An intelligent digital management and control system for luggage production equipment

Abstract

The present application relates to the technical field of luggage production equipment control, and particularly relates to an intelligent digital management and control system for luggage production equipment, comprising: an equipment feature acquisition module, which acquires cutting tool running pressure, cutting speed and running time length; a fabric feature acquisition module, which acquires cutting surface images and infrared temperature images to determine cutting fabric features; a feature alignment module, which determines cutting surface feature areas based on cutting surface adhesion features and identifies temperature dominant feature rates in combination with infrared temperature images; a feature analysis module, which forms a multi-dimensional equipment feature vector and determines temperature cumulative equivalent; a correlation analysis module, which fits and establishes a cutting tool running temperature model; a defect analysis module, which predicts cutting surface defect distribution; and an optimization module, which determines cutting tool target cooling efficiency and outputs a cooling parameter set, thereby achieving precise perception of cutting process thermal state and prior prediction of defects, forming a closed-loop optimization of cooling parameters, and significantly reducing cutting defect rates.

Description

Technical Field

[0001] This invention relates to the field of control technology for bag and luggage production equipment, and in particular to an intelligent digital control system for bag and luggage production equipment. Background Technology

[0002] In the bag manufacturing process, the cutting process is a crucial step that determines product quality and material utilization. Typically, a cutting blade cuts multiple layers of fabric into pieces in a single operation. During high-speed, continuous operation, the blade's temperature rises significantly due to frictional heat, leading to defects such as melting and adhesion, burrs, and thermal shrinkage on the cut surface. These defects severely impact cutting accuracy and the finished product's appearance. Currently, mainstream bag manufacturing equipment typically only monitors and controls basic parameters such as cutting blade pressure, cutting speed, and operating time, lacking the ability to effectively sense and dynamically regulate the thermal state of the cut surface.

[0003] Chinese invention patent publication number CN115194835A discloses a fine and efficient cutting process and cutting machine for bag fabrics. When an electric hydraulic cylinder drives a connecting plate downwards, a connecting rod drives a push plate downwards to increase the pressure inside the cooling chamber. This allows gas to be discharged through an exhaust pipe to cool the cutting device during operation. When the cutting device moves upwards, external gas is introduced into the cooling chamber through an intake pipe. However, this solution relies on mechanical linkage for air cooling, with a single cooling trigger method. It passively exhausts gas only with the lifting and lowering of the cutting device, failing to differentiate cooling adjustments based on the fabric's thermal sensitivity and cutting process parameters. Furthermore, this solution lacks real-time sensing and feedback of the actual thermal state of the cutting surface, making it impossible to verify and adaptively optimize the cooling effect. In addition, its fixed cooling parameters cannot dynamically adapt to different fabrics, cutting speeds, and pressure conditions, leading to energy waste due to insufficient or excessive cooling.

[0004] It is evident that existing cutting control systems suffer from several technical shortcomings: crude methods for monitoring cutter temperature, failing to acquire full-area thermal distribution data of the cutting surface; fixed cooling control strategies, failing to dynamically adapt to different fabric thermal response characteristics and cutting process parameters; and insufficient ability to predict cutting defects, making it difficult to proactively intervene by adjusting cooling parameters before defects occur. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent digital control system for bag production equipment, which solves the technical problems of incomplete temperature monitoring of cutting equipment, lack of fabric adaptability in cooling control, and disconnect between defect prediction and process optimization in existing technologies.

[0006] To achieve the above objectives, the present invention provides an intelligent digital control system for bag production equipment, comprising: The equipment feature acquisition module is used to collect the cutting blade operating pressure, cutting speed and running time to determine the characteristics of the cutting equipment; The fabric feature acquisition module is used to acquire cross-sectional images and infrared temperature images of the cut surface to determine the characteristics of the cut fabric. The feature alignment module is used to determine several cross-sectional feature regions based on the adhesion features of the cross-sectional image, and to determine the cutting-related feature regions by combining the cross-sectional infrared temperature image, so as to identify the temperature dominant feature rate of the fabric. The feature analysis module is used to generate multi-dimensional equipment feature vectors corresponding to each cut surface feature region based on the cutting order, and to determine the corresponding temperature cumulative equivalent based on the temporal distribution of the cut surface feature regions and the temperature dominant feature rate. The correlation analysis module is used to fit the multidimensional device feature vector with the corresponding cumulative temperature equivalent based on the cutting order, so as to determine the operating temperature model of the cutter. The defect analysis module is used to predict the cumulative temperature equivalent of any cutting surface based on a specified set of cutting equipment features and the operating temperature model, so as to predict the defect distribution. The optimization module is used to determine the target cooling efficiency of the cutter based on the cumulative temperature equivalent corresponding to the predicted defect distribution, so as to output the cutter cooling parameter set corresponding to the specified cutting equipment feature set.

