A method for operating a carbon fiber warp knitting machine based on the Internet of Things

Abstract

The present invention relates to the field of warp knitting machine control technology, and in particular to a carbon fiber warp knitting machine operation method based on the Internet of Things, including determining the weaving control state of the warp knitting machine, determining the initial weaving speed and matching the pulling speed accordingly; determining the central area and edge area of ​​the woven fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density; determining the movement trajectory of the warp knitting needle and the sinker during the weaving process to determine the equipment characterization state of the warp knitting machine; determining whether the warp knitting machine obtains the surface image of the woven fabric according to the equipment characterization state; obtaining the surface image of the woven fabric at each preset time node to determine the density characterization trend of the woven fabric; determining the operation characterization trend according to the density characterization trend to determine whether to adjust the initial weaving speed; and determining the operation characterization trend twice according to the center flattening state and the fabric edge state to determine whether to adjust the pulling speed. In order to realize the linkage between monitoring equipment, woven fabric quality control and optimization of various links in the production process.

Description

Technical Field

[0001] The present invention relates to the technical field of warp knitting machine control, and in particular to an operation method of a carbon fiber warp knitting machine based on the Internet of Things. Background Art

[0002] With the widespread application of carbon fiber in many fields such as aerospace, automotive industry, and high-end sports equipment, extremely high requirements are placed on the quality and production efficiency of woven fabrics produced by carbon fiber warp knitting machines; the operation and management of traditional carbon fiber warp knitting machines mostly rely on manual experience and regular inspections, which have many limitations.

[0003] During the weaving process, the characteristics of carbon fiber raw materials (such as raw material diameter) and target fabric density and other factors have a complex impact on the setting of process parameters such as weaving speed and pulling speed, but there is a lack of accurate and real-time determination methods. At the same time, the operating status of key components inside the warp knitting machine, such as warp knitting needles and sinkers, is difficult to monitor intuitively and continuously. Once a fault or abnormal movement occurs, it is difficult to detect and deal with it in time, which easily leads to a large number of defective products. In addition, there is a lack of systematic and efficient means for quality inspection of woven fabrics, especially quality control of the central and edge areas. Often, random inspections can only be carried out after the finished product, and the process cannot be adjusted in time during the production process to avoid quality problems. Moreover, the data between each process link is isolated, and an effective feedback and linkage mechanism cannot be formed, making it difficult to achieve optimization and refined management of the overall production process. Summary of the invention

[0004] To this end, the present invention provides a carbon fiber warp knitting machine operation method based on the Internet of Things, which is used to overcome the problems in the prior art that the equipment cannot be monitored in real time, the quality of woven fabrics cannot be fully controlled, and the linkage between various links in the production process cannot be optimized; the problems of unstable woven fabric quality and low production efficiency caused by unreasonable parameters, difficult to detect equipment failures, insufficient quality control and disconnected production links in the production of carbon fiber warp knitting machines are effectively solved, thereby improving the overall production efficiency and product competitiveness.

[0005] To achieve the above object, the present invention provides an operation method of a carbon fiber warp knitting machine based on the Internet of Things, comprising:

[0006] Obtain the qualified rate of the historical carbon fiber braided fabrics of the warp knitting machine to determine the weaving control status of the warp knitting machine;

[0007] Obtaining the raw material diameter and target fabric density of the carbon fiber raw material to determine the initial weaving speed and matching the pulling speed accordingly;

[0008] Determining the center area and the edge area of ​​the braided fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density;

[0009] Determine the motion trajectory of warp knitting needles and sinkers during knitting to determine the equipment characterization state of the warp knitting machine;

[0010] determining whether the warp knitting machine acquires a surface image of the woven fabric according to the device characterization state;

[0011] Acquire a surface image of the woven fabric at each preset time point to determine a density characterization trend of the woven fabric;

[0012] Determining an operation characterization trend according to the density characterization trend to determine whether to adjust an initial weaving speed comprises:

[0013] adjusting the initial weaving speed so that the adjusted weaving speed is less than the initial weaving speed;

[0014] or, not adjusting the initial weaving speed and separately determining the center flatness state of the center area and the fabric edge state of the edge area;

[0015] A running characterization trend is secondarily determined according to the center flatness state and the fabric edge state to determine whether to adjust the drawing speed.

[0016] Further, the method of obtaining the qualified rate of the historical carbon fiber braided fabric of the warp knitting machine to determine the weaving control state of the warp knitting machine includes:

[0017] Obtain the historical pass rate of carbon fiber braids of warp knitting machines;

[0018] The knitting control state of the warp knitting machine is determined according to the relationship between the qualified rate and the preset qualified rate, wherein:

[0019] If the qualified rate is less than or equal to the preset qualified rate, the knitting control state is determined to be a low-precision control state;

[0020] If the qualified rate is greater than the preset qualified rate, the weaving control state is determined to be a high-precision control state. Further, the method for determining the central area and the edge area of ​​the woven fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density includes:

[0021] The area ratio of the central area to the edge area is determined according to the raw material diameter and the target fabric density, wherein:

[0022] If the raw material diameter is greater than or equal to a preset diameter and the target fabric density is less than or equal to a preset density, determining that the area ratio is a standard area ratio;

[0023] If the raw material diameter is smaller than a preset diameter and / or the target fabric density is greater than a preset density, determining that the area ratio is determined based on a standard area ratio and a correction coefficient;

[0024] determining a central area and an edge area of ​​the woven fabric according to the area ratio;

[0025] Wherein, the correction coefficient is less than 1.

[0026] Further, the method of determining the motion trajectory of the warp knitting needle and the sinker during the knitting process to determine the device characterization state of the warp knitting machine includes:

[0027] The real-time motion trajectory of warp knitting needles and sinkers during weaving is obtained through binocular cameras;

[0028] Determining whether the real-time motion trajectories of the warp knitting needles and the sinkers meet normal motion conditions;

[0029] The device characterization state is determined according to the result of the determination of whether the normal motion condition is met, wherein:

[0030] If the normal motion condition is met, determining that the device representation state is a normal state;

[0031] If the normal motion condition is not met, determining that the device representation state is an abnormal state;

[0032] The normal motion condition is that the real-time motion trajectories of the warp knitting needles and the sinkers are both within the corresponding motion trajectory range.

