sewing coefficient, and then compares the best sewing parameters to determine the direction of parameter adjustment.

[0017] The present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters.

[0018] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters are implemented.

[0019] The beneficial effects of this invention are: This invention can predict and judge before sewing defects are formed, thereby realizing advance prediction and prevention, which will change the current passive work situation of post-event inspection and retrospective rectification. It is a fundamental innovation of intelligent autonomous sewing robots and related technologies.

[0020] This invention combines sewing material performance parameters with virtual simulation technology to achieve a visual representation of the formation mechanism of sewing defects, providing a quantifiable, characterizable, and controllable theoretical model for the development and performance improvement of sewing equipment and the development of digital intelligent management and control systems.

[0021] This invention can simultaneously characterize the theoretical feed displacement, actual deformation rebound, and comprehensive force direction of the sewing material within a single needle cycle. Based on this, it can quantitatively identify and predict the trends of typical sewing defects such as wrinkles, uneven stitches, and narrow stitch width. This provides a basis for real-time optimization of sewing parameters, screening of process windows, and closed-loop adjustment, thereby improving the stability, consistency, and finished product qualification rate of the sewing process.

[0022] This invention establishes a correspondence between experimental data of fabric materials, sewing mechanism models and virtual simulation results, forming a generalized characterization framework applicable to different fabric materials, different sewing mechanisms and different process conditions. This provides a quantifiable, characterizable and reusable theoretical basis and technical support for the development of intelligent sewing of flexible materials and digital process control. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 The overall flowchart of a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, provided in an embodiment of the present invention.

[0025] Figure 2 The image shows the result of data processing using MATLAB software for a method to characterize the instantaneous deformation state of seam fabric based on fabric performance parameters, as provided in an embodiment of the present invention.

[0026] Figure 3 This is a diagram illustrating the fit between the sewing material and the sewing mechanism in a method for characterizing the instantaneous deformation state of sewing material based on fabric performance parameters, as provided in an embodiment of the present invention.

[0027] Figure 4 This is a meshed model diagram of a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, provided in an embodiment of the present invention.

[0028] Figure 3 and Figure 4 The labels in the attached diagram are: 1. Needle; 2. Presser foot; 3. Fabric; 4. Needle plate. Detailed Implementation

[0029] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0030] Example 1, referring to Figure 1 This is one embodiment of the present invention, which provides a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, including: S1. Obtain the original data of the fabric material, and form a material parameter vector dataset through segmented fitting and feature extraction.

[0031] S2. Based on the material parameter vector dataset, construct a unified coordinate system according to the stitch period to obtain an equivalent model of the sewing process.

[0032] S3. Solve the equivalent model of the sewing process according to the single-needle cycle sequence, and calculate the corresponding sewing coefficient.

[0033] S4. Obtain sewing parameters, calibrate and correct the sewing parameters based on the sewing coefficient, and then compare the best sewing parameters to obtain the direction of parameter adjustment.

[0034] It should be noted that, taking the formation of three typical sewing defects (sewing shrinkage, uneven stitches, and uneven stitch width) in flat stitches as examples, this illustrates the relationship between fabric properties, sewing equipment parameters, and defect manifestations. Among them, sewing shrinkage (tight thread) is essentially due to the mismatch between the supply of sewing thread (top thread, bottom thread) and the deformation of the sewing material within the stitch range. The amount of rebound of the sewing material after the stitch is formed and the tension and pressure are unloaded exceeds the maximum volume of space that the sewing loop can provide. Therefore, if we can detect the two key variables in a timely manner—the amount of thread supplied and the amount of fabric rebound—we can predict the mismatch between the two, thus having the data to adjust the parameters in advance and eliminate the defect.

[0035] Furthermore, uneven stitches manifest as inconsistencies in the actual length of adjacent stitches. That is, even with a fixed stitch length set on the sewing machine, the stitches on the fabric surface after sewing exhibit varying lengths and densities. Essentially, this is because the theoretical feed amount provided by the feed mechanism within a single needle cycle is inconsistent with the actual displacement of the fabric under the pressure of the presser foot, the push force of the feed dog, the thread tension, and the material's own stretching and rebound. Especially when the sewing force and friction of the presser foot and feed dog on the fabric fluctuate, the fabric may slip, lag, stretch locally, or retract, causing the actual distance between the two needle insertion points to deviate from the set stitch length. Therefore, if we can promptly perceive two key variables: the theoretical feeding displacement of the fabric feeding mechanism and the actual effective displacement of the sewing fabric between two adjacent needle drops, we can predict the deviation and trend of change between the two, thus having the data to adjust parameters in advance and eliminate the defect.