[0007] Furthermore, the fabric feature acquisition module establishes the cut fabric features based on the appearance features of the cut surface image and the fabric temperature gradient features of the infrared temperature image of the cut surface.

[0008] Furthermore, the feature alignment module determines the adhesion set of the cross-sectional image based on the boundary transition width between the non-cut edge regions determined by the cross-sectional appearance features, and determines several cross-sectional feature regions based on the adhesion set. The characteristic regions of each cut surface are determined based on the set of adhesion degrees and the average adhesion degree of the corresponding cut edge region in the non-cut edge direction.

[0009] Furthermore, the feature alignment module determines the cutting path position corresponding to the cut surface image based on the cut surface appearance features to establish a cut surface distance parameter, and determines the heat-affected boundary distance based on the temperature attenuation boundary of the cut surface infrared temperature image determined by the fabric temperature gradient features, so as to determine the temperature dominance feature rate based on the selected first-level temperature influence region.

[0010] Furthermore, the feature analysis module determines the cutting time of each cut feature region and the cutting interval time of each cut feature region based on the cutting order, and arranges them based on the cutting time and the corresponding cutting equipment features to establish a multi-dimensional equipment feature vector.

[0011] Furthermore, the feature analysis module determines the temperature decay coefficient and the cumulative temperature base value corresponding to each cut feature region based on the cutting interval time, and corrects the cumulative temperature base value based on the temperature decay coefficient corresponding to each cut feature region to determine the cumulative temperature equivalent corresponding to each cut feature region.

[0012] Furthermore, the correlation analysis module determines the corresponding numerical mapping set based on the multidimensional equipment feature vectors and cumulative temperature equivalents of each cross-sectional feature region, establishes initial coefficient values ​​based on the multidimensional equipment feature vectors, establishes fitting residuals by combining the difference in cumulative temperature equivalents to determine the component fitting coefficients corresponding to each component of the multidimensional equipment feature vectors, determines the temperature prediction values ​​corresponding to each cross-sectional feature region based on the component fitting coefficients and the corresponding multidimensional equipment feature vectors, and establishes the operating temperature model of the cutting tool based on the sum of squared residuals of the linear model and the variance of the cumulative temperature equivalent sequence.

[0013] Furthermore, the correlation analysis module filters based on the residual sum of squares of the linear model and the variance of the cumulative temperature equivalent sequence. When the residual sum of squares of the linear model is less than the variance of the cumulative temperature equivalent sequence, the operating temperature model is determined to be a linear prediction model with each component of the multidimensional equipment feature vector as input and the cumulative temperature equivalent as output as the operating temperature model of the cutter. When the sum of squared residuals of the linear model is not less than the variance of the cumulative temperature equivalent sequence, the operating temperature model is determined to be a nonlinear prediction model with each component of the multidimensional equipment feature vector as input and the cumulative temperature equivalent as output as the operating temperature model of the cutting tool.

[0014] Furthermore, the defect analysis module obtains the predicted cumulative temperature equivalent based on the input operating temperature model of the specified cutting equipment feature set, and determines the predicted defect distribution by combining the difference between the corresponding cumulative temperature equivalent and the cumulative temperature equivalent corresponding to the non-defect cut surface.

[0015] Furthermore, the optimization module determines the cutting defect interference factor based on the distance between the defect region corresponding to the cumulative temperature equivalent of the predicted defect distribution and the cutting blade path position. Based on the cutting defect interference factor and the cumulative temperature equivalent of the corresponding region, it determines the target cooling efficiency of the cutting blade and uses the corresponding historical initial cooling parameters as the current initial cooling parameters. Based on the ratio of the historical target cooling efficiency to the corresponding actual cooling efficiency, it establishes a cutting speed correction factor and a cutting pressure correction factor. Combined with the current initial cooling parameters, it outputs a cutting blade cooling parameter set corresponding to the specified cutting equipment feature set.

[0016] Compared with the closest existing technology, the present invention has the following advantages: This invention acquires cutting blade operating parameters, cutting surface images, and infrared temperature images through a device feature acquisition module and a fabric feature acquisition module, respectively, thereby achieving synchronous perception of mechanical and thermal parameters during the cutting process and providing a multi-dimensional data foundation for accurate temperature modeling.

[0017] Furthermore, this invention uses a feature alignment module to divide the cut surface feature region based on the cut surface adhesion feature, and combines infrared temperature image recognition to identify the temperature dominance feature rate, effectively filtering out the interference of the fabric's background temperature, extracting the temperature feature region that is strongly correlated with the thermal effect of the cutting knife, and improving the targeting of temperature analysis.

