Line tension adaptive adjustment methods and systems, electronic devices and media

By constructing a two-dimensional line tension parameter matrix and combining it with fabric type and binding width, the multi-line tension of the overlock sewing machine is automatically adjusted, solving the problem of reliance on manual experience in existing technologies and achieving efficient and accurate line tension control and stable stitch quality.

CN123113336APending Publication Date: 2026-11-17JACK SEWING MASCH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611285673.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-24
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Current overlock sewing machines rely on manual experience for thread tension adjustment, resulting in low efficiency and poor repeatability. They fail to comprehensively consider the coupled influence of multiple factors on thread tension requirements, leading to stitch quality problems such as loose threads, wrinkles, weak edges, or incomplete binding.

Method used

By constructing a two-dimensional thread tension parameter matrix, combining fabric type and hem width information, the system automatically matches multi-line tension parameters, adjusts them through a thread tension actuator, and corrects the parameters based on stitch quality feedback to achieve adaptive adjustment.

Benefits of technology

It improves the targeting and accuracy of line tension matching, reduces the amount of manual adjustment, increases production efficiency and parameter reproducibility consistency, and realizes digital optimization and reuse of process parameters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123113336A_ABST
    Figure CN123113336A_ABST
Patent Text Reader

Abstract

This application provides a method and system for adaptive thread tension adjustment, an electronic device, and a medium. The method includes: acquiring fabric type information and hem width information corresponding to the current sewing operation; determining a corresponding target thread tension parameter vector based on a pre-constructed two-dimensional thread tension parameter matrix, wherein the two-dimensional thread tension parameter matrix uses fabric type as the first dimension and hem width as the second dimension, and each matrix unit corresponds to a combination of one fabric type and one hem width; converting the target thread tension parameter vector into a corresponding thread tension control command and outputting it to a thread tension actuator, which adjusts the thread tension of the target sewing thread. This application improves the accuracy of thread tension matching under different fabrics and different hem widths, reduces repeated trial sewing and manual adjustment processes, and improves the machine setup efficiency when changing sewing equipment, reordering, and producing multiple varieties.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of sewing equipment technology, and relates to a method and system for adaptive adjustment of thread tension, electronic equipment and medium. Background Technology

[0002] Overlock machines are widely used in sewing industries such as clothing, knitting, and home textiles, mainly for overlocking, hemming, and trimming fabric edges. During the stitch formation process, thread tension is one of the important process parameters affecting the quality of the overlock stitch. It includes not only the tension of the machine needle thread but also the tension of the upper and lower looper threads, among other multi-path tensions. The matching state between these tensions directly affects whether the overlock stitch is smooth, free of loose threads, wrinkled, has a weak edge, and whether the overlock is full.

[0003] When adjusting the thread tension of existing overlock sewing machines, manual experience is usually used. Operators manually rotate the thread tension knob or input the target tension value in the electronic control interface based on the stitch condition after a trial sewing. This method is inefficient, has poor repeatability, and is prone to parameter differences between different operators.

[0004] With the development of digital and intelligent overlock sewing machines, some equipment can now automatically adjust single parameters. For example, it can control the thread tension actuator based on a preset tension value, or correct some sewing parameters based on single input variables such as fabric thickness, sewing speed, and feed status. However, these solutions only compensate for single variables and fail to comprehensively consider the coupled influence of multiple factors on thread tension requirements during sewing. Therefore, quality problems such as loose threads, wrinkles, weak edges, or incomplete binding may still occur under different sewing conditions. Summary of the Invention

[0005] This application provides a method and system for adaptive line tension adjustment, an electronic device, and a medium to solve the technical problems of existing line tension adjustment methods relying on manual experience and having low adjustment efficiency.

[0006] In a first aspect, this application provides a method for adaptive adjustment of thread tension, comprising: acquiring fabric type information and binding width information corresponding to the current sewing operation; determining a target thread tension parameter vector based on a pre-constructed two-dimensional thread tension parameter matrix, wherein the two-dimensional thread tension parameter matrix uses fabric type as the first dimension and binding width as the second dimension, and includes multiple matrix units, each matrix unit corresponding to a combination of a fabric type and a binding width, and is associated with a set of thread tension parameters corresponding to the combination of ...

[0007] In one implementation of the first aspect, the steps for constructing the two-dimensional linear tension parameter matrix include: obtaining a preset set of fabric types and a set of binding widths, wherein the set of fabric types is divided according to material properties, process properties, or preset classification rules, and the set of binding widths includes preset width values ​​or preset width levels; for preset combination conditions in the set of fabric types and the set of binding widths, obtaining at least two linear tension parameters corresponding to each combination condition through experimental calibration; constructing a two-dimensional parameter matrix using the fabric type as the row index and the binding width as the column index; and writing the two linear tension parameters corresponding to each combination condition into the matrix unit in the two-dimensional parameter matrix that matches the corresponding fabric category and binding width to obtain the two-dimensional linear tension parameter matrix.