[0033] Further, the method for determining whether the warp knitting machine acquires the surface image of the woven fabric according to the device characterization state includes:

[0034] Determine the device characterization state to determine whether the warp knitting machine continues to operate, wherein:

[0035] If the device characterization state is a normal state, determining that the warp knitting machine continues to operate;

[0036] If the device is in an abnormal state, the warp knitting machine is determined to stop running;

[0037] According to the result of the determination that the warp knitting machine continues to run, it is determined whether to obtain the surface image of the woven fabric, wherein:

[0038] If the warp knitting machine continues to run, it is determined to obtain a surface image of the woven fabric;

[0039] If the warp knitting machine stops running, it is determined that the surface image of the knitted fabric is not acquired.

[0040] Furthermore, the method of acquiring the surface image of the woven fabric at each preset time node to determine the density characterization trend of the woven fabric includes:

[0041] Acquire a surface image of the woven fabric at a preset time point;

[0042] dividing the surface image into a plurality of sub-surface images;

[0043] Determine the weaving density of each sub-surface image respectively, and determine the density standard deviation and the density average according to the weaving density of each sub-surface image;

[0044] The density characterization trend of the woven fabric is determined according to the density standard deviation and the density average value, wherein:

[0045] If the density standard deviation is less than the preset standard deviation and the density average value is within the preset density range, then the density characterization trend is determined to be a uniform weaving density;

[0046] If the density standard deviation is greater than or equal to the preset standard deviation, and / or the density average value is not within the preset density range, then the density characterization trend is determined to be a random weaving density;

[0047] Wherein, the weaving density of the sub-surface image is determined according to computer vision and / or machine learning.

[0048] Furthermore, the time intervals between any two adjacent preset time nodes are equal;

[0049] The time interval is determined according to the initial weaving speed, and the time interval is negatively correlated with the initial weaving speed.

[0050] Further, the method of determining the operation characterization trend according to the density characterization trend to determine whether to adjust the initial weaving speed includes:

[0051] If the operation characterization trend is a uniform weaving density, determining the operation characterization trend as a normal operation and not adjusting the initial weaving speed, and determining the center flatness state of the center area and the fabric edge state of the edge area respectively;

[0052] If the operation characterization trend is a disordered knitting density, the operation characterization trend is determined to be an abnormal operation and the initial knitting speed is adjusted so that the adjusted knitting speed is less than the initial knitting speed.

[0053] Further, the method of respectively determining the center flatness state of the center area and the fabric edge state of the edge area includes:

[0054] Determine the central flatness of the surface image based on its central area, including:

[0055] Determine the chromaticity value of each pixel point of the central surface image corresponding to the central area;

[0056] The maximum chromaticity difference is determined according to the chromaticity value of each pixel to determine the center flatness state, where:

[0057] If the maximum chromaticity difference is greater than the preset chromaticity difference, the center flat state is determined to be an uneven state;

[0058] If the maximum chromaticity difference is less than or equal to the preset chromaticity difference, the center flat state is determined to be a flat state;

[0059] The fabric edge state is determined according to the average edge width of the edge area of ​​the surface image, including:

[0060] If the average edge width is within a preset width range, the edge state of the fabric is determined to be regular;

[0061] If the average edge width is not within the preset width range, it is determined that the edge state of the fabric is in a jagged state.

[0062] Further, the method of secondarily determining the operation characterization trend according to the center flattening state and the fabric edge state to determine whether to adjust the pulling speed includes:

[0063] If the center flatness state is an uneven state and / or the fabric edge state is a jagged state, a second determination is made that the operation characterization trend is an abnormal operation, and the pulling speed is adjusted;

[0064] If the center flatness state is a flat state and the fabric edge state is a regular state, the secondary determination operation characterization trend is a normal operation, and the pulling speed is not adjusted.

[0065] Compared with the prior art, the beneficial effect of the present invention is that the carbon fiber warp knitting machine operation method based on the Internet of Things provided by the present invention determines the weaving control state according to the historical qualified rate of carbon fiber braided fabrics, which is conducive to accurate debugging and maintenance before weaving, reduces equipment failures and maintenance costs, and prolongs the life of the equipment; during operation, the equipment characterization state is monitored by means of the movement trajectory of the warp knitting needles and sinkers to ensure the operation stability; the weaving speed and the pulling speed are determined and adjusted in time according to the raw material diameter and the target fabric density, and the visual inspection of the center and edge areas and the surface image analysis are combined to optimize the yarn interweaving, avoid uneven density due to improper speed and pulling, improve the quality of the braided fabric, make its mechanical properties and appearance meet the high-end application requirements, and can also accurately control the quality of different areas to improve the overall uniformity and consistency; in addition, the intelligent parameter adjustment also reduces the scrap rate and the waste of raw materials, and the automatic monitoring feedback of the Internet of Things reduces the labor cost, shortens the problem handling time, improves the production efficiency, and makes the production process more efficient, stable and high-quality;

[0066] Furthermore, the present invention determines the area ratio of the center and edge areas scientifically based on the raw material diameter and the target fabric density, and then accurately divides the areas, which helps to improve the accuracy and efficiency of woven fabric quality monitoring and production process optimization, ensure the stability of the production process and the high-quality output of products, reduce the quality risks and resource waste caused by unreasonable regional division, and improve the overall production efficiency and product competitiveness.

[0067] Furthermore, using binocular cameras to monitor the motion trajectories of warp knitting needles and sinkers to determine the equipment characterization status has important beneficial effects. It can accurately and in real time grasp the operating conditions of key components, effectively ensure the stable operation of warp knitting machines, quickly discover and warn potential faults, improve equipment maintenance efficiency, ensure the continuity of the carbon fiber weaving process and the reliability of the quality of the woven materials, reduce the risk of production interruptions and the incidence of quality problems caused by equipment failures, and greatly enhance the controllability of the production process and the overall stability of the production system;

[0068] Furthermore, deciding whether to obtain the surface image of the woven fabric based on the equipment characterization status can effectively integrate the equipment operation status and the woven fabric quality inspection link, reasonably allocate resources, avoid unnecessary image acquisition and analysis, improve the inspection efficiency, and at the same time, stop abnormal equipment operation in time to prevent the production of defective products, ensure the orderliness of the production process and the stability of product quality, reduce the material waste and subsequent processing costs caused by the continuous operation of equipment failure, and improve the overall production efficiency and quality control level;

[0069] Furthermore, by acquiring the surface image of the woven fabric at a preset time node and analyzing its density characterization trend, the advanced image segmentation and analysis technology is used to accurately quantify the density characteristics of the woven fabric, effectively monitor the density uniformity changes during the weaving process, and timely discover weaving abnormalities, providing a reliable basis for adjusting the production process, ensuring the quality stability of carbon fiber woven fabrics, improving the level of refined management of the production process, reducing the defective rate caused by uneven density, and improving overall production efficiency and product competitiveness;

[0070] Furthermore, by determining the operation characterization trend based on the density characterization trend and further analyzing the status of the center and edge areas, we can gain deep insight into the quality of the woven fabric, accurately determine whether the operation is normal during the weaving process and adjust the weaving speed accordingly. At the same time, the center flatness and edge regularity are fully considered, which can effectively improve the overall quality of the woven fabric, reduce the defective rate caused by improper speed, uneven center or uneven edges, enhance the adaptability and stability of the production process, and improve the refined management level of carbon fiber warp knitting machine production and the market competitiveness of products.

