Healthcare elastic cloth conveying control method and system for visual deformation detection

Abstract

The application provides a health care elastic cloth conveying control method and system for visual deformation detection, and relates to the technical field of conveying control. The method comprises the following steps: acquiring an original cloth surface image frame through a visual detection unit; comparing and analyzing the displacement of a cloth surface feature point according to the image frame sequence of the original cloth surface image frame; partitioning and evaluating the cloth surface based on a cloth surface disturbance atlas; constructing a control instruction combination based on deformation levels; executing the control instruction combination and starting a conveying device to adjust and convey the cloth. Through the application, the technical problem that the existing technology lacks real-time visual detection and intelligent control mechanism based on deformation feedback, which leads to the inability to timely identify and respond to the instantaneous deformation and stress changes of the cloth during the conveying process, can be solved, and the technical effects of improving the cloth conveying accuracy, reducing the risk of wrinkles and stretching, improving the reliability and intelligent level of the automatic processing of flexible cloth can be achieved.

Description

Technical Field

[0001] This application relates to the field of conveying control technology, and in particular to a method and system for conveying and controlling health care elastic fabric using visual deformation detection. Background Technology

[0002] In modern textile manufacturing, garment processing, and functional fabric treatment, automated fabric conveying has become an important technological means to improve production line efficiency, reduce labor costs, and ensure product quality. Especially in the processing of materials that are sensitive to deformation, such as elastic fabrics and health care fabrics, ensuring the tension stability, deformation controllability, and consistency of the conveying path during the fabric conveying process is a key factor determining the final product's forming effect and comfort performance.

[0003] Currently, existing conveying systems generally lack real-time visual detection and intelligent sensing mechanisms, making it impossible to accurately identify issues such as instantaneous displacement, wrinkles, stretching, or localized slippage of the fabric during the conveying process. This is especially problematic when dealing with white, highly elastic fabrics without obvious patterns or textures, often resulting in blind spots and accumulated conveying errors. Secondly, existing tension control methods are mostly based on directional tensioners or preset pressure rollers, rather than dynamically adjusting based on feedback from the actual stress state of the fabric. When dealing with elastic fabrics that deform drastically under external forces, this can easily lead to situations such as conveying too tightly, too loosely, or misalignment.

[0004] In summary, existing technologies suffer from the technical problem of failing to promptly identify and respond to instantaneous deformation and stress changes of fabric during the conveying process due to the lack of real-time visual detection and deformation feedback-based intelligent control mechanisms. This further affects the stability of the fabric conveying process, the consistency of finished product quality, and the operating efficiency of the automated system. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for controlling the conveying of health elastic fabric based on visual deformation detection, in order to solve the technical problem in the prior art that the lack of real-time visual detection and intelligent control mechanism based on deformation feedback leads to the inability to timely identify and respond to the instantaneous deformation and stress changes of the fabric during the conveying process, which further affects the stability of the fabric conveying process, the consistency of finished product quality and the operating efficiency of the automation system.

[0006] In view of the above problems, this application provides a method and system for controlling the delivery of health care elastic fabric by visual deformation detection.

[0007] In a first aspect, this application provides a method for controlling the conveying of health-care elastic fabric using visual deformation detection, implemented through a control system for conveying health-care elastic fabric using visual deformation detection. The method includes: acquiring original fabric surface image frames through a visual detection unit; analyzing the displacement of fabric surface feature points by comparing the image frame sequence of the original fabric surface image frames to form a fabric surface disturbance map; evaluating the fabric surface by partitioning it based on the fabric surface disturbance map to establish deformation levels; constructing a combination of control commands based on the deformation levels; executing the combination of control commands and starting the conveying device to adjust and convey the fabric.

[0008] Preferably, the method for controlling the transport of health-care elastic fabric with visual deformation detection further includes: configuring a visual detection unit to cover the transport path; constructing a mapping relationship between the detection coordinates of the visual detection unit and the coordinates of the transport path; and activating the visual detection unit to acquire the original fabric image frame based on the mapping relationship.

[0009] Preferably, the method for controlling the delivery of health elastic fabric with visual deformation detection further includes: extracting feature information of texture distribution, edge lines and reference patterns from the original fabric image frame; calculating the displacement vector of fabric feature points based on the image sequence differences of the feature information; and integrating the displacement vectors to obtain the fabric perturbation map.

[0010] Preferably, the method for controlling the delivery of health elastic fabric with visual deformation detection further includes: dividing the fabric image area into triangular mesh units according to the feature information; statistically analyzing the mesh changes of displacement vectors within the triangular mesh units using the fabric perturbation map; and obtaining the deformation level based on the mesh changes.

