Mold parameter adjusting method and system

Abstract

The invention relates to the technical field of die cutting machining, and particularly discloses a die parameter adjusting method and system.The method comprises the steps that blade sharpness features and material hard point features are obtained; obtaining the edge quality score and the size deviation characteristic of the cut edge; obtaining local structure non-uniformity characteristics of the material; mold wear state characteristics are estimated; inputting the blade sharpness feature, the material hard point feature, the edge quality score, the dimensional deviation feature, the material local structure non-uniformity feature and the mold wear state feature into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; controlling an executing mechanism of the die cutting machine to perform die cutting based on the die adjusting parameters; according to the method, quality fluctuation caused by individual differences and abrasion of the die and local nonuniformity superposition of materials is effectively coped with, the stability of die cutting machining and the consistency of product quality are improved, and closed-loop control and optimization of the die cutting process are achieved through sensing, analysis and intelligent decision making.

Description

Technical Field

[0001] The present application relates to the field of die-cutting processing technology, and in particular to a die parameter adjustment method and system. Background Art

[0002] In the field of die-cutting processing, traditional processes rely on empirical parameter settings, which makes it difficult to deal with quality fluctuations caused by the superposition of microscopic individual differences in molds and local material heterogeneity.

[0003] Specifically, the same model of molds has significant individual differences in actual cutting performance due to manufacturing tolerances, microscopic blade curling, and heat treatment fluctuations. Traditional fixed parameter strategies cannot adapt to the dynamic attenuation and regional fluctuations of blade sharpness (such as increased hair stimulation caused by local blunting). At the same time, during the processing of rolled materials, due to microscopic characteristics such as random distribution of fiber orientation and uneven bonding of laminated structures, the tear resistance and deformation behavior of the material in the die-cutting area show dynamic changes. Although existing visual inspection systems can capture edge defects, it is difficult to establish a real-time correlation model between the internal microstructure of the material and process parameters. More importantly, the accumulated wear of the mold and the local hard points of the material form coupled interference. The traditional static compensation model cannot decouple the combined influence of the two on the force distribution, resulting in parameter adjustment lag or even reverse compensation, which ultimately restricts the mass production stability of high-consistency products.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a mold parameter adjustment method and system to comprehensively sense the blade sharpness, cutting edge characteristics, local microscopic characteristics of the material, and mold wear characteristics to generate mold adjustment parameters, so as to achieve adaptive adjustment control of the die-cutting machine.

[0006] In a first aspect, the present application provides a mold parameter adjustment method for use in a die-cutting machine, the method comprising the steps of: S1. Obtaining transient force distribution data, material surface image data, thickness distribution data, density distribution data, and die usage history of the die-cutting area of ​​the workpiece; S2. Obtaining blade sharpness characteristics and material hard point characteristics based on the transient force distribution data; S3. Obtaining edge quality scores and dimensional deviation characteristics of the cut edges based on the material surface image data; S4. Obtaining local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; S5. estimating mold wear characteristics based on the mold usage history; S6. Inputting the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structure heterogeneity characteristics, and mold wear state characteristics into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; S7. Controlling the actuator of the die-cutting machine to perform die-cutting based on the die adjustment parameters.

[0007] The mold parameter adjustment method of the present application comprehensively perceives the various factors affecting the die-cutting quality by collecting transient forces, material images, local physical properties of the material and mold history data during the die-cutting process, and generates mold adjustment parameters based on an adaptive parameter configuration model by integrating multi-source data to achieve adaptive adjustment control of the die-cutting machine, so that the die-cutting parameters are no longer fixed empirical values, but are dynamically adjusted according to the current mold status, material properties and preliminary cutting results.

[0008] The mold parameter adjustment method, wherein step S2 includes: S21. Perform force waveform analysis, peak value analysis, and distribution unevenness analysis on the transient force distribution data in sequence to extract blade sharpness characteristics and material hard point characteristics.