[0071] Furthermore, the center flatness state and the edge state of the fabric are comprehensively considered to secondary determine the operation characterization trend and decide on the adjustment of the pulling speed. Starting from the overall shape of the woven fabric, the key factors affecting the quality are deeply explored, and various problems caused by improper pulling speed are accurately located and targeted adjustments are made in a timely manner. This effectively ensures the structural integrity, appearance flatness and edge regularity of the woven fabric, greatly reduces the defective rate, and significantly improves the stability and controllability of the production process, laying a solid foundation for the efficient production of high-quality carbon fiber warp knitting products and enhancing the company's core competitiveness in related fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a step diagram of a carbon fiber warp knitting machine operation method based on the Internet of Things according to an embodiment of the present invention;

[0073] Figure 2 A flow chart for determining and obtaining a surface image of a woven fabric according to an embodiment of the present invention;

[0074] Figure 3 A flow chart for determining a density characterization trend of a woven fabric according to an embodiment of the present invention;

[0075] Figure 4 The present invention is a flowchart for determining whether to adjust the initial knitting speed according to an embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0077] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0078] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0079] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0080] See also Figure 1 As shown, it is a step diagram of a carbon fiber warp knitting machine operation method based on the Internet of Things according to an embodiment of the present invention. An embodiment of the present invention provides a carbon fiber warp knitting machine operation method based on the Internet of Things, comprising:

[0081] Step S1, obtaining the qualified rate of the historical carbon fiber braids of the warp knitting machine to determine the weaving control state of the warp knitting machine; it can be understood that before starting to weave, by understanding the weaving effect of the warp knitting machine to be used this time, it is determined whether to debug and maintain it before weaving;

[0082] Step S2, obtaining the raw material diameter and target fabric density of the carbon fiber raw material to determine the initial weaving speed and match the pulling speed accordingly; it can be understood that the initial weaving speed is determined according to the diameter (thickness) of the carbon fiber raw material and the target fabric density, and the pulling speed is matched according to the initial weaving speed; generally, the weaving speed corresponding to a thicker carbon fiber raw material or a fabric with a higher target fabric density is relatively low;

[0083] It can be understood that the weaving speed is inversely proportional to the diameter of the carbon fiber raw material and the target fabric density. When the diameter of the carbon fiber raw material is large, the yarn is relatively thick, and the amount of yarn passing through the weaving mechanism per unit time is limited, so the weaving speed needs to be reduced; similarly, the higher the target fabric density, the more yarns need to be interwoven per unit area. In order to ensure that the yarns can be accurately interwoven, the weaving speed also needs to be reduced accordingly;

[0084] In practice, the initial weaving speed V is determined according to the following formula: ;

[0085] Wherein: V0 is the reference weaving speed (the ideal weaving speed determined by experiment under the standard carbon fiber diameter and standard fabric density, which varies according to each model of warp knitting machine and should be set at the factory), the unit is revolutions per minute (r / min); d0 is the standard carbon fiber diameter, the unit is mm; ρ0 is the standard fabric density, the unit is roots / square centimeter; d is the actual carbon fiber diameter, the unit is mm; ρ is the actual fabric density, the unit is roots / square centimeter; in practice, V0 is usually 1000 revolutions per minute, the standard carbon fiber diameter is 0.5 mm, and the standard fabric density is 50 roots / square centimeter;

[0086] In practice, the pulling speed and the weaving speed should maintain a certain proportional relationship to ensure the structural stability of the fabric: if the pulling speed is too fast, the yarn will be pulled away before it has time to fully interweave relative to the weaving speed, which will lead to a decrease in fabric density, an uneven surface, and even yarn breakage; on the contrary, if the pulling speed is too slow, the fabric will accumulate in the weaving area, resulting in a higher density, which may also affect the normal operation of the weaving mechanism;

[0087] In practice, there is usually a roughly proportional relationship between the pulling speed and the initial weaving speed. The pulling speed is equal to the product of the empirical coefficient (this coefficient is determined according to factors such as the type of warp knitting machine and the type of yarn) and the initial weaving speed, that is, Vp=k×V; in one implementation, for a certain carbon fiber warp knitting machine and a specific carbon fiber yarn, the empirical coefficient is determined experimentally;

[0088] In an ideal carbon fiber warp knitting process, the pulling speed is usually lower than the weaving speed. This is because the weaving speed determines the speed at which the yarn forms a coil. If the pulling speed is too fast, the yarn will be pulled away before it is fully interwoven, resulting in a lower fabric density, a loose structure, or even yarn breakage. In one implementation, when the weaving speed is 1000 revolutions per minute (at this speed, the yarn can be normally interwoven to form a coil), the pulling speed may be set to about 800 revolutions per minute, which can ensure that the yarn has enough time to be interwoven in the weaving area to form a fabric of better quality. Generally, k=0.7-0.9, preferably, k=0.8.