[0018] Furthermore, this invention establishes a multi-dimensional equipment feature vector indexed by the cutting order through a feature analysis module, and determines the cumulative temperature equivalent of each region by combining the temporal distribution and temperature decay coefficient, and temporally correlates the equipment operating parameters with the thermal response characteristics of the fabric, providing accurate sample labels for the construction of the operating temperature model.

[0019] Furthermore, this invention establishes a cutting blade operating temperature model by performing linear and nonlinear adaptive fitting of multidimensional equipment feature vectors and cumulative temperature equivalents through a correlation analysis module. This model can predict the cumulative temperature equivalent of any cutting surface based on different cutting equipment feature sets, and combine it with defect judgment criteria to achieve pre-prediction of defect distribution, avoiding the lag of traditional post-detection.

[0020] Furthermore, this invention determines the target cooling efficiency based on the predicted defect distribution through an optimization module, and establishes speed correction factors and pressure correction factors in combination with historical data, outputting a set of cooling parameters that match the current cutting process conditions, forming a closed-loop control mechanism of perception, modeling, prediction, and optimization, which significantly reduces the cutting defect rate and improves the fabric utilization rate. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of a module of an intelligent digital control system for bag production equipment according to an embodiment of the present invention; Figure 2 This is an execution flowchart of an intelligent digital control system for bag production equipment according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating the pre-processing of the cross-sectional feature region division for an intelligent digital control system for bag production equipment according to an embodiment of the present invention. Figure 4 This is a flowchart illustrating the construction of an operating temperature model and defect prediction for an intelligent digital control system used in bag production equipment, as described in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0023] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0024] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0025] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0026] Please see Figure 1 As shown, it is an intelligent digital control system for bag production equipment according to an embodiment of the present invention, including: The equipment feature acquisition module is used to collect the cutting blade operating pressure, cutting speed and running time to determine the characteristics of the cutting equipment; The fabric feature acquisition module is used to acquire cross-sectional images and infrared temperature images of the cut surface to determine the characteristics of the cut fabric. The feature alignment module is used to determine several cross-sectional feature regions based on the adhesion features of the cross-sectional image, and to determine the cutting-related feature regions by combining the cross-sectional infrared temperature image, so as to identify the temperature dominant feature rate of the fabric. The feature analysis module is used to generate multi-dimensional equipment feature vectors corresponding to each cut surface feature region based on the cutting order, and to determine the corresponding temperature cumulative equivalent based on the temporal distribution of the cut surface feature regions and the temperature dominant feature rate. The correlation analysis module is used to fit the multidimensional device feature vector with the corresponding cumulative temperature equivalent based on the cutting order, so as to determine the operating temperature model of the cutter. The defect analysis module is used to predict the cumulative temperature equivalent of any cutting surface based on a specified set of cutting equipment features and the operating temperature model, so as to predict the defect distribution. The optimization module is used to determine the target cooling efficiency of the cutter based on the cumulative temperature equivalent corresponding to the predicted defect distribution, so as to output the cutter cooling parameter set corresponding to the specified cutting equipment feature set.

[0027] In this embodiment, the device feature acquisition module includes: A pressure acquisition unit is installed at the bottom of the cutting die to collect the operating pressure of the cutting blade; A speed monitoring unit, located on the servo motor, is used to collect pulse signals and convert them into cutting speed. The time acquisition unit is located inside the control system of the bag production equipment and is used to collect running time.

[0028] Specifically, the pressure acquisition unit, speed monitoring unit, and time acquisition unit acquire the cutting blade operating pressure, cutting speed, and running time in sequence to determine the characteristics of the cutting equipment.

[0029] In this embodiment, please refer to Figure 2 As shown, the fabric feature acquisition module includes: The cross-sectional appearance feature determination unit is used to simultaneously acquire visible light cross-sectional images and infrared temperature images of the cut surface after each cutting action, and to extract cross-sectional appearance features. The fabric temperature gradient feature determination unit is used to extract fabric temperature gradient features based on the temperature amplitude distribution of the cross-sectional infrared temperature image; wherein, the fabric temperature gradient feature is the actual temperature corresponding to each pixel in the cross-sectional infrared temperature image.

[0030] The fabric cutting feature determination unit is used to determine the fabric cutting features based on the cut surface appearance features and the fabric temperature gradient features, and then transmit them to the feature alignment module. Specifically, the cross-sectional appearance feature determination unit establishes the cross-sectional appearance features of the cross-sectional image based on the color distribution and grayscale distribution of the cross-sectional image. The fabric temperature gradient feature determination unit obtains the fabric temperature gradient features of the cross-sectional infrared temperature image based on the temperature amplitude distribution of the cross-sectional infrared temperature image. The fabric feature determination unit establishes fabric features based on the appearance features of the cut surface image and the fabric temperature gradient features of the infrared temperature image of the cut surface.

