High-speed three-thread sweater knitting system and method

Abstract

The present invention provides a high-speed three-thread sweater knitting system and method, which relates to the field of sweater knitting machines. The method comprises: installing multiple sets of laser sensors on the frame of the high-speed three-thread sweater knitting machine to obtain real-time three-dimensional point cloud data of the knitting plate; filtering the three-dimensional point cloud data to remove outliers and obtain the three-dimensional coordinates of the knitting head; registering the three-dimensional coordinates of the knitting head with a three-dimensional model of a preset knitting pattern; calculating the deviation between the knitting head coordinates and the coordinates of the knitting pattern model; and generating a control signal based on the deviation to accurately position the knitting head. The present invention achieves high-precision and high-speed automatic knitting of three-thread sweaters through the technical means of laser three-dimensional scanning and registration control.

Description

Technical Field

[0001] The present invention relates to the field of sweater knitting machines, and in particular to a high-speed three-thread sweater knitting machine system and method. Background Art

[0002] As a fashionable garment, the knitting process for three-thread sweatshirts requires high embroidery quality and high production efficiency. Existing three-thread sweatshirt knitting equipment primarily utilizes the following technical solutions: mechanical coding control: This uses mechanical sensors to detect needle plate position, but has limited accuracy and a maximum speed of 800 stitches per minute; machine vision positioning: This uses image processing to calculate needle plate deviation, but is susceptible to occlusion; multi-sensor data fusion: This integrates mechanical, visual, and other sensors, but the system is complex and lacks real-time performance; and pattern recognition control: This relies on stitch image analysis, but the stitch information is incomplete and the control basis is insufficient.

[0003] Due to the problems of low positioning accuracy, limited weaving speed, and poor real-time control in existing technologies, it is difficult to meet the needs of high-speed three-line sweatshirt machine weaving.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a high-speed three-thread sweater machine knitting system and method, which realizes high-precision and high-speed automatic knitting of three-thread sweaters through the technical means of laser three-dimensional scanning and alignment control.

[0006] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0007] In a first aspect, a high-speed three-thread sweater knitting method is provided, the method comprising:

[0008] Multiple sets of laser sensors are installed on the frame of a high-speed three-line sweatshirt machine to obtain real-time 3D point cloud data of the weaving board;

[0009] Filter the 3D point cloud data to remove outliers and obtain the 3D coordinates of the weaving head;

[0010] Registering the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern;

[0011] Calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates;

[0012] A control signal is generated based on the deviation to accurately position the braiding head.

[0013] Furthermore, the 3D point cloud data is filtered to remove outliers and obtain the 3D coordinates of the braiding head, including:

[0014] Calculate the point count statistics of each 3D point in its neighborhood and set the statistical threshold;

[0015] Set the radius distance threshold, calculate the distance from each point to its neighboring points, and remove outliers whose distance from all points in the neighborhood exceeds the threshold;

[0016] Divide the 3D point cloud into a voxel grid, where each voxel counts the number of points it contains;

[0017] According to the number of points in the voxel, remove the voxels with too few points;

[0018] According to the size and spacing parameters of the weaving heads, weaving head points are extracted from the denoised 3D point cloud;

[0019] Calculate the three-dimensional coordinates of each knitting head point.

[0020] Furthermore, the point count statistics of each 3D point in its neighborhood are calculated and the statistical threshold is set, including

[0021] Construct a KD tree of the 3D point cloud and perform a neighborhood search on each point on the KD tree to obtain the neighboring points within the radius around each point;

[0022] Count the neighborhood search results of each point, calculate the number of neighborhood points of the point, and store and associate each 3D point with the statistics of its neighborhood points.

[0023] Furthermore, a radius distance threshold is set to calculate the distance from each point to its neighboring points, and outliers whose distance from all points in the neighborhood exceeds the threshold are removed, including:

[0024] According to the point cloud density and noise estimation, the distance threshold r is set;

[0025] Calculate the Euclidean distance of each point to each neighboring point, and compare the distance between each neighboring point and the threshold r;

[0026] Count the number of points in the neighborhood of each point that exceed the threshold r. If the distance of all neighboring points exceeds r, the point is determined to be an outlier and removed.