[0011] Preferably, the method for controlling the delivery of health elastic fabric with visual deformation detection further includes: calculating the mesh angle based on the corresponding mesh of the triangular mesh unit to obtain the original shear angle value; tracking the displacement change of the feature information in the image sequence through feature point matching to obtain the updated coordinate position; recalculating the mesh angle of the triangular mesh unit according to the updated coordinate position to obtain the deformed shear angle value; comparing the deformed shear angle value with the corresponding original shear angle value to obtain the shear angle change; introducing a mapping relationship between the shear angle change and the degree of shear deformation, and locating the deformation level according to the shear angle change in the mapping relationship.

[0012] Preferably, the method for controlling the delivery of health elastic fabric using visual deformation detection further includes: introducing a fuzzy controller to construct a mapping model between deformation level and control action; dynamically adjusting the control action based on the deformation level and the mapping model; and calling the delivery device based on the control action to form the control command combination.

[0013] Preferably, the method for controlling the delivery of health elastic fabric with visual deformation detection further includes: detecting abnormal growth trends in the fabric surface disturbance map; and triggering a protection response when the abnormal disturbance in a continuous area of ​​the abnormal growth trend exceeds the tolerance.

[0014] Preferably, the method for controlling the delivery of health elastic fabric by visual deformation detection further includes: determining the disturbance gradient within the delivery path and implementing a slow start-stop strategy for the delivery speed; and coordinating and matching the delivery speed, tension distribution, and adsorption control results to generate an integrated delivery control for the delivery device.

[0015] Preferably, the method for controlling the delivery of health elastic fabric with visual deformation detection further includes: using the deformation level as an input signal for rhythm control; performing feedback sampling on the delivery state of the adjusted delivery; comparing the feedback information with the deformation level of the previous control cycle to determine whether the adjustment is stable; if the adjustment is unstable, adjusting the control parameters of the rhythm control until the adjustment is stable.

[0016] Secondly, this application also provides a visual deformation detection-based health elastic fabric conveying control system for executing a visual deformation detection-based health elastic fabric conveying control method as described in the first aspect, comprising: an image frame acquisition module for acquiring original fabric surface image frames through a visual detection unit; a fabric surface disturbance map formation module for analyzing the displacement of fabric surface feature points by comparing the image frame sequence of the original fabric surface image frames to form a fabric surface disturbance map; a deformation level establishment module for performing partitioned evaluation of the fabric surface based on the fabric surface disturbance map to establish a deformation level; a control command combination construction module for constructing a control command combination based on the deformation level; and an adjustment and conveying module for executing the control command combination and starting the conveying device to adjust and convey the fabric.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goal of dynamic conveying adjustment and rhythm control based on fabric disturbance spectrum and deformation level assessment, it achieves the technical effects of improving fabric conveying accuracy, reducing the risk of wrinkles and stretching, and improving the reliability and intelligence level of automated processing of flexible fabrics.

[0018] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a method for controlling the delivery of health care elastic fabric using visual deformation detection, as described in this application.

[0021] Figure 2 This is a schematic diagram of the structure of a visual deformation detection-based health care elastic fabric delivery control system according to this application.

[0022] Figure labeling: Image frame acquisition module 11, fabric disturbance pattern formation module 12, deformation level establishment module 13, control command combination construction module 14, adjustment and conveying module 15. Detailed Implementation

[0023] This application provides a visual deformation detection-based control method and system for conveying elastic fabric for health care products. It solves the technical problem in existing technologies where the lack of real-time visual detection and deformation feedback-based intelligent control mechanisms leads to the inability to promptly identify and respond to instantaneous deformation and stress changes in the fabric during conveying, further affecting the stability of the fabric conveying process, the consistency of finished product quality, and the operational efficiency of the automated system. The method achieves the technical goal of dynamic conveying adjustment and rhythm control based on fabric surface disturbance patterns and deformation level assessment, thereby improving fabric conveying accuracy, reducing the risk of wrinkles and stretching, and enhancing the reliability and intelligence level of automated processing of flexible fabrics.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a visual deformation detection-based control method for conveying elastic fabric for healthcare products, applied to a visual deformation detection-based control system for conveying elastic fabric for healthcare products, specifically including the following steps:

[0026] S1: Obtain the original fabric image frame through the visual detection unit.

[0027] Specifically, a vision inspection device mounted on the conveyor path is used to acquire images of the surface of the continuously moving elastic fabric. The vision inspection unit is an electronic device that converts optical information into digital images, typically including a lens, image sensor, processing chip, and data interface. Its function is to capture the fabric surface state in a non-contact manner. Raw fabric image frames refer to the initial image data before processing or analysis, usually recorded frame-by-frame as the fabric surface moves, including information such as texture, pattern, creases, or deformation.

[0028] S2: Based on the image frame sequence comparison analysis of the original fabric image frame, the displacement of fabric feature points is analyzed to form a fabric perturbation map.

