A high-speed braiding machine intelligent control system and method

Abstract

The present invention discloses an intelligent control system and method for a high-speed braiding machine, and relates to the technical field of braiding machine control. The system acquires a first data group, a second data group, and a third data group through a tension monitoring module, a yarn path change acquisition module, and an environmental perception module, and performs feature extraction, calculates the tension fluctuation index Zbd and the environmental impact coefficient Es, and then associates them, generates and evaluates the yarn break prediction coefficient Dfxs, generates a first control strategy and a second control strategy, and optimizes the braiding process according to the prediction results, thereby reducing the occurrence of yarn breakage and improving production efficiency. The system can also collect and evaluate the yarn wear in real time, construct a yarn wear index Yw, and adjust the speed of the braiding machine and the yarn supply speed according to the risk level, and automatically optimize the braiding process. This not only improves the uniformity and strength of the fabric, but also extends the service life of the braiding machine and reduces maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of braiding machine control, and in particular to an intelligent control system and method for a high-speed braiding machine. Background Art

[0002] With the development of science and technology, the technology of knitting machines has been continuously improved. From the earliest manual knitting machines to mechanized knitting machines, and then to modern high-speed automated knitting machines, the textile industry has achieved remarkable development. However, there are still some key problems in traditional high-speed knitting machines, mainly focusing on yarn tension control, yarn path monitoring, and yarn wear management.

[0003] First, the yarn tension control of traditional high-speed braiding machines is not precise, and the yarn tension fluctuates violently during the braiding process, which can easily lead to yarn breakage, resulting in production interruptions and reduced product quality. Especially in situations where the yarn tension changes frequently, traditional equipment lacks accurate monitoring and adjustment mechanisms, and cannot promptly identify abnormal fluctuations in yarn tension, which ultimately affects braiding efficiency and finished product quality.

[0004] Secondly, the changes of yarns on the weaving path are complex, and traditional weaving machines lack sufficient sensors and data processing capabilities to monitor and adjust the yarn path in real time. Especially when the yarn turns or interweaves, it is difficult for traditional weaving machines to predict the exact position of the yarn, resulting in frequent twisting, knotting or entanglement of the yarn. This problem is often exacerbated without an effective path monitoring and optimization mechanism, further increasing the complexity and cost of production.

[0005] In addition, traditional knitting machines have deficiencies in yarn wear management and are unable to detect yarn wear in real time. For example, during the knitting process, factors such as needle wear and the frequency of yarn interlacing points often lead to excessive yarn wear, affecting the uniformity and strength of the fabric. However, traditional knitting machines lack real-time monitoring of these key parameters, resulting in the inability to take timely adjustment measures to ensure production quality. Summary of the invention

[0006] In view of the deficiencies of the prior art, the present invention provides an intelligent control system and method for a high-speed braiding machine. The system uses a high-resolution industrial camera or a high-speed camera to capture the yarn in the working area of ​​the braiding machine in real time, and uses image processing technology to accurately extract the characteristic data of the yarn, especially through edge detection algorithms, Hough transforms, morphological processing and other methods, to achieve efficient monitoring of parameters such as yarn tension, yarn path, interlacing point frequency, and needle wear. Through this image recognition technology, the system can analyze the relative distance between yarns, yarn surface burrs, the number and morphology of nodules in real time, so as to derive key parameters such as braiding density and yarn surface quality. A yarn wear index Yw is constructed, and further used to predict potential wear risks and abnormal tension problems during the braiding process.

[0007] To solve the problems mentioned in the background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent control system for a high-speed braiding machine, including a tension monitoring module, a yarn path change acquisition module, an environment perception module, a yarn break prediction module and a braiding density control module;

[0009] The tension monitoring module is used to monitor the tension changes of the yarn in the weaving process in real time to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set;

[0010] The yarn path change acquisition module is used to collect the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration of the yarn supply wheel drum Sd, the yarn supply wheel speed v, and the total yarn path length , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set;

[0011] The environment sensing module is used to monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set;

[0012] The yarn break prediction module is used to extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, and obtain the tension fluctuation trend analysis result to generate the first control strategy and the second control strategy;

[0013] The weaving density control module is used to collect real-time images in the weaving process after the implementation of the first control strategy and the second control strategy, obtain an image data set, and analyze the image data set through image processing technology to obtain the weaving density md, needle wear ztms, frequency of yarn interlacing points Jzpl, number of yarn burrs Mc and number of yarn surface nodules JJs, and obtain the knitting machine running time yxsj through the running timer measurement, generate the fourth data group, and construct the yarn wear index Yw, then evaluate the yarn wear index Yw to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the knitting machine speed and yarn supply speed according to the wear risk level to automatically optimize the weaving process.

[0014] Preferably, the tension monitoring module includes a tension sensing unit and a fracture testing unit;

[0015] The tension sensing unit is used to monitor the change of yarn tension in real time during the weaving process and obtain the tensile force F and the cross-sectional area A of the yarn fiber;

[0016] The breaking test unit is used to test the yarn before stretching and the breaking test data, and obtain the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking .

[0017] Preferably, the environment sensing module includes a temperature monitoring unit, a humidity monitoring unit, a static electricity monitoring unit and a dust concentration monitoring unit;

[0018] The temperature monitoring unit is used to monitor the temperature changes around the knitting machine and generate a temperature value wd;

[0019] The humidity monitoring unit is used to monitor the change of environmental humidity and generate a humidity value sdz;

[0020] The static electricity monitoring unit is used to monitor the static electricity accumulation degree during the weaving process and generate static electricity Jdz;

[0021] The dust concentration monitoring unit is used to monitor the dust concentration accumulation degree during the weaving process and generate a dust particle concentration value ndz.

[0022] Preferably, the yarn break prediction module includes a summary calculation unit, which is used to extract features from the data in the first data group, the second data group and the third data group to obtain the tension fluctuation index Zbd and the environmental impact coefficient Es;

[0023] The steps for obtaining the tension fluctuation index Zbd are:

[0024] S11, extracting the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching from the first data set , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking After dimensionless processing, the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs are calculated by the following formula:

[0025]

[0026] In the formula, represents stress, Indicates strain, which is the ratio of the incremental length change during the stretching process to the original length;

[0027] S12, extracting the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the yarn supply wheel drum angular acceleration Sd, the yarn supply wheel rotation speed v, and the yarn total path length from the second data set , the turning angle of the yarn at the i-th turning point on the path And the total number of yarn turning on the path n, after dimensionless processing, is calculated by the following formula: drum moment of inertia Irt, yarn supply wheel speed fluctuation rate Sws and weaving path turning rate Crv:

[0028]

[0029] In the formula, It represents the speed of the yarn feeding wheel in the i-th time period, which is measured by the speed sensor. Indicates the average speed of the yarn supply wheel, N is the total time period for measuring the speed data;

[0030] S13, after dimensionless processing of the calculated yarn fiber tensile elastic coefficient Fec, yarn fiber breaking strength coefficient Fbs, drum rotational inertia Irt, yarn supply wheel speed fluctuation rate Sws and braiding path turning rate Crv, the tension fluctuation index Zbd is calculated by the following formula:

[0031] In the formula, It is the weight coefficient of the product of the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs. , and They represent the weight coefficients of the drum moment of inertia Irt, the yarn supply wheel speed fluctuation rate Sws and the braiding path turning rate Crv, respectively. Represents the first correction constant.