[0089] Step S3, determining the central area and the edge area of ​​the woven fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density; it can be understood that the woven fabric is divided into the central area and the edge area according to the data of the raw material to be woven and the target fabric, so as to perform visual inspection on the central area and the edge area respectively, and determine the weaving quality of the fabric according to the result of the visual inspection;

[0090] Step S4, determining the motion trajectories of the warp knitting needles and the sinkers during the knitting process to determine the equipment characterization state of the warp knitting machine; it can be understood that during the operation of the warp knitting machine, by observing the motion trajectories of the warp knitting needles and the sinkers, it is possible to intuitively judge whether the equipment is operating normally (abnormal operation of the equipment will directly affect the quality of the woven fabric), so the motion trajectories of the warp knitting needles and the sinkers are monitored in real time during the operation to monitor the equipment characterization state of the warp knitting machine equipment;

[0091] Step S5, determining whether the warp knitting machine obtains the surface image of the woven fabric according to the device characterization state; it can be understood that when the running trajectories of the warp knitting needles and the sinkers are normal, it means that the knitting speed or tension has no effect on them, but it does not mean that it has no effect on the quality of the woven fabric, so it is necessary to analyze the surface image of the woven fabric to ensure the efficiency and knitting quality of the woven fabric;

[0092] In practice, a warp knitting machine is equipped with an image capturing device for capturing the woven fabric (before curling), which is usually a high-definition camera and a lighting lamp. The illumination direction of the lighting lamp is not perpendicular to the surface of the fabric, and the shooting direction of the high-definition camera is perpendicular to the surface of the fabric, that is, the lighting lamp emits an oblique light so that the convexity and concavity of the fabric can be displayed on the surface image.

[0093] Step S6, acquiring a surface image of the woven fabric at each preset time point to determine a density characterization trend of the woven fabric;

[0094] Step S7, determining the operation characterization trend according to the density characterization trend to determine whether to adjust the initial weaving speed, including:

[0095] The initial weaving speed is adjusted so that the adjusted weaving speed is less than the initial weaving speed. It is understandable that when the weaving speed is too fast, the yarns (carbon fiber raw materials) may not be interwoven in a predetermined position and manner, resulting in uneven fabric density. In practice, in the case of high-speed weaving, the yarns are pulled away by the pulling mechanism before they are interwoven in the correct position, resulting in a lower density of the fabric in certain areas. In addition, a too fast weaving speed may also result in an unstable pulling speed, further affecting the fabric density.

[0096] Or, the initial weaving speed is not adjusted and the center flatness state of the center area and the fabric edge state of the edge area are determined separately; it can be understood that if the weaving speed is appropriate, the yarns can be interwoven in an orderly manner, which can ensure that the fabric has a uniform density;

[0097] Step S8, secondarily determining the running characteristic trend according to the center flatness state and the fabric edge state to determine whether to adjust the pulling speed; it is understandable that the pulling speed and force of the pulling mechanism of the warp knitting machine will also affect the fabric density. If the running characteristic trend is still not normal after adjusting the weaving speed, it may be that the pulling speed is not appropriate, so the pulling speed needs to be adjusted; in implementation, too slow a pulling speed may cause the fabric stacking density to increase; too fast a pulling speed may cause insufficient yarn interweaving and a lower density.

[0098] It is understandable that by obtaining the historical qualified rate of carbon fiber braids of the warp knitting machine to determine the weaving control status, it is possible to accurately determine whether the equipment needs to be debugged and maintained before weaving; this helps to discover potential problems with the equipment in advance, avoid production interruptions or product quality degradation due to equipment failure during the weaving process, effectively ensure the normal operation of the equipment, extend the service life of the equipment, and reduce maintenance costs and production delays caused by sudden equipment failures; during operation, the motion trajectories of the warp knitting needles and sinkers are determined to determine the equipment characterization status of the warp knitting machine, and real-time monitoring of the operation of key components of the equipment is achieved. Once the motion trajectory is abnormal, it can be discovered in time and corresponding measures can be taken to ensure that the equipment is always in a good operating state, improve the stability and reliability of the production process, and reduce the defective rate.

[0099] Specifically, in step S1, the method of obtaining the qualified rate of the historical carbon fiber braids of the warp knitting machine to determine the weaving control state of the warp knitting machine includes:

[0100] Step S11, obtaining the qualified rate of the historical carbon fiber braided fabrics of the warp knitting machine;

[0101] Step S12, determining the knitting control state of the warp knitting machine according to the relationship between the qualified rate and the preset qualified rate, wherein:

[0102] If the qualified rate is less than or equal to the preset qualified rate, the knitting control state is determined to be a low-precision control state; it is understandable that if the qualified rate of the historical knitted fabrics does not meet the standard (less than or equal to the preset qualified rate), it means that the running smoothness and completion of the equipment are unqualified, and it needs to be debugged / repaired before the knitting starts;

[0103] If the qualified rate is greater than the preset qualified rate, it is determined that the weaving control state is a high-precision control state, and no debugging / maintenance is required, and weaving can be started directly;

[0104] In implementation, the preset pass rate is determined according to the precision requirement of the prepared carbon fiber braided fabric. The higher the preparation precision requirement, the larger the corresponding preset pass rate. Usually, the preset pass rate ∈ [92%, 100%]. If the preparation precision requirement is a low precision requirement, the preset pass rate is preferably set to 92%. If the preparation precision requirement is a medium precision requirement, the preset pass rate is preferably set to 95%. If the preparation precision requirement is a medium precision requirement, the preset pass rate is preferably set to 98%.

[0105] Specifically, in step S3, the method for determining the central area and the edge area of ​​the woven fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density includes:

[0106] Step S31, determining the area ratio of the central area and the edge area according to the raw material diameter and the target fabric density, wherein:

[0107] If the raw material diameter is greater than or equal to the preset diameter and the target fabric density is less than or equal to the preset density, the area ratio is determined to be the standard area ratio; it can be understood that the preset area ratio is ≥8:1, and the corresponding standard area ratio is 8:1;

[0108] In practice, the smaller the raw material diameter is, the more repeated weaving contents will be contained in the edge area of ​​the same area. However, when considering edge features, there is no need to consider too many repeated weaving contents (they should be merged into the central area), so the corresponding edge area should be smaller, that is, the larger the area ratio; the greater the target fabric density is, the more repeated weaving contents will be contained in the edge area of ​​the same area, so the corresponding edge area should be smaller, that is, the larger the area ratio;

[0109] If the raw material diameter is smaller than the preset diameter and / or the target fabric density is greater than the preset density, it is determined that the area ratio is determined according to the standard area ratio and the correction coefficient; in implementation, the area ratio is the product of the standard area ratio and the correction coefficient;

[0110] It can be understood that the preset diameter and the preset density are used as a criterion for determining the area ratio. This criterion helps to reasonably divide the edge area and the center area when considering the edge characteristics of the fabric, and avoids interference of too much repeated weaving content on the edge characteristic analysis; in implementation, the preset diameter is usually 1 mm, and the preset density is usually based on 80% of the highest density that can be stably woven by the warp knitting machine at the corresponding weaving speed. In implementation, a corresponding relationship table between the weaving speed of the warp knitting machine and the highest density of stable weaving is pre-stored;