[0031] In this embodiment, the feature alignment module includes: The image registration unit is used to perform pixel-level spatial alignment between the cross-sectional image and the infrared temperature image; Specifically, the image registration unit performs inverse calculations on the actual spatial positions of the cross-sectional image and the infrared temperature image to determine the spatial coordinates of each pixel in the cross-sectional image and the infrared temperature image, and matches and aligns the features of each pixel in the two images based on the spatial coordinates. An adhesion feature extraction unit is used to extract the adhesion degree of the corresponding cross-sectional image based on the boundary transition width between non-cut edge regions determined by the appearance features of the cross-section, and to establish an adhesion degree set. Please see Figure 3 As shown, the adhesion feature extraction unit determines the boundary transition width between non-cut edge regions based on the appearance features of the cut surface, and determines the adhesion set of the cut surface image based on the boundary transition width. Specifically, the adhesion feature extraction unit identifies the boundary positions between each fabric layer in the cross-section image based on the color and grayscale distribution in the cross-section appearance features, calculates the boundary transition width of the non-cut edge area, and selects sampling points from the cross-section infrared temperature image that are greater than the adhesion judgment threshold based on the boundary transition width at the sampling point, so as to establish adhesion feature points and perform spatial clustering to form an adhesion set.

[0032] Understandably, the boundary transition width is determined by the maximum distance between the area where the fabric temperature maintains its pre-cut temperature and the cut edge boundary. The adhesion threshold is the lowest temperature at which high-temperature adhesion occurs, determined by the fabric's own material properties.

[0033] A section feature region division unit is used to establish several section feature regions based on the adhesion set; the section feature region is formed by dividing a continuous region with a transition width from the edge boundary to the inner boundary of the fabric at equal intervals along the cutting direction.

[0034] Temperature influence region segmentation unit, which is used to determine the first-level temperature influence region; Specifically, the temperature-affected region segmentation unit determines the cutting path position corresponding to the cut surface image based on the appearance features of the cut surface; establishes a cut surface distance parameter based on the distance between the cutting path position and each pixel of the cut surface image; determines the temperature attenuation boundary of the infrared temperature image of the cut surface based on the fabric temperature gradient features; establishes a heat-affected boundary distance based on the distance between the temperature attenuation boundary and the cutting path position; and filters based on the cut surface distance parameter and the heat-affected boundary distance to establish a first-level temperature-affected region. In this embodiment, the temperature-affected region segmentation unit determines the temperature attenuation boundary in the infrared temperature image of the cut surface based on the fabric temperature gradient characteristics, and establishes a heat-affected boundary distance based on the distance between the temperature attenuation boundary and the cutting path position; it determines the cutting path position corresponding to the cut surface image based on the appearance characteristics of the cut surface, and establishes a cut surface distance parameter based on the spatial distance between the cutting path position and each pixel in the cut surface image; the temperature-affected region segmentation unit compares and filters the cut surface distance parameter with the heat-affected boundary distance, and establishes a continuous region composed of pixels whose cut surface distance parameter is less than or equal to the heat-affected boundary distance as a first-level temperature-affected region, wherein the first-level temperature-affected region is used to characterize the fabric area directly affected by heat conduction from the cutting blade during the cutting process. The temperature attenuation boundary is determined based on the continuous boundary formed by the fabric temperature maintaining the temperature before cutting.

[0035] Temperature dominance characteristic rate calculation unit, which is used to calculate the temperature dominance characteristic rate of the fabric.

[0036] Specifically, the temperature dominance feature rate calculation unit determines the temperature amplitude deviation sequence of the primary temperature influence region based on the difference between the temperature amplitude corresponding to the pixel in the primary temperature influence region and the average temperature amplitude. Based on the temperature amplitude deviation sequence of the primary temperature influence region, it obtains the number of dominant pixels in the primary region and establishes the primary region dominance feature rate as the temperature dominance feature rate for identifying the fabric by the ratio of the number of dominant pixels in the primary region to the total number of pixels in the primary temperature influence region.