[0032] Preferably, the environmental impact coefficient Es is obtained by extracting the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the third data group, and after dimensionless processing, the environmental impact coefficient Es is calculated by the following formula:

[0033] In the formula, Indicates the preset ideal temperature threshold in the weaving environment. Indicates the preset ideal humidity threshold in the weaving environment. Indicates the preset ideal electrostatic threshold in the weaving environment. Indicates the preset ideal dust particle concentration threshold in the weaving environment. , , and They are expressed as weight coefficients respectively; Represents the second correction constant.

[0034] Preferably, the yarn break prediction module includes a tension fluctuation analysis unit and a tension control unit;

[0035] The tension fluctuation analysis unit is used to generate the yarn break prediction coefficient Dfxs according to the tension fluctuation index Zbd and the environmental impact coefficient Es through dimensionless processing through the following formula to analyze the tension fluctuation trend:

[0036]

[0037] In the formula, and Respectively represent the weight coefficients of tension fluctuation index Zbd and environmental impact coefficient Es;

[0038] The tension control unit is used to preset the yarn break threshold value X, and compare the yarn break prediction coefficient Dfxs with the yarn break threshold value X to obtain the tension fluctuation trend analysis results, including:

[0039] When the yarn break prediction coefficient Dfxs> the yarn break threshold value X, it means that the tension fluctuates drastically and there is a risk of the first yarn breaking. The tension control unit generates a first control strategy, including: adjusting the speed of the yarn supply wheel to reduce the current speed by 6%-10%, and adjusting the tension controller to reduce the current tension by 5%-8%;

[0040] When the yarn break prediction coefficient Dfxs = the yarn break threshold value X, it means that the tension fluctuates at a high frequency and there is a risk of second yarn breakage, and the tension control unit generates a second control strategy, including: adjusting the speed of the yarn supply wheel to reduce the current speed by 4%-5%, and adjusting the tension controller to reduce the current tension by 1%-4%;

[0041] When the yarn break prediction coefficient Dfxs is less than the yarn break threshold value X, it means that the yarn breakage is in a stable state, there is no risk of yarn breakage, and the current yarn supply wheel speed and the pressure value of the tension controller are continuously maintained.

[0042] Preferably, the weaving density control module includes an image acquisition unit, an image processing unit and a yarn wear calculation unit;

[0043] The image acquisition unit is used to capture the image data of the working area of ​​the knitting machine in real time through a high-resolution industrial camera or a high-speed camera during the knitting process to obtain an image data set;

[0044] The image processing unit is used to receive the image data set from the image acquisition unit, process the image data set through the edge monitoring algorithm in the image processing algorithm, analyze, extract and detect the distance features between adjacent yarns, identify the yarn position through the edge detection algorithm or Hough transform, count the number of yarns in a certain area, and specifically calculate the pixel ratio occupied by the yarn in the specified area, so as to deduce the density of weaving to obtain the weaving density md;

[0045] By morphologically processing the image data set, the edge contour of the needle is identified, compared with the ideal needle shape, and the change of the wear area is detected to obtain the needle wear amount ztms;

[0046] By detecting the intersection of yarns in the image data set, using corner detection or intersection feature recognition algorithm, the position of the yarn interlacing point is found, and the movement path of the yarn in unit time is identified through motion detection technology, and the frequency of the interlacing point is counted to obtain the frequency Jzpl of the yarn interlacing point;

[0047] Using edge detection and image segmentation technology, the protruding burr features on the yarn surface are extracted, and the height and length of the burr on the yarn surface are quantified to obtain the number of burr yarns Mc on the yarn surface;

[0048] By using region growing or threshold segmentation technology, the number of nodules on the yarn surface and the area and shape characteristics of each nodule in the image data set are extracted to obtain the number of nodules on the yarn surface JJs;

[0049] The yarn wear calculation unit is used to extract the weaving density md, needle wear ztms, knitting machine running time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface nodule number JJs in the fourth data group, and after dimensionless processing, the yarn wear index Yw is calculated by the following formula:

[0050] In the formula, , , , , and They represent the weight coefficients of weaving density md, needle wear ztms, weaving machine operation time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface knot number JJs, respectively. Represents the third correction constant.

[0051] Preferably, the weaving density control module further includes a yarn fatigue analysis unit and a second control unit;

[0052] The yarn fatigue analysis unit is used to preset a wear threshold W, and compare and evaluate the yarn wear index Yw with the wear threshold W to obtain a second evaluation result, including:

[0053] When the yarn wear index Yw> the wear threshold W, it indicates that the yarn wear is abnormal, and the first wear risk level is generated. The second control unit generates a third control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 5%-8% to reduce the friction force of the yarn during the knitting process, thereby slowing down the yarn wear, starting the yarn burr removal device to clean the burrs on the yarn surface, and reducing the speed of the yarn supply wheel by 4%-6% of the current speed;

[0054] When the yarn wear index Yw=wear threshold W, it indicates that the yarn wear is abnormal, and a second wear risk level is generated. The second control unit generates a fourth control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 3%-4% to moderately reduce the pressure on the yarn, thereby controlling the wear speed, the yarn burr removal device enables the detection mode to identify and remove slight burrs on the yarn surface, and the yarn supply wheel speed is reduced by 2%-3% of the current speed to prevent further tension fluctuations from causing accelerated wear of the yarn;

[0055] When the yarn wear index Yw is less than the wear threshold W, it indicates that the yarn wear is normal. At this time, the needle knitting speed and the yarn supply wheel speed remain at the current level and no adjustment is required. The yarn burr removal device is in monitoring mode, continuously detecting but not actively removing burrs. It will only take action when an abnormality is detected on the yarn surface.