[0009] Through this series of processing and analysis, this step converts complex transient force data into structured, quantifiable characteristic data. These characteristic data accurately describe the sharpness of the blade and the distribution of material hard points, providing accurate input information for subsequent adaptive adjustment of mold parameters.

[0010] The mold parameter adjustment method, wherein step S21 includes: S211, performing force waveform analysis on the transient force distribution data using fast Fourier transform, extracting the main frequency component and each order harmonic component, and constructing a frequency spectrum; S212, calculating the spectrum energy concentration according to the spectrum graph, and converting the blade sharpness characteristics based on the spectrum energy concentration; S213, using a peak detection algorithm to identify peak points in the transient force distribution data, and recording the force value and position coordinates corresponding to each peak point; S214. Calculate the force distribution uniformity coefficient of the die-cutting area based on the force value and position coordinates of the peak point, and determine the hard point characteristics of the material based on the force distribution uniformity coefficient.

[0011] By decomposing the force signal into frequency components and analyzing the local peak distribution, the above processing method can distinguish and quantify the overall vibration characteristics related to blade sharpness and the local force changes and distribution related to material hard points, thereby solving the problem of difficulty in distinguishing and quantifying the effects of the two and providing more targeted input for subsequent mold parameter adjustments.

[0012] The mold parameter adjustment method, wherein step S3 includes: S31 , performing edge detection, defect recognition, and size measurement on the material surface image data in sequence to obtain edge quality scores and size deviation characteristics of the cut edges.

[0013] The mold parameter adjustment method, wherein step S4 includes: S41. Perform local change rate detection and mutation point detection on the thickness distribution data and the density distribution data in sequence to obtain the local structural inhomogeneity characteristics of the material.

[0014] The mold parameter adjustment method, wherein step S41 includes: S411, performing Gaussian filtering on the thickness distribution data and the density distribution data to obtain smoothed thickness data and density distribution data; S412, calculating the first-order difference of the smoothed thickness data and density distribution data to obtain a thickness change rate and a density change rate; S413, counting the number of the local mutation points within the unit area, where the local mutation points are locations where the thickness change rate is greater than a preset thickness change rate threshold and / or the density change rate is greater than a preset density change rate threshold; S414: Calculate the proportion of the local mutation points, and convert the proportion into a local structural heterogeneity characteristic of the material.

[0015] The mold parameter adjustment method, wherein the local mutation point includes a thickness mutation point and a density mutation point, the thickness mutation point is a position point where the thickness change rate is greater than a preset thickness change rate threshold, and the density mutation point is a position point where the density change rate is greater than a preset density change rate threshold; Step S414 includes: The proportion of thickness mutation points and the proportion of density mutation points are calculated respectively, and the proportion of thickness mutation points and the proportion of density mutation points are weighted based on a preset weight coefficient to obtain the local structural heterogeneity characteristics of the material.

[0016] The mold parameter adjustment method, wherein step S5 includes: S51, obtaining the cumulative die-cutting length, average die-cutting pressure, and overload frequency of the die according to the die usage history statistics; S52 : Calculate the fatigue value of the mold based on the accumulated die-cutting length, average die-cutting pressure, and overload frequency based on a preset wear model or wear mapping table, as a mold wear state feature.

[0017] The mold parameter adjustment method further includes the following steps performed after step S7: S8. According to the visual inspection system or offline quality inspection results, actual product die-cutting quality data is obtained, and the data is input into the adaptive parameter configuration model as a feedback signal, and the adaptive parameter configuration model is iteratively optimized.

[0018] In a second aspect, the present application further provides a mold parameter adjustment system for use in a die-cutting machine, the system comprising: An acquisition module is used to obtain transient force distribution data of the die-cutting area of ​​the workpiece, material surface image data, thickness distribution data, density distribution data, and die usage history; A first analysis module is used to obtain blade sharpness characteristics and material hard point characteristics based on the transient force distribution data; a second analysis module, configured to obtain an edge quality score and a dimensional deviation characteristic of a cut edge based on the material surface image data; The third analysis module is used to obtain the local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; a fourth analysis module, configured to estimate mold wear state characteristics based on the mold usage history; a parameter generation module, configured to input the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structural heterogeneity characteristics, and mold wear state characteristics into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; An actuator control module is used to control the actuator of the die-cutting machine to perform die-cutting based on the mold adjustment parameters.