[0036] Furthermore, defects in stitch width manifest as inconsistencies between the stitch width and the seam allowance. Essentially, this is due to a directional deviation in the thrust exerted on the fabric by the presser foot and feed mechanism. Therefore, if the direction of the combined feed force can be detected in time, it's possible to predict whether the force direction aligns with the previous stitch's feed direction, thus providing an immediate signal as to whether seam correction (correcting the feed direction) is necessary.

[0037] Example 2, refer to Figure 1 This is one embodiment of the present invention, which provides a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, including: In this embodiment of the invention, step S1 involves acquiring the original data of the fabric material and forming a material parameter vector dataset through piecewise fitting and feature extraction, including the following steps S11-S12: S11. Perform warp and weft tensile and compression recovery tests on the fabric material to obtain the initial raw data of the fabric; perform stiffness tests and friction coefficient measurements on the fabric material to obtain the fabric stiffness and fabric friction coefficient; perform a first preprocessing on the raw data through logical judgment, and perform a second preprocessing using moving average filtering, specifically: The fabric material is subjected to warp / weft tensile and compression recovery tests using a universal testing machine to obtain the initial stress-strain data and pressure-deformation data of the fabric as raw data. The stiffness of the fabric was tested by a stiffness tester and the friction coefficient of the fabric was measured by an instrument. The initial stress-strain data and pressure-deformation data of the fabric were imported into the engineering simulation finite element software. The original data was preprocessed in the engineering simulation finite element software by logical judgment, including outlier removal, removal of null values ​​and negative values. The second preprocessing step involves smoothing using a moving average filter, i.e., smoothing the first... There are points, and the window length is [value]. The neighborhood window, the window with the first Centered on the point: in, For the first The tensile force value after point moving average filtering; The length of the window; For the first in the window range One original (or truncated) tensile force sample value; The width is half the window width, rounded down; j is only a variable index and belongs to natural numbers.

[0038] S12. Divide the data into segments, perform segmented fitting, perform local linear fitting for each segment and judge the fitting effect, and extract the data features after fitting; based on the fitted data features, the fabric stiffness and the fabric friction coefficient, form a material parameter vector dataset, specifically: Divide the data into segments with 5% of the data volume, and perform local linear fitting on the initial modulus segment for each segment. The coefficient of determination (COD) and RMSE (root mean square error) are used to judge the fitting effect. The features of the fitted data are extracted, including elastic modulus, shear modulus, and Poisson's ratio, forming a material parameter vector dataset. It should be noted that, based on the stress-strain data, stress-strain curves are obtained through uniaxial tensile tests, and the initial slope is fitted to the elastic modulus and the transverse / longitudinal strain ratio is Poisson's ratio; shear stress-strain curves are obtained through shear tests (such as off-axis tension or frame shear), and the shear modulus is fitted. In summary, the material parameter vector dataset includes warp elastic parameters, weft elastic parameters, thickness compression parameters, bending stiffness, and fabric friction coefficient.

[0039] In this embodiment of the invention, step S2 involves constructing a unified coordinate system based on the stitch period according to the material parameter vector dataset to obtain an equivalent model of the sewing process, including the following steps S21-S23: S21. Set the fabric as an orthogonal anisotropic nonlinear material, establish a unified coordinate system, and divide one stitch cycle into different analysis stages, specifically: By setting the fabric as an orthogonal anisotropic nonlinear material and establishing a unified coordinate system, a stitch cycle is divided into several analysis stages. The action of the presser foot is equivalent to normal pressure; The feeding action is equivalent to a periodic feeding displacement. A theoretical displacement is applied to the feed dog, which simplifies the actual movement of the feed dog to the fabric's movement within the feed area. The periodic displacement in the direction is measured according to the actual feeding cycle.