[0056] Preferably, an environment control module is further included, and the environment control module is used to preset an environment threshold R, and compare the environment impact coefficient Es with the environment threshold R to obtain a third evaluation result, including:

[0057] When the environmental impact coefficient Es ≥ environmental threshold R, it means that the environmental conditions are abnormal and have a negative impact on the production quality of the yarn and the operation of the equipment. The fifth control strategy is generated, including: the temperature control device starts the cooling or heating system, and adjusts the temperature by ±3°C according to the current temperature change; keeps the yarn at the preset ideal temperature threshold range; the humidity regulator activates the dehumidification or humidification device to adjust the current humidity level to the preset ideal humidity threshold Preset ideal humidity threshold The setting is: the relative humidity is kept between 45% and 60% to ensure that the yarn fiber will not expand due to high humidity or generate static electricity due to low humidity during the weaving process; the static electricity control device is started so that the current static electricity level is within the preset ideal static electricity threshold range; and turn on the air purification equipment to set the ideal dust particle concentration threshold Inside;

[0058] When the environmental impact coefficient Es is less than the environmental threshold R, it means that the environmental conditions are normal, the temperature control equipment and the humidity regulator are in standby mode, continuously monitoring the changes in temperature and humidity, and the electrostatic control equipment and the air purification equipment remain in the monitoring state without additional adjustment, but the environmental conditions are continuously detected.

[0059] A high-speed braiding machine intelligent control method comprises the following steps:

[0060] Step 1: Real-time monitoring of the tension changes of the yarn during the weaving process to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set;

[0061] Step 2: Collect the torque NJ of the yarn supply wheel, the radius r of the yarn supply wheel drum, the angular acceleration Sd of the yarn supply wheel drum, the rotation speed v of the yarn supply wheel, and the total path length of the yarn , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set;

[0062] Step 3: monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set;

[0063] Step 4: extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, obtain the tension fluctuation trend analysis results to generate the first control strategy and the second control strategy;

[0064] Step 5: After the first control strategy and the second control strategy are implemented, the weaving density md, the needle wear ztms, the knitting machine running time yxsj, the frequency of the yarn interlacing points Jzpl, the number of yarn burrs Mc and the number of yarn surface nodules JJs are collected to generate a fourth data set, and after constructing the yarn wear index Yw, the yarn wear index Yw is evaluated to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the speed of the knitting machine and the yarn supply speed according to the wear risk level to automatically optimize the knitting process;

[0065] Step 6: Compare the environmental impact coefficient Es with the environmental threshold R to obtain a third evaluation result, and perform environmental control on the area with abnormal environmental conditions based on the third evaluation result.

[0066] The present invention provides an intelligent control system and method for a high-speed braiding machine, which has the following beneficial effects:

[0067] (1) The tension monitoring module can monitor the tension changes of the yarn in real time and collect relevant data to obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking Through the generated first data set, the system can accurately analyze the tension fluctuations of the yarn and adjust the parameters of the knitting machine in time to keep the tension stable, reduce the risk of yarn breakage, and reduce production interruptions and raw material waste.

[0068] The yarn path change acquisition module collects the relevant parameters of the yarn supply wheel, such as the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration of the yarn supply wheel drum Sd, the yarn supply wheel speed v, and the total yarn path length , and the turning point data on the yarn path, the second data set generated can be used to monitor the changes in the yarn path in real time. This enables the system to adjust the operation of the knitting machine in time to prevent the yarn from twisting, knotting or entanglement, ensure the stability of knitting quality, and reduce production complexity and cost.

[0069] The yarn break prediction module extracts features from the first data group, the second data group, and the third data group, calculates the tension fluctuation index and the environmental impact coefficient, and generates the yarn break prediction coefficient Dfxs. The system can generate the first control strategy and the second control strategy based on these data, and optimize the weaving process according to the prediction results, thereby reducing the occurrence of yarn breakage and improving production efficiency.

[0070] (2) The environmental perception module can monitor factors such as temperature, humidity, static electricity, and dust particle concentration in the weaving environment. The generated third data set helps to evaluate the impact of the environment on the weaving process. This enables the system to adjust the operation strategy of the weaving machine according to environmental changes and reduce the impact of environmental factors on weaving quality.

[0071] (3) The weaving density control module generates the fourth data set and constructs the yarn wear index Yw through the weaving density md, needle wear ztms, weaving machine running time yxsj, frequency of yarn interlacing points Jzpl, number of yarn burrs Mc and number of yarn surface nodules JJs. The system can evaluate the yarn wear in real time and adjust the speed of the weaving machine and the yarn supply speed according to the risk level to automatically optimize the weaving process. This not only improves the uniformity and strength of the fabric, but also extends the service life of the weaving machine and reduces maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 The present invention is a schematic diagram of a high-speed braiding machine intelligent control block diagram flow chart. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] See also Figure 1 , the present invention provides an intelligent control system for a high-speed braiding machine, including a tension monitoring module, a yarn path change acquisition module, an environment perception module, a yarn break prediction module and a braiding density control module;

[0075] The tension monitoring module is used to monitor the tension changes of the yarn in the weaving process in real time to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set;

[0076] The yarn path change acquisition module is used to collect the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration of the yarn supply wheel drum Sd, the yarn supply wheel speed v, and the total yarn path length , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set;

[0077] The environment sensing module is used to monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set;

[0078] The yarn break prediction module is used to extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, and obtain the tension fluctuation trend analysis result to generate the first control strategy and the second control strategy;

[0079] The weaving density control module is used to collect real-time images in the weaving process after the implementation of the first control strategy and the second control strategy, obtain an image data set, and analyze the image data set through image processing technology to obtain the weaving density md, needle wear ztms, frequency of yarn interlacing points Jzpl, number of yarn burrs Mc and number of yarn surface nodules JJs, and obtain the knitting machine running time yxsj through the running timer measurement, generate the fourth data group, and construct the yarn wear index Yw, then evaluate the yarn wear index Yw to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the knitting machine speed and yarn supply speed according to the wear risk level to automatically optimize the weaving process.

[0080] In this embodiment, the tension monitoring module can monitor the tension change of the yarn in real time and collect relevant data to obtain the tensile force F, the cross-sectional area A of the yarn fiber, the original length of the yarn fiber before stretching, and the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking Through the generated first data set, the system can accurately analyze the tension fluctuations of the yarn and adjust the parameters of the knitting machine in time to keep the tension stable, reduce the risk of yarn breakage, and reduce production interruptions and raw material waste.

[0081] The yarn path change acquisition module collects the relevant parameters of the yarn supply wheel, such as the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration of the yarn supply wheel drum Sd, the yarn supply wheel speed v, and the total yarn path length , and the turning point data on the yarn path, the second data set generated can be used to monitor the changes in the yarn path in real time. This enables the system to adjust the operation of the knitting machine in time to prevent the yarn from twisting, knotting or entanglement, ensure the stability of knitting quality, and reduce production complexity and cost.

[0082] The environmental sensing module can monitor factors such as temperature, humidity, static electricity and dust particle concentration in the weaving environment, and the generated third data set helps to evaluate the impact of the environment on the weaving process. This enables the system to adjust the operation strategy of the knitting machine according to environmental changes and reduce the impact of environmental factors on the weaving quality.