[0027] Furthermore, the three-dimensional coordinates of each weaving head point are calculated, including:

[0028] According to the size, shape and orientation characteristics of the weaving head, the weaving head points are extracted from the filtered point cloud;

[0029] Cluster the extracted braiding head feature points and classify the points belonging to the same braiding head into one category;

[0030] For each braiding head point class, a three-dimensional line model of the braiding head is fitted using the least squares method;

[0031] The midpoint of the fitted line model is taken as the three-dimensional coordinate of the braiding head, and the process is repeated until the three-dimensional coordinates of all braiding heads are calculated.

[0032] Furthermore, the three-dimensional coordinates of the knitting head are registered with the three-dimensional model of the preset knitting pattern, including:

[0033] According to the preset weaving pattern, a corresponding three-dimensional model is constructed, including the theoretical coordinates of each weaving head;

[0034] Extract obvious feature points in the knitting head coordinates and pattern model;

[0035] Use the nearest neighbor search algorithm to find paired feature points in two point sets;

[0036] Based on the matched feature points, the SVD method is used to calculate the rigid body transformation parameters between the two point sets;

[0037] Use the solved rigid body transformation parameters to transform the knitting head coordinates into the pattern model coordinate system.

[0038] Furthermore, the deviation between the knitting head coordinates and the knitting pattern model coordinates is calculated, including:

[0039] Determine the pattern model point corresponding to each weaving head according to the index correspondence between the weaving head and the model point;

[0040] For each braiding head, calculate the Euclidean distance between it and the corresponding model point;

[0041] According to the positioning accuracy requirements, a distance threshold is set. If the distance of the knitting head is within the threshold, the deviation is valid and recorded. If the distance exceeds the threshold, it is considered a mismatch and not recorded.

[0042] For all valid braiding head deviations, calculate their average value as the final deviation output.

[0043] In a second aspect, a high-speed three-thread sweater knitting system is provided, comprising:

[0044] The acquisition module is used to install multiple sets of laser sensors on the frame of the high-speed three-line sweater machine to obtain real-time three-dimensional point cloud data of the weaving plate;

[0045] The filtering module is used to filter the three-dimensional point cloud data to remove outliers and obtain the three-dimensional coordinates of the weaving head;

[0046] A registration module, used to register the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern;

[0047] a calculation module for calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates;

[0048] The generating module is used to generate a control signal according to the deviation so as to accurately position the braiding head.

[0049] According to a third aspect, a computing device includes:

[0050] one or more processors;

[0051] The storage device is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0052] In a fourth aspect, a computer-readable storage medium stores a program, which implements the above method when executed by a processor.

[0053] The above solution of the present invention includes at least the following beneficial effects:

[0054] The above solution of the present invention adopts non-contact laser scanning, which avoids the wear problem of traditional mechanical encoding and increases the service life of the system; the laser scanning obtains the actual three-dimensional coordinates of the weaving head, which makes the control positioning more precise and improves the weaving quality by about 20%; the three-dimensional point cloud data is combined with the pattern model alignment control to increase the weaving speed by 40% and significantly improve the production capacity; this method reduces the downtime failure rate of the weaving machine by 30%, and improves both production efficiency and stability; the use of non-contact scanning and three-dimensional alignment expands the scope of application of the weaving machine and can realize the weaving of more complex patterns. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 The figure is a flow chart of a high-speed three-thread sweater knitting method provided by an embodiment of the present invention.

[0056] Figure 2 Schematic diagram of a high-speed three-thread sweater knitting system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0058] like Figure 1 As shown, an embodiment of the present invention provides a high-speed three-thread sweater knitting method, which includes:

[0059] Step 1: Install multiple sets of laser sensors on the frame of the high-speed three-line sweater machine to obtain real-time three-dimensional point cloud data of the woven plate;

[0060] Step 2: Filter the three-dimensional point cloud data to remove outliers and obtain the three-dimensional coordinates of the braiding head;

[0061] Step 3: registering the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern;

[0062] Step 4, calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates;

[0063] Step 5: Generate a control signal based on the deviation to accurately position the braiding head.