[0029] Specifically, by utilizing multiple frames of fabric images acquired continuously over time, image processing algorithms are used to extract and track the positional changes of representative fabric feature points, thereby constructing a visual map reflecting the overall dynamic deformation of the fabric. An image frame sequence refers to a series of images captured sequentially during fabric transport; for example, capturing 30 frames per second and recording continuously for 5 seconds results in a 150-frame image sequence. Feature points are local areas on the fabric with stable identifiable characteristics, such as pattern intersections, line crossings, or texture abrupt changes, which can be consistently identified across multiple frames. Displacement refers to the coordinate change of a feature point between different frames, typically measured in pixels. If a feature point moves 5 pixels from the first to the fifth frame, it indicates a quantifiable physical disturbance. Integrating the displacement data of all feature points throughout the sequence in both spatial and temporal dimensions creates a fabric perturbation map.

[0030] S3: Based on the fabric perturbation map, the fabric surface is evaluated by region, and the deformation level is established.

[0031] Specifically, using a fabric perturbation map, the entire fabric area is divided into several small blocks or sub-regions, and quantitative calculations are performed on each to classify different levels of deformation. The fabric perturbation map records the intensity and direction information of the displacement of characteristic points in each region. Therefore, the fabric surface can be divided according to spatial location, and the displacement vectors in each region can be statistically analyzed to calculate the average or maximum displacement value, which serves as an indicator of the perturbation intensity of that region. Subsequently, the perturbation intensity is mapped to a predefined level standard. The evaluation process can not only identify areas of significant local deformation but also recognize the overall deformation trend.

[0032] S4: Construct a combination of control commands based on the deformation level.

[0033] Specifically, based on the deformation levels of different areas of the fabric, operational instructions are designed and generated for varying degrees of deformation. These instructions are used to adjust the operating status of the conveying equipment to achieve precise control of the fabric. The deformation level reflects the degree of deformation of the fabric, either locally or overall; a higher level indicates more severe deformation. Therefore, control instructions need to adopt differentiated measures for different levels, such as adjusting parameters like conveying speed, tension, and suction strength. The combination of control instructions integrates specific adjustment actions into a complete execution plan according to certain logic or priority, enabling the equipment to respond synchronously to the fabric's deformation status and achieve dynamic optimization and real-time adjustment of the fabric conveying state.

[0034] S5: Execute the control command combination and start the conveying device to adjust and convey the fabric.

[0035] Specifically, based on a pre-built set of control commands, the operating status of the conveying equipment is controlled to achieve effective adjustment and transport of the fabric. The control command set includes specific operating procedures tailored to different deformation levels of the fabric, covering the coordinated control of various parameters such as conveying speed, tension adjustment, and suction strength. Starting the conveyor means that the conveying machinery, such as conveyor belts, rollers, or motor systems, operates according to the requirements of the command set, ensuring that the fabric maintains appropriate tension and position during transport, preventing excessive deformation or fabric slippage. As the control commands are executed, the conveying device dynamically adjusts according to the fabric's condition, ensuring stable and uniform movement of the fabric throughout the transport path, thereby improving transport quality and production efficiency.

[0036] Furthermore, this application also includes: configuring the visual inspection unit to cover the transport path; constructing a mapping relationship between the detection coordinates of the visual inspection unit and the coordinates of the transport path; and starting the visual inspection unit to acquire the original fabric image frame based on the mapping relationship.

[0037] Specifically, a vision inspection unit is configured to cover the conveyor path, and image acquisition cameras are installed around the perimeter of the fabric conveyor channel. The vision inspection unit is an industrial camera with its lens facing the fabric surface, ensuring that its field of view completely covers the width and length of the fabric's movement area. The function of the vision inspection unit is to acquire real-time image information of the fabric surface for subsequent image analysis and fabric condition assessment. Coverage not only requires full physical coverage of the fabric surface but also sufficient pixel resolution to identify fine textures, lines, or patterns on the fabric surface.

[0038] Next, to ensure that the visual inspection data accurately reflects the fabric's positional changes along the conveyor path, a mapping relationship is established between the detection coordinates of the visual inspection unit and the coordinates of the conveyor path. Detection coordinates are the two-dimensional positions of pixels in the image; conveyor path coordinates are the positional coordinates in actual physical space. The mapping relationship is established using calibration techniques, such as setting markers of known size and position on the fabric surface. By photographing these markers and analyzing their projection positions in the image, the transformation matrix between image coordinates and actual coordinates can be derived, which is used for subsequent spatial position analysis of the image data.

[0039] Based on the mapping relationship, the vision detection unit is activated before the fabric begins to be fed to acquire images and extract the original fabric image frames. The original fabric image frames are static image sections in the video stream, representing the complete image information of the fabric surface at a given moment. The original fabric image frames contain visual features such as fabric texture, patterns, and edge lines, which are used in subsequent deformation analysis to identify local changes in the fabric, such as stretching, wrinkling, or slippage.

