An electronic control data optimization system for a rapier loom

Abstract

The present invention provides an electronic control data optimization system for a rapier loom, which relates to the technical field of electronic control data optimization. The system includes: a material perception module for real-time identifying the material type of a fabric through a spectral analysis sensor array and a dielectric feature extraction unit, including the fusion analysis of the hydroxyl vibration characteristics of cotton fibers and the phase difference of the dielectric constant of chemical fiber materials; a density analysis module for quantifying the distribution density of warp and weft yarns and generating a three-dimensional heat map of the yarn crossing points per square centimeter. Through the cooperation of multiple modules, accurate material identification, quantification of warp and weft yarn density, monitoring of operating parameters and pattern recognition, the present invention realizes the intelligent cooperative control of the main motor and the let-off / take-up motor, thereby reducing the yarn breakage rate, improving the production efficiency and reducing the energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic control data optimization, and particularly to an electronic control data optimization system for a rapier loom. Background Art

[0002] In the textile industry, as an important weaving equipment, the working efficiency and product quality of rapier looms are affected by various factors. Among them, fabric material and warp and weft density are key factors affecting the running stability and weaving quality of looms.

[0003] Among them, fabric material and warp and weft density are key factors affecting the running stability and weaving quality of looms. When traditional looms weave fabrics with these two different materials and densities, it is often necessary to manually adjust loom parameters, such as the speed of the main motor and the response speed of the let-off / warping motor. When switching from weaving pure cotton sheets to chemical fiber curtain fabrics, the operator needs to manually and significantly reduce the speed of the main motor based on experience, and at the same time finely adjust the response speed of the let-off / warping motor to adapt to the greater friction of chemical fiber materials and different warp and weft density requirements. However, manual adjustment not only increases the operation difficulty but also is prone to errors.

[0004] In addition, most of the existing electronic control systems lack the function of automatically adjusting loom parameters according to fabric material and warp and weft density, and it is difficult to meet the requirements of the textile industry for efficient and high-quality weaving. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an electronic control data optimization system for a rapier loom, which automatically adjusts the speed of the loom main motor and the response speed of the let-off / warping motor to reduce yarn breakage or downtime and improve weaving efficiency and product quality.

[0006] To solve the above technical problem, the technical solution of the present invention is as follows:

[0007] In a first aspect, an electronic control data optimization system for a rapier loom includes:

[0008] A material perception module, configured to use a spectral analysis sensor array and a dielectric feature extraction unit to identify the material type of the fabric in real time, including the fusion analysis of the hydroxyl vibration characteristics of cotton fibers and the dielectric constant phase difference of chemical fiber materials;

[0009] A density analysis module, configured to quantify the distribution density of warp and weft yarns and generate a three-dimensional heat map of yarn intersections per square centimeter;

[0010] A monitoring module, configured to continuously collect dynamic parameters during the operation of the loom, including the speed of the main motor, the torque of the let-off motor, the response speed of the take-up motor, and the warp tension data, and identify four working modes of the loom, namely startup, steady-state operation, variable-speed weaving, and shutdown transition, according to the dynamic parameters;

[0011] Intelligent decision-making module, used to dynamically calculate the final response speed of the main motor and generate motor control instructions based on fabric material type, warp and weft density data and dynamic parameters combined with the current working mode;

[0012] The execution optimization module is used to drive the main motor to operate according to the motor control instructions, and to link the warp feeding / winding motor speed ratio relationship to follow the changes in the main motor speed, so as to adjust the equipment operation status in real time.

[0013] Furthermore, the material type of the fabric can be identified in real time through the spectral analysis sensor array and the dielectric feature extraction unit, including the fusion analysis of the cotton fiber hydroxyl vibration characteristics and the dielectric constant phase difference of the chemical fiber material, including:

[0014] The multi-band spectral reflectance of the fabric is detected by the spectral analysis sensor array to generate multi-band spectral reflectance data; the dielectric feature extraction unit measures the response of the fabric in the electric field to obtain the dielectric constant phase difference data of the chemical fiber material;

[0015] Extract spectral features related to the hydroxyl vibration characteristics of cotton fibers from multi-band spectral reflectance data, including the absorption peak and peak area of the band; analyze the dielectric constant phase difference data, and extract characteristic parameters from the original dielectric constant phase difference data, including the average value, standard deviation, and spectrum characteristics of the phase difference;

[0016] The characteristic parameters extracted from the spectral features and the dielectric constant phase difference data are fused to form a fused feature vector;

[0017] The fused feature vector is input into the three-level classifier for material determination, thus realizing real-time identification of the material type of the fabric.

[0018] Furthermore, the three-level classifier determination process includes:

[0019] Primary classification: The hydroxyl-related parameter value ≥ 0.65 is set as the threshold, and the natural fibers containing cotton components and pure synthetic fibers are distinguished based on the relevant features in the fused feature vector;

[0020] Secondary classification: For samples judged to contain cotton in the primary classification, the Mahalanobis distance classifier is used to match the cotton fiber purity grade based on the principal component distribution from the first principal component to the third principal component obtained by principal component analysis based on the fused feature vector;

[0021] Three-level classification: For samples judged as pure synthetic fibers in the first-level classification, a support vector machine is used to construct a hyperplane by fusing the loss tangent value in the feature vector with the second principal component to distinguish between three types of chemical fiber materials: polyester, polyamide, and nylon.

[0022] Furthermore, quantize the distribution density of warp and weft yarns to generate a three-dimensional heat map of yarn intersections per square centimeter, including:

[0023] During the operation of the loom, continuously photograph the fabric to obtain a series of images containing warp and weft yarns;

[0024] Preprocess a series of images containing warp and weft yarns, and binarize the preprocessed images; use an edge detection algorithm to identify the edges of warp and weft yarns in the binarized images, and identify the intersections and corresponding coordinates of warp and weft yarns;

[0025] Divide the fabric image into small regions, count the yarn intersections in each small region to obtain the number of intersections in each region;

[0026] According to the number of intersections in each region, calculate the distribution density data of warp and weft yarns in the corresponding region;

[0027] Map the distribution density data of warp and weft yarns in each small region into three-dimensional space, where the position of the region is used as the two-dimensional coordinate and the density value is used as the third-dimensional coordinate;

[0028] Perform interpolation processing on the mapped distribution density data of warp and weft yarns in three-dimensional space, and draw a three-dimensional heat map according to the interpolated distribution density data of warp and weft yarns.

[0029] Furthermore, continuously collect the dynamic parameters during the operation of the loom, including the main motor speed, warp feeding motor torque, take-up motor response speed, and warp tension data, and identify the four working modes of the loom, namely startup, steady-state operation, variable-speed weaving, and shutdown transition, according to the dynamic parameters, including:

[0030] Judge the current working mode through the joint analysis of the main motor speed change rate, the average value of the warp feeding motor torque, and the standard deviation of the warp tension, that is:

[0031] When the main motor speed change rate ≥ 50 rpm / s and the standard deviation of the warp tension > 8N, it is marked as the startup mode;

[0032] When the main motor speed change rate ≤ 5 rpm / s and the standard deviation of the warp tension < 3N, it is marked as the steady-state operation mode;

[0033] When a preset weft density parameter change is detected, trigger the variable-speed weaving mode;

[0034] When the main motor speed ≤ 30% of the rated value, activate the shutdown transition mode.

[0035] Furthermore, according to the fabric material type, warp and weft density data, and dynamic parameters, combined with the current working mode, dynamically calculate the final response speed of the main motor and generate a motor control instruction, including:

[0036] Preset a control strategy database under different combinations of fabric material types, warp and weft densities, dynamic parameters, and working modes, and perform a matching operation in the control strategy database to obtain the corresponding reference value of the main motor response speed;

[0037] Set corresponding evaluation indicators and preset standards for different working modes, analyze and evaluate the current dynamic parameters, and obtain the analysis and evaluation results;

[0038] Generate an adjustment plan for the control strategy according to the analysis and evaluation results, and apply the adjustment plan to the reference value of the main motor response speed to obtain the preliminarily adjusted main motor response speed;

[0039] Calculate the final response speed of the main motor according to the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and the current working mode;

[0040] Convert the final response speed of the main motor into a motor control instruction, and the instruction includes the target speed, acceleration, and running time information of the motor.

[0041] Further, calculate the final response speed of the main motor according to the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and the current working mode, including:

[0042] Analyze the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and the current working mode, and obtain the adjusted basic speed according to the reference value of the main motor response speed and the speed adjustment amount in the analysis and evaluation results;

[0043] Determine the influence amount of the fabric material on the main motor speed according to the material category to which the current fabric belongs; determine the influence amount of the warp and weft density on the main motor speed according to the warp and weft density of the fabric;

[0044] Determine the adjustment amount for the dynamic parameters according to the main motor speed, let-off motor torque, take-up motor response speed, and warp tension parameters;

[0045] Determine the corresponding working mode adjustment amount from the preset mode parameter table according to the current working mode of the rapier loom;

[0046] Integrate the adjusted basic speed, the influence amount of the fabric material on the main motor speed, the influence amount of the warp and weft density on the main motor speed, the adjustment amount for the dynamic parameters, and the working mode adjustment amount to obtain the final response speed of the main motor.