[0019] The mold parameter adjustment system of the present application comprehensively perceives the various factors affecting the die-cutting quality by collecting transient forces, material images, local physical properties of materials and mold history data during the die-cutting process, and generates mold adjustment parameters based on an adaptive parameter configuration model by integrating multi-source data to achieve adaptive adjustment control of the die-cutting machine, so that the die-cutting parameters are no longer fixed empirical values, but are dynamically adjusted according to the current mold status, material properties and preliminary cutting results.

[0020] From the above, it can be seen that the present application provides a mold parameter adjustment method and system, wherein the mold parameter adjustment method of the present application comprehensively perceives the various factors affecting the die-cutting quality by collecting transient forces, material images, local physical properties of materials and mold history data during the die-cutting process, and generates mold adjustment parameters based on an adaptive parameter configuration model by integrating multi-source data to realize adaptive adjustment control of the die-cutting machine, so that the die-cutting parameters are no longer fixed empirical values, but are dynamically adjusted according to the current mold state, material properties and preliminary cutting results. This adaptive adjustment mechanism can effectively deal with quality fluctuations caused by the superposition of individual differences, wear and tear of molds and local material non-uniformity, and improve the stability of die-cutting processing and the consistency of product quality. The method of the present application realizes closed-loop control and optimization of the die-cutting process through perception, analysis and intelligent decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Flowchart of a mold parameter adjustment method provided in some embodiments of the present application.

[0022] Figure 2 Flowchart of a mold parameter adjustment method provided in some further embodiments of the present application.

[0023] Figure 3 A schematic structural diagram of a mold parameter adjustment system provided in some embodiments of the present application.

[0024] Figure 4 This is a schematic structural diagram of a mold parameter adjustment system provided in some other embodiments of the present application.

[0025] Figure numerals: 201, acquisition module; 202, first analysis module; 203, second analysis module; 204, third analysis module; 205, fourth analysis module; 206, parameter generation module; 207, actuator control module; 208, model optimization module; 209, normalization processing module. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0028] First, please refer to Figure 1 and Figure 2 Some embodiments of the present application provide a mold parameter adjustment method for use in a die-cutting machine, the method comprising the steps of: S1. Obtaining transient force distribution data, material surface image data, thickness distribution data, density distribution data, and die usage history of the die-cutting area of ​​the workpiece; S2. Obtaining blade sharpness characteristics and material hard point characteristics based on transient force distribution data; S3. Obtaining edge quality scores and dimensional deviation characteristics of the cut edges based on the material surface image data; S4. Obtaining local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; S5. Estimating mold wear characteristics based on mold usage history; S6. Inputting blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structural heterogeneity characteristics, and mold wear state characteristics into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; S7. Controlling the actuator of the die-cutting machine to perform die-cutting based on the die adjustment parameters.

[0029] Specifically, step S1 is the data acquisition link. The transient force distribution data is obtained to reflect the real-time mechanical state during the die-cutting process, which is directly related to the sharpness of the blade and the hardness of the material. The material surface image data is obtained to provide intuitive information about the die-cutting results, which is used to evaluate the edge quality and size. The thickness distribution data and density distribution data are obtained to reflect the physical heterogeneity of the material itself. The mold usage history provides clues to the changes in the overall state of the mold over time. These data are the basis for subsequent analysis and parameter adjustment. In this way, the key influencing factors in the die-cutting process can be fully perceived.

[0030] More specifically, step S2 characterizes the cutting performance of the blade and the properties of high-resistance areas in the material by processing the transient force distribution data to obtain blade sharpness characteristics and material hard spot characteristics. This step converts the raw force data into physically meaningful features, helping to quantify the microscopic state of the mold and material.