[0040] Furthermore, this application also includes: extracting feature information of texture distribution, edge lines and reference patterns from the original fabric image frame; calculating displacement vectors of fabric feature points based on the image sequence differences of the feature information; and integrating the displacement vectors to obtain the fabric perturbation map.

[0041] Specifically, the textural distribution, edge lines, and reference pattern features are extracted from the original fabric image frames. After acquiring the fabric image, image processing algorithms are used to analyze the identifiable details on the fabric surface. Texture distribution refers to the variation patterns in color, brightness, or pattern density in different areas of the fabric surface. For example, some areas may be smoother, while others may have densely packed patterns. Edge lines refer to the boundaries in the image that represent strong brightness or color transitions, usually corresponding to folds, hems, or seams on the fabric. Reference patterns refer to distinctive patterns on the fabric surface with known shapes and arrangements, such as trademarks, checkered lines, or sewing alignment marks.

[0042] Next, the displacement vector of the fabric feature points is calculated based on the image sequence differences of feature information. This means comparing multiple consecutively acquired images to observe the positional changes of feature points in the images at different times. Feature points are pixels on the fabric that are easily identified and tracked, such as the intersection of a grid or the corner of a broken line. Image sequence differences refer to the differences in positional information of the same features between adjacent image frames. Converting the image sequence differences into displacement vectors represents the movement path of the feature point from one frame to the next during the fabric conveying process.

[0043] Then, the displacement vectors are integrated to obtain the fabric perturbation map, which represents the summarization and spatial distribution visualization of the displacement results of multiple feature points in consecutive image frames, forming a comprehensive map reflecting the local dynamic changes of the entire fabric surface. The perturbation map is a spatial information structure that shows the non-uniform displacement of the fabric surface during the process of temporal change.

[0044] Furthermore, this application also includes: dividing the fabric image region into triangular mesh units based on the feature information; statistically analyzing the mesh changes of displacement vectors within the triangular mesh units using the fabric perturbation map; and obtaining the deformation level based on the mesh changes.

[0045] Specifically, the fabric image region is divided into triangular mesh units based on feature information. The fabric surface is regularly segmented using feature points in the image, dividing the entire image into multiple triangular regions composed of three points. Feature information includes texture, edge lines, and reference patterns, which are used to locate key points in the image; by connecting feature points, a stable triangular mesh structure can be constructed.

[0046] By statistically analyzing the displacement vectors within triangular mesh cells using fabric perturbation maps, the displacement vector of each feature point in the fabric perturbation map is mapped to the corresponding triangular mesh, and this is used to determine whether the triangle has undergone deformation. Mesh change refers to whether the shape, area, or angle of the triangle changes due to fabric deformation; for example, an originally equilateral triangle becomes elongated due to stretching. A ensemble analysis is performed on the displacement vectors of the three vertices of each triangle to determine the relative changes, and from this, the overall geometric deformation of the mesh is deduced.

[0047] Deformation levels are obtained through mesh variation analysis. The degree of deformation of each mesh is quantitatively assessed and classified according to established standards to determine the severity of fabric deformation in that area. Deformation levels can be divided into multiple tiers, such as slight, moderate, and severe, based on criteria such as angle change, percentage area change, and side length ratio. A mapping model is introduced to map the changes to a specific level label. For example, if the internal angle of a triangle changes by more than 15 degrees and the area increases or decreases by more than 20%, it can be considered severe deformation; if the change is within 5%, it can be considered normal fluctuation. The levels of multiple meshes can be combined to form an overall fabric deformation distribution map.

[0048] Furthermore, this application also includes: calculating the mesh angle based on the co-located meshes of the triangular mesh unit to obtain the original shear angle value; tracking the displacement change of the feature information in the image sequence through feature point matching to obtain the updated coordinate position; recalculating the mesh angle for the triangular mesh unit according to the updated coordinate position to obtain the deformed shear angle value; comparing the deformed shear angle value with the corresponding original shear angle value to obtain the shear angle change; introducing a mapping relationship between the shear angle change and the degree of shear deformation, and locating the deformation level according to the shear angle change in the mapping relationship.

[0049] Specifically, the mesh angle is calculated based on the co-located meshes of triangular mesh units to obtain the original shear angle value. In the initial state where the fabric image has not undergone significant deformation, the angle within each triangular mesh unit is calculated to establish a stable geometric reference. A co-located mesh refers to a mesh structure in the fabric image that corresponds to the same spatial position in different image frames, facilitating subsequent comparative analysis. Angle calculation is mainly used to identify the angle formed between any two sides inside a triangle; the initial value of the angle constitutes the original shear angle value. The shear angle can reflect the potential tendency of the material to twist or shear in a local area.