[0040] S22. For each of the different analysis stages, different fabric material points are selected as tracking points. The actual displacement component along the feeding direction of each tracking point within one stitch cycle is calculated. The average of the actual displacement components of all tracking points is taken to obtain the actual displacement corresponding to the difference between the theoretical feeding amount and the actual feeding amount. Specifically: The feed dog interacts with the fabric through contact friction. The actual displacement of the fabric is calculated using finite element method (FEA) software to obtain the difference between the theoretical feed rate and the actual feed rate, i.e., the actual displacement. for: in, , ; in, The unit vector for the feeding direction; For the first The tracking point at the 1st The actual displacement component along the feeding direction within each cycle; For the first The tracking point at the 1st The actual coordinates of the pointer at that moment; The representative is to select in front of the needle. Each fabric material point is used as a tracking point; For the first The tracking point at the 1st The actual coordinates of the pointer at that moment; Let be the total displacement vector of the j-th tracking point from the d-th needle to the (d+1)-th needle.

[0041] S23. The interaction between the needle and the stitch is equivalent to constraint points generated stitch by stitch along the sewing path. The first feeding cycle is performed, and the fabric displacement field at the end of the first feeding cycle is solved. Specifically: S231. Locate the fabric material point directly below the needle axis in the displacement field to obtain the stitch point, and activate the constraint corresponding to the stitch point. Specifically: After the first feeding cycle is completed, the displacement field of the fabric at the end of the first feeding cycle is solved using finite element method. Then, the fabric material point directly below the needle axis is located from this point, and its coordinates are taken as the stitch point to generate the stitch point. ,Right now: in, Fabric nodes The initial coordinates; The displacement of this node obtained by finite element method ( ); The horizontal coordinates of the needle axis are fixed respectively; Number the nearest node; This refers to the end time of the first feeding cycle; and is the horizontal coordinate of fabric node f; N represents the needle insertion moment within this feeding cycle, or can be understood as the instant the needle pierces the fabric.

[0042] For needle marks Activate the corresponding constraint C1, define the reference point position, couple the reference point with the surrounding fabric area, and temporarily lock the current point displacement at the moment of needle insertion to simulate needle insertion. After the needle insertion phase ends, the forced displacement constraint is released or weakened, but the distributed coupling relationship is retained, making... It continues to represent this fabric area and moves with subsequent feeds for the second feeding cycle.

[0043] S232. After the second feeding cycle is completed, the needle stitch points are generated in the same way as described above. And activate constraint C2 to establish and The line trace constraints between them, namely: , in, For equivalent suture tightening rate, The axial force generated by the current spring unit (equivalent seam segment) This is the equivalent axial stiffness of the suture. for and Current distance, The natural length of the current line segment; For needle marks Activate the corresponding constraint C2, define the reference point position, couple the reference point with the surrounding fabric area, and temporarily lock the current point displacement at the moment of needle insertion to simulate needle insertion. After the needle insertion phase ends, the forced displacement constraint is released or weakened, but the distributed coupling relationship is retained, making... It continues to represent this fabric area and moves with subsequent feeds for the third feeding cycle.

[0044] S233. Then the third cycle of feeding is completed and stitch points are generated. And activate constraint C3 to establish and The stitch constraints between the lines are then repeated to generate stitch points. and corresponding constraint CN; By using penalty function contact constraints to represent edge contact constraints, the seam guide is simplified into a rigid guide surface or a rigid guide curve, so that the guide surface maintains a fixed lateral position throughout the sewing direction, thus forming an equivalent model of the sewing process of needle-presser foot-fabric-needle plate-feed dog.

[0045] In an embodiment of the present invention, step S3 involves solving the equivalent model of the sewing process according to the single-needle cycle sequence and calculating the corresponding sewing coefficient, including the following steps S31-S32: The material parameter vector is input into the virtual simulation software for each of the different analysis stages, and the stitch point coordinates are output. These stitch point coordinates are then imported into the virtual simulation software to obtain the sewing coefficient. Specifically: Based on the time-series solution of the equivalent sewing process according to the single needle cycle, a stitch cycle is divided into the stages of presser foot pressing down, feed dog rising, feed dog feeding, needle lowering, and unloading and resetting. Using virtual simulation software, input a vector of the material parameters shown, and output the coordinates of the needle point. Import the results into the software to obtain the sewing coefficient; The sewing coefficient includes values ​​such as wrinkle amplitude, seam offset, stitch length variation coefficient, and feed displacement.