[0047] Furthermore, the main motor is driven to operate according to the motor control instruction, and the speed ratio of the warp letting-off / winding motor is linked to follow the speed change of the main motor, so as to adjust the operation status of the equipment in real time, including:

[0048] Generate corresponding motor control instructions, including speed and direction, according to the final response speed of the main motor, and send the motor control instructions to the driving device of the main motor;

[0049] After the main motor is started, the target speeds of the let-off motor and the take-up motor are calculated according to the real-time running speed of the main motor and the preset speed ratio relationship between the let-off / take-up motor and the main motor;

[0050] Operate the drive devices of the warp let-off motor and the take-up motor at the target speed. During operation, monitor the actual speed in real time and compare it with the target speed.

[0051] During the operation of the main motor, let-off motor and take-up motor, the operating status data of the equipment is continuously collected, including the motor current, voltage, temperature, warp tension and fabric density parameters;

[0052] According to the operating status data of the equipment, the operating status of the entire rapier loom is evaluated and analyzed to adjust the operating status of the equipment in real time.

[0053] In a second aspect, a computing device includes:

[0054] one or more processors;

[0055] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the system.

[0056] According to a third aspect, a computer-readable storage medium stores a program, and the program implements the system when executed by a processor.

[0057] The above solution of the present invention includes at least the following beneficial effects:

[0058] The material perception module uses a spectral analysis sensor array and a dielectric feature extraction unit to identify the type of fabric material. For example, for fabrics of different materials, the intelligent decision-making module can dynamically calculate a more appropriate final response speed of the main motor to ensure the adaptation of the warp tension and weaving speed, thereby reducing fabric defects and improving the overall quality of the fabric. The three-dimensional heat map of yarn intersections per square centimeter generated by the density analysis module allows operators to clearly understand the distribution density of warp and weft yarns. During the production process, the operating parameters of the loom can be further optimized based on this precise density information to ensure uniform warp and weft density of the fabric and improve the flatness and quality of the fabric.

[0059] The monitoring module can accurately identify the four working modes of the loom, and the intelligent decision-making module dynamically calculates the response speed of the main motor and generates control instructions based on the fabric material, warp and weft density and dynamic parameters, combined with the working mode. This allows the loom to quickly adjust to the optimal operating state in different working stages, reducing transition time and improving production efficiency. For example, it can quickly reach the appropriate operating speed in the startup mode, and can quickly respond and adjust parameters in the variable speed weaving mode. The execution optimization module drives the main motor to run, and the warp feeding / winding motor speed ratio relationship is linked to follow the changes in the main motor speed, and the equipment operation status is adjusted in real time. This linkage control ensures the coordinated work of various parts of the loom, avoids production stagnation caused by uncoordinated motor speeds, and further improves production efficiency.

[0060] By real-time monitoring of the dynamic parameters and working mode of the loom, the motor's operating speed and torque can be adjusted according to the actual situation to avoid the motor running under high load or inappropriate working conditions for a long time, thereby reducing equipment loss and maintenance costs. For example, in the shutdown transition mode, the motor speed can be smoothly reduced to reduce mechanical shock and extend the service life of the equipment. The intelligent decision-making module dynamically calculates the final response speed of the main motor, so that the motor can reduce energy consumption as much as possible while meeting production needs. According to factors such as fabric material and warp and weft density, the motor power can be reasonably adjusted to avoid energy waste and reduce production costs.

[0061] Through various modules, a large amount of production data is collected and analyzed, including fabric material, warp and weft density, motor dynamic parameters, etc. These data provide strong support for production decisions and realize the transformation from traditional production to data-driven intelligent production. Managers can make more scientific production plans and management based on the data and analysis results provided, monitor the operation status of the loom in real time, and adjust the equipment operation status in real time according to the actual situation. This real-time feedback and optimization mechanism makes the production process of the loom more stable and reliable, and improves the automation and intelligence level of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of a schematic diagram of an electric control data optimization system for a rapier loom provided by an embodiment of the present invention.

[0063] Figure 2 It is a flow chart of an electric control data optimization system of a rapier loom provided by an embodiment of the present invention, in which a driving main motor of the system operates according to a motor control instruction, and a speed ratio relationship of the warp feeding / winding motor is linked to follow the speed change of the main motor, so as to adjust the operating status of the equipment in real time. DETAILED DESCRIPTION

[0064] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0065] like Figure 1 As shown, an embodiment of the present invention provides an electronic control data optimization system for a rapier loom, comprising:

[0066] Material perception module 1, used to identify the material type of fabric in real time through the spectral analysis sensor array and dielectric feature extraction unit, including the fusion analysis of the hydroxyl vibration characteristics of cotton fiber and the phase difference of the dielectric constant of chemical fiber material;

[0067] Density analysis module 2, used to quantify the distribution density of warp and weft yarns and generate a three-dimensional heat map of yarn intersections per square centimeter;

[0068] Monitoring module 3 is used to continuously collect dynamic parameters during the operation of the loom, including the main motor speed, the torque of the warp let-off motor, the response speed of the take-up motor and the warp tension data, and identify the four working modes of the loom, namely, start-up, steady-state operation, variable speed weaving and shutdown transition, according to the dynamic parameters;

[0069] Intelligent decision module 4, used to dynamically calculate the final response speed of the main motor according to the fabric material type, warp and weft density data and dynamic parameters, combined with the current working mode, and generate motor control instructions;

[0070] The execution optimization module 5 is used to drive the main motor to operate according to the motor control instruction, and to link the warp feeding / winding motor speed ratio relationship to follow the change of the main motor speed, so as to adjust the equipment operation status in real time.

[0071] In an embodiment of the present invention, the spectrum analysis sensor array and the dielectric feature extraction unit are used to perform real-time material identification, which can quickly and accurately determine the type of fabric material. By integrating the vibration characteristics of the hydroxyl group of cotton fibers and the phase difference of the dielectric constant of chemical fiber materials, the accuracy of material judgment is improved, which helps the loom to adapt the most suitable weaving parameters in advance and reduce the defective rate caused by misjudgment of materials. For example, when weaving blended fabrics, accurate identification of the material ratio can enable the loom to work at the appropriate tension and speed, reduce yarn breakage, and improve the flatness and uniformity of the fabric.

[0072] The density analysis module 2 quantifies the distribution density of warp and weft yarns and generates a 3D heat map, providing intuitive and detailed fabric density information for operators. Operators can clearly understand the density differences in different parts of the fabric based on the heat map, and thus adjust the loom parameters accordingly. For example, when weaving fabrics with complex patterns and large density variations, the warp feeding and take-up systems can be finely controlled according to the heat map to ensure that the density of each area of the fabric meets the design requirements, improve the weaving accuracy of complex patterns, and make the finished pattern clear and three-dimensional.

[0073] The monitoring module 3 continuously collects a variety of dynamic parameters, which can comprehensively reflect the real-time operating status of the loom. The accurate monitoring of the main motor speed, warp feeding motor torque, take-up motor response speed, and warp tension can promptly detect abnormal situations during the loom operation. For example, when the warp tension suddenly increases, it can quickly determine that there may be problems such as yarn jamming, and stop the machine in time to avoid yarn breakage and equipment damage. Accurately identifying four working modes enables the loom to automatically adjust the operating strategy according to different working conditions. In the startup mode, the motor startup sequence and speed are optimized to reduce startup impact; in the steady-state operation mode, all parameters are kept stable to ensure product quality; in the variable-speed weaving mode, it quickly responds to parameter changes to ensure the weaving effect; in the shutdown transition mode, the motor speed is smoothly reduced to protect the equipment. This improves the stability and reliability of the loom operation, reduces equipment failure rates, and extends the service life of the equipment.

[0074] The intelligent decision-making module 4 dynamically calculates the final response speed of the main motor based on various factors and generates control instructions, realizing the intelligent adjustment of loom parameters. Compared with traditional manual adjustment, it can comprehensively consider fabric materials, warp and weft densities, dynamic parameters, and working modes, and give a more scientific and reasonable motor operation plan. For example, when weaving fabrics of different materials and densities, it can automatically match the final main motor speed, enabling the loom to operate efficiently while ensuring appropriate yarn tension, reducing yarn breakage, improving production efficiency and product quality, and reducing the defective rate to less than 5%.

[0075] The execution optimization module 5 drives the main motor to operate according to the instructions and links the speed ratio relationship of the warp feeding / take-up motors to ensure the coordinated operation of each motor. This precise coordinated control enables the loom to maintain a stable operating state in different working modes, improving the accuracy and consistency of weaving. For example, during high-speed weaving, the warp feeding and take-up motors can closely follow the speed changes of the main motor to ensure the synchronization of warp supply and fabric take-up, avoiding the occurrence of loose warp or tight warp phenomena and improving fabric quality. Real-time adjustment of the equipment operating state can effectively reduce energy consumption. On the premise of ensuring weaving quality, the motor power is reasonably adjusted according to actual working requirements to reduce unnecessary energy consumption and save production costs for enterprises.