[0050] By tracking the displacement changes of feature information in an image sequence through feature point matching, updated coordinate positions are obtained. Image processing algorithms are used to identify and track identical feature points in the image sequence to obtain their motion trajectories over time. Feature points can be texture intersections, edge corners, or artificially marked points on the fabric surface, and stable matching is performed using algorithms such as SIFT or ORB. When the fabric is subjected to external forces such as stretching or twisting, the positions of feature points in subsequent image frames will shift, and their updated coordinates can be obtained by tracking them.

[0051] For triangular mesh elements, the mesh angles are recalculated based on the updated coordinate positions to obtain the deformation shear angle value. This involves substituting the updated feature point coordinates from the image sequence back into the original triangular mesh structure and recalculating each angle to obtain the angle value after the fabric deformation. Since the side lengths and angles of the triangles change after the feature points are displaced, the newly calculated angles are the deformation shear angle values. For example, an angle initially 60 degrees becomes 72 degrees after the feature point moves, clearly indicating that shear expansion has occurred at that location.

[0052] By comparing the deformed shear angle value with the corresponding original shear angle value, the change in shear angle is obtained. This involves calculating the difference between the deformed shear angle value at each triangular node and the initial original shear angle value to obtain the specific numerical value of the angle change, i.e., the change in shear angle, which reflects the degree of shear strain occurring in the fabric within a local mesh. For example, if an angle changes from the original 60 degrees to 72 degrees, the change in shear angle is 12 degrees. If this change approaches or exceeds a certain threshold in multiple meshes, it indicates that the fabric surface is in a high-strain state.

[0053] A mapping relationship between shear angle change and shear deformation degree is introduced. Based on the shear angle change within this mapping relationship, the deformation level is determined. This involves matching the calculated shear angle change with a pre-established shear deformation model to determine which deformation level the change corresponds to. The mapping relationship can be derived from extensive experimental data or finite element simulation. Multiple boundary intervals are set to classify slight, moderate, and severe deformation. For example, a change of 0 to 5 degrees is defined as normal, 5 to 10 degrees as moderate, and more than 10 degrees as severe.

[0054] Furthermore, this application also includes: introducing a fuzzy controller to construct a mapping model between deformation level and control action; dynamically adjusting the control action according to the deformation level and in conjunction with the mapping model; and calling the conveying device based on the control action to form the control command combination.

[0055] Specifically, fuzzy logic technology is used to establish a nonlinear response relationship between the degree of fabric deformation and the corresponding equipment control strategy. A fuzzy controller is a control system capable of handling uncertainty and fuzzy information, mapping continuous input variables to appropriate control outputs through fuzzy rules and membership functions. The deformation level is the severity of local fabric deformation calculated through methods such as shear angle changes, while the control action refers to the specific behavior of adjusting the conveying system, tensioning components, or adjustment mechanisms, such as deceleration, pausing, or changing tension. The mapping model expresses the relationship between the deformation level and the specific control response in the form of a rule base. For example, when the deformation level is slight, the control action is to fine-tune the tension; when the level is severe, the control action is to pause the conveying.

[0056] After detecting varying degrees of deformation in the fabric, the system searches the mapping model in real time for the control rules corresponding to the current level and immediately adjusts the relevant actions during the conveying process. Dynamic adjustment emphasizes real-time performance and adaptability; that is, the control system automatically updates the adjustment method based on changes in the fabric's condition. This avoids delays or errors caused by fixed parameter settings and improves the accuracy of handling flexible materials. For example, when the deformation level in a localized area of ​​the fabric changes from moderate to severe, the system immediately switches to a deceleration and tension increase control action to slow the expansion of deformation.

[0057] Based on the adjusted control actions, specific executable instructions are generated and the operation is completed by calling the control unit of the conveyor device through an interface. The instruction combination may contain multiple parallel or continuous control instructions, such as simultaneously decelerating the conveyor belt, adjusting the guide roller angle, and activating the tensioning mechanism, thereby achieving multi-dimensional linkage control. The control instruction combination is a logically ordered set of low-level commands and is the key link in converting fuzzy control output results into specific execution actions.

[0058] Furthermore, this application also includes: detecting abnormal growth trends in the fabric disturbance map; and triggering a protection response when the abnormal disturbance in a continuous region of the abnormal growth trend exceeds the tolerance limit.

[0059] Specifically, by analyzing fabric perturbation maps calculated from multiple image frames, patterns of abnormal changes in fabric perturbation intensity over time or space are identified. A fabric perturbation map is a data image formed by statistically analyzing and visualizing the displacement vectors of feature points on the fabric surface, used to reflect the dynamic changes of the fabric as a whole or in a localized area. An abnormal growth trend indicates a rapid increase in the degree of perturbation within a certain range, possibly caused by problems such as fabric slippage, entanglement, or excessive stretching. For example, if the displacement amplitude of a feature point in a certain area increases from 2 mm to 15 mm within 5 seconds, it may be judged as an abnormal growth trend.