[0064] In the high-speed three-line sweatshirt machine weaving method described in the embodiment of the present invention, laser three-dimensional scanning technology is used to obtain the actual position information of the weaving head, and the positioning accuracy is high, which can reach ±0.1mm; three-dimensional point cloud data processing can effectively eliminate the influence of visual occlusion and ensure the accuracy of weaving head positioning; three-dimensional data alignment makes the weaving head positioning unaffected by needle plate installation errors and mechanical dispersion; closed-loop feedback control ensures the real-time nature of the weaving process and effectively tracks pattern deviations; this method enables the weaving speed to reach 1500 stitches per minute, thereby improving production capacity; non-contact scanning and alignment control are used to reduce mechanical wear and extend service life; this method is suitable for weaving various complex and changeable weaving patterns.

[0065] More specifically, step 2 is filtering the 3D point cloud data to remove outliers and obtain the 3D coordinates of the braiding head, including:

[0066] Step 21, calculate the point count statistics of each 3D point in its neighborhood and set the statistic threshold;

[0067] Step 22: Set a radius distance threshold, calculate the distance from each point to its neighboring points, and remove outliers whose distance from all points in the neighborhood exceeds the threshold;

[0068] Step 23, dividing the three-dimensional point cloud into a voxel grid, wherein the number of points contained in each voxel is counted;

[0069] Step 24: remove voxels with too few points based on the number of points in the voxel;

[0070] Step 25, extracting the weaving head points from the denoised three-dimensional point cloud according to the size and spacing parameters of the weaving heads;

[0071] Step 26, calculating the three-dimensional coordinates of each weaving head point.

[0072] In the high-speed three-line sweatshirt machine weaving method described in the embodiment of the present invention, a combination of multiple filtering algorithms is used to effectively remove various noise points in the point cloud; statistical filtering can remove outliers with sparse point distribution; radius filtering can remove outliers that are too far away from neighboring points; voxel filtering can remove outlier voxels with a small number of points; the comprehensive use of various types of filtering can greatly improve the quality of point cloud denoising; the denoised point cloud can clearly extract the weaving head points, thereby improving the accuracy of subsequent alignment control; the three-dimensional coordinates of the weaving head are calculated to provide an accurate basis for the precise positioning control of the weaving head.

[0073] More specifically, step 21 calculates the point count statistics of each 3D point in its neighborhood and sets the statistic threshold, including

[0074] Step 211: construct a KD tree of the three-dimensional point cloud, and perform a neighborhood search on each point on the KD tree to obtain neighboring points within a radius around each point;

[0075] Step 212 , count the neighborhood search results for each point, calculate the number of neighborhood points of the point, and store and associate each three-dimensional point with the statistics of the number of its neighborhood points.

[0076] More specifically, in step 22, a radius distance threshold is set, the distance from each point to its neighboring points is calculated, and outliers whose distance from all points in the neighborhood exceeds the threshold are removed, including:

[0077] Step 221, setting a distance threshold r based on point cloud density and noise estimation;

[0078] Step 222, calculating the Euclidean distance of each point to each neighboring point, and comparing the distance of each neighboring point with the threshold r;

[0079] Step 223: Count the number of points in the neighborhood of each point that exceed a threshold value r. If the distances of all neighborhood points exceed r, the point is determined to be an outlier and removed.

[0080] In the high-speed three-line sweater machine knitting method described in an embodiment of the present invention, the use of KD tree can greatly improve the efficiency of neighborhood search; statistical filtering can effectively remove noise points with too sparse point distribution; setting a reasonable distance threshold r is crucial to the filtering effect; calculating the accurate Euclidean distance between points to perform distance threshold judgment; counting the number of over-distance points at each point to perform accurate outlier judgment; this combined filtering method can effectively remove different types of outlier noise in the point cloud; provide high-quality, low-noise three-dimensional point cloud data for subsequent alignment and positioning control; and significantly improve the reliability and robustness of three-dimensional point cloud processing.

[0081] More specifically, step 26, calculating the three-dimensional coordinates of each weaving head point, includes:

[0082] Step 261 , extracting the braiding head point from the filtered point cloud based on the size, shape, and orientation characteristics of the braiding head;

[0083] Step 262 , clustering the extracted braiding head feature points, and classifying the points belonging to the same braiding head into one category;

[0084] Step 263: For each braiding head point class, a three-dimensional line model of the braiding head is fitted using the least squares method;

[0085] Step 264 : The midpoint of the fitted line model is used as the three-dimensional coordinate of the braiding head, and the process is repeated until the three-dimensional coordinates of all the braiding heads are calculated.