[0076] In a preferred embodiment of the present invention, through a spectral analysis sensor array and a dielectric feature extraction unit, the material type of the fabric is identified in real time. The fusion analysis of the hydroxyl vibration characteristics of cotton fibers and the phase difference of the dielectric constant of chemical fiber materials may include:

[0077] Through the spectral analysis sensor array, the multi-band spectral reflectance of the fabric is detected to generate multi-band spectral reflectance data; the dielectric feature extraction unit measures the response of the fabric in the electric field to obtain the dielectric constant phase difference data of the chemical fiber material;

[0078] Spectral features related to the hydroxyl vibration characteristics of cotton fibers are extracted from the multi-band spectral reflectance data, including absorption peaks and peak areas of the bands; the dielectric constant phase difference data is analyzed, and characteristic parameters are extracted from the original dielectric constant phase difference data, including the average value, standard deviation, and spectral characteristics of the phase difference;

[0079] The spectral features and the characteristic parameters extracted from the dielectric constant phase difference data are fused to form a fused feature vector;

[0080] The fused feature vector is input into a three-level classifier for material determination to achieve real-time identification of the material type of the fabric.

[0081] In the embodiment of the present invention, the spectral analysis sensor array is composed of multiple spectral sensors with different wavelengths. These sensors emit light with different wavelengths to the fabric and then measure the intensity of the light reflected back by the fabric. Each sensor corresponds to a specific band. By measuring the light reflectance of multiple bands, multi-band spectral reflectance data can be obtained.

[0082] In specific applications, the sensor array will scan different positions of the fabric in sequence according to a preset program. During the scanning process, the sensor will convert the measured light intensity signal into a digital signal and store these signals, finally forming multi-band spectral reflectance data.

[0083] The dielectric feature extraction unit will apply an alternating electric field around the fabric. When the fabric is in this electric field, due to its different internal molecular structure and charge distribution, it will produce a certain response to the electric field. This response can be reflected by measuring the dielectric constant of the fabric. The dielectric constant is a complex number, including a real part and an imaginary part. The phase difference refers to the angle between the imaginary part and the real part of the dielectric constant. The dielectric feature extraction unit will measure the current and voltage of the fabric in the alternating electric field and calculate the phase difference between the current and the voltage to obtain the dielectric constant phase difference data of the chemical fiber material.

[0084] The hydroxyl groups in cotton fibers vibrate at specific wavelengths, and this vibration causes absorption peaks to appear in the spectral reflectance. By analyzing the multi-band spectral reflectance data, the positions and intensities of these absorption peaks can be found. First, a signal processing algorithm is used to smooth the spectral reflectance data to reduce the influence of noise. Then, the peak detection algorithm is used to find the positions of the absorption peaks. Finally, the area of the absorption peak can be calculated using the integration method. Analyze the dielectric constant phase difference data and extract characteristic parameters from the original dielectric constant phase difference data, including the average value, standard deviation, and spectral characteristics of the phase difference. The average value can reflect the overall level of the dielectric constant phase difference. The standard deviation can reflect the degree of dispersion of the dielectric constant phase difference. The spectral characteristics can be obtained by performing a Fourier transform on the dielectric constant phase difference data. The Fourier transform can convert the time-domain signal into a frequency-domain signal, thereby obtaining the amplitude and phase information of different frequency components.

[0085] Feature fusion is the process of integrating feature information from different sources. First, the spectral characteristics and the characteristic parameters extracted from the dielectric constant phase difference data are arranged in a certain order to form a vector.

[0086] To ensure the comparability between different features, it is necessary to normalize the feature vector. The normalization process can map each element in the feature vector to a specific range, such as [0, 1]. Input the fused feature vector into a three-level classifier for material determination to achieve real-time identification of the fabric material type.

[0087] The three-level classifier consists of multiple classifiers, and each classifier is responsible for the preliminary classification of different types of fabrics. First, input the fused feature vector into the first-level classifier, and the first-level classifier will perform a preliminary classification of the fabric according to the preset rules and divide it into several major categories. Then, input the results of the preliminary classification into the second-level classifier, and the second-level classifier will further subdivide each major category. Finally, input the subdivided results into the third-level classifier, and the third-level classifier will make the final determination of the fabric material type.

[0088] Suppose we want to identify whether a piece of fabric is made of pure cotton, chemical fiber, or blended material.

[0089] The fabric is scanned using a spectral analysis sensor array to obtain multi-band spectral reflectance data. For example, the reflectance is measured at wavelengths such as 1400 nm and 1900 nm. The dielectric feature extraction unit applies an alternating electric field around the fabric and measures the dielectric constant phase difference data of chemical fiber materials. It is found from the multi-band spectral reflectance data that there is an obvious absorption peak at the 1400 nm band, and its peak area is 500. This is related to the hydroxyl vibration characteristics of cotton fibers. By analyzing the dielectric constant phase difference data, the average value of the phase difference is obtained as 30°, the standard deviation is 5°, and the spectral characteristics show an obvious peak at 10 Hz. The spectral features (absorption peak position, peak area) and the characteristic parameters (average value, standard deviation, spectral characteristics) of the dielectric constant phase difference data are fused to form a fused feature vector: [1400, 500, 30, 5, 10]. The fused feature vector is input into a three-level classifier. The first-level classifier classifies it into two categories: natural fibers and chemical fibers. Since the spectral features show the hydroxyl vibration characteristics of cotton fibers, it is initially judged as the natural fiber category. The second-level classifier further subdivides and determines the presence of chemical fiber components based on the dielectric constant phase difference data. Finally, the third-level classifier comprehensively considers all features and determines that the fabric is a blended material.

[0090] By fusing the spectral features and the dielectric constant phase difference features, the optical and electrical properties of the fabric are comprehensively utilized, and the material information of the fabric can be more comprehensively reflected. Compared with a single identification method, the accuracy of material identification is improved. For example, for some fabrics with similar appearances but different materials, it may be difficult for traditional methods to accurately distinguish them, while this fusion analysis method can make judgments through multi-dimensional features, effectively reducing misjudgments. The entire process from data acquisition to material determination is carried out in real time. During the operation of the loom, the material of the fabric can be identified in a timely manner, which helps to improve the automation degree and production efficiency of the loom and reduce manual intervention. For fabrics with complex materials such as blends, the component ratio can be accurately identified. Through the comprehensive analysis of the spectral features and the dielectric constant phase difference features, the content of different materials in the fabric can be judged, providing more accurate information for the parameter adjustment of the loom, thereby improving the weaving quality of the fabric. The real-time and accurate material identification results can provide important inputs for the intelligent decision-making module of the loom. The intelligent decision-making module can dynamically adjust the final response speed of the main motor according to the identified fabric material type, realizing the intelligent operation of the loom and improving the production efficiency and product quality.

[0091] In another preferred embodiment of the present invention, the determination process of the three-level classifier includes:

[0092] First-level classification: Set the hydroxyl-related parameter value ≥ 0.65 as the threshold, and distinguish the natural fibers containing cotton components from pure synthetic fibers according to the relevant features in the fused feature vector;

[0093] Secondary classification: For the samples determined to contain cotton in the primary classification, the Mahalanobis distance classifier is used to match the cotton fiber purity grade according to the principal component distribution from the first principal component to the third principal component obtained by performing principal component analysis on the fused feature vector.

[0094] Tertiary classification: For the samples determined to be pure synthetic fibers in the primary classification, the support vector machine is used to construct a hyperplane with the tangent value of the loss angle and the second principal component in the fused feature vector to distinguish among three types of chemical fiber materials: polyester, polyamide, and nylon.

[0095] In the embodiment of the present invention, the primary classification:

[0096] Assume that the hydroxyl-related parameter value ≥ 0.65 is used as the threshold. The hydroxyl-related parameter is an eigenvalue extracted from the fused feature vector and related to the hydroxyl vibration characteristics of cotton fibers, which can reflect the content of cotton fibers in the fabric. Compare the hydroxyl-related parameter value in the fused feature vector with the threshold of 0.65. If the parameter value ≥ 0.65, it is determined that the fabric is a natural fiber containing cotton components; if < 0.65, it is determined to be a pure synthetic fiber. This step is classified based on the characteristic that cotton fibers contain hydroxyl, while pure synthetic fibers generally do not contain or contain very little hydroxyl.

[0097] Secondary classification:

[0098] Further classification is only performed on the samples determined to contain cotton in the primary classification. Perform principal component analysis (PCA) on the fused feature vectors of these cotton-containing samples. First, calculate the covariance matrix of the fused feature vector, then solve the eigenvalues and eigenvectors of the covariance matrix, sort the eigenvalues from largest to smallest, select the eigenvectors corresponding to the first three eigenvalues as the principal component directions, project the fused feature vector onto these principal component directions to obtain the values of the first principal component to the third principal component. In the secondary classification, the Mahalanobis distance classifier is used to match the cotton fiber purity grade according to the principal component distribution from the first principal component to the third principal component. First, establish a principal component distribution model for different cotton fiber purity grades by performing principal component analysis on cotton-containing samples with known purity grades. Then, calculate the Mahalanobis distance between the principal component values of the sample to be classified and the principal component distribution models of each purity grade , and classify the sample to be classified into the purity grade with the smallest Mahalanobis distance, where, is the principal component value vector of the sample to be classified; is the th principal component mean vector of the cotton fiber purity grade model; is the transpose; is the th covariance matrix of the purity grade model inverse matrix; , is the matrix Determinant; ( = 1, 2, 3; = 1, 2, 3).