[0111] Step S32, determining the central area and the edge area of ​​the braided fabric according to the area ratio; it can be understood that the lengths (in the pulling direction) of the central area and the edge area are equal, and the area ratio is also the ratio of the widths of the central area and the edge area; in the implementation, the edge area is two left and right edge areas of equal area;

[0112] Wherein, the correction coefficient is less than 1; in implementation, the correction coefficient is determined according to the raw material diameter and / or the target fabric density: (1) if only the raw material diameter is less than the preset diameter, the correction coefficient = raw material diameter ÷ preset diameter; (2) if only the target fabric density is greater than the preset density, the correction coefficient = preset density ÷ target fabric density; (3) if the raw material diameter is less than the preset diameter and the target fabric density is greater than the preset density, the correction coefficient = (raw material diameter ÷ preset diameter) × (preset density ÷ target fabric density).

[0113] It can be understood that dividing the central area and the edge area by determining the area ratio based on the raw material diameter and the target fabric density can avoid the edge area from interfering with the edge feature analysis due to too much repeated weaving content; for different raw material diameters and target fabric density combinations, the area ratio can be reasonably determined, making the quality monitoring of the edge and center area of ​​the woven fabric more targeted and effective; accurate area division in the production of high-precision carbon fiber products can ensure timely detection of problems such as wrinkling and unevenness of the edge or abnormal density in the center area, so as to adjust the production parameters in time and improve product quality; using the preset diameter and preset density as the judgment criteria, combined with the correction coefficient to determine the area ratio, this combination of standardization and flexible adjustment helps to optimize the production process. When faced with different specifications of carbon fiber raw materials and diverse target fabric density requirements, it can quickly determine the appropriate area division scheme, so that the adjustment of process parameters such as yarn interweaving and pulling in each area during the weaving process is more accurate; such as when weaving finer raw materials or higher density target fabrics, the area ratio is adjusted by the correction coefficient to ensure the stability of the weaving process and reduce the increase in the defective rate due to process fluctuations.

[0114] See also Figure 2 As shown, it is a flow chart of determining and acquiring the surface image of the woven fabric according to an embodiment of the present invention. Specifically, in step S4, the method of determining the motion trajectory of the warp knitting needle and the sinker during the knitting process to determine the device characterization state of the warp knitting machine includes:

[0115] Step S41, obtaining the real-time motion trajectory of the warp knitting needles and sinkers during the weaving process through the binocular camera; it can be understood that binocular vision is based on the principle of parallax, and the image of the object is obtained from different angles by two cameras at the same time, and then the three-dimensional spatial position information of the object is calculated by using the triangulation principle; the binocular camera can be used to observe the motion trajectory of the sinkers and warp knitting needles inside the warp knitting machine. For the sinkers and warp knitting needles inside the warp knitting machine, as long as they are within the field of view of the binocular camera and the movement speed is within the range that the frame rate of the camera can capture, their real-time motion trajectory can be obtained by analyzing the continuous frame images;

[0116] Step S42, determining whether the real-time motion trajectory of the warp knitting needle and the sinker meets the normal motion condition;

[0117] Step S43, determining the device characterization state according to the result of determining whether the normal motion condition is met, wherein:

[0118] If the normal motion condition is met, determining that the device representation state is a normal state;

[0119] If the normal motion condition is not met, determining that the device representation state is an abnormal state;

[0120] Wherein, the normal motion condition is that the real-time motion trajectories of the warp knitting needles and the sinkers are both within the corresponding motion trajectory range;

[0121] It is understandable that the movement track ranges of the warp knitting needles and the sinkers should be recorded in the user manual / factory manual of the warp knitting machine.

[0122] It is understandable that by using a binocular camera to obtain the real-time motion trajectory of warp knitting needles and sinkers based on the principle of parallax and triangulation, accurate and real-time monitoring of the operating status of key equipment components can be achieved; as long as the components are within the camera's field of view and the movement speed matches the frame rate, their motion trajectory can be continuously tracked, and abnormal conditions such as freezing and offset can be discovered in time to ensure that the warp knitting machine operates stably within the normal parameter range, avoid production interruptions due to sudden equipment failures, and improve the continuity of the production process; by determining whether the real-time motion trajectory meets the normal motion conditions to determine the equipment characterization status, an early warning can be issued in time at the early stage of equipment abnormality, which is different from traditional regular inspections or maintenance after a failure occurs. This early warning mechanism based on motion trajectory monitoring can significantly shorten the time to discover faults, allowing maintenance personnel to prepare maintenance plans and tools in advance, quickly locate and repair faults, reduce equipment downtime, improve equipment maintenance efficiency, and reduce maintenance costs; whether the motion trajectory of warp knitting needles and sinkers is normal directly affects the quality of carbon fiber braids: normal motion trajectories can ensure that yarns are accurately interwoven, looped, and other weaving actions are completed smoothly, making the structure of the braid uniform and flat, and avoiding weaving defects caused by equipment failures, such as uneven coils and missed stitches, thereby improving the reliability of the quality of the braided material, meeting the strict requirements of high-end application fields for the quality of carbon fiber products, and enhancing the market competitiveness of products.

[0123] Specifically, in step S5, the method for determining whether the warp knitting machine acquires the surface image of the woven fabric according to the device characterization state includes:

[0124] Step S51, determining the device characterization state to determine whether the warp knitting machine continues to operate, wherein:

[0125] If the device characterization state is a normal state, determining that the warp knitting machine continues to operate;

[0126] If the device is in an abnormal state, the warp knitting machine is determined to stop running;

[0127] Step S52, determining whether to obtain the surface image of the woven fabric according to the result of the determination that the warp knitting machine continues to run, wherein:

[0128] If the warp knitting machine continues to run, it is determined to obtain a surface image of the woven fabric;

[0129] If the warp knitting machine stops running, it is determined that the surface image of the knitted fabric is not acquired.

[0130] It can be understood that whether to obtain the surface image of the woven fabric is determined based on the equipment characterization status. When the equipment characterization status is abnormal, it is determined not to obtain the image, thereby avoiding unnecessary image acquisition and analysis work when the equipment fails, saving data processing resources and time; and image acquisition is performed only when the equipment is operating normally, so that detection resources can be concentrated on the effective production period, which improves the pertinence and efficiency of image detection for controlling the quality of woven fabrics in normal production processes, and helps to quickly discover potential quality problems and adjust process parameters in a timely manner.