[0031] More specifically, step S3 characterizes the condition and dimensional accuracy of the cut edge by processing the material surface image data to obtain edge quality scores and dimensional deviation characteristics. This step uses image analysis to quantify quality indicators such as cut edge flatness and burrs, as well as the deviation between the actual and target dimensions. These characteristics directly measure product quality under the current die-cutting parameters and provide direct quality feedback.

[0032] More specifically, step S4 processes the thickness and density distribution data to obtain local structural heterogeneity characteristics of the material, which are used to quantify changes in the material's internal structure. This step quantifies the variability of the material itself, which helps understand the impact of the material on the die-cutting process.

[0033] More specifically, step S5 estimates the mold wear characteristics obtained through mold usage history to quantify the degree of mold aging. This step uses historical data to evaluate the macroscopic state of the mold and provides information on the long-term state of the mold.

[0034] More specifically, step S6 feeds the acquired blade sharpness characteristics, material hard spot characteristics, edge quality score, dimensional deviation characteristics, local material structural heterogeneity characteristics, and die wear characteristics into a pre-trained adaptive parameter configuration model. The adaptive parameter configuration model then outputs specific die adjustment parameters based on the relationship between the learned characteristics and the required die adjustment parameters. The adaptive parameter configuration model learns the relationship between different feature combinations and optimal die-cutting parameters, comprehensively considering the die state, material properties, and current cutting results to output die adjustment parameters tailored to the current working conditions.

[0035] More specifically, step S7 controls the die-cutting machine's actuators to perform die-cutting according to these die adjustment parameters. The process may be to drive the die-cutting machine's actuators such as servo motors and hydraulic cylinders to adjust the die-cutting pressure, speed or die gap to optimize the die-cutting process.

[0036] More specifically, the mold parameter adjustment method of the embodiment of the present application aims to solve the problem of unstable die-cutting quality caused by changes in molds and materials by collecting multi-source data and using models to adjust parameters.

[0037] The mold parameter adjustment method of the embodiment of the present application comprehensively perceives the various factors affecting the die-cutting quality by collecting transient forces, material images, local physical properties of the material, and mold history data during the die-cutting process, and generates mold adjustment parameters based on an adaptive parameter configuration model by integrating multi-source data to achieve adaptive adjustment control of the die-cutting machine, so that the die-cutting parameters are no longer fixed empirical values, but are dynamically adjusted according to the current mold state, material properties, and preliminary cutting results. This adaptive adjustment mechanism can effectively cope with quality fluctuations caused by individual differences in molds, wear, and local material heterogeneity, and improve the stability of the die-cutting process and the consistency of product quality. The method of the present application realizes closed-loop control and optimization of the die-cutting process through perception, analysis, and intelligent decision-making.

[0038] In some preferred embodiments, step S2 includes: S21. Perform force waveform analysis, peak value analysis, and distribution unevenness analysis on the transient force distribution data in sequence to extract blade sharpness characteristics and material hard point characteristics.

[0039] Specifically, in some embodiments, the transient force distribution data may be filtered and denoised before subsequent force waveform analysis, peak analysis, and distribution unevenness analysis are performed, thereby removing interference components in the data and improving data quality.

[0040] More specifically, this step performs force waveform analysis on the transient force distribution data, and can extract a pattern reflecting the change of force with time or position, which is associated with the sharpness state of the blade.

[0041] More specifically, this step performs a distribution inhomogeneity analysis to quantify the force distribution within the die-cutting area, which is associated with material hard spots or localized blunting of the blade. Through these analysis steps, characteristic data reflecting blade sharpness and material hard spot conditions are extracted from the transient force data.