[0083] The yarn break prediction module extracts features from the first data group, the second data group, and the third data group, calculates the tension fluctuation index and the environmental impact coefficient, and generates the yarn break prediction coefficient Dfxs. The system can generate the first control strategy and the second control strategy based on these data, and optimize the weaving process according to the prediction results, thereby reducing the occurrence of yarn breakage and improving production efficiency.

[0084] The weaving density control module uses a high-resolution industrial camera or a high-speed camera to capture the yarn in the working area of ​​the braiding machine in real time, and uses image processing technology to accurately extract the characteristic data of the yarn, especially through edge detection algorithms, Hough transforms, morphological processing and other methods, to achieve efficient monitoring of parameters such as yarn tension, yarn path, interlacing point frequency and needle wear. Through this image recognition technology, the system can analyze the relative distance between yarns, yarn surface burrs, the number and morphology of nodules in real time, so as to derive key parameters such as braiding density and yarn surface quality, generate the fourth data group, and construct the yarn wear index Yw. The system can evaluate the yarn wear in real time, adjust the speed of the braiding machine and the yarn supply speed according to the risk level, and automatically optimize the braiding process. This not only improves the uniformity and strength of the fabric, but also extends the service life of the braiding machine and reduces maintenance costs.

[0085] See also Figure 1 ,The tension monitoring module includes a tension sensing unit and a fracture testing unit;

[0086] The tension sensing unit is used to monitor the changes in yarn tension during the weaving process in real time, and to obtain the tensile force F and the cross-sectional area A of the yarn fiber; the tensile force F and the cross-sectional area A of the yarn fiber are measured and obtained by the tension sensor and the laser rangefinder.

[0087] The breaking test unit is used to test the yarn before stretching and the breaking test data, and obtain the original length of the yarn fiber before stretching. , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking . Obtained by tensile testing machine, displacement sensor or strain gauge to stretch the yarn to break test.

[0088] The tension monitoring module can monitor the yarn tension in real time and obtain the break test data. These data are important for accurately controlling the yarn tension during the weaving process, optimizing the weaving quality and reducing the risk of yarn breakage.

[0089] See also Figure 1 ,The environment sensing module includes a temperature monitoring unit, a humidity monitoring unit, an static monitoring unit, and a dust concentration monitoring unit;

[0090] The temperature monitoring unit is used to monitor the temperature change around the knitting machine through a temperature sensor and generate a temperature value wd;

[0091] The humidity monitoring unit is used to monitor the change of environmental humidity through the humidity sensor and generate a humidity value sdz;

[0092] The static electricity monitoring unit is used to monitor the static electricity accumulation degree during the weaving process through the static electricity sensor and generate static electricity Jdz;

[0093] The dust concentration monitoring unit is used to monitor the dust concentration accumulation degree during the weaving process through a dust concentration sensor and generate a dust particle concentration value ndz.

[0094] In this embodiment, by monitoring temperature changes, the braiding machine or the surrounding environment can be prevented from overheating, thereby avoiding yarn material deterioration or braiding machine failure caused by high temperature. Humidity has a significant impact on the elasticity, expansion and strength of the yarn. Timely adjustment of the ambient humidity helps to maintain the stability of the yarn and reduce braiding problems caused by uneven humidity. By real-time monitoring of static electricity levels, timely measures can be taken, such as the use of static eliminators, to reduce the impact of static electricity on the yarn and prevent yarn adhesion, knotting or breakage caused by static electricity. Real-time monitoring of dust concentration can help clean up dust accumulation in a timely manner and avoid dust contamination of the braiding machine and yarn, thereby maintaining braiding quality.

[0095] See also Figure 1 The yarn break prediction module includes a summary calculation unit, which is used to extract features from the data in the first data group, the second data group and the third data group to obtain the tension fluctuation index Zbd and the environmental impact coefficient Es;

[0096] The steps for obtaining the tension fluctuation index Zbd are:

[0097] S11, extracting the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching from the first data set , length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking After dimensionless processing, the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs are calculated by the following formula:

[0098]

[0099] In the formula, represents stress, Indicates strain, which is the ratio of the incremental length change during the stretching process to the original length;

[0100] S12, extracting the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration Sd of the yarn supply wheel drum, the rotation speed v of the yarn supply wheel, and the total path length of the yarn from the second data set , the turning angle of the yarn at the i-th turning point on the path And the total number of yarn turning on the path n, after dimensionless processing, is calculated by the following formula: drum moment of inertia Irt, yarn supply wheel speed fluctuation rate Sws and weaving path turning rate Crv:

[0101]

[0102] In the formula, It represents the speed of the yarn feeding wheel in the i-th time period, which is measured by the speed sensor. Indicates the average speed of the yarn supply wheel, N is the total time period for measuring the speed data;

[0103] S13, after dimensionless processing of the calculated yarn fiber tensile elastic coefficient Fec, yarn fiber breaking strength coefficient Fbs, drum rotational inertia Irt, yarn supply wheel speed fluctuation rate Sws and braiding path turning rate Crv, the tension fluctuation index Zbd is calculated by the following formula:

[0104] In the formula, It is the weight coefficient of the product of the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs. , and They represent the weight coefficients of the drum moment of inertia Irt, the yarn supply wheel speed fluctuation rate Sws and the braiding path turning rate Crv, respectively. , , , , ,and . Represents the first correction constant.

[0105] The yarn fiber tensile elastic coefficient Fec is a measure of the strain caused by unit stress during the yarn stretching process, reflecting the elastic properties of the yarn when subjected to stress. The higher the yarn fiber tensile elastic coefficient Fec, the better the stress stability of the shape under tensile deformation;

[0106] The yarn fiber breaking strength coefficient Fbs indicates the maximum load-bearing capacity of the yarn. A higher breaking strength coefficient means that the yarn can withstand greater tension during the weaving process, thereby reducing the risk of yarn breakage and improving production stability. The higher the better;

[0107] The moment of inertia of the drum Irt. A drum with a larger moment of inertia requires more effort during acceleration or deceleration, which may cause speed fluctuations and tension changes. Understanding the moment of inertia of the drum helps optimize the operating parameters of the braiding machine and reduce tension fluctuations caused by drum inertia; the speed fluctuation rate of the yarn supply wheel Sws indicates that the speed of the yarn supply wheel is unstable, which will directly affect the supply tension of the yarn and cause fluctuations in the braiding quality. Reducing the speed fluctuation rate can improve the stability of the braiding process and product quality;

[0108] A high weaving path turning rate Crv means that the yarn needs to turn frequently during the weaving process, which may increase the friction and tension variation of the yarn and lead to unstable weaving quality. Understanding the turning rate can help optimize the yarn path design, thereby reducing the friction and tension fluctuation of the yarn.