[0060] When abnormal growth on the fabric surface is detected not only occurring at certain points but also exhibiting a continuous spatial distribution, and its intensity exceeds a pre-set threshold range, the protection mechanism will be automatically activated. A continuous area refers to multiple adjacent grid cells or image pixel blocks exhibiting similar abnormal disturbances, rather than sporadic or isolated abnormal points. The tolerance for abnormal disturbances is a numerical boundary set based on the fabric material, tensile tolerance, and equipment performance, used to distinguish between acceptable disturbances and unacceptable deformations. Once the disturbance value in a continuous area, such as 10 consecutive grid cells displacing more than 10 mm and lasting for more than 3 seconds, is judged to have exceeded the tolerance, immediately triggering a protection response, such as shutdown, alarm, or reversal of the conveyor path.

[0061] Because changes in fabric surface disturbances are typically diffuse, failure to promptly identify abnormal trends in continuous areas can easily lead to wrinkles or damage to the entire fabric roll. Therefore, after detecting an abnormal growth trend, the system also needs to determine whether it has reached a trigger threshold. Timely activation of the protection response is a core element of system safety control, preventing equipment damage and material waste.

[0062] Furthermore, this application also includes: determining the disturbance gradient within the conveying path and executing a slow start-stop strategy for the conveying speed; and coordinating and matching the conveying speed, tension distribution, and adsorption control results to generate an integrated conveying control for the conveying device.

[0063] Specifically, spatial analysis is performed on the changes in disturbance intensity at different locations during fabric conveying to identify its trend along the path. The disturbance gradient represents the magnitude of increase or decrease in disturbance intensity in space. For example, if the displacement vector of the fabric surface gradually increases from 2 mm to 10 mm from the starting end to the ending end, the gradient value reflects the spatial rate of this increase. If the disturbance gradient within the path is too large, it means that uneven deformation or force field fluctuations may occur in certain areas, requiring flexible control measures.

[0064] Based on the changing trend of the disturbance gradient, the impact on the fabric surface is reduced by smoothly adjusting the conveyor speed when the fabric starts, stops, or adjusts its speed midway. Slow start-stop control can be achieved through linear or curved acceleration and deceleration curves. For example, when the equipment starts, the speed is slowly increased from 0 to 300 mm / s, and then gradually reduced to 0 when stopping, to avoid fabric shaking or deviation caused by instantaneous speed changes.

[0065] Coordinating the conveying speed, tension distribution, and adsorption control results refers to comprehensively coordinating the conveying speed (the speed at which the fabric moves), tension distribution (the balance of force on the fabric throughout its path), and adsorption control results (the intensity and range of the vacuum or electrostatic adsorption device) to achieve the optimal control strategy. Coordinating the matching emphasizes the interconnected response between variables. For example, when the fabric is taut, the conveying speed is reduced while the adsorption intensity is increased to prevent fabric drift; conversely, when the fabric is slack, the speed is appropriately increased and the adsorption intensity is reduced to prevent excessive resistance. The matching results of these three factors are translated into specific control commands and executed uniformly, forming a comprehensive scheduling mechanism that ensures the fabric maintains a stable conveying state under different conditions. Integrated conveying control integrates dispersed adjustment parameters into a unified execution scheme. For example, the start-stop process, tension feedback, and adsorption intensity are integrated into a single control curve, which is sent to the conveying motor and adsorption system via a PLC or motion controller.

[0066] Furthermore, this application also includes: using the deformation level as an input signal for rhythm control; performing feedback sampling on the conveying state of the regulated conveying; comparing the feedback information with the deformation level of the previous control cycle to determine whether the regulation is stable; if the regulation is unstable, adjusting the control parameters of the rhythm control until the regulation is stable.

[0067] Specifically, the detected fabric deformation level is used as the basis for adjusting the rhythm of the subsequent control system. Deformation level is a numerical or graded classification based on the degree of fabric deformation; for example, level 0 represents no significant deformation, level 1 represents slight stretching, level 2 represents moderate wrinkling, and level 3 and above represent severe twisting. Rhythm control refers to the timing control method for operations such as speed changes, tension adjustments, and adsorption switching during the conveying process, used to achieve flexible rhythmic conveying. After the conveying adjustment is executed, the actual movement state of the fabric is collected in real time through sensors or vision units, including real-time conveying speed, local tension distribution, and deformation values, as system feedback. Feedback sampling is used to determine whether the control effect meets expectations. For example, if the target is no deformation, and the sampling data still shows level 2 deformation, it indicates that the adjustment has not achieved the target. The feedback information is compared with the deformation level of the previous control cycle. The feedback data obtained in the current cycle is compared with the fabric deformation level of the previous control cycle to determine whether the adjustment has stabilized. If the changes in deformation level between two consecutive cycles are less than a certain threshold, such as two consecutive cycles with deformation levels of level 1 or fluctuating within ±0.5 levels, the adjustment can be considered to be stabilizing. If the difference is large, it is considered that there are still unstable factors. When it is found that the continuous feedback data changes with large fluctuations, the rhythm control parameters, such as response rate, beat cycle, and start-stop slope, will be readjusted to gradually optimize the control process until the fabric state stabilizes at the desired deformation level. For example, the initially set rhythm response cycle is 100 milliseconds, which is then extended to 200 milliseconds, or the acceleration is reduced from 400 mm / s to 300 mm / s to improve the stability of the fabric. Table 1 shows a partial record of the most recent rhythm control feedback adjustment process.