[0042] More specifically, step S21 solves the problem that it is difficult to accurately extract information reflecting the sharpness of the blade and the hard points of the material by directly analyzing the raw data through multi-stage processing and analysis of the transient force distribution data collected during the die-cutting process. First, the force waveform analysis is performed on the force data, such as analyzing the rising edge, falling edge, plateau characteristics or frequency components of the force curve. These waveform characteristics are related to the resistance characteristics of the blade when cutting the material, thereby reflecting the sharpness of the blade. Subsequently, a peak detection algorithm is used to identify the local maximum points in the force data, and the force values ​​and spatial positions corresponding to these peak points are recorded. These peak points indicate the high resistance areas encountered during the die-cutting process, which may correspond to material hard points. Finally, the unevenness of the force distribution is calculated based on the identified peak points and their force values, so as to reflect the concentration of material hard points or the influence of local blunting of the blade through the degree of unevenness of the force distribution. Through this series of processing and analysis, this step converts complex transient force data into structured, quantifiable characteristic data. These characteristic data accurately describe the sharpness of the blade and the distribution of material hard points, providing accurate input information for subsequent adaptive adjustment of mold parameters.

[0043] In some preferred embodiments, step S21 includes: S211. Perform force waveform analysis on transient force distribution data using fast Fourier transform, extract main frequency components and harmonic components of each order, and construct a frequency spectrum. S212, calculating the spectrum energy concentration according to the spectrum graph, and converting the blade sharpness characteristics based on the spectrum energy concentration; S213, using a peak detection algorithm to identify peak points in the transient force distribution data, and recording the force value and position coordinates corresponding to each peak point; S214. Calculate the force distribution uniformity coefficient of the die-cutting area based on the force value and position coordinates of the peak point, and determine the material hard point characteristics based on the force distribution uniformity coefficient.

[0044] Specifically, step S211 uses fast Fourier transform to perform force waveform analysis on the transient force distribution data, extracts the main frequency component and each order harmonic component, and constructs a spectrum diagram, so that the time domain information of the transient force distribution data is converted into frequency domain information to reveal the distribution characteristics of force with frequency.

[0045] More specifically, step S212 calculates the spectrum energy concentration by analyzing the energy distribution of the spectrum graph. The concentration of spectrum energy in a specific frequency range is related to the sharpness of the blade. The calculated concentration of spectrum energy in a specific frequency range can be used to convert the blade sharpness characteristics.

[0046] More specifically, step S213 uses a peak detection algorithm to identify peak points in the transient force distribution data and records the force values ​​and locations of these peak points. Step S214 calculates the force distribution uniformity coefficient for the die-cutting area based on the force values ​​and location coordinates of the peak points. The material hard point characteristics are then determined based on the force distribution uniformity coefficient. By analyzing the peak force distribution and calculating the force distribution uniformity coefficient, the impact and distribution of material hard points can be quantified.

[0047] More specifically, the above processing method can distinguish and quantify the overall vibration characteristics related to blade sharpness and the local force changes and distribution related to material hard points by decomposing the force signal into frequency components and analyzing the local peak distribution, thereby solving the problem of difficulty in distinguishing and quantifying the effects of the two and providing more targeted input for subsequent mold parameter adjustments.

[0048] In some preferred embodiments, step S214 includes: S2141. Calculate the deviation between the force value at each peak point and the average force value in the die-cutting area; S2142. Calculate the square sum of the deviation values ​​according to the deviation values, and divide the square sum of the deviation values ​​by the number of peak points to obtain a force variance value; S2143. Divide the force average value by the force variance value to obtain a force distribution uniformity coefficient, and determine the material hard point distribution uniformity based on the force distribution uniformity coefficient and a preset mapping table.

[0049] Specifically, step S2141 quantifies the degree to which each local force point deviates from the overall average level by calculating the deviation between the force value of each peak point and the average force value of the die-cutting area.

[0050] More specifically, the variance value calculated in step S2141 provides a statistical measure of the force fluctuation, reflecting the magnitude of the force fluctuation around the average value. Squaring the deviation can amplify the impact of larger deviations.

[0051] More specifically, the force distribution uniformity coefficient calculated in step S2143 combines the average force level with the degree of force fluctuation to provide a quantitative uniformity indicator. Based on this quantitative uniformity coefficient, combined with a preset mapping table, the distribution uniformity of the material's hard points can be objectively determined, providing a basis for subsequent mold parameter adjustments and improving their accuracy.