[0109] In this embodiment, by calculating the tension fluctuation index Zbd, the tension fluctuation of the yarn during the weaving process can be monitored in real time. This helps to promptly discover and correct the problem of unstable tension, thereby ensuring the consistency and stability of the weaving quality and reducing problems such as yarn breakage and fabric defects. The calculation of the tension fluctuation index can reveal potential tension problems and issue early warnings in a timely manner, thereby avoiding production interruptions caused by yarn breakage. This helps to maintain the continuity of the production process and reduce production losses caused by machine downtime. The settings of the braiding machine can be optimized, such as adjusting the speed of the yarn supply wheel, tension control, etc. This optimization helps to maintain the best weaving quality under different weaving conditions and improve production efficiency. Accurately monitoring and adjusting the yarn tension can effectively reduce yarn breakage and loss caused by tension fluctuations, thereby reducing raw material waste and improving resource utilization efficiency.

[0110] See also Figure 1 The environmental impact coefficient Es is obtained by extracting the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the third data group, and after dimensionless processing, the environmental impact coefficient Es is calculated by the following formula:

[0111] In the formula, Indicates the preset ideal temperature threshold in the weaving environment. Indicates the preset ideal humidity threshold in the weaving environment. Indicates the preset ideal electrostatic threshold in the weaving environment. Indicates the preset ideal dust particle concentration threshold in the weaving environment. , , and They are expressed as weight coefficients respectively; they are adjusted by the user. , , , ,and . Represents the second correction constant.

[0112] In this embodiment, in order to compare various indicators on the same scale, it is necessary to perform dimensionless processing on temperature, humidity, static electricity and dust concentration. Dimensionless processing converts these values ​​into a standardized form so that they can be analyzed at the same magnitude. By comprehensively considering multiple environmental factors such as temperature, humidity, static electricity and dust concentration, the environmental impact coefficient Es can comprehensively evaluate the impact of the environment on the weaving process and provide a more accurate prediction of environmental impact.

[0113] See also Figure 1 ,The yarn break prediction module includes a tension fluctuation analysis unit and a tension control unit;

[0114] The tension fluctuation analysis unit is used to generate the yarn break prediction coefficient Dfxs according to the tension fluctuation index Zbd and the environmental impact coefficient Es through dimensionless processing through the following formula to analyze the tension fluctuation trend:

[0115] In the formula, and Respectively represent the weight coefficients of the tension fluctuation index Zbd and the environmental impact coefficient Es; adjusted and set by the user, , ,and .

[0116] The tension control unit is used to preset the yarn break threshold value X, and compare the yarn break prediction coefficient Dfxs with the yarn break threshold value X to obtain the tension fluctuation trend analysis results, including:

[0117] When the yarn break prediction coefficient Dfxs> the yarn break threshold value X, it means that the tension fluctuates drastically and there is a risk of the first yarn breaking. The tension control unit generates a first control strategy, including: adjusting the speed of the yarn supply wheel to reduce the current speed by 6%-10%, and adjusting the tension controller to reduce the current tension by 5%-8%;

[0118] When the yarn break prediction coefficient Dfxs = the yarn break threshold value X, it means that the tension fluctuates at a high frequency and there is a risk of second yarn breakage, and the tension control unit generates a second control strategy, including: adjusting the speed of the yarn supply wheel to reduce the current speed by 4%-5%, and adjusting the tension controller to reduce the current tension by 1%-4%;

[0119] When the yarn break prediction coefficient Dfxs is less than the yarn break threshold value X, it means that the yarn breakage is in a stable state, there is no risk of yarn breakage, and the current yarn supply wheel speed and the pressure value of the tension controller are continuously maintained.

[0120] In this embodiment, a targeted control strategy can be generated based on the comparison between the yarn break prediction coefficient Dfxs and the preset yarn break threshold value X. When the prediction coefficient indicates that there is a risk of yarn breakage, the settings of the yarn supply wheel speed and the tension controller are adjusted to effectively reduce the occurrence of yarn breakage, thereby optimizing the weaving process and reducing production interruptions. By formulating different control strategies to deal with different levels of yarn breakage risks (such as the first yarn breakage risk and the second yarn breakage risk), more refined production control can be achieved. This hierarchical control can improve production stability and reduce production fluctuations caused by yarn breakage. By adjusting production parameters in a timely manner, yarn breakage and the waste of raw materials caused by breakage can be reduced. An effective control strategy can extend the service life of the yarn and reduce production costs.

[0121] See also Figure 1 , see Figure 1 ,The weaving density control module includes an image acquisition unit, an image processing unit and a yarn wear calculation unit;

[0122] The image acquisition unit is used to capture the image data of the working area of ​​the knitting machine in real time through a high-resolution industrial camera or a high-speed camera during the knitting process to obtain an image data set;

[0123] The image processing unit is used to receive the image data set from the image acquisition unit, process the image data set through the edge monitoring algorithm in the image processing algorithm, analyze, extract and detect the distance features between adjacent yarns, identify the yarn position through the edge detection algorithm or Hough transform, count the number of yarns in a certain area, and specifically calculate the pixel ratio occupied by the yarn in the specified area, so as to deduce the density of weaving to obtain the weaving density md;

[0124] By morphologically processing the image data set, the edge contour of the needle is identified, compared with the ideal needle shape, and the change of the wear area is detected to obtain the needle wear amount ztms;

[0125] By detecting the intersection of yarns in the image data set, using corner detection or intersection feature recognition algorithm, the position of the yarn interlacing point is found, and the movement path of the yarn in unit time is identified through motion detection technology, and the frequency of the interlacing point is counted to obtain the frequency Jzpl of the yarn interlacing point;

[0126] Using edge detection and image segmentation technology, the protruding burr features on the yarn surface are extracted, and the height and length of the burr on the yarn surface are quantified to obtain the number of burr yarns Mc on the yarn surface;

[0127] By using region growing or threshold segmentation technology, the number of nodules on the yarn surface and the area and shape characteristics of each nodule in the image data set are extracted to obtain the number of nodules on the yarn surface JJs;

[0128] The knitting machine running time yxsj is obtained by measuring the running timer;

[0129] The yarn wear calculation unit is used to extract the weaving density md, needle wear ztms, knitting machine running time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface nodule number JJs in the fourth data group, and after dimensionless processing, obtain the yarn wear index Yw by calculating through the following formula:

[0130] In the formula, , , , , and They represent the weight coefficients of weaving density md, needle wear ztms, weaving machine operation time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface knot number JJs, respectively. Represents the third correction constant.