[0099] is the algebraic cofactor of the element in the matrix The definition of the algebraic cofactor is where is the cofactor of the element That is, the determinant of the 2×2 sub-matrix obtained by removing the th row and the th column of the matrix

[0100] For example, where so .

[0101] , so .

[0102] Tertiary classification:

[0103] Only the samples determined to be pure synthetic fibers in the primary classification are further classified. The tangent of the loss angle and the second principal component are selected from the fusion feature vector as the classification features. The tangent of the loss angle reflects the energy loss of the material in an alternating electric field, and different chemical fiber materials have different tangents of the loss angle. The second principal component is obtained through principal component analysis and contains some important information of the original data. In the tertiary classification, a support vector machine is used to construct a hyperplane with the tangent of the loss angle and the second principal component as features. First, the sample data of known chemical fiber materials (polyester, polyamide, nylon) are used for training to obtain the classification model of the support vector machine. Then, the tangent of the loss angle and the second principal component of the pure synthetic fiber sample to be classified are input into the trained model, and the sample is classified into one of the three chemical fiber materials of polyester, polyamide or nylon according to the position of the hyperplane.

[0104] Suppose there is a fabric of unknown material, and its fusion feature vector is [0.7, 0.2, 0.1, 0.3, 0.4, 0.5] after the previous steps. The first element is the parameter value related to hydroxyl, and the subsequent elements respectively contain other spectral features and dielectric constant phase difference features, etc. The parameter value related to hydroxyl in the fusion feature vector is 0.7, which is greater than the threshold of 0.65. Therefore, this fabric is determined to be a natural fiber containing cotton components. Principal component analysis is performed on the fusion feature vector of this cotton-containing sample, and the first principal component value is 0.8, the second principal component value is 0.6, and the third principal component value is 0.4.

[0105] The pre - established principal component distribution models for different cotton fiber purity grades are as follows:

[0106] Purity grade A: The mean of the first principal component is 0.9, and the covariance matrix is [[0.1, 0.05, 0.02], [0.05, 0.12, 0.03], [0.02, 0.03, 0.1]].

[0107] Purity grade B: The mean of the first principal component is 0.7, and the covariance matrix is [[0.15, 0.06, 0.03], [0.06, 0.13, 0.04], [0.03, 0.04, 0.11]].

[0108] Purity grade C: The mean of the first principal component is 0.6, and the covariance matrix is [[0.18, 0.07, 0.04], [0.07, 0.14, 0.05], [0.04, 0.05, 0.12]].

[0109] Calculate the Mahalanobis distance between this sample and the models of each purity grade:

[0110] The Mahalanobis distance from purity grade A is 1.2.

[0111] The Mahalanobis distance from purity grade B is 0.8.

[0112] The Mahalanobis distance from purity grade C is 1.5.

[0113] Since the Mahalanobis distance between this sample and purity grade B is the smallest, the cotton fiber purity grade of this fabric is determined to be B.

[0114] Suppose another sample is pure synthetic fiber;

[0115] Suppose the fusion feature vector of another sample is [0.2, 0.3, 0.4, 0.5, 0.6, 0.7], where the hydroxyl - related parameter value is 0.2, less than the threshold of 0.65, and it is determined to be pure synthetic fiber in the first - level classification.

[0116] Extract the tangent of the loss angle value of 0.5 and the second principal component value of 0.6 from the fusion feature vector. Use the trained support vector machine model for classification, and the model classifies this sample as polyester material according to the hyperplane constructed by the tangent of the loss angle value and the second principal component.

[0117] In a preferred embodiment of the present invention, quantifying the warp and weft yarn distribution density and generating a three - dimensional heat map of yarn intersections per square centimeter may include:

[0118] During the operation of the loom, continuously photograph the fabric to obtain a series of images containing warp and weft yarns;

[0119] Preprocess a series of images containing warp and weft yarns, and binarize the preprocessed images; use an edge detection algorithm to identify the edges of the warp and weft yarns in the binarized images, and identify the intersection points of the warp and weft yarns and their corresponding coordinates;

[0120] Divide the fabric image into small regions, count the yarn intersection points in each small region, and obtain the number of intersection points in each region;

[0121] According to the number of intersection points in each region, calculate the warp and weft yarn distribution density data for the corresponding region;

[0122] Map the warp and weft yarn distribution density data of each small region into three-dimensional space, where the position of the region is used as the two-dimensional coordinate, and the density value is used as the third-dimensional coordinate;

[0123] Perform interpolation processing on the mapped warp and weft yarn distribution density data in three-dimensional space, and draw a three-dimensional heat map based on the interpolated warp and weft yarn distribution density data.

[0124] In the embodiment of the present invention, install a high-resolution industrial camera beside the loom, and its frame rate needs to be set according to the running speed of the loom to ensure that the continuous state of the fabric during weaving can be clearly captured and avoid blurring of yarn movement. For example, for a medium-speed loom, the camera frame rate may be set to 50 frames per second. Adjust parameters such as the focal length, aperture, and exposure time of the camera to make the contrast of the captured fabric image clear and accurately display the characteristics of the warp and weft yarns. Synchronize the camera with the control system of the loom to ensure automatic shooting at a predetermined frequency when the loom is running. The image storage format generally selects a lossless compression format, such as PNG, to retain image details. Use Gaussian filtering to remove random noise in the image, such as noise generated by the camera sensor. Gaussian filtering performs weighted averaging on the neighboring pixels around each pixel point in the image.

[0125] Adopt a suitable threshold segmentation algorithm, such as the Otsu method. The Otsu method automatically finds a threshold by calculating the between-class variance of the image, and converts the grayscale image into a binary image with only black and white pixel values. In the binary image, the warp and weft yarn parts are white pixels, and the background part is black pixels. Taking the Canny algorithm as an example, it first uses a Gaussian filter to smooth the image to reduce noise interference; then calculates the gradient magnitude and direction of the image; then performs non-maximum suppression on the gradient magnitude, retaining the pixels at the local gradient maximum and removing other non-edge pixels; finally, determines the true edge pixels through double-threshold detection and edge connection. In the detected edge image of the warp and weft yarns, the intersection points are identified by searching for changes in adjacent pixel points. When it is detected that the edge pixels in the horizontal and vertical directions intersect at a certain point, that point can be determined as the intersection point of the warp and weft yarns. Using the image coordinate system, the coordinate values of each intersection point are obtained. For example, in a coordinate system with the upper left corner of the image as the origin, the positive x-axis to the right, and the positive y-axis downward, the (x, y) coordinates of the intersection point are recorded. In a coordinate system with the upper left corner of the image as the origin, the positive x-axis to the right, and the positive y-axis downward, record the (x, y) coordinates of the intersection point.

[0126] Divide the entire fabric image evenly into several small square or rectangular regions, and the region size is determined according to actual needs and image resolution. For example, for an image with a resolution of 1000×1000 pixels, it can be divided into 100×100 small regions with a size of 10×10 pixels. Traverse each small region, match the intersection point coordinates within the region, and count the number of intersection points falling within the region. A loop structure can be used to check one by one whether the coordinates of all intersection points are within the coordinate range of the current small region. If so, the counter is incremented by 1, and finally the number of yarn intersection points in each small region is obtained.

[0127] Assume that the area of each small region is S (unit: square centimeter, which can be calculated according to the actual size of the image and the region division ratio), and the number of intersection points in this region is N. Then the calculation formula for the warp and weft yarn distribution density D (unit: pieces / square centimeter) of this region is D = . For example, if the area of a small region is 0.01 square centimeter and the number of intersection points is 50, then the warp and weft yarn distribution density of this region is = 5000 pieces / square centimeter. For the divided small regions, establish a plane rectangular coordinate system with the upper left corner of the image as the origin. The position indices of the small region in the horizontal direction ( axis) and the vertical direction ( axis) can be used as two-dimensional coordinates. For example, for the small region in the th row and the th column, its two-dimensional coordinates can be expressed as ( , )。The density value of the warp and weft yarn distribution calculated for this area is used as the z - coordinate in three - dimensional space. In this way, each small area corresponds to a point (x, y, z) in three - dimensional space, where = , = , =D。

[0128] Since the directly mapped data points are discrete in three - dimensional space, in order to obtain a smoother heat map, interpolation processing is required. Taking bilinear interpolation as an example, for the blank area between two adjacent data points in three - dimensional space, the density values of other points in this area are calculated by linearly interpolating the surrounding four known data points. Use plotting software, such as the Matplotlib library in Python or the plotting function of MATLAB. Input the three - dimensional coordinate data after interpolation processing into the plotting function, set the color mapping table, and assign different colors according to the size of the density value. The higher the density, the warmer the color (such as red); the lower the density, the cooler the color (such as blue). By adjusting parameters such as the viewing angle and lighting, a clear and intuitive three - dimensional heat map is generated to show the distribution density of the warp and weft yarns on the fabric.