[0046] S31. The wrinkling amplitude is calculated by removing the rigid translation and tilt components of the fabric using least-squares spatial plane fitting, and extracting the residual out-of-plane displacement field (U3 residual). That is, the least-squares method is used to fit the local reference plane of the fabric to obtain the height value of the fitted plane. in, Let be the height value of the fitted plane at the j-th data point. and Let j be the horizontal coordinate of the j-th data point; Reference plane parameters; Specifically, the reference plane parameters are obtained by solving... This causes the actual out-of-plane displacement of all data points. with fitted plane values The reference plane parameters are obtained by minimizing the sum of squared errors between them. ;in, The total number of data points used for fitting the plane is usually selected as the number of nodes within a local area of ​​the fabric; Only for variable indexing; The actual out-of-plane displacement of the j-th data point, i.e., U3 obtained from the finite element solution, is the displacement perpendicular to the fabric plane.

[0047] Calculate the normal undulation of the node relative to the reference plane for Using the normal undulation as the wrinkling height, calculate the wrinkling amplitude. for: in, To select a wrinkle evaluation area of ​​fixed width on both sides of the suture, j is the variable index; The degree of local out-of-plane buckling is quantitatively characterized by the peak-valley value (PV) and root mean square value (RMS) of the residual field. The PV value directly reflects the maximum fold depth. ; Furthermore, RMS describes the overall fluctuation energy, and RMS is calculated as follows: in, In the evaluation area The number of finite element nodes included, where j is the variable index.

[0048] S32. Extract the initial principal direction of the seam edge based on singular value decomposition and construct a normal vector; select a fabric edge node for each actual stitch point, fit a local fabric edge straight line, and calculate the perpendicular distance from the current stitch point to the fitted local fabric edge line; set a target seam allowance, calculate the seam edge offset of the current stitch, and calculate the average seam edge offset for the stitch point; project the stitch point coordinates based on the initial principal direction of the seam edge, and calculate the projection distance between adjacent points as the actual stitch distance. Specifically: The initial principal direction of the seam edge is extracted based on singular value decomposition (SVD) and a normal vector is constructed. The in-plane displacements (U1, U2) of the nodal plane are projected onto the normal vector. The normal vector offset is calculated using the mean and range of the in-plane displacements of the nodal plane to evaluate the seam edge offset. That is, let the first... The actual stitch points are: Select fabric edge nodes near the stitch point and fit a local fabric edge straight line as follows: Then the first The vertical distance from each stitch point to the local selvage fitting line for: in, , , These are the coefficients of the equation of the line. and For the first The horizontal vector of each actual stitch point, where k is the variable index; Let the target seam allowance be Then the first Needle seam offset for: ; for all Calculate the average seam offset based on the number of stitch points. for: seam offset standard deviation for: The actual stitch distance is calculated by projecting the coordinates of the stitch points along the main sewing direction obtained from SVD decomposition to the coordinates of adjacent points. in, The actual horizontal stitch distance between the kth stitch and the (k-1th stitch)th stitch only considers the projected distance on the x and y planes, ignoring the influence of height. The coordinates of the k-th stitch point; The coordinates of the (k-1)th stitch point; The difference between the start and end points of the feed direction displacement (U1) within each sewing cycle is extracted as the feed displacement, and the standard deviation and CV value of multiple cycles are statistically analyzed to evaluate the repeatability of the feed mechanism.

[0049] In an embodiment of the present invention, in step S4, sewing parameters are obtained, and the sewing parameters are calibrated and corrected based on the sewing coefficient. After calibration and correction, the sewing parameters are compared to determine the optimal adjustment direction, including the following steps S41-S42: S41. The fitted data features are combined with the sewing parameters for calibration, and all parameters are jointly corrected and verified using the coefficient of determination. Specifically: Using sewing parameters collected during the actual sewing process, including material displacement, shape image, seam position or stitch coordinates, the material parameters and boundary conditions in the finite element model are calibrated. Calibration is performed by considering material parameters, contact friction parameters, boundary conditions of presser foot and feed dog, stitch and suture tightening constraints, seam guide constraints, and the overall joint calibration sequence. S411. Use material test curves to calibrate the elastic modulus, shear modulus, Poisson's ratio, and compression and bending parameters.