[0131] The real-time image data of the yarn is analyzed by the image acquisition unit and the image processing unit, and important features such as weaving density, needle wear, and the frequency of yarn interlacing points are accurately extracted, so that potential problems in the weaving process, such as uneven yarn tightness and needle wear, can be discovered in time. By reasonably adjusting the weaving density and speed, the uniformity and quality of yarn weaving can be significantly improved. Through real-time monitoring of needle wear, needle wear can be predicted and discovered in time to avoid needle breakage or textile quality problems caused by excessive wear, thereby reducing equipment failure rate, extending equipment life, and reducing maintenance costs. Real-time detection of the number of burrs and nodules on the yarn surface helps to quickly identify unqualified yarns and weaving defects, reduce the generation of waste products, reduce the waste of raw materials, and improve production efficiency. The system realizes the automatic monitoring and control of key parameters such as weaving density and yarn wear through the combination of high-resolution industrial cameras and image processing algorithms, without manual intervention, ensuring the intelligent and efficient production process. Through the calculation of the yarn wear index Yw, the wear state of yarn and equipment can be predicted in advance, maintenance plans can be reasonably arranged, sudden equipment failures can be avoided, and the continuity and stability of production can be ensured.

[0132] The weaving density control module also includes a yarn fatigue analysis unit and a second control unit;

[0133] The yarn fatigue analysis unit is used to preset a wear threshold W, and compare and evaluate the yarn wear index Yw with the wear threshold W to obtain a second evaluation result, including:

[0134] When the yarn wear index Yw> the wear threshold W, it indicates that the yarn wear is abnormal, and the first wear risk level is generated. The second control unit generates a third control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 5%-8% to reduce the friction force of the yarn during the knitting process, thereby slowing down the yarn wear, starting the yarn burr removal device to clean the burrs on the yarn surface, and reducing the speed of the yarn supply wheel by 4%-6% of the current speed;

[0135] When the yarn wear index Yw=wear threshold W, it indicates that the yarn wear is abnormal, and a second wear risk level is generated. The second control unit generates a fourth control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 3%-4% to moderately reduce the pressure on the yarn, thereby controlling the wear speed, the yarn burr removal device enables the detection mode to identify and remove slight burrs on the yarn surface, and the yarn supply wheel speed is reduced by 2%-3% of the current speed to prevent further tension fluctuations from causing accelerated wear of the yarn;

[0136] When the yarn wear index Yw is less than the wear threshold W, it indicates that the yarn wear is normal. At this time, the needle knitting speed and the yarn supply wheel speed remain at the current level and no adjustment is required. The yarn burr removal device is in monitoring mode, continuously detecting but not actively removing burrs. It will only take action when an abnormality is detected on the yarn surface.

[0137] In this embodiment, even after the implementation of the first control strategy and the second control strategy, continuous regulation can monitor the actual state of the yarn and the operating parameters of the knitting machine in real time. After the initial adjustment, continued regulation helps to further optimize according to the actual production situation. This can effectively avoid the decline in production efficiency caused by insufficient parameter adjustment and ensure the smooth operation of the knitting process. By calculating the yarn wear index Yw and combining factors such as knitting density, needle wear, and knitting machine operation time, the degree of wear of the yarn can be accurately evaluated. The comprehensive evaluation after dimensionless processing makes wear management more scientific and accurate. According to the yarn wear index Yw and the preset wear threshold W, a targeted control strategy is automatically generated. When abnormal wear is found, the knitting speed of the knitting machine needle and the speed of the yarn supply wheel can be dynamically adjusted, and measures can be taken in time to slow down the wear of the yarn. The third control strategy and the fourth control strategy are implemented for further regulation. By adjusting the operating parameters of the knitting machine and cleaning the yarn burr device, the wear speed of the yarn can be effectively slowed down, the production shutdown and raw material waste caused by wear can be reduced, and the production efficiency can be improved.

[0138] See also Figure 1, and also includes an environment control module, which is used to preset an environment threshold R, and compare the environmental impact coefficient Es with the environment threshold R to obtain a third evaluation result, including:

[0139] When the environmental impact coefficient Es ≥ environmental threshold R, it means that the environmental conditions are abnormal and have a negative impact on the production quality of the yarn and the operation of the equipment. The fifth control strategy is generated, including: the temperature control device starts the cooling or heating system, and adjusts the temperature by ±3°C according to the current temperature change; keeps the yarn at the preset ideal temperature threshold range; the humidity regulator activates the dehumidification or humidification device to adjust the current humidity level to the preset ideal humidity threshold Preset ideal humidity threshold The setting is: the relative humidity is kept between 45% and 60% to ensure that the yarn fiber will not expand due to high humidity or generate static electricity due to low humidity during the weaving process; the static electricity control device is started so that the current static electricity level is within the preset ideal static electricity threshold range; and turn on the air purification equipment to set the ideal dust particle concentration threshold Inside;

[0140] When the environmental impact coefficient Es is less than the environmental threshold R, it means that the environmental conditions are normal, the temperature control equipment and the humidity regulator are in standby mode, continuously monitoring the changes in temperature and humidity, and the electrostatic control equipment and the air purification equipment remain in the monitoring state without additional adjustment, but the environmental conditions are continuously detected.

[0141] In this embodiment, by adjusting the temperature, humidity, static electricity and dust concentration in real time, it is possible to ensure that the weaving environment is always in the optimal state, thereby avoiding fluctuations in yarn quality caused by environmental factors. Stable environmental conditions help improve the uniformity and overall quality of the yarn and reduce production defects.

[0142] A high-speed braiding machine intelligent control method comprises the following steps:

[0143] Step 1: Real-time monitoring of the tension changes of the yarn during the weaving process to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , the length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set;

[0144] Step 2: Collect the torque NJ of the yarn supply wheel, the radius r of the yarn supply wheel drum, the angular acceleration Sd of the yarn supply wheel drum, the rotation speed v of the yarn supply wheel, and the total path length of the yarn , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set;

[0145] Step 3: monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set;

[0146] Step 4: extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, obtain the tension fluctuation trend analysis results to generate the first control strategy and the second control strategy;

[0147] Step 5: After the first control strategy and the second control strategy are implemented, the weaving density md, the needle wear ztms, the knitting machine running time yxsj, the frequency of the yarn interlacing points Jzpl, the number of yarn burrs Mc on the yarn surface and the number of nodules JJs on the yarn surface are collected and acquired to generate a fourth data set. After the yarn wear index Yw is constructed, the yarn wear index Yw is evaluated to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the speed of the knitting machine and the yarn supply speed according to the wear risk level to automatically optimize the knitting process.

[0148] Step 6: Compare the environmental impact coefficient Es with the environmental threshold R to obtain a third evaluation result, and perform environmental control on the area with abnormal environmental conditions based on the third evaluation result.