[0129] Suppose there is a loom weaving a fabric with a specification of 100×100 square centimeters. An industrial camera installed beside the loom continuously shoots the fabric at a speed of 30 frames per second, and 1000 images with a resolution of 2000×2000 pixels are obtained during the weaving process. The captured images are successively subjected to Gaussian filtering for denoising, grayscale conversion, and Otsu's binarization. After pre - processing, the originally colored and noisy image is converted into a clear black - and - white binary image, and the warp and weft yarns form a distinct contrast with the background. Using the Canny edge detection algorithm, the edges of the warp and weft yarns are successfully detected. By analyzing the edge image, 50000 warp and weft yarn crossing points are identified, and their coordinates in the image coordinate system are recorded. The fabric image is divided into 10000 small areas with a size of 20×20 pixels. After calculation, the actual area corresponding to each small area is 0.01 square centimeters. By traversing the crossing point coordinates, the number of crossing points in each small area is counted. For example, the number of crossing points in a certain area is 30. According to the number of crossing points and the area of the area, the distribution density of the warp and weft yarns in this area is =3000 pieces per square centimeter. Similar calculations are performed for all small areas to obtain the distribution density data of the warp and weft yarns in each area.

[0130] Taking the row and column positions of small regions in the image as two-dimensional coordinates and the density value as the third-dimensional coordinate. For example, for a small region in the 10th row and 20th column, its two-dimensional coordinates are (20, 10). If the density value of this region is 3000, then its coordinates in three-dimensional space are (20, 10, 3000). Map all small regions to obtain a large number of data points in three-dimensional space. Use the bilinear interpolation algorithm to interpolate the discrete data points in three-dimensional space and supplement the density values of blank regions. Then use the Matplotlib library to draw a three-dimensional heat map. From the heat map, it can be clearly seen that the distribution density of warp and weft yarns in the upper left corner of the fabric is relatively high and the color is reddish; the density in the lower right corner is relatively low and the color is bluish, intuitively showing the uneven distribution of warp and weft yarns on the fabric.

[0131] By continuously photographing and subsequent processing of the fabric, the distribution density of warp and weft yarns can be accurately quantified, which helps to timely detect possible density unevenness problems in the fabric, such as local sparseness or denseness of warp and weft yarns. For example, in the production of high-grade fabrics, once density anomalies are detected, the loom parameters can be immediately adjusted to avoid producing a large number of defective products, thereby improving product quality, reducing the defective rate, and enhancing the economic benefits of the enterprise. The three-dimensional heat map visually presents the distribution of warp and weft yarns in different regions of the fabric. Production personnel can clearly understand the operating state of the loom during the weaving process based on this and judge which parts are prone to problems. For example, if the heat map shows that density anomalies frequently occur in a certain region, the corresponding parts of the loom can be inspected specifically, maintained or adjusted in advance, the production process can be optimized, the downtime can be reduced, and the production efficiency can be improved. The detailed distribution density data of warp and weft yarns and the three-dimensional heat map provide a strong basis for the research and development of new fabrics. According to the density distribution characteristics of different fabrics and combined with actual needs, new weaving processes and design schemes are explored. For example, when developing functional fabrics, by analyzing the relationship between density and functional characteristics, the layout of warp and weft yarns is optimized to make the fabric better meet specific performance requirements and accelerate the product R & D process. Precise density quantification and visual analysis enable enterprises to produce higher-quality products that better meet market demands. Compared with competitors, it can provide higher-quality and more stable fabrics, which helps to enhance the enterprise's reputation and market share in the industry and strengthen the enterprise's core competitiveness. Discovering and solving fabric density problems in advance avoids waste of raw materials and repeated production caused by quality problems. At the same time, the optimization of equipment maintenance based on the heat map reduces the maintenance costs and production delay losses caused by equipment failures, thereby reducing the overall production cost of the enterprise.

[0132] In a preferred embodiment of the present invention, dynamic parameters during the operation of the loom are continuously collected, including the main motor speed, the torque of the let-off motor, the response speed of the take-up motor, and the warp tension data. And according to the dynamic parameters, four working modes of the loom, namely startup, steady-state operation, variable-speed weaving, and shutdown transition, can be identified, which may include:

[0133] By jointly analyzing the change rate of the main motor speed, the average torque of the warp feeding motor, and the standard deviation of the warp tension, the current working mode is determined, i.e.:

[0134] When the change rate of the main motor speed ≥ 50 rpm / s and the standard deviation of the warp tension > 8N, it is marked as the startup mode;

[0135] When the change rate of the main motor speed ≤ 5 rpm / s and the standard deviation of the warp tension < 3N, it is marked as the steady-state operation mode;

[0136] When the detected change in the preset weft density parameter is triggered, the variable-speed weaving mode is activated;

[0137] When the main motor speed ≤ 30% of the rated value, the shutdown transition mode is activated.

[0138] In the embodiment of the present invention, in order to collect the main motor speed, the warp feeding motor torque, the take-up motor response speed, and the warp tension data, corresponding sensors need to be installed. For the main motor speed, a speed sensor such as an optical encoder can be used, which calculates the speed by measuring the rotation angle and time interval of the motor shaft; for the warp feeding motor torque, a torque sensor can be used, and its working principle is based on a strain gauge, which measures the torque value by detecting the strain caused by the torque of the motor shaft; the take-up motor response speed can be measured by a speed sensor (such as a Hall sensor); for the warp tension, a tension sensor is used, which can convert the warp tension into an electrical signal. Connect these sensors to the data acquisition card, and the data acquisition card converts the analog signal into a digital signal and transmits it to the computer through an interface (such as USB, Ethernet, etc.). Run the data acquisition software on the computer and set an appropriate sampling frequency to ensure that the dynamic parameters during the operation of the loom can be collected in real time and accurately. For example, the sampling frequency can be set to 10 times per second to capture the subtle changes in the parameters.

[0139] By jointly analyzing the change rate of the main motor speed, the average torque of the warp feeding motor, and the standard deviation of the warp tension, the current working mode is determined

[0140] At each sampling moment, the speed of the main motor is recorded. The change rate of the main motor speed is calculated by dividing the speed difference between two adjacent sampling moments by the time interval. For example, if the sampling interval is 0.1s, and the speed at the current moment is 1000 rpm and the speed at the next moment is 1005 rpm, then the change rate of the speed is 50 rpm / s. Within a certain time window (such as 10 sampling periods), the torque values of the warp feeding motor are recorded, and the average torque of the warp feeding motor is obtained. Also within this time window, the warp tension values are recorded. According to the average value of the warp tension, the standard deviation of the warp tension is obtained.

[0141] When the change rate of the main motor speed ≥ 50 rpm / s and the standard deviation of the warp tension > 8 N, it is marked as the startup mode. In the program, the change rate of the main motor speed and the standard deviation of the warp tension are calculated in real time. When these two conditions are met simultaneously, the current working mode is marked as the startup mode.

[0142] When the change rate of the main motor speed ≤ 5 rpm / s and the standard deviation of the warp tension < 3 N, it is marked as the steady-state operation mode. Similarly, these two parameters are monitored in real time. When the conditions are met, it is marked as the steady-state operation mode.

[0143] In the loom control system, the weft density parameter is preset. When it is detected that the preset weft density parameter changes, the variable-speed weaving mode is triggered. It can be achieved by monitoring the register value of the weft density parameter in the control system. When this value changes, the working mode is marked as the variable-speed weaving mode.

[0144] The main motor has a rated speed. When the main motor speed ≤ 0.3, the shutdown transition mode is activated. The main motor speed is monitored in real time. When this condition is met, it is marked as the shutdown transition mode.

[0145] By accurately identifying different working modes of the loom, the operating parameters of the loom can be optimized according to the characteristics of the modes. For example, in the startup mode, the feeding and winding speeds can be adjusted in advance to enable the loom to reach a stable operating state faster and reduce the startup time; in the variable-speed weaving mode, the coordination of each motor can be adjusted in a timely manner to ensure that the fabric quality is not affected during the weft density change, thereby improving the overall production efficiency. Under different working modes, the operating state of the loom has different effects on the fabric quality. In the steady-state operation mode, strictly controlling the stability of the warp tension and the motor speed can ensure the evenness of the warp and weft densities of the fabric and reduce the defective rate; in the variable-speed weaving mode, responding to the weft density change in a timely manner can avoid fabric defects caused by unstable transitions and improve the consistency and quality of the product. Accurately identifying the working mode helps to reasonably control the operation of the motor. For example, in the startup and shutdown transition modes, over-acceleration and deceleration of the motor can be avoided to reduce the wear of the motor and mechanical components; in the steady-state operation mode, the motor can operate under suitable working conditions, reducing the energy consumption and the probability of equipment failures and extending the service life of the equipment. Real-time acquisition of dynamic parameters and identification of working modes provide a basis for the intelligent management of the loom. These data can be uploaded to the industrial Internet platform to achieve remote monitoring and fault warning. Managers can arrange production plans and equipment maintenance reasonably according to the working mode and operating state of the loom, improving the management level and decision-making efficiency of the enterprise.

[0146] In a preferred embodiment of the present invention, according to the fabric material type, warp and weft density data, and dynamic parameters, combined with the current working mode, dynamically calculate the final response speed of the main motor and generate a motor control instruction, which may include:

[0147] Preset a control strategy database under combinations of different fabric material types, warp and weft densities, dynamic parameters, and working modes, and perform a matching operation in the control strategy database to obtain the corresponding reference value of the main motor response speed;

[0148] Set corresponding evaluation indicators and preset standards for different working modes, analyze and evaluate the current dynamic parameters to obtain the analysis and evaluation results;

[0149] Generate an adjustment plan for the control strategy according to the analysis and evaluation results, and apply the adjustment plan to the reference value of the main motor response speed to obtain the preliminarily adjusted main motor response speed;

[0150] Calculate the final response speed of the main motor according to the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and the current working mode;

[0151] Convert the final response speed of the main motor into a motor control instruction, and the instruction includes the target speed, acceleration, and running time information of the motor.