[0037] In this embodiment, the feature analysis module includes: The clipping timing parsing unit is used to determine the clipping time of each region based on the timestamps corresponding to the clipping sequence records; The cutting interval time calculation unit is used to determine the cutting interval time of each region based on the cutting time difference between two adjacent feature regions; The multidimensional feature vector construction unit is used to construct a three-dimensional device feature vector sequence based on the cutting order, taking the cutting pressure, cutting speed and running time corresponding to each cut surface feature area as three components, and using the cutting order as an index, so as to provide input data for the subsequent fitting of temperature cumulative equivalent. The temperature decay coefficient determination unit is used to calculate the temperature drop per unit time as the temperature decay coefficient based on the temperature change difference between the cutting interval time of the current cutting feature area and the cutting end time of the previous feature area and the cutting start time of the current area. Specifically, the temperature decay coefficient is obtained by dividing the temperature change difference by the cutting interval time, and is used to characterize the heat dissipation rate of the cutting blade during non-working intervals.

[0038] The temperature cumulative base value calculation unit is used to set the temperature cumulative base value of the first cut surface feature region as its corresponding temperature dominant characteristic rate. For each current cut surface feature region after the first cut surface feature region, the temperature cumulative amount after decay is obtained by multiplying the temperature cumulative equivalent of the previous adjacent region by the temperature decay coefficient of the current region. The temperature dominant characteristic rate of the previous adjacent region is divided by the temperature decay coefficient of the current region to obtain the heat source input equivalent of the current region. The temperature cumulative base value of the current region is then determined by summing the temperature cumulative amount after decay with the heat source input equivalent in a recursive manner. The temperature decay coefficient is determined based on the cutting interval time. The longer the cutting interval time, the smaller the temperature decay coefficient, which is used to characterize the heat dissipation of the cutting blade during the non-working interval. The temperature cumulative equivalent calculation unit is used to obtain the product of the temperature cumulative equivalent of the adjacent previous region and the temperature decay coefficient corresponding to the current region based on the current cut feature region, as the heat accumulation after decay. At the same time, it obtains the temperature dominant characteristic rate of the adjacent previous region and divides it by the temperature decay coefficient corresponding to the current region to obtain the heat source input equivalent of the current region. The heat accumulation after decay is added to the heat source input equivalent to establish the temperature cumulative base value of the current cut feature region, so that the region with a longer cutting interval and more heat dissipation receives a larger cumulative equivalent compensation, so as to accurately reflect the real heat accumulation state of the cutter during subsequent cutting.

[0039] Specifically, the clipping timing analysis unit determines the clipping time of each slice feature region according to the clipping order; The cutting interval calculation unit determines the cutting interval time of each cutting feature region based on the cutting time of each cutting feature region; The multidimensional feature vector construction unit establishes a cutting device feature sequence based on the cutting time and the corresponding cutting device features, and arranges the cutting device feature sequence according to the cutting order to establish a multidimensional device feature vector. The multidimensional device feature vector is based on the cutting blade running pressure, cutting speed and running time as components, and the cutting order is determined by the index. The temperature decay coefficient determination unit determines the temperature decay coefficient corresponding to each cut surface feature region based on the cutting interval time. The temperature cumulative baseline value calculation unit determines the temperature cumulative baseline value corresponding to each cross-sectional feature region based on the temperature attenuation coefficient and temperature dominant characteristic rate before cutting based on each cross-sectional feature region. Please see Figure 4 As shown, the temperature cumulative equivalent calculation unit corrects the temperature cumulative base value based on the temperature attenuation coefficient corresponding to each cross-sectional feature region to determine the temperature cumulative equivalent corresponding to each cross-sectional feature region.

[0040] In this embodiment, the correlation analysis module includes: The numerical mapping set establishment unit is used to pair the multidimensional equipment feature vector of each feature region with the corresponding temperature cumulative equivalent according to the cutting order, so as to establish a numerical mapping set from the equipment parameter space to the temperature cumulative equivalent space. The initial coefficient value establishment unit is used to establish an equal number of initial fitting coefficients based on the number of components of the multidimensional device feature vector, and to set each initial coefficient value to a preset initial value. The iterative adjustment unit is used to iteratively update the initial coefficient values ​​using the gradient descent method, based on the minimum sum of squares of the fitted residuals as the objective function, until the objective function converges, so as to determine the final component fitting coefficients corresponding to each component. The temperature prediction value determination unit is used to determine the temperature prediction value of each cross-sectional feature region based on the sum of the products of the fitting coefficients of each component and the corresponding multidimensional equipment feature vectors. The linear model residual sum of squares determination unit is used to establish a fitted residual sequence based on the difference between the temperature prediction value and the temperature cumulative equivalent in each cross-sectional feature region, and to sum the squares of each residual value in the fitted residual sequence to determine the residual sum of squares of the linear model. The temperature cumulative equivalent sequence variance determination unit is used to establish a temperature cumulative equivalent deviation sequence based on the difference between each value in the temperature cumulative equivalent sequence and the sequence mean, and to sum the squares of each deviation value in the deviation sequence to determine the variance of the temperature cumulative equivalent sequence, which is used to measure the overall dispersion of the temperature cumulative equivalent. The model selection unit determines the method of establishing the temperature model based on the comparison between the sum of squared residuals of the linear model and the variance of the cumulative temperature equivalent sequence. If the sum of squared residuals is less than the variance, a linear regression model is selected to fit the operating temperature model, indicating that there is an approximately linear relationship between the equipment parameters and the cumulative temperature equivalent. If the sum of squared residuals is not less than the variance, a nonlinear model is selected to fit the operating temperature model in order to capture the complex nonlinear coupling relationship between the equipment parameters and the cumulative temperature equivalent.