[0008] In one implementation of the first aspect, determining the corresponding target line tension parameter vector based on the pre-constructed two-dimensional line tension parameter matrix and the fabric type information and the binding width information includes: when there is a target matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type and matches the current binding width, extracting the line tension parameter vector from the target matrix unit and using it as the target line tension parameter vector corresponding to the current sewing operation.

[0009] In one implementation of the first aspect, determining the corresponding target line tension parameter vector based on the pre-constructed two-dimensional line tension parameter matrix and the fabric type information and the binding width information includes: when there is a matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type but does not match the current binding width, obtaining two reference binding widths adjacent to the current binding width in the parameter row corresponding to the current fabric type in the two-dimensional line tension parameter matrix; calculating interpolated line tension parameters based on the reference line tension parameters corresponding to the two reference binding widths respectively; and generating the target tension parameter vector corresponding to the current sewing operation based on the interpolated line tension parameters.

[0010] In one implementation of the first aspect, determining the corresponding target tension parameter vector based on the pre-constructed two-dimensional tension parameter matrix and the fabric type information and the hem width information includes: when there is no matrix unit in the two-dimensional tension parameter matrix that corresponds to the current fabric type but matches the current hem width, selecting at least one fabric type similar to the current fabric type from the existing fabric types in the two-dimensional tension parameter matrix; determining the similarity weight corresponding to each similar fabric type based on the comprehensive similarity between the current fabric type and each selected similar fabric type, wherein the sum of the similarity weights corresponding to each similar fabric type is 1; calculating the weighted tension parameters corresponding to each similar fabric type under the current hem width based on the similarity weights corresponding to each similar fabric type to obtain the migration tension parameter; and generating the target tension parameter vector corresponding to the current sewing operation using the migration tension parameter.

[0011] In one implementation of the first aspect, the method further includes: performing trial sewing or formal sewing according to the target tension parameter vector, and simultaneously acquiring multi-source stitch quality feedback information; the multi-source stitch quality feedback information includes direct quality feedback signals generated by manual confirmation by the operator or identification of stitch status by an image recognition module, and indirect quality feedback signals generated by tension sensor detection, thread breakage detection signals, spindle current detection, or feed resistance detection; determining whether the current stitch meets the preset quality requirements based on the stitch quality feedback information; if the current stitch does not meet the preset quality requirements, then correcting the target tension parameter vector; continuing trial sewing or formal sewing according to the corrected target tension parameter vector, and reacquiring the stitch quality feedback information until the current stitch meets the preset quality requirements; if the current stitch meets the preset quality requirements, then storing at least one of the following in the preset parameter database: current fabric type, current binding width, corrected target tension parameter vector, actual executed tension parameter vector, tension parameter correction amount, and stitch quality evaluation result, and updating the corresponding matrix unit in the two-dimensional stitch tension parameter matrix.

[0012] In one implementation of the first aspect, correcting the target tension parameter vector includes: acquiring the actual characteristic parameters of the current fabric and calculating the deviation of the actual characteristic parameters relative to the corresponding characteristic parameters of a preset reference fabric; the characteristic parameters include fabric thickness, fabric elasticity, and fabric density; determining, according to preset characteristic parameter correction rules, a thickness correction coefficient for the fabric thickness deviation, an elasticity correction coefficient for the fabric elasticity deviation, and a density correction coefficient for the fabric density deviation; performing weighted calculations on the fabric thickness deviation, the fabric elasticity deviation, and the fabric density deviation based on each correction coefficient to obtain a stitch quality feedback correction amount; superimposing the stitch quality feedback correction amount with the fine-tuning amount corresponding to historical qualified process records to obtain a total tensor parameter correction amount; and superimposing the total tensor parameter correction amount onto the target tension parameter vector to obtain the corrected target tension parameter vector.

[0013] Secondly, this application provides a line tension adaptive adjustment system, comprising:

[0014] A line tension adaptive adjustment device for performing the method described in any of the above to generate line tension control commands;

[0015] The thread tension actuator is communicatively connected to the thread tension adaptive adjustment device and is used to adjust the thread tension of the target suture according to the thread tension control command.

[0016] Thirdly, this application provides an electronic device, comprising:

[0017] The memory is used to store computer programs;

[0018] A processor, the processor being configured to execute a computer program stored in the memory, so as to cause the electronic device to perform the method described in any of the preceding descriptions.

[0019] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the preceding claims.

[0020] As described above, the adaptive line tension adjustment method and system, electronic device, and medium described in this application have the following beneficial effects:

[0021] (1) By taking both fabric type and binding width as the basis for generating line tension parameters, a two-dimensional parameter matching relationship of “fabric type × binding width” is established. This can determine multiple line tension parameters according to the actual stitch formation requirements of different fabrics under different binding widths, thereby improving the pertinence and accuracy of line tension matching.

[0022] (2) It can automatically call, calculate or correct the corresponding thread tension parameters according to the current fabric type and binding width, reduce the workload of operators relying on experience to repeatedly test the sewing and adjust the thread clamp one by one, shorten the machine adjustment time, and improve production efficiency and parameter reproduction consistency.