[0152] In the embodiment of the present invention, a large amount of experimental data or empirical data under combinations of different fabric material types (such as cotton, linen, silk, etc.), warp and weft densities (such as the number of warp and weft yarns per centimeter), dynamic parameters (main motor speed, let-off motor torque, take-up motor response speed, warp tension, etc.), and working modes (start-up, steady-state operation, variable-speed weaving, stop transition) are collected. These data are sorted into a database, and each record includes the fabric material type, warp and weft density, dynamic parameter range, working mode, and the corresponding reference value of the main motor response speed. For example, for cotton fabric, with a warp density of 50 warp yarns / cm and a weft density of 40 weft yarns / cm, in the steady-state operation mode, when the main motor speed is in the range of 800 - 1000 rpm and the let-off motor torque is in the range of 10 - 15 N·m, etc., the reference value of the main motor response speed is 900 rpm. Real-time obtain the current fabric material type, warp and weft density data, dynamic parameters, and working mode information. Search for records matching the current situation in the control strategy database to obtain the corresponding reference value of the main motor response speed.

[0153] For the startup mode, the evaluation metrics can include the change rate of the main motor speed, the standard deviation of the warp tension, etc. The preset standards can be that the change rate of the main motor speed should be between 50 - 100 rpm / s, and the standard deviation of the warp tension should be less than 10 N. For the steady-state operation mode, the evaluation metrics can be the stability of the main motor speed, the stability of the warp tension, etc. The preset standards are that the fluctuation range of the main motor speed is within ±5 rpm, and the fluctuation range of the warp tension is within ±3 N. For the variable-speed weaving mode, the evaluation metrics can be the response time of the main motor when the weft density changes, the adjustment speed of the warp tension, etc. The preset standards are that the response time is less than 1 s, and the warp tension adjustment reaches stability within 2 s. For the shutdown transition mode, the evaluation metrics can be the deceleration speed of the main motor, the relaxation of the warp tension, etc. The preset standards are that the deceleration speed of the main motor is between 20 - 30 rpm / s, and the warp tension relaxes to the safe range during shutdown.

[0154] According to the current working mode, select the corresponding evaluation metrics and preset standards. Compare and analyze the current dynamic parameters with the preset standards to determine whether they meet the standards. For example, in the steady-state operation mode, if the fluctuation of the main motor speed exceeds ±5 rpm, it is considered not to meet the standards. Based on the comparison results, obtain the analysis and evaluation results, such as meeting the standards, partially meeting the standards, or not meeting the standards, etc. If the analysis and evaluation results show that the standards are not met, generate an adjustment plan for the control strategy according to the non-compliant metrics and degrees. For example, in the startup mode, if the change rate of the main motor speed exceeds 100 rpm / s, it is necessary to reduce the acceleration of the main motor; if the standard deviation of the warp tension is greater than 10 N, it is necessary to adjust the torque of the let-off motor. For the situation of partially meeting the standards, fine-tuning can also be carried out according to the specific situation. For example, in the steady-state operation mode, when the fluctuation of the main motor speed is about ±6 rpm, the control parameters of the motor can be appropriately adjusted to reduce the fluctuation.

[0155] Apply the adjustment plan to the reference value of the main motor response speed. For example, if the adjustment plan requires reducing the acceleration of the main motor, appropriately reduce the reference value of the main motor response speed; if it is required to increase the response speed, increase the reference value accordingly. Obtain the preliminarily adjusted main motor response speed. Considering comprehensively the preliminarily adjusted main motor response speed, the fabric material type, the warp and weft density data, the dynamic parameters, and the current working mode, obtain the final response speed. According to the final response speed of the main motor, determine the target speed of the motor. The target speed is the final response speed. The acceleration can be calculated based on the actual speed and the target speed of the current main motor, as well as the preset acceleration time. For example, if the current speed is , the target speed is , the preset acceleration time is , then the acceleration = The running time can be determined according to the weaving process requirements and the current working mode. For example, in the steady-state running mode, the running time can be calculated based on the length of the fabric and the weaving speed, and the target speed, acceleration, and running time information are combined into a motor control command.

[0156] Suppose a cotton fabric is being woven currently, with a warp density of 60 ends / cm and a weft density of 50 picks / cm, and the loom is in the steady-state running mode. Looking up in the control strategy database, a record that matches the fabric material type, warp and weft density, and working mode is found, and the reference value of the main motor response speed is 1000 rpm.

[0157] The evaluation indicators are the stability of the main motor speed and the stability of the warp tension. The preset standard is that the fluctuation range of the main motor speed is within ±5 rpm, and the fluctuation range of the warp tension is within ±3 N. Currently, the fluctuation of the main motor speed is between ±8 rpm, and the fluctuation of the warp tension is between ±2 N. The analysis and evaluation result is that it partially meets the standard, and the stability of the main motor speed does not meet the standard. A control strategy adjustment plan is generated to appropriately reduce the target speed of the main motor to reduce the speed fluctuation. The reference value of the main motor response speed is adjusted from 1000 rpm to 980 rpm, and the preliminary adjusted main motor response speed is obtained. Considering that the fluctuation of the main motor speed in the current dynamic parameters is relatively large, after calculation by the comprehensive calculation model, the final response speed is assumed to be 975 rpm.

[0158] The target speed is 975 rpm, the current main motor speed is 990 rpm, and the preset acceleration time is 2 s, then the acceleration = = -7.5 rpm / s (deceleration). According to the weaving process requirements, the running time of the motor in this steady-state running mode is 30 minutes. The motor control command is: target speed 975 rpm, acceleration -7.5 rpm / s, running time 30 minutes.

[0159] By dynamically calculating the final response speed of the main motor according to factors such as fabric material type, warp and weft density, and dynamic parameters, the loom can operate at the optimal speed under different working conditions. For example, for fabrics with different materials and warp and weft densities, adjusting the appropriate main motor speed can ensure the uniform tension of warp and weft yarns, reduce fabric defects, improve the flatness and density uniformity of the fabric, and thus improve the overall quality of the fabric.

[0160] Under different working modes, adjusting the response speed of the main motor according to the actual situation can enable the loom to more quickly adapt to various changes in working conditions. In the start-up mode, a reasonable acceleration strategy can shorten the start-up time; in the variable-speed weaving mode, quickly and accurately adjusting the speed can reduce the transition time, improve production efficiency, and reduce production costs. Dynamically calculating the response speed of the main motor can prevent the motor from operating at an inappropriate speed and reduce the wear of the motor and mechanical components. For example, in the stop transition mode, stopping at an appropriate deceleration speed can reduce mechanical shock, extend the service life of the equipment, and reduce equipment maintenance costs. This dynamic control method based on multiple factors reflects the intelligent production level of the loom. By presetting a control strategy database and analyzing and evaluating dynamic parameters in real time, the loom can automatically adjust the operating state of the main motor, reduce manual intervention, improve the automation degree and stability of the production process, and meet the development needs of the modern textile industry.

[0161] In another preferred embodiment of the present invention, calculating the final response speed of the main motor according to the preliminarily adjusted response speed of the main motor, the type of fabric material, the warp and weft density data, the dynamic parameters, and the current working mode may include:

[0162] Analyze the preliminarily adjusted response speed of the main motor, the type of fabric material, the warp and weft density data, the dynamic parameters, and the current working mode, and obtain the adjusted basic speed according to the reference value of the main motor response speed and the speed adjustment amount in the analysis and evaluation result;

[0163] Determine the influence amount of the fabric material on the main motor speed according to the material category to which the current fabric belongs; determine the influence amount of the warp and weft density on the main motor speed according to the warp and weft density of the fabric;

[0164] Determine the adjustment amount for the dynamic parameters according to the main motor speed, the torque of the let-off motor, the response speed of the take-up motor, and the warp tension parameters;

[0165] Determine the corresponding working mode adjustment amount from the preset mode parameter table according to the working mode of the current rapier loom;

[0166] Integrate the adjusted basic speed, the influence amount of the fabric material on the main motor speed, the influence amount of the warp and weft density on the main motor speed, the adjustment amount of the dynamic parameters, and the working mode adjustment amount to obtain the final response speed of the main motor.

[0167] In an embodiment of the present invention, obtain the preliminarily adjusted response speed of the main motor and the reference value of the main motor response speed and the speed adjustment amount in the analysis and evaluation result . These data can be obtained through steps such as matching in the control strategy database and analyzing and evaluating dynamic parameters. According to the formula, the adjusted basic speed For example, if the response speed of the main motor after preliminary adjustment is 900 rpm and the speed adjustment amount is 20 rpm, then the adjusted base speed is 900 + 20 = 920 rpm. Classify the fabric materials, such as cotton, linen, silk, chemical fiber, etc. For each material, determine the influence coefficient on the main motor speed and the corresponding adjustment factor through experience. These coefficients and factors can be stored in a material parameter table. The influence amount of the fabric material on the main motor speed is . For example, for cotton fabric, through experience, it is determined that = 1.05 and = 0.9, then the influence amount of the fabric material on the main motor speed is 1.05 × 0.9 = 0.945.