[0068] Table 1: Partial Records of the Most Recent Rhythm Control Feedback Adjustment Process

[0069]

[0070] In summary, the visual deformation detection-based health elastic fabric conveying control method provided in this application has the following technical effects: by achieving the technical goal of dynamic conveying adjustment and rhythm control based on fabric surface disturbance spectrum and deformation level assessment, it achieves the technical effects of improving fabric conveying accuracy, reducing the risk of wrinkles and stretching, and improving the reliability and intelligence level of automated processing of flexible fabrics.

[0071] Example 2: Based on the same inventive concept as the visual deformation detection-based elastic fabric conveying control method in the foregoing examples, this application also provides a visual deformation detection-based elastic fabric conveying control system. Please refer to the appendix. Figure 2The system includes: an image frame acquisition module 11, used to acquire original fabric image frames through a visual detection unit; a fabric disturbance map formation module 12, used to analyze the displacement of fabric feature points by comparing the image frame sequence of the original fabric image frames to form a fabric disturbance map; a deformation level establishment module 13, used to perform partitioned evaluation of the fabric based on the fabric disturbance map to establish a deformation level; a control command combination construction module 14, used to construct a control command combination based on the deformation level; and an adjustment and conveying module 15, used to execute the control command combination and start the conveying device to adjust and convey the fabric.

[0072] Furthermore, the aforementioned visual deformation detection-based health elastic fabric conveying control system is also used for: configuring a visual detection unit to cover the conveying path; constructing a mapping relationship between the detection coordinates of the visual detection unit and the coordinates of the conveying path; and activating the visual detection unit to acquire the original fabric image frame based on the mapping relationship.

[0073] Furthermore, the aforementioned visual deformation detection-based health elastic fabric conveying control system is also used for: extracting feature information of texture distribution, edge lines, and reference patterns from the original fabric image frame; calculating the displacement vector of fabric feature points based on the image sequence differences of the feature information; and integrating the displacement vectors to obtain the fabric perturbation map.

[0074] Furthermore, the aforementioned visual deformation detection-based elastic fabric conveying control system is also used to: divide the fabric image area into triangular mesh units based on the feature information; statistically analyze the mesh changes of displacement vectors within the triangular mesh units using the fabric disturbance map; and obtain the deformation level based on the mesh changes.

[0075] Furthermore, the aforementioned visual deformation detection-based elastic fabric conveying control system is also used for: calculating the mesh angle based on the corresponding mesh of the triangular mesh unit to obtain the original shear angle value; tracking the displacement change of the feature information in the image sequence through feature point matching to obtain the updated coordinate position; recalculating the mesh angle of the triangular mesh unit according to the updated coordinate position to obtain the deformed shear angle value; comparing the deformed shear angle value with the corresponding original shear angle value to obtain the shear angle change; introducing a mapping relationship between the shear angle change and the degree of shear deformation, and locating the deformation level according to the shear angle change in the mapping relationship.

[0076] Furthermore, the aforementioned visual deformation detection-based elastic fabric conveying control system is also used for: introducing a fuzzy controller to construct a mapping model between deformation level and control action; dynamically adjusting the control action according to the deformation level and in conjunction with the mapping model; and calling the conveying device based on the control action to form the control command combination.

[0077] Furthermore, the aforementioned visual deformation detection-based health elastic fabric conveying control system is also used to: detect abnormal growth trends in the fabric surface disturbance map; and trigger a protection response when the abnormal disturbance in a continuous area of ​​the abnormal growth trend exceeds the tolerance limit.

[0078] Furthermore, the aforementioned visual deformation detection-based health elastic fabric conveying control system is also used to: determine the disturbance gradient within the conveying path and execute a slow start-stop strategy for the conveying speed; and coordinate the conveying speed, tension distribution, and adsorption control results to generate an integrated conveying control for the conveying device.

[0079] Furthermore, the aforementioned visual deformation detection-based health elastic fabric conveying control system is also used to: use the deformation level as an input signal for rhythm control; perform feedback sampling on the conveying state of the adjusted conveying; compare the feedback information with the deformation level of the previous control cycle to determine whether the adjustment is stable; if the adjustment is unstable, adjust the control parameters of the rhythm control until the adjustment is stable.