[0023] (3) It can associate and store fabric type, binding width, multi-line tension parameters, manual fine-tuning amount and stitch quality results, and generate target line tension parameters through adjacent width interpolation, similar fabric parameter migration, fabric feature correction and quality feedback correction, and write qualified parameters back to the database, so that the equipment can gradually transform manual machine adjustment experience into digital process data that can be accumulated, optimized and reused. Attached Figure Description

[0024] Figure 1 The diagram shown is an architecture diagram of a line tension adaptive adjustment system according to an embodiment of this application.

[0025] Figure 2 The diagram shown is a structural schematic of a line tension adaptive adjustment device according to an embodiment of this application.

[0026] Figure 3 The flowchart shown is a method for adaptive adjustment of line tension according to an embodiment of this application.

[0027] Figure 4 The diagram shown is a flowchart of the construction of a two-dimensional line tension parameter matrix in one embodiment of this application.

[0028] Figure 5 The diagram shown is a schematic representation of a two-dimensional line tension parameter matrix in one embodiment of this application.

[0029] Figure 6 The flowchart shown is a process for determining the target line tension parameter vector in one embodiment of this application.

[0030] Figure 7 The diagram shown is a flowchart of line quality feedback and parameter correction in one embodiment of this application.

[0031] Figure 8 The diagram shown is a structural schematic of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0033] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0034] This application provides a method and system for adaptive thread tension adjustment, an electronic device, and a medium. This method acquires the working condition information corresponding to the current sewing operation, automatically matches and outputs the corresponding multi-thread tension parameters, thereby improving the stability of stitch quality, reducing the difficulty of manual machine adjustment, and enabling continuous optimization and reuse of process parameters.

[0035] The technical solution provided in this application can be applied to overlock sewing machines, digital overlock sewing machines, intelligent overlock sewing machines, and sewing equipment with edge binding or overlock functions, and has good application versatility and scenario adaptability.

[0036] The following will describe in detail the principle and implementation of the adaptive line tension adjustment method and system, electronic device and medium of this embodiment, so that those skilled in the art can understand the adaptive line tension adjustment method and system, electronic device and medium of this embodiment without creative effort.

[0037] Please see Figure 1 The diagram shown is an architecture diagram of a line tension adaptive adjustment system according to an embodiment of this application.

[0038] like Figure 1 As shown, the line tension adaptive adjustment system includes a line tension adaptive adjustment device and a line tension actuator.

[0039] Specifically, the adaptive tension adjustment device is used to execute the adaptive tension adjustment method described in this application to generate a tension control command. The tension actuator is communicatively connected to the adaptive tension adjustment device and is used to adjust the tension of the target suture according to the tension control command.

[0040] Please see Figure 2 The diagram shown is a schematic diagram of the structure of a line tension adaptive adjustment device according to an embodiment of this application.

[0041] like Figure 2 As shown, the adaptive line tension adjustment device described in this application includes a fabric type acquisition module, a hem width acquisition module, a two-dimensional line tension parameter matrix module, a target line tension calculation module, and a line tension execution control module.

[0042] Specifically, the fabric type acquisition module is used to acquire the fabric type information corresponding to the current sewing operation; the binding width acquisition module is used to acquire the binding width information corresponding to the current sewing operation. The fabric type information and the binding width information can be input by the operator through a touch screen or operation panel, or they can be acquired through other data sources.

[0043] The two-dimensional thread tension parameter matrix module is used to store and manage the two-dimensional thread tension parameter matrix. The two-dimensional thread tension parameter matrix uses fabric type as the first dimension index and hem width as the second dimension index, and includes multiple matrix units. Each matrix unit corresponds to a combination of fabric type and hem width, and is associated with a set of thread tension parameters corresponding to the combination. The set of thread tension parameters includes at least two of the following: left needle thread tension parameter, right needle thread tension parameter, upper bend needle thread tension parameter, and lower bend needle thread tension parameter.

[0044] The target line tension calculation module is used to determine the target line tension parameter vector that matches the current sewing operation from the two-dimensional line tension parameter matrix based on the obtained fabric type information and hem width information.

[0045] The line tension execution control module is used to generate corresponding line tension control commands based on the target line tension parameter vector, and output the line tension control commands to the line tension execution mechanism to adjust the line tension of at least one suture, thereby realizing synchronous or differentiated adjustment of the tension of multiple sutures.

[0046] In one embodiment of this application, the adaptive tension adjustment device further includes a manual fine-tuning module, a parameter learning and updating module, and a stitch quality feedback module. The functional implementation details of these modules will be described in detail in the adaptive tension adjustment method section.

[0047] Please see Figure 3 The above is a flowchart of a line tension adaptive adjustment method according to an embodiment of this application.

[0048] like Figure 3 As shown, this embodiment provides a method for adaptive adjustment of line tension, including the following steps S100 to S300.

[0049] In step S100, obtain the fabric type information and edge width information corresponding to the current sewing operation.

[0050] The fabric type information and the edge width information can be manually selected by the operator on the touch screen or operation panel, or they can be automatically read from the process sheet, order system, MES system or barcode information.