[0168] During the textile production process, in order to accurately grasp the relationship between the warp and weft density and the main motor speed, a quadratic function about the warp and weft density can be fitted by analyzing the actual production data, where , , are fitting coefficients. The warp and weft density can be obtained by means such as image analysis mentioned above. Collect multiple groups of data on different warp and weft densities and the corresponding influence of the main motor speed. Then use mathematical methods, such as the least squares method, to process these data to determine the values of the coefficients , , so that the function can most accurately reflect the relationship between the warp and weft density and the influence amount of the main motor speed. Select the main motor speed, let-off motor torque, take-up motor response speed, and warp tension as dynamic parameters, denoted as , , , respectively, and set weights , , , for each parameter, and = 1. At the same time, determine the standard values of each parameter.

[0169] Calculate the relative deviation of each parameter, and then according to the formula . Calculate the adjustment amount for the dynamic parameters. For example, assume = 0.3, = 0.2, =0.2, =0.3. According to the different working modes of the rapier loom (start-up, steady-state operation, variable speed weaving, shutdown transition), a mode parameter table is established to record the adjustment coefficient corresponding to each working mode. According to the current working mode of the rapier loom, find the corresponding adjustment coefficient from the mode parameter table For example, if the current mode is steady-state, the corresponding =1.02. The influence of the adjusted basic speed and fabric material on the main motor speed , the influence of warp and weft density on the speed of the main motor , Dynamic parameter adjustment and working mode adjustment To integrate, according to the formula Calculate the final response speed of the main motor.

[0170] Considering the influence of factors such as fabric material and warp and weft density on the speed of the main motor, the motor speed can be adjusted according to the characteristics of different fabrics to ensure uniform tension of the warp and weft yarns, reduce fabric defects, improve fabric flatness and density uniformity, and thus improve the overall quality of the fabric. For example, for thinner silk fabrics, appropriately reducing the main motor speed can avoid yarn breakage and wrinkling. The main motor speed is dynamically adjusted in combination with dynamic parameters and working modes, so that the loom can adapt to various working conditions more quickly. In the startup and variable speed weaving modes, reasonable speed adjustment can shorten the transition time and improve production efficiency; in the steady-state operation mode, maintaining a stable optimal speed can increase the weaving speed and reduce production costs.

[0171] By real-time monitoring of dynamic parameters and adjusting the main motor speed, the motor can be prevented from running at an inappropriate speed, reducing the wear of the motor and mechanical parts. For example, in the shutdown transition mode, stopping at an appropriate deceleration speed can reduce mechanical impact, extend the service life of the equipment, and reduce equipment maintenance costs. This formula reflects the intelligent production level of the rapier loom. By comprehensively considering multiple factors, the operating status of the main motor is automatically adjusted, manual intervention is reduced, the automation and stability of the production process are improved, and the development needs of the modern textile industry are met.

[0172] In a preferred embodiment of the present invention, driving the main motor to operate according to the motor control instruction, and linking the let-off / winding motor speed ratio relationship to follow the change of the main motor speed, and adjusting the operating state of the equipment in real time, may include:

[0173] Generate corresponding motor control instructions, including speed and direction, according to the final response speed of the main motor, and send the motor control instructions to the driving device of the main motor;

[0174] After the main motor starts, according to the real-time operating speed of the main motor and in combination with the preset speed ratio relationship between the warp let-off / take-up motor and the main motor, calculate the target speeds of the warp let-off motor and the take-up motor;

[0175] Operate the driving devices of the warp let-off motor and the take-up motor at the target speeds. During the operation, monitor the actual speed in real time and compare it with the target speed;

[0176] During the operation of the main motor, the warp let-off motor and the take-up motor, continuously collect the operation status data of the equipment, including the current, voltage, temperature of the motors, as well as the warp tension and fabric density parameters;

[0177] According to the operation status data of the equipment, evaluate and analyze the operation status of the entire rapier loom to adjust the operation status of the equipment in real time.

[0178] In the embodiment of the present invention, according to the final response speed of the main motor, determine the rotation speed and rotation direction information of the motor. For example, if the final response speed is positive, set the rotation direction to forward; if it is negative, set the rotation direction to reverse. At the same time, accurately determine the rotation speed information to specific values to meet the requirements of different production processes.

[0179] Send the generated motor control instructions (including rotation speed and rotation direction) to the driving device of the main motor through a communication interface (such as a serial port, Ethernet, etc.). After receiving the instructions, the driving device will parse and process them to prepare for driving the main motor. After the main motor starts, use a speed sensor (such as an encoder) to monitor the operation speed of the main motor in real time. The speed sensor will convert the real-time speed of the main motor into an electrical signal and transmit it to the control system.

[0180] In the control system, the speed ratio relationship between the warp let-off / take-up motor and the main motor is pre-stored. According to the real-time operating speed of the main motor and the preset speed ratio relationship, calculate the target speeds of the warp let-off motor and the take-up motor through mathematical operations. For example, if the speed ratio of the warp let-off motor to the main motor is 0.5 and the real-time speed of the main motor is 1000 rpm, then the target speed of the warp let-off motor is 1000 × 0.5 = 500 rpm. Send the calculated target speed instructions of the warp let-off motor and the take-up motor to their respective driving devices. The driving device adjusts the input voltage and current of the motor according to the instructions to make the motor operate at the target speed. During the operation of the warp let-off motor and the take-up motor, use a speed sensor to monitor their actual speeds in real time. Compare the actual speed with the target speed and calculate the speed deviation. If the deviation exceeds the preset allowable range, the control system will issue an adjustment instruction to adjust the driving parameters of the motor to reduce the deviation.

[0181] During the operation of the main motor, let-off motor, and take-up motor, the operating status data of the equipment is continuously collected through various sensors. The current sensor is used to monitor the current of the motor, the voltage sensor is used to monitor the voltage of the motor, and the temperature sensor is used to monitor the temperature of the motor. In addition, a tension sensor can be used to monitor the warp tension, and a density sensor can be used to monitor the fabric density parameters. The collected operating status data is transmitted to the data storage module through the communication interface. The collected equipment operating status data is analyzed and evaluated. By using machine learning algorithms, data such as the current, voltage, and temperature of the motor, as well as the warp tension and fabric density parameters, are processed to determine whether the operating status of the equipment is normal. If the analysis result indicates that the operating status of the equipment is abnormal, the operating status of the equipment is adjusted in real time according to the type and severity of the abnormal situation. For example, if the warp tension is too high, the control system will reduce the speed of the main motor or adjust the speed ratio of the let-off motor to reduce the warp tension; if the motor temperature is too high, the load of the motor will be reduced or heat dissipation measures will be increased.

[0182] Suppose a rapier loom, the final response speed of the main motor is 1200 rpm, and the rotation direction is forward. The speed ratio of the let-off motor to the main motor is 0.6, and the speed ratio of the take-up motor to the main motor is 0.8. According to the final response speed of 1200 rpm and the forward rotation direction of the main motor, a motor control instruction is generated and sent to the drive device of the main motor through the Ethernet interface. After receiving the instruction, the main motor drive device drives the main motor to run forward at a speed of 1200 rpm. After the main motor starts, the speed sensor continuously monitors the running speed of the main motor. Suppose the real-time speed of the main motor is stable at 1200 rpm. According to the preset speed ratio relationship, the target speed of the let-off motor is 1200×0.6 = 720 rpm, and the target speed of the take-up motor is 1200×0.8 = 960 rpm.

[0183] The target speed instructions of the let-off motor and the take-up motor are respectively sent to their respective drive devices. The let-off motor and the take-up motor start to run at the target speed. During the operation, the speed sensor continuously monitors their actual speeds. Suppose the actual speed of the let-off motor is 710 rpm, with a deviation of 10 rpm from the target speed of 720 rpm. After detecting the deviation, the input voltage of the let-off motor drive device is adjusted to make the speed of the let-off motor gradually approach the target speed. During the operation of the main motor, let-off motor, and take-up motor, the current sensor, voltage sensor, temperature sensor, tension sensor, and density sensor continuously collect the operating status data of the equipment. For example, the current of the main motor is 5 A, the voltage is 380 V, and the temperature is 50°C; the warp tension is 20 N, and the fabric density is 50 pieces / cm.