[0131] It is understandable that if the equipment characterization state is abnormal, the warp knitting machine is judged to stop running to prevent the equipment from continuing to produce defective products in a faulty state; in this way, quality defects of woven fabrics caused by equipment failure can be effectively avoided, such as uneven weaving and surface defects caused by abnormal movement of warp knitting needles or sinkers, ensuring that only woven fabrics produced under normal equipment conditions enter the subsequent quality inspection process, thereby ensuring the stability of product quality, improving the product qualification rate, and meeting the market demand for high-quality carbon fiber woven fabrics; in addition, timely stopping of abnormally operating warp knitting machines can reduce the waste of raw materials caused by continued operation due to equipment failure, avoid further processing of woven fabrics that have already had quality problems, and save manpower, material and time costs.

[0132] See also Figure 3 As shown, it is a flow chart of determining the density characterization trend of a woven fabric according to an embodiment of the present invention. Specifically, in step S6, the method of acquiring a surface image of the woven fabric at each preset time node to determine the density characterization trend of the woven fabric according to the surface image includes:

[0133] Step S61, obtaining a surface image of the woven fabric at a preset time point;

[0134] Step S62, dividing the surface image into a plurality of sub-surface images; usually divided into 500 sub-surface images of the same area;

[0135] Step S63, determining the weaving density of each sub-surface image respectively, and determining the density standard deviation and the density average value according to the weaving density of each sub-surface image;

[0136] It is understandable that high-resolution images can provide more details of the weave, and the weave density can be determined through image analysis software. Modern image processing techniques (such as machine learning and computer vision) can automatically identify and count line segments in the image, thereby calculating the weave density of the sub-surface image;

[0137] Step S64, determining the density characterization trend of the woven fabric according to the density standard deviation and the density average value, wherein:

[0138] If the density standard deviation is less than the preset standard deviation and the density average value is within the preset density range, then the density characterization trend is determined to be a uniform weaving density;

[0139] If the density standard deviation is greater than or equal to the preset standard deviation, and / or the density average value is not within the preset density range, then the density characterization trend is determined to be a random weaving density;

[0140] It is understandable that the calculation method of the standard deviation and the average value is prior art, so it will not be described in detail.

[0141] In implementation, the preset density range is determined according to the target fabric density and weaving precision requirements. The higher the weaving precision requirements, the smaller the preset density range. Usually, the preset density range ∈ [target fabric density × minimum deviation, target fabric density × maximum deviation]. The deviation is determined according to the weaving precision, usually the deviation ∈ [98%, 102%]; for high-precision braids, the deviation ∈ [99.5%, 100.5%];

[0142] In practice, the standard deviation is a statistic that measures the degree of data dispersion. It represents the average distance between each data point in the data set and the mean value. The standard deviation ranges from 0 to positive infinity in theory, and the specific value depends on the nature and distribution of the data set: when all data points are exactly the same, the standard deviation is 0, which means that the data has no dispersion; when the data points begin to differ, the standard deviation will be greater than 0. The larger the standard deviation, the greater the deviation of the data point from the mean value, and the higher the degree of data dispersion; in practical applications, the value of the standard deviation will vary according to the specific data set; therefore, the preset standard deviation ∈(0,1] is preferably set to 0.5;

[0143] Wherein, the weaving density of the sub-surface image is determined according to computer vision and / or machine learning.

[0144] It can be understood that dividing the surface image into several sub-surface images and determining the weaving density respectively, and then calculating the density standard deviation and density average, this method can accurately quantify the density characteristics of the woven fabric in different areas; with the help of high-resolution images and modern image processing technology (such as computer vision and machine learning), the microstructure of the woven fabric can be carefully analyzed, and the weaving density information can be accurately obtained, which provides an accurate data basis for the comprehensive evaluation of the quality of the woven fabric and helps to gain a deeper understanding of the execution effect of the weaving process; by comparing the density standard deviation with the preset standard deviation and the density average with the preset density range, the density uniformity of the woven fabric during the production process can be effectively monitored. Uniformity change: When the density standard deviation is less than the preset standard deviation and the density average is within the preset density range, it can be determined as uniform weaving density, otherwise it is a messy weaving density; this enables production managers to promptly detect density unevenness problems that may occur during the weaving process, such as local density differences caused by factors such as inappropriate weaving speed, so as to take corresponding measures to make adjustments; based on the determination results of the density characterization trend, it can provide a reliable basis for the adjustment of the production process. Once it is found that the weaving density shows a messy trend, it can be traced back to the process links that may affect the density, such as adjusting the weaving speed, checking the yarn supply system, etc., thereby ensuring the quality stability of carbon fiber braids.

[0145] Specifically, in step S6, the time intervals between any two adjacent preset time nodes are equal;

[0146] The time interval is determined according to the initial weaving speed, and the time interval is negatively correlated with the initial weaving speed.

[0147] It can be understood that the larger the time interval, the worse the continuity of the captured surface image. If the time interval is infinitesimal, a continuous surface image will be captured. Since the surface fabric can be judged by random sampling, there is no need to set a too small time interval. In practice, it is preferably set to 30s to 1min. If the weaving accuracy is high, it is set to 30s, otherwise it can be set to 30s to 1min.

[0148] See also Figure 4 As shown, it is a flow chart of determining whether to adjust the initial weaving speed according to an embodiment of the present invention. Specifically, in step S7, the method of determining the operation characterization trend according to the density characterization trend to determine whether to adjust the initial weaving speed includes:

[0149] If the operation characterization trend is a uniform weaving density, determining the operation characterization trend as a normal operation and not adjusting the initial weaving speed, and determining the center flatness state of the center area and the fabric edge state of the edge area respectively;

[0150] If the operation characterization trend is a disordered knitting density, the operation characterization trend is determined to be an abnormal operation and the initial knitting speed is adjusted so that the adjusted knitting speed is less than the initial knitting speed.