[0050] S412. Fix the material parameters and calibrate the friction coefficient using the actual feeding displacement.

[0051] S413. Fix the material and friction parameters, and calibrate the presser foot pressure and feeding motion curve.

[0052] S414. Use wrinkle shape and rebound amount to calibrate suture tightening constraint.

[0053] S415. Use the seam position and lateral displacement to calibrate the guide position and gap.

[0054] S416. Perform a small-range joint correction of all parameters, through... Verification required: in, Experimental value The mean, For simulation of the first One output quantity; This is the experimental value of the k-th output. Once calibration is complete, all subsequent simulations with different parameter combinations must use the same calibrated base model.

[0055] S42. After calibration, a comparative analysis will be conducted, specifically: After calibration, the state quantities under different combinations of sewing parameters can be compared by changing the presser foot pressure, feed displacement, feed speed, stitch length, thread tightening effect, or seam guide constraint, providing a basis for adjusting the sewing parameters. Among them, different combinations of sewing parameters include single-factor sewing and multi-factor sewing; Specifically, when comparing single-factor sewing parameters, other sewing parameters are kept constant while the value of this parameter is adjusted. For example, if the single factor is presser foot pressure, too little pressure will lead to insufficient contact, insufficient or fluctuating feed, uneven stitch spacing, unstable sewing edges, etc.; too much pressure will lead to presser foot resistance and increased friction, wrinkling, or increased feed lag, etc.

[0056] Furthermore, when comparing the multi-factor sewing parameters, an orthogonal experiment was used, with each parameter set at high, medium, and low levels; that is, the basic parameters were set as follows: The intermediate level is: , ; The low level is: The high level refers to: ; in, For the first The horizontal spacing of the factors For the first The relative rate of change of each factor The baseline level for the j-th factor is... Let j be the baseline value for the j-th factor. For the j-th factor, the low level The j-th factor is at a high level.

[0057] Different levels of different parameters are selected and sequentially put into the model for solution. Finally, the results are output according to each working condition. The average value of the results of each factor at each level is calculated by range analysis. Then, the difference between the maximum and minimum values ​​is calculated. The larger the difference, the more significant the influence of the factor on the result. The optimal parameter combination is determined, providing a basis for adjusting the sewing parameters.

[0058] Example 3, referring to Figures 2-4 This invention provides a method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters. To verify the beneficial effects of this invention, scientific demonstration is conducted through experiments.

[0059] The example has a thickness of 0.7 mm and a basis weight of 247 g / m³. 2 The specific steps for making twill fabric are as follows: The fabric mechanical parameter data obtained from experimental tests are processed in software for outlier removal, smoothing filtering, curve fitting, and feature parameter extraction, such as... Figure 2 As shown; summarizing the results of five longitudinal tensile tests, the average maximum tensile force was 29.881 N, the average peak elongation was 163.182 mm, and the results were obtained from three fitting tests. The RMSE is 1.817030 N, and the elastic modulus E is 1.4655 N / mm. In this example, the fabric model is simplified to a cuboid fabric shell, but different warp and weft model parameters are set as shown in Table 1 and Table 2.

[0060] Table 1. Parameters of the warp stitching model for example fabrics

[0061] Table 2 Parameters of the Weft Sewing Model for Example Fabrics

[0062] Where E1 represents the warp elastic modulus; E2 represents the weft elastic modulus; E3 represents the thickness compressive modulus; ν represents Poisson's ratio; ν12 represents the weft contraction caused by warp stretching; ν13 represents the thickness change caused by warp stretching; ν23 represents the thickness change caused by weft stretching; G12 represents the in-plane shear modulus; G13 represents the warp shear modulus; and G23 represents the weft shear modulus.

[0063] In the Part module of the software, draw the 3D model of the needle, presser foot, needle plate, and feed dog.

[0064] After establishing each model, reference points and material properties are set. The needle model, presser foot model, fabric model, needle plate model, and feed dog model are assembled according to the actual sewing environment to create a fabric sewing process model, such as... Figure 3 As shown.

[0065] Set the analysis step parameters as shown in Table 3, and establish the analysis steps, which are: presser foot down, feed dog up, feed dog feed, needle down, and unload reset.