[0051] Specifically, the fabric type information is used to characterize the fabric category of the fabric to be sewn. It can be classified according to material properties such as cotton, chemical fiber, blended fabric, knitted fabric, and woven fabric; or according to processing properties such as thin fabric, thick fabric, elastic fabric, and loose fabric; or it can be classified according to a combination of material and processing properties, such as regular knitted fabric, elastic knitted fabric, and elastic blended knitted fabric. This application does not limit the specific classification method of fabric types.

[0052] The edge width information is used to characterize the target edge width or actual edge width corresponding to the current sewing operation. It can be represented by a specific width value, such as 5mm, 5.5mm, 6mm, etc.; or it can be represented by a width range or a preset width level, such as narrow edge, medium-narrow edge, medium-wide edge, wide edge, etc. This application does not limit the specific representation of the edge width information.

[0053] In this implementation, by using fabric type and hem width as dual-dimensional input variables, a standardized input basis is provided for subsequent parameter matching based on a two-dimensional line tension parameter matrix. This enables the system to perform differentiated tension adjustment for different combinations of fabric types and hem widths, thereby reducing the workload of operators relying on experience to repeatedly test sew and adjust the thread tensioner one by one, shortening the machine setup time when changing styles and reordering, and improving production efficiency and parameter reproducibility consistency.

[0054] In step S200, based on the pre-constructed two-dimensional line tension parameter matrix, the corresponding target line tension parameter vector is determined according to the fabric type information and the edge width information.

[0055] In this embodiment, the target thread tension parameter vector may include at least two of the following: left needle thread target tension parameter, right needle thread target tension parameter, upper bend needle thread target tension parameter, and lower bend needle thread target tension parameter.

[0056] The tension parameters of the upper and lower looper threads mainly affect the coverage of the sewing thread on the fabric edge, while the tension parameters of the left and right needle threads mainly affect the tightening of the stitch. This application sets corresponding tension parameters for different sewing paths when determining the target thread tension parameters, thereby achieving differentiated matching between tensions of multiple paths.

[0057] Please see Figure 4 The diagram shows a flowchart of the construction of a two-dimensional line tension parameter matrix in one embodiment of this application.

[0058] like Figure 4 As shown, the construction steps of the two-dimensional line tension parameter matrix include steps S210 to S240.

[0059] In step S210, a preset set of fabric types and a set of binding widths are obtained.

[0060] Specifically, the set of fabric types can be divided according to material properties, process properties, or preset classification rules. For example, the set of fabric types may include one or more fabric types such as thin fabric, regular knitted fabric, elastic knitted fabric, thick fabric, elastic fabric, and loose fabric.

[0061] The set of edge widths includes preset width values ​​or preset width levels. For example, it may include preset width values ​​such as 4mm, 5mm, 5.5mm, 6mm, and 7mm, or preset width levels such as narrow edge, medium-narrow edge, medium-wide edge, and wide edge.

[0062] In step S220, for the preset combination conditions in the set of fabric types and the set of binding widths, at least two tension parameters corresponding to each combination condition are obtained through experimental calibration.

[0063] Specifically, trial sewing calibration can be performed for a preset combination of "fabric type × binding width". During the calibration process, at least two of the following parameters are adjusted for the corresponding combination of left needle thread tension, right needle thread tension, upper looper thread tension, and lower looper thread tension: and the thread tension parameter that meets the preset stitch quality requirements is determined based on the stitch quality.

[0064] Please refer to Table 1. Taking conventional knitted fabric as an example, the multi-path tension parameters under different binding widths were experimentally calibrated. When the binding width is 5.0 mm, in the corresponding matrix unit, the tension parameter of the left needle thread is 60, the tension parameter of the right needle thread is 54, the tension parameter of the upper looper thread is 42, and the tension parameter of the lower looper thread is 46. When the binding width is 6.0 mm, in the corresponding matrix unit, the tension parameter of the left needle thread is 68, the tension parameter of the right needle thread is 60, the tension parameter of the upper looper thread is 48, and the tension parameter of the lower looper thread is 52.

[0065] Table 1. Linear tension calibration parameters for conventional knitted fabrics at different binding widths

[0066]

[0067] In step S230, a two-dimensional parameter matrix is ​​constructed using the fabric type as the row index and the hem width as the column index.

[0068] In step S240, the tension parameters of the two lines corresponding to each combination of working conditions are written into the matrix unit of the two-dimensional parameter matrix that matches the corresponding fabric type and hem width, thus obtaining the two-dimensional line tension parameter matrix.

[0069] Please see Figure 5The diagram shown is a schematic diagram of a two-dimensional line tension parameter matrix in one embodiment of this application.

[0070] Taking elastic material as an example, when 5.0 mm ≤ current edge width < 8.0 mm, the corresponding matrix element expression is:

[0071] ;

[0072] in This indicates the thread tension parameter of the left-hand sewing machine. Indicates the tension parameter of the right-hand needle thread. Indicates the tension parameter of the upper bend needle thread and This indicates the tension parameter of the bent thread.