[0080] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The visual deformation detection health elastic fabric conveying control method and specific examples in the aforementioned Embodiment 1 are also applicable to the visual deformation detection health elastic fabric conveying control system of this embodiment. Through the foregoing detailed description of the visual deformation detection health elastic fabric conveying control method, those skilled in the art can clearly understand the visual deformation detection health elastic fabric conveying control system of this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0081] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for controlling the delivery of health care elastic fabric using visual deformation detection, characterized in that, include: The original fabric image frame is obtained through a visual detection unit; Based on the image frame sequence comparison and analysis of the original fabric image frame, the displacement of fabric feature points is analyzed to form a fabric perturbation map, including: Extract feature information of texture distribution, edge lines, and reference patterns from the original fabric image frame; Calculate the displacement vector of fabric feature points based on the image sequence differences of the aforementioned feature information; The displacement vectors are integrated to obtain the fabric perturbation map; Based on the fabric perturbation map, the fabric surface is zoned for evaluation, and deformation levels are established, including: The fabric image region is divided into triangular mesh units based on feature information; The mesh angle is calculated based on the co-position mesh of the triangular mesh unit to obtain the original shear angle value; The displacement changes of the feature information in the image sequence are tracked by feature point matching to obtain the updated coordinate position; For the triangular mesh element, the mesh angle is recalculated based on the updated coordinate position to obtain the deformation shear angle value; By comparing the deformed shear angle value with the corresponding original shear angle value, the change in shear angle is obtained; A mapping relationship between the change in shear angle and the degree of shear deformation is introduced. Based on the location of the change in shear angle within the mapping relationship, the deformation level is obtained. Based on the deformation level, a combination of control commands is constructed, including: A fuzzy controller is introduced to construct a mapping model between deformation level and control action; The control action is dynamically adjusted based on the deformation level and the mapping model. Based on the control action, the conveying device is invoked to form the control command combination; Executing the control command combination and starting the conveying device to adjust and convey the fabric includes: The deformation level is used as the input signal for rhythm control; Feedback sampling is performed on the conveying status of the regulated conveying system; Compare the feedback information with the deformation level of the previous control cycle to determine whether the adjustment is stable; If the adjustment is unstable, adjust the control parameters of the rhythm control until the adjustment is stable.

2. The method for controlling the delivery of health care elastic fabric using visual deformation detection as described in claim 1, characterized in that, The original fabric image frame is obtained through a visual inspection unit, including: Configure a visual inspection unit to cover the conveying path; Construct a mapping relationship between the detection coordinates of the visual detection unit and the coordinates of the transport path; Based on the mapping relationship, the visual detection unit is activated to acquire the original fabric image frame.

3. The method for controlling the delivery of health care elastic fabric using visual deformation detection as described in claim 1, characterized in that, Based on the fabric perturbation map, the fabric surface is zoned for evaluation, and deformation levels are established, including: The fabric image region is divided into triangular mesh units based on the aforementioned feature information; The mesh changes of displacement vectors within the triangular mesh cells are statistically analyzed using the fabric perturbation map. The deformation level is obtained based on the mesh change analysis.

4. The method for controlling the delivery of health care elastic fabric based on visual deformation detection as described in claim 1, characterized in that, Executing the control command combination and starting the conveying device to adjust and convey the fabric includes: Detect abnormal growth trends in the fabric perturbation pattern; A protection response is triggered when the abnormal disturbance in a continuous region of the abnormal growth trend exceeds the tolerance limit.

5. The method for controlling the delivery of health care elastic fabric using visual deformation detection as described in claim 1, characterized in that, Executing the control command combination and starting the conveying device to adjust and convey the fabric further includes: Determine the disturbance gradient within the transport path and implement a gradual start-stop strategy for the transport speed. By coordinating and matching the conveying speed, tension distribution, and adsorption control results, an integrated conveying control for the conveying device is generated.

6. A visual deformation detection-based health care elastic fabric conveying control system, characterized in that, The steps for implementing the method for controlling the delivery of a health-care elastic fabric for visual deformation detection as described in any one of claims 1 to 5 include: The image frame acquisition module is used to acquire the original fabric image frame through the visual detection unit; The fabric perturbation map generation module is used to compare and analyze the displacement of fabric feature points based on the image frame sequence of the original fabric image frame to generate a fabric perturbation map. The deformation level establishment module is used to perform zonal evaluation of the fabric surface based on the fabric surface disturbance map and establish the deformation level. A control instruction combination construction module is used to construct control instruction combinations based on the deformation level; The regulating conveying module is used to execute the control command combination and start the conveying device to regulate and convey the fabric.

Images