[0149] In this embodiment, according to steps 1 to 5, the weaving process can be precisely controlled by real-time monitoring of yarn tension, yarn supply wheel parameters and environmental conditions. This helps to ensure that the yarn works in the best condition, thereby improving the quality of the woven product, reducing the defect rate and improving the consistency of textiles. By monitoring parameters such as weaving density and needle wear, the wear of the equipment can be reduced, and overuse and equipment failure can be avoided. This helps to extend the service life of the equipment and reduce the frequency and cost of maintenance. By automatically adjusting the speed of the braiding machine and the yarn supply speed, the high efficiency of production can be maintained during the real-time monitoring and adjustment process, and the production downtime caused by equipment problems or improper operation can be reduced. Through the intelligent control method, environmental monitoring, tension control and equipment adjustment are automated to improve the intelligence level of the production process. Reduce dependence on manual intervention and improve the automation and efficiency of the system.

[0150] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0151] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A high-speed braiding machine intelligent control system, characterized in that: It includes tension monitoring module, yarn path change acquisition module, environment perception module, yarn break prediction module and weaving density control module; The tension monitoring module is used to monitor the tension changes of the yarn in the weaving process in real time, so as to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, the original length of the yarn fiber before stretching, and the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , the length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set; The yarn path change acquisition module is used to collect the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the angular acceleration Sd of the yarn supply wheel drum, the yarn supply wheel speed v, and the total yarn path length. , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set; The environment sensing module is used to monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set; The yarn break prediction module is used to extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, and associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, and obtain the tension fluctuation trend analysis result to generate the first control strategy and the second control strategy; The yarn break prediction module includes a summary calculation unit, which is used to extract features from the data in the first data group, the second data group and the third data group to obtain the tension fluctuation index Zbd and the environmental impact coefficient Es; The steps for obtaining the tension fluctuation index Zbd are: S11, extracting the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching from the first data set , the length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking After dimensionless processing, the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs are calculated by the following formula: In the formula, represents stress, Indicates strain, which is the ratio of the incremental length change during the stretching process to the original length; S12, extracting the yarn supply wheel torque NJ, the yarn supply wheel drum radius r, the yarn supply wheel drum angular acceleration Sd, the yarn supply wheel rotation speed v, and the yarn total path length from the second data set , the turning angle of the yarn at the i-th turning point on the path And the total number of yarn turning on the path n, after dimensionless processing, is calculated by the following formula: drum moment of inertia Irt, yarn supply wheel speed fluctuation rate Sws and weaving path turning rate Crv: In the formula, It represents the speed of the yarn feeding wheel in the i-th time period, which is measured by the speed sensor. Indicates the average speed of the yarn supply wheel, N is the total time period for measuring the speed data; S13, after dimensionless processing of the calculated yarn fiber tensile elastic coefficient Fec, yarn fiber breaking strength coefficient Fbs, drum rotational inertia Irt, yarn supply wheel speed fluctuation rate Sws and braiding path turning rate Crv, the tension fluctuation index Zbd is calculated by the following formula: In the formula, It is the weight coefficient of the product of the yarn fiber tensile elastic coefficient Fec and the yarn fiber breaking strength coefficient Fbs. , and They represent the weight coefficients of the drum moment of inertia Irt, the yarn supply wheel speed fluctuation rate Sws and the braiding path turning rate Crv, respectively. represents the first correction constant; The yarn break prediction module includes a tension fluctuation analysis unit and a tension control unit; The tension fluctuation analysis unit is used to generate a yarn break prediction coefficient Dfxs according to the tension fluctuation index Zbd and the environmental impact coefficient Es through dimensionless processing through the following formula to analyze the tension fluctuation trend: In the formula, and Respectively represent the weight coefficients of tension fluctuation index Zbd and environmental impact coefficient Es; The tension control unit is used to preset a yarn break threshold value X, and compare the yarn break prediction coefficient Dfxs with the yarn break threshold value X to obtain a tension fluctuation trend analysis result, including: When the yarn break prediction coefficient Dfxs> the yarn break threshold value X, it indicates that the tension fluctuation changes dramatically and there is a risk of the first yarn breaking, and the tension control unit generates a first control strategy, including: adjusting the rotation speed of the yarn supply wheel to reduce the current speed by 6%-10%, and adjusting the tension controller to reduce the current tension by 5%-8%; When the yarn break prediction coefficient Dfxs=the yarn break threshold value X, it indicates that the tension fluctuates at a high frequency and there is a risk of second yarn breakage, and the tension control unit generates a second control strategy, including: adjusting the rotation speed of the yarn supply wheel to reduce the current speed by 4%-5%, and adjusting the tension controller to reduce the current tension by 1%-4%; When the yarn break prediction coefficient Dfxs is less than the yarn break threshold value X, it indicates that the yarn breakage is in a stable state, there is no risk of yarn breakage, and the current yarn supply wheel speed and the pressure value of the tension controller are continuously maintained; the weaving density control module is used to collect real-time images in the weaving process after the first control strategy and the second control strategy are implemented, obtain an image data set, and analyze the image data set through image processing technology to obtain the weaving density md, the needle wear amount ztms, the frequency of the yarn interlacing points Jzpl, the number of yarn burrs Mc on the yarn surface and the number of nodules JJs on the yarn surface, and obtain the braiding machine running time yxsj through the running timer measurement, generate the fourth data group, and after constructing the yarn wear index Yw, evaluate the yarn wear index Yw to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the braiding machine speed and the yarn supply speed according to the wear risk level to automatically optimize the weaving process; The weaving density control module includes an image acquisition unit, an image processing unit and a yarn wear calculation unit; The image acquisition unit is used to capture image data of the working area of ​​the knitting machine in real time through a high-resolution industrial camera or a high-speed camera during the knitting process to obtain an image data set; The image processing unit is used to receive the image data set from the image acquisition unit, process the image data set through the edge detection algorithm in the image processing algorithm, analyze, extract and detect the distance features between adjacent yarns, identify the yarn position through the edge detection algorithm or Hough transform, count the number of yarns in a certain area, and specifically calculate the pixel ratio occupied by the yarn in the specified area, so as to deduce the density of weaving to obtain the weaving density md; By morphologically processing the image data set, the edge contour of the needle is identified, compared with the ideal needle shape, and the change of the wear area is detected to obtain the needle wear amount ztms; By detecting the intersection of yarns in the image data set, using corner detection or intersection feature recognition algorithm, the position of the yarn interlacing point is found, and the movement path of the yarn in unit time is identified through motion detection technology, and the frequency of the interlacing point is counted to obtain the frequency Jzpl of the yarn interlacing point; Using edge detection and image segmentation technology, the protruding burr features on the yarn surface are extracted, and the height and length of the burr on the yarn surface are quantified to obtain the number of burr yarns Mc on the yarn surface; By using region growing or threshold segmentation technology, the number of nodules on the yarn surface and the area and shape characteristics of each nodule in the image data set are extracted to obtain the number of nodules on the yarn surface JJs; The yarn wear calculation unit is used to extract the weaving density md, needle wear ztms, knitting machine running time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface nodule number JJs in the fourth data group, and after dimensionless processing, obtain the yarn wear index Yw by calculating through the following formula: In the formula, , , , , and They represent the weight coefficients of weaving density md, needle wear ztms, weaving machine operation time yxsj, yarn interlacing point frequency Jzpl, yarn surface burr yarn number Mc, yarn surface knot number JJs, respectively. represents the third correction constant; The braiding density control module also includes a yarn fatigue analysis unit and a second control unit; The yarn fatigue analysis unit is used to preset a wear threshold W, and compare and evaluate the yarn wear index Yw with the wear threshold W to obtain a second evaluation result, including: When the yarn wear index Yw> the wear threshold W, it indicates that the yarn wear is abnormal, and the first wear risk level is generated. The second control unit generates a third control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 5%-8% to reduce the friction force of the yarn during the knitting process, thereby slowing down the yarn wear, starting the yarn burr removal device to clean the burrs on the yarn surface, and reducing the speed of the yarn supply wheel by 4%-6% of the current speed; When the yarn wear index Yw=wear threshold W, it indicates that the yarn wear is abnormal, and a second wear risk level is generated. The second control unit generates a fourth control strategy, including: adjusting the knitting speed of the knitting machine needle to reduce the current speed by 3%-4% to moderately reduce the pressure on the yarn, thereby controlling the wear speed, the yarn burr removal device enables the detection mode to identify and remove slight burrs on the yarn surface, and the yarn supply wheel speed is reduced by 2%-3% of the current speed to prevent further tension fluctuations from causing accelerated wear of the yarn; When the yarn wear index Yw is less than the wear threshold W, it indicates that the yarn wear is normal. At this time, the needle knitting speed and the yarn supply wheel speed remain at the current level without adjustment. The yarn burr removal device is in monitoring mode, continuously detecting but not actively removing burrs.