[0066] Table 3 Analysis Step Parameters

[0067] Establish contacts and contact pairs, set the parameters as shown in Table 4, and create contact properties. In the Interaction module of the software, create contact properties between the presser foot and the fabric, the needle plate and the fabric, and the feed dog and the fabric.

[0068] Table 4 Contact Attribute Parameters

[0069] Establish a stitch reference point; generally, the needle is too difficult to converge, so the needle is only used as a position reference, and the reference point is used as the stitch position; at the same time, the stitch point is coupled with the fabric to create a constraint.

[0070] Set boundary conditions: In the software, create boundary conditions for the needle, presser foot, fabric, needle plate, and feed dog in the Load module; in the Initial module, set parameters U1, U2, U3, UR1, UR2, and UR3 for each model; where U1 represents the displacement along the X-axis, U2 represents the displacement along the Y-axis, U3 represents the displacement along the Z-axis, UR1 represents the rotation angle around the X-axis, UR2 represents the rotation angle around the Y-axis, and UR3 represents the rotation angle around the Z-axis.

[0071] Apply motion to each analysis step. In the software, select the analysis step for each model in the Load module and Step. Then select the reference point for each model and set the corresponding U1, U2, and U3 parameters for each model.

[0072] Based on the grid parameters provided in Table 5, the grid is divided as follows: Figure 4 The mesh shown is generated by the Mesh module in the software, which divides the surface of each model into meshes. Table 5 Mesh Parameters

[0073] In the software, create and submit a job using the Job module, outputting U3 and the final X-axis coordinates of the stitch points. Import the output results into the software to calculate the elastic modulus E1 / E2, wrinkle amplitude, seam offset, stitch pitch variation coefficient, and feed displacement. Compare the simulation results for different parameters to obtain the optimal sewing parameters. When performing weft sewing, you can directly convert the warp data to weft data in the Property module of the software. The remaining steps are the same as above.

[0074] Example 4 is an embodiment of the present invention. The above is an illustrative scheme of the method for characterizing the instant deformation state of seam fabric based on fabric performance parameters. It should be noted that the technical solution of the system for characterizing the instant deformation state of seam fabric based on fabric performance parameters and the technical solution of the method for characterizing the instant deformation state of seam fabric based on fabric performance parameters described above belong to the same concept. For details not described in detail in the technical solution of the system for characterizing the instant deformation state of seam fabric based on fabric performance parameters described above, please refer to the description of the technical solution of the method for characterizing the instant deformation state of seam fabric based on fabric performance parameters.

[0075] This embodiment provides a characterization system for the instantaneous deformation state of seam fabric based on fabric performance parameters, including: a data acquisition module, an equivalent module, a solution module, and a calibration module; The data acquisition module acquires the original data of the fabric material and forms a material parameter vector dataset through segmented fitting and feature extraction. The equivalent module constructs a unified coordinate system based on the stitch period according to the material parameter vector dataset to obtain an equivalent model of the sewing process. The solution module solves the equivalent model of the sewing process according to the single-needle cycle sequence and calculates the corresponding sewing coefficient; The calibration module acquires sewing parameters, calibrates and corrects the sewing parameters based on the sewing coefficient, and then compares the best sewing parameters to determine the direction of parameter adjustment.

[0076] This embodiment also provides a computer device applicable to the characterization method of the instantaneous deformation state of seam fabric based on fabric performance parameters, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the characterization method of the instantaneous deformation state of seam fabric based on fabric performance parameters as proposed in the above embodiment.

[0077] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as proposed in the above embodiments.

[0078] The storage medium proposed in this embodiment and the method for characterizing the instant deformation state of sewing fabric based on fabric performance parameters proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0079] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters, characterized in that: include, Obtain raw data of fabric materials, and form a material parameter vector dataset through piecewise fitting and feature extraction; Based on the material parameter vector dataset, a unified coordinate system is constructed according to the stitch period to obtain an equivalent model of the sewing process; The equivalent model of the sewing process is solved according to the single-needle cycle sequence, and the corresponding sewing coefficient is calculated. Obtain sewing parameters, calibrate and correct the sewing parameters based on the sewing coefficient, and then compare the best sewing parameters to obtain the direction of parameter adjustment.

2. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 1, characterized in that, The process of forming a material parameter vector dataset through piecewise fitting and feature extraction includes: The original data of the initial fabric were obtained by conducting warp and weft tensile and compression recovery tests on the fabric material. The stiffness and friction coefficient of the fabric material are tested to obtain the fabric stiffness and the fabric friction coefficient. The original data undergoes a first preprocessing step through logical judgment, followed by a second preprocessing step using a moving average filter. Divide the data into segments, perform segmented fitting, perform local linear fitting for each segment and judge the fitting effect, and extract the features of the fitted data. A material parameter vector dataset is formed based on the fitted data features, the fabric stiffness, and the fabric friction coefficient.

3. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 2, characterized in that, The method for obtaining an equivalent model of the sewing process includes: By setting the fabric as an orthogonal anisotropic nonlinear material and establishing a unified coordinate system, a stitch cycle is divided into different analysis stages. For each of the different analysis stages, different fabric material points are selected as tracking points, and the actual displacement component of each tracking point along the feeding direction is calculated within one stitch cycle. The actual displacement components of all tracking points are averaged to obtain the actual displacement corresponding to the difference between the theoretical feed amount and the actual feed amount.

4. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 3, characterized in that, The method for obtaining an equivalent model of the sewing process also includes: The interaction between the needle and the stitch is equivalent to the constraint points generated stitch by stitch along the sewing path. The first cycle of feeding is performed, and the displacement field of the fabric at the end of the first cycle of feeding is solved. The fabric material point directly below the needle axis in the displacement field is located to obtain the stitch point, and the constraint corresponding to the stitch point is activated. Define a reference point position, couple the reference point to the fabric, lock the current point displacement at the moment of needle insertion, release the constraint after needle insertion, retain the coupling relationship, and perform the next cycle of feeding, and repeat the generation of stitch points and corresponding constraints in sequence.

5. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 4, characterized in that, The process of solving the equivalent model of the sewing process according to the single-needle cycle sequence includes: The material parameter vector is input into the virtual simulation software for the different analysis stages, and the needle point coordinates are output. Import the stitch point coordinates into virtual simulation software to obtain the sewing coefficient; The sewing coefficient includes the wrinkle amplitude value. The height value of the fitted plane is obtained by fitting a local reference plane of the fabric using the least squares method. The normal undulation relative to the reference plane is calculated using the height value of the fitted plane.

6. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 5, characterized in that, The sewing coefficient also includes seam offset; The initial principal direction of the seam edge is extracted and a normal vector is constructed based on singular value decomposition. For each actual stitch point, select a fabric edge node, fit a local fabric edge straight line, and calculate the vertical distance from the current stitch point to the local fabric edge fitted line. Set the target seam allowance, calculate the seam offset of the current needle, and calculate the average seam offset for the stitch point. Based on the coordinates of the initial main direction projection stitch points of the seam edge, the projection distance between adjacent points is calculated as the actual stitch distance.

7. The method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in claim 6, characterized in that, The calibration correction includes: The fitting data features are combined with the sewing parameters for calibration, and all parameters are jointly corrected and verified using the coefficient of determination. After calibration, a comparative analysis is performed, which includes a comparison of multiple sewing parameters. An orthogonal experiment is used, and the average value of each parameter and the difference between the maximum and minimum values ​​are calculated through range analysis.

8. A characterization system for the instantaneous deformation state of seam fabric based on fabric performance parameters, employing the characterization method for the instantaneous deformation state of seam fabric based on fabric performance parameters as described in any one of claims 1 to 7, characterized in that, include: Data acquisition module, equivalent module, solution module, calibration module; The data acquisition module acquires the original data of the fabric material and forms a material parameter vector dataset through segmented fitting and feature extraction. The equivalent module constructs a unified coordinate system based on the stitch period according to the material parameter vector dataset to obtain an equivalent model of the sewing process. The solution module solves the equivalent model of the sewing process according to the single-needle cycle sequence and calculates the corresponding sewing coefficient; The calibration module acquires sewing parameters, calibrates and corrects the sewing parameters based on the sewing coefficient, and then compares the best sewing parameters to determine the direction of parameter adjustment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for characterizing the instantaneous deformation state of seam fabric based on fabric performance parameters as described in any one of claims 1 to 7.

Images