[0073] In this implementation, a two-dimensional linear tension parameter matrix with fabric type and hem width as dual-dimensional indices is constructed through experimental calibration. This allows the system to adjust linear tension based on a single variable instead of fabric type and hem width together as the basis for generating linear tension parameters, thereby improving the pertinence and accuracy of linear tension parameter matching under different working conditions.

[0074] Please see Figure 6 The flowchart shown is a flowchart of the determination of the target line tension parameter vector in one embodiment of this application.

[0075] like Figure 6 As shown, the system determines the target linear tension parameter vector by three methods: direct matching, edge width interpolation, or similar fabric parameter migration, based on whether there is a matrix unit in the two-dimensional linear tension parameter matrix that matches the current fabric type and hem width.

[0076] In one embodiment of this application, determining the corresponding target line tension parameter vector based on the pre-constructed two-dimensional line tension parameter matrix and the fabric type information and the binding width information includes: when there is a target matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type and matches the current binding width, extracting the line tension parameter vector from the target matrix unit and using it as the target line tension parameter vector corresponding to the current sewing operation.

[0077] In this implementation, when a perfectly matching matrix unit exists, the system directly calls the target line tension value in that matrix unit, achieving fast and accurate parameter matching and shortening the setup time.

[0078] In one embodiment of this application, determining the corresponding target line tension parameter vector based on the pre-constructed two-dimensional line tension parameter matrix and the fabric type information and the binding width information includes: when there is a matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type but does not match the current binding width, obtaining two reference binding widths adjacent to the current binding width in the parameter row corresponding to the current fabric type in the two-dimensional line tension parameter matrix; calculating interpolated line tension parameters based on the reference line tension parameters corresponding to the two reference binding widths respectively; and generating the target tension parameter vector corresponding to the current sewing operation based on the interpolated line tension parameters.

[0079] Specifically, if the current binding width W is between the reference binding widths W1 and W2, the system obtains the line tension parameters corresponding to the reference binding widths W1 and W2 respectively from the parameter set corresponding to the current fabric type, and determines the interpolated line tension parameters using the following linear interpolation formula:

[0080] ;

[0081] in This is the current border width; , These represent the widths of two reference margins adjacent to the current margin width, and satisfy the following conditions: < < ; This indicates that the j-th seam is at the reference binding width. The corresponding reference line tension parameters; This indicates that the j-th seam is at the reference binding width. The corresponding reference line tension parameters; This represents the first value obtained through interpolation. The seam line is at the current edge width The corresponding interpolation line tension parameter; j represents different suture paths, which can correspond to at least one of the left needle thread, right needle thread, upper looper thread, and lower looper thread.

[0082] Please refer to Table 2, which shows the interpolation calculation process and interpolation results for the tension parameters of each route when the target edge width is 5.5 mm.

[0083] Table 2. Interpolation Calculation Results of Tension Parameters for Each Route

[0084]

[0085] Specifically, if the binding width corresponding to the current sewing operation is 5.5 mm, since 5.5 mm falls between the two reference binding widths of 5.0 mm and 6.0 mm, linear interpolation can be performed based on the thread tension parameters corresponding to the two reference binding widths. The interpolation ratio corresponding to the current binding width of 5.5 mm between the two reference binding widths of 5.0 mm and 6.0 mm is... It can be calculated using the following formula:

[0086] .

[0087] Based on the interpolation ratio, the tension parameters of the left needle thread, right needle thread, upper looper thread, and lower looper thread were interpolated and calculated respectively. The calculation process and results of the tension parameters of each route are shown in Table 2.

[0088] Therefore, we can obtain the base line tension parameter vector when the current hem width is 5.5 mm:

[0089] .

[0090] It should be noted that this method is not only applicable to 5.5mm, but also to widths such as 5.2mm and 5.7mm located between adjacent calibration points. If the actuator can only be adjusted in integer steps, the system can round off or take the nearest executable value according to preset rules.

[0091] In this implementation, the coverage of the two-dimensional line tension parameter matrix is ​​expanded by interpolating the widths of adjacent edges, enabling the system to automatically generate appropriate tension parameters under non-standard width conditions, thereby reducing the number of trial seams and the amount of manual adjustment work under non-standard width conditions.

[0092] In one embodiment of this application, determining the corresponding target tension parameter vector based on a pre-constructed two-dimensional tension parameter matrix and the fabric type information and the binding width information includes: when there is no matrix unit in the two-dimensional tension parameter matrix that corresponds to the current fabric type but matches the current binding width, at least one fabric type similar to the current fabric type is selected from the existing fabric types in the two-dimensional tension parameter matrix; based on the comprehensive similarity between the current fabric type and each selected similar fabric type, the similarity weight corresponding to each similar fabric type is determined, wherein the sum of the similarity weights corresponding to each similar fabric type is 1; based on the similarity weights corresponding to each similar fabric type, the tension parameters corresponding to each similar fabric type under the current binding width are weighted and calculated to obtain the migration tension parameter; and the migration tension parameter is used to generate the target tension parameter vector corresponding to the current sewing operation.