[0041] Specifically, the numerical mapping set establishment unit determines the numerical mapping set between each component of the multidimensional equipment feature vector and the cumulative temperature equivalent for each section feature region based on the cutting order and the multidimensional equipment feature vector and the cumulative temperature equivalent. The initial coefficient value establishment unit establishes initial coefficient values ​​based on the multi-dimensional device feature vector; The iterative adjustment unit establishes a fitting residual based on the difference between the initial coefficient value and the cumulative temperature equivalent. Based on the minimum value of the sum of squares of the fitting residual as an iterative constraint, the initial coefficient value is iteratively adjusted to determine the component fitting coefficients corresponding to each component of the multidimensional device feature vector. The temperature prediction value determination unit determines the temperature prediction value corresponding to each cross-sectional feature region based on the component fitting coefficients and the corresponding multi-dimensional device feature vectors. The linear model residual sum of squares determination unit determines the fitted residual sequence based on the temperature prediction value and the corresponding cumulative temperature equivalent of each cross-sectional feature region, and determines the residual sum of squares of the linear model based on the sum of squares of the fitted residuals in the fitted residual sequence. The temperature cumulative equivalent sequence variance determination unit determines the temperature cumulative equivalent deviation sequence based on the difference between each temperature cumulative equivalent in the temperature cumulative equivalent sequence and the average value of the temperature cumulative equivalent sequence, and determines the variance of the temperature cumulative equivalent sequence based on the sum of squares of the deviation values ​​in the temperature cumulative equivalent deviation sequence. The model selection unit establishes a cutting temperature model based on the sum of squared residuals of the linear model and the variance of the cumulative temperature equivalent sequence.

[0042] In this embodiment, the defect analysis module includes: The predicted temperature cumulative equivalent acquisition unit is used to input the feature set of the cutting equipment specified by the user into the established operating temperature model, so as to output the predicted temperature cumulative equivalent under the current specified conditions. The defect judgment benchmark establishment unit is used to multiply the difference between the cumulative equivalent temperature of all samples marked as defective cut surfaces in historical cutting data and the cumulative equivalent temperature of all samples marked as non-defective cut surfaces by a preset judgment coefficient as the defect judgment benchmark. This benchmark value is used for subsequent prediction and judgment. The preset judgment coefficient is determined based on the thermal sensitivity of the fabric and the stability characteristics of the cutting process. It is usually set with redundancy to trigger safety alarms in advance according to the actual scenario or process requirements.

[0043] The predicted defect distribution determination unit is used to compare the predicted cumulative temperature equivalent with the defect judgment benchmark. If the predicted cumulative temperature equivalent is greater than the defect judgment benchmark, the corresponding cutting surface area is marked as a predicted defect area; otherwise, it is marked as a non-defect area, so as to generate a predicted defect distribution map distributed along the cutting path.

[0044] Specifically, the predicted temperature cumulative equivalent acquisition unit inputs the operating temperature model according to the specified feature set of the cutting equipment to obtain the predicted temperature cumulative equivalent; The defect judgment benchmark establishment unit determines the sensitivity of the fabric to the thermal influence of the cutting blade based on the thermal conductivity and heat distortion temperature corresponding to the current fabric type, and determines the value benchmark of the preset judgment coefficient by combining the process consistency level characterized by the fluctuation range of the current cutting speed and the cutting blade running pressure. The defect distribution prediction unit determines the predicted defect distribution based on the cumulative equivalent of the predicted temperature and the defect judgment criteria.