2. The intelligent control system for a high-speed braiding machine according to claim 1 is characterized in that: The tension monitoring module includes a tension sensing unit and a fracture testing unit; The tension sensing unit is used to monitor the change of yarn tension in real time during the weaving process, and obtain the tensile force F and the cross-sectional area A of the yarn fiber; The breaking test unit is used to test the yarn before stretching and the breaking test data of the yarn, and obtain the original length of the yarn fiber before stretching. , the length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking .

3. The intelligent control system for a high-speed braiding machine according to claim 1 is characterized in that: The environment sensing module includes a temperature monitoring unit, a humidity monitoring unit, a static electricity monitoring unit and a dust concentration monitoring unit; The temperature monitoring unit is used to monitor the temperature change around the knitting machine and generate a temperature value wd; The humidity monitoring unit is used to monitor the change of environmental humidity and generate a humidity value sdz; The static electricity monitoring unit is used to monitor the static electricity accumulation degree during the weaving process and generate static electricity Jdz; The dust concentration monitoring unit is used to monitor the dust concentration accumulation degree during the weaving process and generate a dust particle concentration value ndz.

4. The intelligent control system for a high-speed braiding machine according to claim 1 is characterized in that: The environmental impact coefficient Es is obtained by extracting the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the third data group, and after dimensionless processing, the environmental impact coefficient Es is calculated by the following formula: In the formula, Indicates the preset ideal temperature threshold in the weaving environment. Indicates the preset ideal humidity threshold in the weaving environment. Indicates the preset ideal electrostatic threshold in the weaving environment. Indicates the preset ideal dust particle concentration threshold in the weaving environment. , , and They are expressed as weight coefficients respectively; Represents the second correction constant.

5. The intelligent control system for a high-speed braiding machine according to claim 1 is characterized in that: The system further includes an environment control module, which is used to preset an environment threshold R and compare the environment impact coefficient Es with the environment threshold R to obtain a third evaluation result, including: When the environmental impact coefficient Es ≥ environmental threshold R, it means that the environmental conditions are abnormal and have a negative impact on the production quality of the yarn and the operation of the equipment. The fifth control strategy is generated, including: the temperature control device starts the cooling or heating system, and adjusts the temperature by ±3°C according to the current temperature change; keeps the yarn at the preset ideal temperature threshold range; the humidity regulator activates the dehumidification or humidification device to adjust the current humidity level to the preset ideal humidity threshold Preset ideal humidity threshold The setting is: the relative humidity is kept between 45% and 60% to ensure that the yarn fiber will not expand due to high humidity or generate static electricity due to low humidity during the weaving process; the static electricity control device is started so that the current static electricity level is within the preset ideal static electricity threshold range; and turn on the air purification equipment to set the ideal dust particle concentration threshold Inside; When the environmental impact coefficient Es is less than the environmental threshold R, it means that the environmental conditions are normal, the temperature control equipment and the humidity regulator are in standby mode, continuously monitoring the changes in temperature and humidity, and the electrostatic control equipment and the air purification equipment remain in the monitoring state without additional adjustment, but the environmental conditions are continuously detected.

6. A high-speed braiding machine intelligent control method, applied to a high-speed braiding machine intelligent control system according to any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: Real-time monitoring of the tension changes of the yarn during the weaving process to collect and obtain the tensile force F, the cross-sectional area A of the yarn fiber, and the original length of the yarn fiber before stretching. , the length increment during stretching and the maximum tensile force that the yarn fiber can withstand before breaking , generating a first data set; Step 2: Collect the torque NJ of the yarn supply wheel, the radius r of the yarn supply wheel drum, the angular acceleration Sd of the yarn supply wheel drum, the rotation speed v of the yarn supply wheel, and the total path length of the yarn , the turning angle of the yarn at the i-th turning point on the path and the total number n of turns of the yarn on the path, to generate a second data set; Step 3: monitor the temperature value wd, humidity value sdz, static electricity Jdz and dust particle concentration value ndz in the weaving environment to generate a third data set; Step 4: extract features from the data in the first data group, the second data group and the third data group, obtain the tension fluctuation index Zbd and the environmental influence coefficient Es, associate the tension fluctuation index Zbd with the environmental influence coefficient Es, obtain the yarn break prediction coefficient Dfxs and evaluate it, obtain the tension fluctuation trend analysis result to generate the first control strategy and the second control strategy; Step 5: After the first control strategy and the second control strategy are implemented, the weaving density md, the needle wear ztms, the knitting machine running time yxsj, the frequency of the yarn interlacing points Jzpl, the number of yarn burrs Mc on the yarn surface and the number of nodules JJs on the yarn surface are collected and acquired to generate a fourth data set. After the yarn wear index Yw is constructed, the yarn wear index Yw is evaluated to analyze whether there is abnormal yarn wear, obtain the wear risk level, and further adjust the speed of the knitting machine and the yarn supply speed according to the wear risk level to automatically optimize the knitting process. Step 6: Compare the environmental impact coefficient Es with the environmental threshold R to obtain a third evaluation result, and perform environmental control on the area with abnormal environmental conditions based on the third evaluation result.

Images