[0151] Specifically, in step S7, the method of respectively determining the center flatness state of the center area and the fabric edge state of the edge area includes:

[0152] Step S71, determining the central flatness state of the surface image according to the central area thereof, including:

[0153] Step S711, determining the chromaticity value of each pixel point of the central surface image corresponding to the central area;

[0154] Step S712, determining the maximum chromaticity difference value according to the chromaticity value of each pixel point to determine the center flatness state, wherein:

[0155] If the maximum chromaticity difference is greater than the preset chromaticity difference, the center flat state is determined to be an uneven state;

[0156] If the maximum chromaticity difference is less than or equal to the preset chromaticity difference, the center flat state is determined to be a flat state;

[0157] It can be understood that after determining the chromaticity value of each pixel point, the minimum chromaticity value and the maximum chromaticity value can be determined, and the maximum chromaticity difference value can be determined according to the difference between the maximum chromaticity value and the minimum chromaticity value;

[0158] In implementation, the chromaticity value of a single pixel = the value of the pixel in the red channel + the value of the pixel in the green channel + the value of the pixel in the blue channel;

[0159] In implementation, the preset chromaticity difference is 10 to 50, preferably set to 25;

[0160] Step S72, determining the fabric edge state according to the average edge width of the edge area of ​​the surface image, including:

[0161] If the average edge width is within a preset width range, the edge state of the fabric is determined to be regular;

[0162] If the average edge width is not within the preset width range, the edge state of the fabric is determined to be a jagged state;

[0163] In implementation, in step S32, the standard width of the edge area can be determined by determining the width ratio, and the preset width range is determined according to the standard width and deviation of the edge area, and the preset width range ∈ [standard width × minimum deviation, standard width × maximum deviation].

[0164] It can be understood that the central area is a standard rectangle.

[0165] It can be understood that judging the operation characterization trend according to the density characterization trend can accurately determine whether the weaving process is running normally: when it is a uniform weaving density, the initial weaving speed is maintained and the center and edge areas are further analyzed to avoid unnecessary speed adjustment; when it is a messy weaving density, it is judged as abnormal operation and the weaving speed is reasonably reduced; this precise judgment and adjustment mechanism can effectively solve the problem of uneven fabric density caused by poor yarn interweaving due to excessively fast weaving speed, ensure that the weaving process is carried out at an appropriate speed, and improve the quality stability of the woven fabric;

[0166] In addition, the center flatness is determined by determining the chromaticity value of each pixel point of the surface image of the center area and calculating the maximum chromaticity difference, which provides a detailed and quantitative method for evaluating the quality of the center area: if the maximum chromaticity difference exceeds the preset chromaticity difference, it indicates that the center area is uneven, which may be caused by factors such as changes in yarn tension and abnormal movement of knitting needles during weaving. Timely discovery of the center unevenness problem helps to specifically troubleshoot and solve equipment or process failures, ensure the quality of the woven fabric in the center area, and improve the appearance and performance of the overall product; the edge state of the fabric is determined based on the comparison between the average edge width of the edge area and the preset width range, and the quality of the edge area can be accurately judged; when the average edge width is not within the preset width range, it is determined to be an edge jagged state, which may be caused by reasons such as uncoordinated weaving speed and pulling speed or abnormal arrangement of yarns at the edge; accurate identification of the edge jagged problem can timely adjust relevant process parameters, such as adjusting the pulling speed or checking the yarn guide device, to ensure the regularity of the edge area, improve the overall quality and aesthetics of the product, and meet the market demand for high-quality carbon fiber braids.

[0167] Specifically, in step S8, the method of secondarily determining the running characterization trend according to the center flattening state and the fabric edge state to determine whether to adjust the pulling speed includes:

[0168] If the center flatness state is an uneven state and / or the fabric edge state is a jagged state, a second determination is made that the operation characterization trend is an abnormal operation, and the pulling speed is adjusted;

[0169] If the center flatness state is a flat state and the fabric edge state is a regular state, the secondary determination operation characterization trend is a normal operation, and the pulling speed is not adjusted.

[0170] It can be understood that (1) when the pulling speed and weaving speed are properly coordinated, the surface flatness of the woven fabric is better; if the pulling speed is too fast, the weaving mechanism will not have time to complete the interweaving of the yarns, which will make the surface of the fabric uneven (the center flat state is uneven), and the fabric may be locally tightened and wrinkled. This is because the yarns are forcibly pulled away before they are fully interwoven, resulting in an unstable fabric structure; (2) The pulling speed also has an important influence on the arrangement of the edge yarns of the woven fabric. If the pulling speed is unstable or too fast, the edge yarns may be offset due to uneven force, resulting in a In practice, a too fast pulling speed during the weaving process of the carbon fiber uniaxial warp knitting machine may cause the yarn at the edge to deviate toward the center or outside, so that the edge is no longer a neat straight line, but wavy or jagged; changes in the pulling speed may also cause changes in the width direction of the fabric. When the pulling speed is too fast, the fabric may shrink in the width direction, causing the edge to curl inward (irregular state and the average edge width is less than the preset width range); when the pulling speed is too slow, the fabric may relax in the width direction and the edge will expand outward (irregular state and the average edge width is greater than the preset width range).

[0171] In practice, the pulling speed is adjusted according to the phenomenon described above.

[0172] It is understandable that judging whether the pulling speed is appropriate based on the state of the center and the edge, and adjusting the pulling speed when the center is uneven or the edge is uneven, can effectively avoid insufficient yarn interweaving or uneven force caused by improper pulling speed, making the woven structure more stable; for example, the pulling speed is too fast, causing the weaving mechanism to be unable to complete the interweaving in time. After adjustment, it can ensure that the yarns are fully interwoven to form a stable structure, thereby ensuring the mechanical properties and durability of the woven fabric, and meeting the stringent requirements for the structural strength of carbon fiber products in fields such as aerospace and high-end sports equipment;

[0173] Through precise control of the pulling speed, the problems of uneven surface and irregular edges caused by unreasonable pulling speed can be effectively solved; when the pulling speed and the weaving speed are not well matched, resulting in wrinkles in the center or wavy edges, timely adjustment can make the surface of the braided fabric smoother and flatter, and the edges more neat and straight, significantly improving the appearance quality of the product. This can enhance the market appeal and product added value of carbon fiber braids used in automotive interiors, fashion apparel, etc., which have high requirements for appearance.

[0174] Based on the center and edge states, the operation characterization trend is determined secondary and the pulling speed is adjusted, so that the production process forms a closed-loop quality monitoring and adjustment system; it can timely discover and correct quality deviations caused by pulling speed fluctuations or mismatches, avoid the accumulation and expansion of problems, and ensure the consistency and stability of the quality of each batch of woven materials; at the same time, it is also convenient for operators to accurately grasp the production process parameters, improve the level of refinement of production management, reduce uncertainty and scrap rate in the production process, and improve overall production efficiency and economic benefits.