[0045] In this embodiment, the optimization module includes: The defect region location determination unit is used to determine the spatial location of the defect region in the cross-sectional image based on the set of pixel coordinates marked as defect regions in the predicted defect distribution. The cutting defect interference factor determination unit is used to determine the spacing value based on the shortest distance from the geometric center of the defect area to the cutting path position, and the ratio of the spacing value to the distance of the heat-affected boundary is used as the cutting defect interference factor. The smaller the spacing, the larger the interference factor, indicating that the defect area is more directly affected by the heat of the cutting blade. The target cooling efficiency determination unit is used to determine the target cooling efficiency based on the product of the cutting defect interference factor and the corresponding area temperature cumulative equivalent. The higher the efficiency value, the stronger the cooling measures are needed to suppress the occurrence of defects. The current initial cooling parameter determination unit is used to retrieve the closest historical target cooling efficiency from the historical database based on the target cooling efficiency, and extract the cooling medium flow rate and cooling time corresponding to the historical data as the current initial cooling parameters. The speed correction factor establishment unit is used to establish a cutting speed correction factor by averaging the ratio of historical target cooling efficiency to actual cooling efficiency at the same cutting speed in historical data. This factor reflects the degree of influence of cutting speed on the deviation of cooling efficiency. The pressure correction factor establishment unit is used to establish a cutting pressure correction factor by taking the average value of the ratio of historical target cooling efficiency to actual cooling efficiency under the same cutting pressure in historical data. This factor reflects the degree of influence of cutting pressure on the deviation of cooling efficiency. The cooling parameter set output unit is used to multiply the current initial cooling parameters by the speed correction factor and the pressure correction factor respectively to obtain the cooling parameters after speed compensation and the cooling parameters after pressure compensation. The two sets of parameters are then weighted and averaged to output the final cutting blade cooling parameter set that matches the specified cutting equipment feature set, for the equipment actuator to perform real-time control.

[0046] Specifically, the defect area location determination unit determines the location of the corresponding cutting defect area based on the cumulative temperature equivalent corresponding to the predicted defect distribution. The cutting defect interference factor determination unit obtains the distance between the defect area and the cutting path position based on the location of the cutting defect area, and determines the cutting defect interference factor based on the distance between the defect area and the cutting path position. The target cooling efficiency determination unit determines the target cooling efficiency of the cutting blade based on the cutting defect interference factor and the temperature cumulative equivalent of the corresponding area, wherein the target cooling efficiency is determined based on the product of the cutting defect interference factor and the temperature cumulative equivalent of the corresponding area. The current initial cooling parameter determination unit determines the corresponding historical initial cooling parameters as the current initial cooling parameters based on the target cooling efficiency. The cooling parameters include the cooling medium flow rate and the cooling duration. The speed correction factor establishment unit establishes a cutting speed correction factor under the same cutting speed based on the ratio of historical target cooling efficiency to the corresponding actual cooling efficiency. The historical target cooling efficiency is obtained by acquiring sample data of the corresponding cutting surface marked as non-defect based on the current cutting speed and cutting blade operating pressure. After removing all sample records containing defective areas, the average value of the remaining target cooling efficiency values ​​is taken as the historical target cooling efficiency under the current cutting speed and cutting blade operating pressure. The cutting speed correction factor is based on the average ratio of the historical target cooling efficiency to the actual cooling efficiency corresponding to each sample. The pressure correction factor establishment unit establishes a cutting pressure correction factor under the same cutting blade operating pressure based on the ratio of historical target cooling efficiency to the corresponding actual cooling efficiency. The cooling parameter set output unit outputs a cutting blade cooling parameter set corresponding to a specified cutting equipment feature set based on the current initial cooling parameters, speed correction factor, and pressure correction factor. The cutting blade cooling parameter set is obtained by multiplying the initial cooling medium flow rate and pressure correction factor in the current initial cooling parameters, and multiplying the initial cooling duration and speed correction factor, respectively, to obtain the compensated cooling medium flow rate and compensated cooling duration. The compensated cooling medium flow rate and compensated cooling duration are then used as the cutting blade cooling parameter set for the specified cutting equipment feature set and output.

[0047] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An intelligent digital control system for bag production equipment, characterized in that, include: The equipment feature acquisition module is used to collect the cutting blade operating pressure, cutting speed and running time to determine the characteristics of the cutting equipment; The fabric feature acquisition module is used to acquire cross-sectional images and infrared temperature images of the cut surface to determine the characteristics of the cut fabric. The feature alignment module is used to determine several cross-sectional feature regions based on the adhesion features of the cross-sectional image, and to determine the cutting-related feature regions by combining the cross-sectional infrared temperature image, so as to identify the temperature dominant feature rate of the fabric. The feature analysis module is used to generate multi-dimensional equipment feature vectors corresponding to each cut surface feature region based on the cutting order, and to determine the corresponding temperature cumulative equivalent based on the temporal distribution of the cut surface feature regions and the temperature dominant feature rate. The correlation analysis module is used to fit the multidimensional device feature vector with the corresponding cumulative temperature equivalent based on the cutting order, so as to determine the operating temperature model of the cutter. The defect analysis module is used to predict the cumulative temperature equivalent of any cutting surface based on a specified set of cutting equipment features and the operating temperature model, so as to predict the defect distribution. The optimization module is used to determine the target cooling efficiency of the cutter based on the cumulative temperature equivalent corresponding to the predicted defect distribution, so as to output the cutter cooling parameter set corresponding to the specified cutting equipment feature set.