[0093] In one embodiment, the migration tension parameter can be calculated according to the following formula:

[0094] ;

[0095] in Indicates the first The thread tension parameters for similar fabric types at the current binding width; For the current fabric type and the first The similarity weights corresponding to similar fabric types can be determined by considering factors such as thickness, elasticity, material type, weave structure, and density; n represents the total number of similar fabric types involved in parameter migration. This represents the migration tension parameter.

[0096] For example, when an elastic blended knitted fabric is put into production for the first time, and the two-dimensional linear tension parameter matrix has not yet stored the linear tension parameters corresponding to this fabric type, assuming the current hem width is 5.5 mm, the system filters out elastic knitted fabric and regular blended knitted fabric as similar fabric types. The similarity weight for elastic knitted fabric is 0.7, and the similarity weight for regular blended knitted fabric is 0.3. Specific parameters are shown in Table 3.

[0097] Table 3. Linear tension parameters for similar fabric types of elastic blended knitted fabrics with a target hem width of 5.5 mm.

[0098]

[0099] In this embodiment, the sum of the similarity weights is 1. Based on the weighted calculation of the above similarity weights and the line tension parameter vector, we can obtain:

[0100]

[0101] The tension parameters for the shift thread corresponding to the left needle thread are: 0.7×58+0.3×64=59.8; the tension parameters for the shift thread corresponding to the right needle thread are: 0.7×55+0.3×58=55.9; the tension parameters for the shift thread corresponding to the upper bend needle thread are: 0.7×42+0.3×45=42.9; and the tension parameters for the shift thread corresponding to the lower bend needle thread are: 0.7×46+0.3×49=46.9.

[0102] When the line tension actuator can only be adjusted according to integer steps, discrete tension levels, or other discrete control quantities, the aforementioned migrated line tension parameters can be processed according to a preset discretization rule. For example, after rounding, the following can be obtained:

[0103] .

[0104] In this implementation, by migrating similar fabric parameters, the system can quickly generate suitable initial tension parameters when the target fabric type is missing in the database, which reduces the difficulty of setting up the machine when a new fabric is put into production for the first time. At the same time, as qualified parameters are continuously written back during use, the system's coverage of various fabrics continues to expand.

[0105] In step S300, the target thread tension parameter vector is converted into a corresponding thread tension control command and output to the thread tension actuator, which adjusts the thread tension of the target suture according to the thread tension control command.

[0106] Specifically, the wire tension actuator can be a stepper motor driving the wire clamping disc, a linear pulse motor driving the wire clamping mechanism, a servo motor adjusting mechanism, an electromagnetic actuator, a pneumatic actuator, or other mechanisms capable of changing the wire clamping pressure and wire tension.

[0107] In one embodiment, the thread tension corresponding to each sewing path can be adjusted synchronously, or it can be adjusted differently according to the current fabric type, binding width, and target thread tension parameters corresponding to each sewing path, so as to form a tension matching relationship between different sewing paths that is compatible with the current sewing conditions.

[0108] In this implementation, by converting the target line tension parameter vector into control commands and outputting them to the actuator, closed-loop control from parameter matching to physical tension adjustment is achieved. This enables the tension of multiple lines under different fabric types and binding width combinations to be automatically and accurately adjusted to the target value, avoiding reliance on manual adjustment of the tensioner by the operator.

[0109] In one embodiment of this application, the adaptive tension adjustment method of this application further includes a stitch quality feedback and parameter correction step.

[0110] Please see Figure 7 The diagram shows a flowchart of line quality feedback and parameter correction in one embodiment of this application.

[0111] like Figure 7 As shown, the adaptive line tension adjustment method described in this application further includes the following steps S410 to S440.

[0112] In step S410, trial sewing or formal sewing is performed according to the target tension parameter vector, and multi-source stitch quality feedback information is collected simultaneously.

[0113] The multi-source stitch quality feedback information includes direct quality feedback signals generated by manual confirmation by the operator or identification of the stitch status by the image recognition module, as well as indirect quality feedback signals generated by tension sensor detection, stitch breakage detection signals, spindle current detection, or feed resistance detection.

[0114] In step S420, it is determined whether the current stitch meets the preset quality requirements based on the stitch quality feedback information.

[0115] The stitch quality feedback information includes whether there is floating thread, broken thread, skipped stitch, wrinkling, blurred edge, full edge, flat stitch, and whether the fabric is stretched or deformed.

[0116] In step S430, if the current stitch does not meet the preset quality requirements, the target tension parameter vector is corrected; trial sewing or sewing continues according to the corrected target tension parameter vector, and the stitch quality feedback information is re-acquired until the current stitch meets the preset quality requirements.

[0117] In one embodiment of this application, the correction of the target tension parameter vector includes the following steps S431 to S435.

[0118] In step S431, the actual characteristic parameters of the current fabric are obtained, and the deviation of the actual characteristic parameters from the corresponding characteristic parameters of the preset reference fabric is calculated.