[0175] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0176] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for operating a carbon fiber warp knitting machine based on the Internet of Things, characterized in that: include: Obtain the qualified rate of the historical carbon fiber braided fabrics of the warp knitting machine to determine the weaving control status of the warp knitting machine; Obtaining the raw material diameter and target fabric density of the carbon fiber raw material to determine the initial weaving speed and matching the pulling speed accordingly; Determining the center area and the edge area of ​​the braided fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density; Determine the motion trajectory of warp knitting needles and sinkers during knitting to determine the equipment characterization state of the warp knitting machine; determining whether the warp knitting machine acquires a surface image of the woven fabric according to the device characterization state; According to the result of determining that the device characterization state is a normal state, acquiring a surface image of the woven fabric at each preset time node to determine a density characterization trend of the woven fabric; Determining an operation characterization trend according to the density characterization trend to determine whether to adjust an initial weaving speed comprises: According to the determination result that the operation characterization trend is a disordered knitting density, determining that the operation characterization trend is an abnormal operation and adjusting the initial knitting speed so that the adjusted knitting speed is less than the initial knitting speed; or, according to the determination result that the operation characterization trend is uniform weaving density, determining that the operation characterization trend is normal operation and not adjusting the initial weaving speed, and determining the center flatness state of the center area and the fabric edge state of the edge area respectively; A running characterization trend is secondarily determined according to the center flatness state and the fabric edge state to determine whether to adjust the drawing speed.

2. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method for obtaining the qualified rate of the historical carbon fiber woven fabric of the warp knitting machine to determine the weaving control state of the warp knitting machine includes: Obtain the historical pass rate of carbon fiber braids of warp knitting machines; The knitting control state of the warp knitting machine is determined according to the relationship between the qualified rate and the preset qualified rate, wherein: If the qualified rate is less than or equal to the preset qualified rate, the knitting control state is determined to be a low-precision control state; If the qualified rate is greater than the preset qualified rate, the weaving control state is determined to be a high-precision control state.

3. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method of determining the center area and the edge area of ​​the braided fabric according to the raw material diameter of the carbon fiber raw material and the target fabric density includes, The area ratio of the central area to the edge area is determined according to the raw material diameter and the target fabric density, wherein: If the raw material diameter is greater than or equal to a preset diameter and the target fabric density is less than or equal to a preset density, determining that the area ratio is a standard area ratio; If the raw material diameter is smaller than a preset diameter and / or the target fabric density is greater than a preset density, determining that the area ratio is determined based on a standard area ratio and a correction coefficient; determining a central area and an edge area of ​​the woven fabric according to the area ratio; Wherein, the correction coefficient is less than 1.

4. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method for determining the motion trajectory of the warp knitting needle and the sinker during the knitting process to determine the equipment characterization state of the warp knitting machine includes: The real-time motion trajectory of warp knitting needles and sinkers during weaving is obtained through binocular cameras; Determining whether the real-time motion trajectories of the warp knitting needles and the sinkers meet normal motion conditions; The device characterization state is determined according to the result of the determination of whether the normal motion condition is met, wherein: If the normal motion condition is met, determining that the device representation state is a normal state; If the normal motion condition is not met, determining that the device representation state is an abnormal state; The normal motion condition is that the real-time motion trajectories of the warp knitting needles and the sinkers are both within the corresponding motion trajectory range.

5. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method for determining whether a warp knitting machine acquires a surface image of a woven fabric according to the device characterization state comprises: Determine the device characterization state to determine whether the warp knitting machine continues to operate, wherein: If the device characterization state is a normal state, determining that the warp knitting machine continues to operate; If the device is in an abnormal state, the warp knitting machine is determined to stop running; According to the result of the determination that the warp knitting machine continues to run, it is determined whether to obtain the surface image of the woven fabric, wherein: If the warp knitting machine continues to run, it is determined to obtain a surface image of the woven fabric; If the warp knitting machine stops running, it is determined that the surface image of the knitted fabric is not acquired.

6. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method of acquiring the surface image of the woven fabric at each preset time node to determine the density characterization trend of the woven fabric includes: Acquire a surface image of the woven fabric at a preset time point; dividing the surface image into a plurality of sub-surface images; Determine the weaving density of each sub-surface image respectively, and determine the density standard deviation and the density average according to the weaving density of each sub-surface image; The density characterization trend of the woven fabric is determined according to the density standard deviation and the density average value, wherein: If the density standard deviation is less than the preset standard deviation and the density average value is within the preset density range, then the density characterization trend is determined to be a uniform weaving density; If the density standard deviation is greater than or equal to the preset standard deviation, and / or the density average value is not within the preset density range, then the density characterization trend is determined to be a random weaving density; Wherein, the weaving density of the sub-surface image is determined according to computer vision and / or machine learning.

7. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The time intervals between any two adjacent preset time nodes are equal; The time interval is determined according to the initial weaving speed, and the time interval is negatively correlated with the initial weaving speed.

8. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method of determining the center flatness state of the center area and the fabric edge state of the edge area respectively includes: Determine the central flatness of the surface image based on its central area, including: Determine the chromaticity value of each pixel point of the central surface image corresponding to the central area; The maximum chromaticity difference is determined according to the chromaticity value of each pixel to determine the center flatness state, where: If the maximum chromaticity difference is greater than the preset chromaticity difference, the center flat state is determined to be an uneven state; If the maximum chromaticity difference is less than or equal to the preset chromaticity difference, the center flat state is determined to be a flat state; The fabric edge state is determined according to the average edge width of the edge area of ​​the surface image, including: If the average edge width is within a preset width range, the edge state of the fabric is determined to be regular; If the average edge width is not within the preset width range, it is determined that the edge state of the fabric is in a jagged state.

9. The method for operating a carbon fiber warp knitting machine based on the Internet of Things according to claim 1, characterized in that: The method of secondarily determining the running characterization trend according to the center flattening state and the fabric edge state to determine whether to adjust the pulling speed includes: If the center flatness state is an uneven state and / or the fabric edge state is a jagged state, a second determination is made that the operation characterization trend is an abnormal operation, and the pulling speed is adjusted; If the center flatness state is a flat state and the fabric edge state is a regular state, the secondary determination operation characterization trend is a normal operation, and the pulling speed is not adjusted.

Images