2. The intelligent digital control system for bag production equipment according to claim 1, characterized in that, The fabric feature acquisition module establishes the cut fabric features based on the appearance features of the cut surface image and the fabric temperature gradient features of the infrared temperature image of the cut surface.

3. The intelligent digital control system for bag production equipment according to claim 2, characterized in that, The feature alignment module determines the adhesion set of the cross-sectional image based on the boundary transition width between the non-cut edge regions determined by the cross-sectional appearance features, and determines several cross-sectional feature regions based on the adhesion set. The characteristic regions of each cut surface are determined based on the set of adhesion degrees and the average adhesion degree of the corresponding cut edge region in the non-cut edge direction.

4. The intelligent digital control system for bag production equipment according to claim 3, characterized in that, The feature alignment module determines the cutting path position corresponding to the cut surface image based on the cut surface appearance features to establish the cut surface distance parameter, and determines the heat-affected boundary distance based on the temperature attenuation boundary of the cut surface infrared temperature image determined by the fabric temperature gradient features, so as to determine the temperature dominance feature rate based on the selected first-level temperature influence region.

5. The intelligent digital control system for bag production equipment according to claim 4, characterized in that, The feature analysis module determines the cutting time and the cutting interval of each feature region based on the cutting order, and arranges them based on the cutting time and the corresponding cutting equipment features to establish a multi-dimensional equipment feature vector.

6. The intelligent digital control system for bag production equipment according to claim 5, characterized in that, The feature analysis module determines the temperature decay coefficient and the cumulative temperature base value corresponding to each cut feature region based on the cutting interval time, and corrects the cumulative temperature base value based on the temperature decay coefficient corresponding to each cut feature region to determine the cumulative temperature equivalent corresponding to each cut feature region.

7. The intelligent digital control system for bag production equipment according to claim 6, characterized in that, The correlation analysis module determines the corresponding numerical mapping set based on the multidimensional equipment feature vectors and cumulative temperature equivalents of each cross-sectional feature region, establishes initial coefficient values ​​based on the multidimensional equipment feature vectors, establishes fitting residuals based on the difference in cumulative temperature equivalents to determine the component fitting coefficients corresponding to each component of the multidimensional equipment feature vectors, determines the temperature prediction values ​​corresponding to each cross-sectional feature region based on the component fitting coefficients and the corresponding multidimensional equipment feature vectors, and establishes the operating temperature model of the cutting tool based on the sum of squared residuals of the linear model and the variance of the cumulative temperature equivalent sequence.

8. The intelligent digital control system for bag production equipment according to claim 7, characterized in that, The correlation analysis module is used to filter based on the residual sum of squares of the linear model and the variance of the cumulative temperature equivalent sequence. When the residual sum of squares of the linear model is less than the variance of the cumulative temperature equivalent sequence, the operating temperature model is determined to be a linear prediction model with each component of the multidimensional equipment feature vector as input and the cumulative temperature equivalent as output as the operating temperature model of the cutting tool. When the sum of squared residuals of the linear model is not less than the variance of the cumulative temperature equivalent sequence, the operating temperature model is determined to be a nonlinear prediction model with each component of the multidimensional equipment feature vector as input and the cumulative temperature equivalent as output as the operating temperature model of the cutting tool.

9. The intelligent digital control system for bag production equipment according to claim 8, characterized in that, The defect analysis module is used to obtain the predicted cumulative temperature equivalent based on the input operating temperature model of the specified cutting equipment feature set, and to determine the predicted defect distribution by combining the difference between the corresponding cumulative temperature equivalent and the cumulative temperature equivalent of the non-defect cut surface.

10. The intelligent digital control system for bag production equipment according to claim 9, characterized in that, The optimization module is used to determine the cutting defect interference factor based on the distance between the defect area corresponding to the temperature cumulative equivalent of the predicted defect distribution and the cutting path position. The target cooling efficiency of the cutting blade is determined based on the cutting defect interference factor and the temperature cumulative equivalent of the corresponding area. The corresponding historical initial cooling parameters are used as the current initial cooling parameters. Based on the ratio of the historical target cooling efficiency to the corresponding actual cooling efficiency, a cutting speed correction factor and a cutting pressure correction factor are established. Combined with the current initial cooling parameters, the cutting blade cooling parameter set corresponding to the specified cutting equipment feature set is output.

Images