[0119] The characteristic parameters include fabric thickness, fabric elasticity, and fabric density.

[0120] In step S432, according to the preset feature parameter correction rules, the thickness correction coefficient for fabric thickness deviation, the elasticity correction coefficient for fabric elasticity deviation, and the density correction coefficient for fabric density deviation are determined respectively.

[0121] It should be noted that the correction coefficients for different routes can be different. For example, the upper and lower looper threads mainly affect the covering state, while the left and right needle threads have more impact on the stitch tightness. The specific correction direction and value should be obtained through experimental calibration.

[0122] In step S433, based on the various correction coefficients, the fabric thickness deviation, the fabric elasticity deviation, and the fabric density deviation are weighted and calculated to obtain the stitch quality feedback correction amount.

[0123] In step S434, the line quality feedback correction amount is superimposed with the fine-tuning amount corresponding to the historical qualified process record to obtain the total tensor parameter correction amount.

[0124] In step S435, the total correction amount of the tensor parameters is superimposed on the target tension parameter vector to obtain the corrected target tension parameter vector.

[0125] Specifically, for the j-th suture, the corrected target tension parameter vector can be calculated using the following formula:

[0126] ;

[0127] in Indicates the first The target tension parameters corresponding to the road seam line; This indicates the thickness deviation of the fabric; This indicates the elasticity deviation of the fabric; This indicates the density deviation of the fabric; They represent the first The thickness correction factor, elasticity correction factor, and density correction factor corresponding to the road surface; This indicates the fine-tuning amount corresponding to the historical qualified process record.

[0128] For example, taking the aforementioned conventional knitted fabric and a current binding width of 5.5 mm as an example, the target linear tension parameter vector obtained by interpolating adjacent binding widths is:

[0129] .

[0130] Assuming the current fabric is found to be thicker, more elastic, and looser in structure than the baseline knitted fabric in the database, and considering the current stitch quality feedback and historical qualified process records, the correction amounts are obtained according to the pre-established correction rules, as shown in the table below.

[0131] Table 4. Correction values ​​obtained according to pre-established correction rules

[0132]

[0133] Based on the above example, the corrected target tension parameter vector can be obtained as follows:

[0134] .

[0135] When the linear tension actuator adjusts according to integer steps or integer tension levels, the above parameters can be processed according to a preset discretization rule. For example, after rounding, the following can be obtained:

[0136] .

[0137] In this implementation, the target line tension parameter vector is corrected by multi-source line quality feedback information, and qualified parameters are written back to the database to update the two-dimensional line tension parameter matrix. This enables the continuous accumulation, optimization and reuse of process parameters, allowing the equipment to gradually transform manual machine adjustment experience into accumulative, optimizable and reusable digital process data, providing a foundation for subsequent intelligent parameter adjustment and self-learning control.

[0138] In step S440, if the current stitch meets the preset quality requirements, at least one of the following is stored in the preset parameter database: the current fabric type, the current hem width, the corrected target tension parameter vector, the actual executed tension parameter vector, the tension parameter correction amount, and the stitch quality evaluation result. The corresponding matrix unit in the two-dimensional line tension parameter matrix is ​​then updated.

[0139] In this implementation, by superimposing characteristic corrections for fabric thickness, elasticity, and density, as well as historical fine-tuning, on the basic tension parameters, the adaptability of the tension parameters to different batches of the same fabric category is further improved, so that the stitch quality can remain stable under the condition of fabric batch differences.

[0140] It should be noted that the scope of protection of the adaptive tension adjustment method described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0141] Please see Figure 8 The image shown is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0142] like Figure 8 As shown, this application provides an electronic device, including:

[0143] The memory is used to store computer programs;

[0144] A processor, the processor being configured to execute a computer program stored in the memory, so as to cause the electronic device to perform the method described in any of the preceding descriptions.

[0145] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0146] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0147] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0148] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0149] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the methods described in any of the above embodiments. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0150] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0151] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for adaptive adjustment of line tension, characterized in that, include: Obtain the fabric type and binding width information corresponding to the current sewing operation; Based on a pre-constructed two-dimensional thread tension parameter matrix, a corresponding target thread tension parameter vector is determined according to the fabric type information and the binding width information. The two-dimensional thread tension parameter matrix uses fabric type as the first dimension and binding width as the second dimension, and includes multiple matrix units. Each matrix unit corresponds to a combination of fabric type and binding width, and is associated with a set of thread tension parameters corresponding to the combination. The set of thread tension parameters includes at least two of the following: left needle thread tension parameter, right needle thread tension parameter, upper bevel needle thread tension parameter, and lower bevel needle thread tension parameter. The target suture tension parameter vector is converted into a corresponding suture tension control command and output to the suture tension actuator, which then adjusts the suture tension of the target suture according to the suture tension control command.