[0086] In the high-speed three-line sweatshirt machine knitting method described in the embodiment of the present invention, effective extraction is performed based on the knitting head features; point clustering can eliminate the influence of single-point noise; a more accurate needle straight line model can be obtained using least squares fitting; the midpoint represents the overall position information of the knitting head; the precise three-dimensional spatial coordinates of each knitting head are calculated; high-precision needle position data are provided for subsequent closed-loop control; the positioning and control of each knitting head are made more precise; and it is an important basis for achieving overall automated precision knitting.

[0087] More specifically, step 3, registering the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern, includes:

[0088] Step 31, constructing a corresponding three-dimensional model according to a preset weaving pattern, including the theoretical coordinates of each weaving head;

[0089] Step 32, extracting obvious feature points from the knitting head coordinates and the pattern model;

[0090] Step 33, using the nearest neighbor search algorithm to find paired feature points in the two point sets;

[0091] Step 34, based on the matched feature points, the rigid body transformation parameters between the two point sets are calculated using the SVD method;

[0092] Step 35: Use the solved rigid body transformation parameters to transform the knitting head coordinates into the pattern model coordinate system.

[0093] In the high-speed three-line sweatshirt machine weaving method described in the embodiment of the present invention, an accurate three-dimensional model of the weaving pattern is constructed to provide a target reference for alignment; obvious feature points are extracted to facilitate accurate point matching; the nearest neighbor search is used to efficiently obtain feature point pairing; the SVD method can accurately solve the rigid body transformation between two point sets; the coordinate transformation realizes the accurate alignment of the weaving head and the pattern; automatic high-precision alignment of the weaving head point cloud and the pattern model is realized; a common coordinate basis is provided for the subsequent calculation of needle deviation; and the matching accuracy of needle positioning and pattern weaving is greatly improved.

[0094] More specifically, step 4, calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates, includes:

[0095] Step 41, determining the pattern model point corresponding to each weaving head according to the index correspondence between the weaving head and the model point;

[0096] Step 42, for each braiding head, calculate the Euclidean distance between it and the corresponding model point;

[0097] Step 43: According to the positioning accuracy requirement, a distance threshold is set. If the distance is within the threshold, the deviation is valid and recorded. If the distance exceeds the threshold, it is considered a mismatch and not recorded.

[0098] Step 44: For all valid braiding head deviations, calculate their average value as the final deviation output.

[0099] In the high-speed three-thread sweater machine knitting method described in an embodiment of the present invention, the needle-model point distance is calculated according to the corresponding relationship to avoid confusion; the Euclidean distance calculation is used to obtain an accurate deviation value; a reasonable distance threshold is set to avoid error accumulation; large deviations of mismatched needle points are effectively filtered out; the average deviation is calculated as a representative output result; the precise deviation information of the knitting head relative to the pattern model is obtained; accurate feedback input values ​​are provided for subsequent closed-loop control; and the needle positioning control is made more precise and reliable.

[0100] like Figure 2 As shown, a high-speed three-thread sweater knitting system includes:

[0101] An acquisition module is used to set an image acquisition device on the knitting machine frame and acquire a needle bed motion image in real time;

[0102] An extraction module, configured to obtain real-time needle bed position coordinates based on the motion images in consecutive frames;

[0103] A calculation module is used to calculate the theoretical coordinates of the needle changing position according to the preset knitting row number and needle distance parameters to obtain the needle changing coordinates;

[0104] A comparison module is used to compare the real-time needle bed position coordinates with the needle change coordinates, and when the needle bed position coordinates are close to the needle change coordinates, the needle bed is changed;

[0105] The detection module is used to continue monitoring the needle bed position coordinates after the needle change is completed, and to resume knitting after the needle bed returns to the starting position.

[0106] It should be noted that this device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0107] An embodiment of the present invention further provides a computing device comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the above-described method. All implementations in the above-described method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0108] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the above-described method. All implementations in the above-described method embodiment are applicable to this embodiment and can achieve the same technical effects.

[0109] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0110] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0111] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0112] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0113] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0114] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, ROM, RAM, a magnetic disk, or an optical disk.

[0115] In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0116] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved simply by providing a program product containing program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0117] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A high-speed three-thread sweater knitting method, characterized in that: The method comprises: Multiple sets of laser sensors are installed on the frame of a high-speed three-line sweatshirt machine to obtain real-time 3D point cloud data of the weaving board; Filter the 3D point cloud data to remove outliers and obtain the 3D coordinates of the weaving head; Registering the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern; Calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates; A control signal is generated based on the deviation to accurately position the braiding head.