[0184] Analyze and evaluate the collected operating status data. Suppose the analysis result shows that the warp tension is close to the upper limit value of 22 N, and there is a risk of warp breakage. Immediately reduce the speed of the main motor to 1100 rpm, and at the same time adjust the speed ratio of the let-off motor to 0.58 to reduce the warp tension. After a period of adjustment, the warp tension drops to 18 N, and the equipment resumes normal operation. By adjusting the speed of the let-off / take-up motor in real time, ensure the stability of the warp tension and fabric density, reduce fabric defects and flaws, and improve the quality and consistency of the fabric. For example, during the weaving process, the warp tension can be adjusted in a timely manner to avoid warp breakage or slack, making the warp and weft density of the fabric uniform and the surface smooth. The interlocking control among the main motor, let-off motor, and take-up motor enables the loom to quickly respond to changes in production requirements and improve production efficiency. For example, when changing the fabric variety or adjusting the weaving process, the speed and speed ratio of the motor can be quickly adjusted to reduce the downtime and improve the utilization rate of the equipment. Real-time monitoring of the operating status data of the equipment can promptly detect abnormal conditions of the equipment and take corresponding adjustment measures to avoid damage to the equipment caused by overload, overheating, etc., reduce the maintenance cost and replacement frequency of the equipment, and extend the service life of the equipment. Through the analysis and evaluation of the equipment operating status data, realize the intelligent control and management of the rapier loom. For example, use machine learning algorithms to analyze historical data, predict equipment failures and maintenance requirements, and perform preventive maintenance in advance to improve the reliability and stability of production.

[0185] An embodiment of the present invention further provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the system as described above. All implementation manners in the above system embodiment are applicable to this embodiment and can also achieve the same technical effects.

[0186] An embodiment of the present invention further provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is made to execute the system as described above. All implementation manners in the above system embodiment are applicable to this embodiment and can also achieve the same technical effects.

[0187] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An electronic control data optimization system for a rapier loom, characterized in that, include: The material perception module is used to identify the material type of the fabric in real time through the spectral analysis sensor array and the dielectric feature extraction unit, including the fusion analysis of the hydroxyl vibration characteristics of cotton fibers and the phase difference of the dielectric constant of chemical fiber materials; Density analysis module, used to quantify the distribution density of warp and weft yarns and generate a three-dimensional heat map of yarn intersections per square centimeter; The monitoring module is used to continuously collect dynamic parameters during the operation of the loom, including the main motor speed, the torque of the warp let-off motor, the response speed of the take-up motor and the warp tension data, and identify the four working modes of the loom: startup, steady-state operation, variable speed weaving and shutdown transition according to the dynamic parameters; Intelligent decision-making module, used to dynamically calculate the final response speed of the main motor and generate motor control instructions based on fabric material type, warp and weft density data and dynamic parameters combined with the current working mode; The execution optimization module is used to drive the main motor to operate according to the motor control instructions, and to link the warp feeding / winding motor speed ratio relationship to follow the changes in the main motor speed, so as to adjust the equipment operation status in real time.

2. The electronic control data optimization system of a rapier loom according to claim 1, characterized in that, Through the spectral analysis sensor array and dielectric feature extraction unit, the material type of the fabric can be identified in real time, including the fusion analysis of the hydroxyl vibration characteristics of cotton fibers and the phase difference of the dielectric constant of chemical fiber materials, including: The multi-band spectral reflectance of the fabric is detected by the spectral analysis sensor array to generate multi-band spectral reflectance data; the dielectric feature extraction unit measures the response of the fabric in the electric field to obtain the dielectric constant phase difference data of the chemical fiber material; Extract spectral features related to the hydroxyl vibration characteristics of cotton fibers from multi-band spectral reflectance data, including the absorption peak and peak area of the band; analyze the dielectric constant phase difference data, and extract characteristic parameters from the original dielectric constant phase difference data, including the average value, standard deviation, and spectrum characteristics of the phase difference; The characteristic parameters extracted from the spectral features and the dielectric constant phase difference data are fused to form a fused feature vector; The fused feature vector is input into the three-level classifier for material determination, thus realizing real-time identification of the material type of the fabric.

3. The electronic control data optimization system of a rapier loom according to claim 2, characterized in that, The three-level classifier determination process includes: Primary classification: The hydroxyl-related parameter value ≥ 0.65 is set as the threshold, and the natural fibers containing cotton components and pure synthetic fibers are distinguished based on the relevant features in the fused feature vector; Secondary classification: For samples judged to contain cotton in the primary classification, the Mahalanobis distance classifier is used to match the cotton fiber purity grade based on the principal component distribution from the first principal component to the third principal component obtained by principal component analysis based on the fused feature vector; Three-level classification: For samples judged as pure synthetic fibers in the first-level classification, a support vector machine is used to construct a hyperplane by fusing the loss tangent value in the feature vector with the second principal component to distinguish between three types of chemical fiber materials: polyester, polyamide, and nylon.

4. The electronic control data optimization system of a rapier loom according to claim 3, characterized in that Quantify the warp and weft yarn distribution density and generate a 3D heat map of yarn intersections per square centimeter, including: During the operation of the loom, the fabric is continuously photographed to obtain a series of images containing warp and weft yarns; Preprocess a series of images containing warp and weft yarns, and binarize the preprocessed images; use an edge detection algorithm to identify the edges of the warp and weft yarns in the binarized images, and identify the intersection points of the warp and weft yarns and their corresponding coordinates. Divide the fabric image into small regions, count the number of yarn intersection points in each small region, and obtain the number of intersection points in each region. Calculate the warp and weft yarn distribution density data for the corresponding region based on the number of intersection points in each region. Map the warp and weft yarn distribution density data of each small region into three-dimensional space, where the position of the region is used as the two-dimensional coordinate and the density value is used as the third-dimensional coordinate. Perform interpolation processing on the mapped warp and weft yarn distribution density data in three-dimensional space, and draw a three-dimensional heat map based on the interpolated warp and weft yarn distribution density data.

5. The electronic control data optimization system of a rapier loom according to claim 4, wherein Continuously collect dynamic parameters during the operation of the loom, including the main motor speed, warp let-off motor torque, take-up motor response speed, and warp tension data, and identify the four working modes of the loom, namely start-up, steady-state operation, variable-speed weaving, and stop transition, based on the dynamic parameters, including: Determine the current working mode through the joint analysis of the main motor speed change rate, the average value of the warp let-off motor torque, and the standard deviation of the warp tension, that is: When the main motor speed change rate ≥ 50 rpm / s and the standard deviation of the warp tension > 8N, it is marked as the start-up mode. When the main motor speed change rate ≤ 5 rpm / s and the standard deviation of the warp tension < 3N, it is marked as the steady-state operation mode. When a preset weft density parameter change is detected, trigger the variable-speed weaving mode. When the main motor speed ≤ 30% of the rated value, activate the stop transition mode.

6. The electronic control data optimization system of a rapier loom according to claim 5, characterized in that Based on the fabric material type, warp and weft density data, and dynamic parameters, combined with the current working mode, dynamically calculate the final response speed of the main motor and generate motor control instructions, including: Preset a control strategy database containing different combinations of fabric material types, warp and weft densities, dynamic parameters, and working modes, and perform a matching operation in the control strategy database to obtain the corresponding reference value of the main motor response speed. Set corresponding evaluation indicators and preset standards for different working modes, analyze and evaluate the current dynamic parameters, and obtain the analysis and evaluation results. Generate an adjustment plan for the control strategy based on the analysis and evaluation results, and apply the adjustment plan to the reference value of the main motor response speed to obtain the preliminarily adjusted main motor response speed. Calculate the final response speed of the main motor based on the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and current working mode. Convert the final response speed of the main motor into a motor control instruction, and the instruction includes the target speed, acceleration, and running time information of the motor.

7. The electronic control data optimization system of a rapier loom according to claim 6, characterized in that Calculate the final response speed of the main motor based on the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and current working mode, including: Analyze the preliminarily adjusted main motor response speed, fabric material type, warp and weft density data, dynamic parameters, and current working mode, and based on the reference value of the main motor response speed, combined with the speed adjustment amount in the analysis and evaluation results, obtain the adjusted basic speed. According to the material category of the current fabric, determine the influence of the fabric material on the speed of the main motor; according to the warp and weft density of the fabric, determine the influence of the warp and weft density on the speed of the main motor; Determine the adjustment amount for the dynamic parameters according to the main motor speed, the let-off motor torque, the take-up motor response speed and the warp tension parameters; According to the current working mode of the rapier loom, a corresponding working mode adjustment amount is determined from a preset mode parameter table; The final response speed of the main motor is obtained by integrating the adjusted basic speed, the influence of fabric material on the main motor speed, the influence of warp and weft density on the main motor speed, the adjustment of dynamic parameters and the adjustment of working mode.

8. The electronic control data optimization system of a rapier loom according to claim 7, characterized in that The main motor is driven to operate according to the motor control instructions, and the warp let-off / winding motor speed ratio is linked to follow the speed change of the main motor, and the equipment operation status is adjusted in real time, including: Generate corresponding motor control instructions, including speed and direction, according to the final response speed of the main motor, and send the motor control instructions to the driving device of the main motor; After the main motor is started, the target speeds of the let-off motor and the take-up motor are calculated according to the real-time running speed of the main motor and the preset speed ratio relationship between the let-off / take-up motor and the main motor; Operate the drive devices of the warp let-off motor and the take-up motor at the target speed. During operation, monitor the actual speed in real time and compare it with the target speed. During the operation of the main motor, let-off motor and take-up motor, the operating status data of the equipment is continuously collected, including the motor current, voltage, temperature, warp tension and fabric density parameters; According to the operating status data of the equipment, the operating status of the entire rapier loom is evaluated and analyzed to adjust the operating status of the equipment in real time.

9. A computing device, characterized in that, include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the system according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program, and when the program is executed by a processor, the system according to any one of claims 1 to 8 is implemented.

Images