2. The method according to claim 1, characterized in that, The steps for constructing the two-dimensional line tension parameter matrix include: Obtain a preset set of fabric types and a preset set of binding widths, wherein the set of fabric types is divided according to material properties, process properties or preset classification rules, and the set of binding widths includes preset width values ​​or preset width levels; For a preset combination of working conditions in the set of fabric types and the set of binding widths, at least two tension parameters corresponding to each combination of working conditions are obtained through experimental calibration. A two-dimensional parameter matrix is ​​constructed using the fabric type as the row index and the hem width as the column index; The tension parameters of the two lines corresponding to each combination of working conditions are written into the matrix unit of the two-dimensional parameter matrix that matches the corresponding fabric type and hem width to obtain the two-dimensional line tension parameter matrix.

3. The method according to claim 1, characterized in that, Based on the pre-constructed two-dimensional line tension parameter matrix, determining the corresponding target line tension parameter vector according to the fabric type information and the binding width information includes: when there is a target matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type and matches the current binding width, extracting the line tension parameter vector from the target matrix unit and using it as the target line tension parameter vector corresponding to the current sewing operation.

4. The method according to claim 1, characterized in that, Based on a pre-constructed two-dimensional line tension parameter matrix, the corresponding target line tension parameter vector is determined according to the fabric type information and the hem width information, including: When there is a matrix unit in the two-dimensional linear tension parameter matrix that corresponds to the current fabric type but does not match the current binding width, obtain two reference binding widths adjacent to the current binding width in the parameter row corresponding to the current fabric type in the two-dimensional linear tension parameter matrix. Based on the reference line tension parameters corresponding to the two reference edge widths, the interpolation line tension parameters are calculated. Based on the interpolation line tension parameters, the target tension parameter vector corresponding to the current sewing operation is generated.

5. The method according to claim 1, characterized in that, Based on a pre-constructed two-dimensional line tension parameter matrix, the corresponding target line tension parameter vector is determined according to the fabric type information and the hem width information, including: When there is no matrix unit in the two-dimensional line tension parameter matrix that corresponds to the current fabric type but matches the current hem width, at least one fabric type similar to the current fabric type is selected from the existing fabric types in the two-dimensional line tension parameter matrix. Based on the overall similarity between the current fabric type and each of the selected similar fabric types, the similarity weight corresponding to each similar fabric type is determined, and the sum of the similarity weights corresponding to each similar fabric type is 1. Based on the similarity weights of each similar fabric type, the line tension parameters corresponding to each similar fabric type under the current hemming width are calculated by weighting to obtain the migration tension parameters. The migration tension parameters are used to generate the target tension parameter vector corresponding to the current sewing operation.

6. The method according to claim 1, characterized in that, Also includes: Trial sewing or formal sewing is performed according to the target tension parameter vector, and multi-source stitch quality feedback information is collected simultaneously; the multi-source stitch quality feedback information includes direct quality feedback signals generated by manual confirmation by the operator or identification of stitch status by the image recognition module, and indirect quality feedback signals generated by tension sensor detection, thread breakage detection signal, spindle current detection or feeding resistance detection; Based on the stitch quality feedback information, determine whether the current stitch meets the preset quality requirements; If the current stitch does not meet the preset quality requirements, the target tension parameter vector is corrected. Continue to perform trial sewing or sewing according to the corrected target tension parameter vector, and reacquire the stitch quality feedback information until the current stitch meets the preset quality requirements; If the current stitch meets the preset quality requirements, at least one of the following will be stored in the preset parameter database: the current fabric type, the current hem width, the corrected target tension parameter vector, the actual executed tension parameter vector, the tension parameter correction amount, and the stitch quality evaluation result. The corresponding matrix unit in the two-dimensional line tension parameter matrix will also be updated.

7. The method according to claim 6, characterized in that, Correcting the target tension parameter vector includes: Obtain the actual characteristic parameters of the current fabric and calculate the deviation of the actual characteristic parameters from the corresponding characteristic parameters of the preset reference fabric; the characteristic parameters include fabric thickness, fabric elasticity and fabric density; Based on the preset feature parameter correction rules, the thickness correction coefficient for fabric thickness deviation, the elasticity correction coefficient for fabric elasticity deviation, and the density correction coefficient for fabric density deviation are determined respectively. Based on various correction coefficients, the fabric thickness deviation, fabric elasticity deviation, and fabric density deviation are weighted and calculated to obtain the stitch quality feedback correction amount. The total tensor parameter correction is obtained by superimposing the correction amount of the line quality feedback with the fine-tuning amount corresponding to the historical qualified process record. The total correction amount of the tensor parameters is superimposed on the target tension parameter vector to obtain the corrected target tension parameter vector.

8. A line tension adaptive adjustment system, characterized in that, include: A line tension adaptive adjustment device for performing the method as described in any one of claims 1 to 7 to generate line tension control commands; The thread tension actuator is communicatively connected to the thread tension adaptive adjustment device and is used to adjust the thread tension of the target suture according to the thread tension control command.

9. An electronic device, characterized in that, include: The memory is used to store computer programs; A processor for executing a computer program stored in the memory to cause the electronic device to perform the method of 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 a processor, it implements the method of any one of claims 1 to 7.