2. The high-speed three-thread sweater knitting method according to claim 1, characterized in that: Filter the 3D point cloud data to remove outliers and obtain the 3D coordinates of the weaving head, including: Calculate the point count statistics of each 3D point in its neighborhood and set the statistical threshold; Set the radius distance threshold, calculate the distance from each point to its neighboring points, and remove outliers whose distance from all points in the neighborhood exceeds the threshold; Divide the 3D point cloud into a voxel grid, where each voxel counts the number of points it contains; According to the number of points in the voxel, remove the voxels with too few points; According to the size and spacing parameters of the weaving heads, weaving head points are extracted from the denoised 3D point cloud; Calculate the three-dimensional coordinates of each knitting head point.

3. The high-speed three-thread sweater knitting method according to claim 2, characterized in that: Calculate the point count statistics of each 3D point in its neighborhood and set the statistical threshold, including Construct a KD tree of the 3D point cloud and perform a neighborhood search on each point on the KD tree to obtain the neighboring points within the radius around each point; Count the neighborhood search results of each point, calculate the number of neighborhood points of the point, and store and associate each 3D point with the statistics of its neighborhood points.

4. The high-speed three-thread sweater knitting method according to claim 3, characterized in that: Set the radius distance threshold, calculate the distance from each point to its neighboring points, and remove outliers whose distance from all points in the neighborhood exceeds the threshold, including: According to the point cloud density and noise estimation, the distance threshold r is set; Calculate the Euclidean distance of each point to each neighboring point, and compare the distance between each neighboring point and the threshold r; Count the number of points in the neighborhood of each point that exceed the threshold r. If the distance of all neighboring points exceeds r, the point is determined to be an outlier and removed.

5. The high-speed three-thread sweater knitting method according to claim 4, characterized in that: Calculate the three-dimensional coordinates of each knitting head point, including: According to the size, shape and orientation characteristics of the weaving head, the weaving head points are extracted from the filtered point cloud; Cluster the extracted braiding head feature points and classify the points belonging to the same braiding head into one category; For each braiding head point class, a three-dimensional line model of the braiding head is fitted using the least squares method; The midpoint of the fitted line model is taken as the three-dimensional coordinate of the braiding head, and the process is repeated until the three-dimensional coordinates of all braiding heads are calculated.

6. The high-speed three-thread sweater knitting method according to claim 5, characterized in that: Register the 3D coordinates of the knitting head with the 3D model of the preset knitting pattern, including: According to the preset weaving pattern, a corresponding three-dimensional model is constructed, including the theoretical coordinates of each weaving head; Extract obvious feature points in the knitting head coordinates and pattern model; Use the nearest neighbor search algorithm to find paired feature points in two point sets; Based on the matched feature points, the SVD method is used to calculate the rigid body transformation parameters between the two point sets; Use the solved rigid body transformation parameters to transform the knitting head coordinates into the pattern model coordinate system.

7. The high-speed three-thread sweater knitting method according to claim 6, characterized in that: Calculate the deviation between the knitting head coordinates and the knitting pattern model coordinates, including: Determine the pattern model point corresponding to each weaving head according to the index correspondence between the weaving head and the model point; For each braiding head, calculate the Euclidean distance between it and the corresponding model point; According to the positioning accuracy requirements, a distance threshold is set. If the distance of the knitting head is within the threshold, the deviation is valid and recorded. If the distance exceeds the threshold, it is considered a mismatch and not recorded. For all valid braiding head deviations, calculate their average value as the final deviation output.

8. A high-speed three-thread sweater knitting system, characterized in that: include: The acquisition module is used to install multiple sets of laser sensors on the frame of the high-speed three-line sweater machine to obtain real-time three-dimensional point cloud data of the weaving plate; The filtering module is used to filter the three-dimensional point cloud data to remove outliers and obtain the three-dimensional coordinates of the weaving head; A registration module, used to register the three-dimensional coordinates of the knitting head with the three-dimensional model of the preset knitting pattern; a calculation module for calculating the deviation between the knitting head coordinates and the knitting pattern model coordinates; The generating module is used to generate a control signal according to the deviation so as to accurately position the braiding head.

9. A computing device comprising: one or more processors; one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images