[0052] In some preferred embodiments, step S3 includes: S31. Perform edge detection, defect recognition, and size measurement on the material surface image data in sequence to obtain edge quality scores and size deviation characteristics of the cut edges.

[0053] Specifically, edge detection is used to determine the actual cutting boundary of the material. Defect recognition searches for and marks existing defects on the detected edges. Dimension measurement calculates the actual size of the workpiece based on the detected edges. Through these steps, the method of the present application can extract quantitative edge quality information and dimension information from the original image data for calculating edge quality scores and dimension deviation features. This processing flow provides a specific path from the original image data to the desired features, making the feature extraction process more clear and controllable, thereby improving the accuracy and reliability of the obtained edge quality scores and dimension deviation features, and providing more effective data input for the subsequent adaptive parameter configuration model.

[0054] In some preferred embodiments, step S31 includes: S311, using the Canny operator to perform edge detection on the material surface image data to obtain an initial edge image; S312, smoothing the initial edge image using Gaussian filtering to obtain a smoothed edge image; S313, fitting the cutting edge to obtain a cutting edge curve for the smooth edge image; S314, calculating the curvature of the cutting edge curve, and determining the edge whose curvature exceeds a threshold as a defective edge; S315. Count the length and number of defect edges to calculate the defect density, and calculate the edge quality score based on the defect density; S316. Obtaining a size deviation feature based on the position and size of the cutting edge.

[0055] Specifically, step S311 uses the Canny operator to perform edge detection on the material surface image data, aiming to identify areas in the image where pixel grayscale changes significantly, and generate an initial edge image containing potential edge information.

[0056] More specifically, step S312 uses Gaussian filtering to smooth the initial edge image, with the goal of suppressing noise, reducing false edges, and making subsequent processing more stable.

[0057] More specifically, step S313 performs edge fitting on the smooth edge image to obtain a cutting edge curve representing the cutting edge, and determines the main shape and position of the cutting edge. More specifically, More specifically, step S314 calculates the curvature of the cutting edge curve and quantitatively identifies defective edges that deviate from the ideal shape by comparing it with a preset threshold.

[0058] More specifically, step S315 counts the length and number of defective edges, calculates the defect density according to a preset mapping relationship or formula, and then converts the severity and distribution of edge defects into a numerical indicator, namely, an edge quality score, according to the preset mapping relationship or formula. The score reflects the overall smoothness and integrity of the edge.

[0059] More specifically, step S316 obtains dimensional deviation characteristics based on the analysis of the cutting edge relative to the designed position and size, reflecting the processing accuracy.

[0060] More specifically, these edge quality scores and dimensional deviation characteristics, as quantitative indicators, can accurately and stably reflect the status and precision of the cut edges, providing reliable input data for subsequent adaptive adjustment of mold parameters, thereby solving the problem that traditional methods are difficult to accurately evaluate edge quality and dimensional deviation.

[0061] In some preferred embodiments, step S4 includes: S41. Perform local change rate detection and mutation point detection on the thickness distribution data and the density distribution data in sequence to obtain the local structural inhomogeneity characteristics of the material.

[0062] Specifically, local rate of change detection aims to identify the spatial trend and rate of change in material thickness or density. Inhomogeneities in material structure are often manifested by rapid changes in thickness or density. The above steps quantify this inhomogeneity by calculating the rate of change.

[0063] More specifically, mutation point detection further focuses on areas or points where the rate of change exceeds a certain threshold. These mutation points may correspond to hard spots, voids, lamination defects, or other structural anomalies within the material. These anomalies are key factors that lead to uneven force and reduced cutting quality during the die-cutting process.

[0064] More specifically, step S41 extracts key information reflecting material structural heterogeneity from the raw data by performing local rate of change detection and mutation point detection on the thickness and density distribution data. This information is integrated into a local structural heterogeneity feature, which more accurately describes the material's actual structural state in the die-cutting area. This feature is then fed into the adaptive parameter configuration model, which adjusts die parameters based on the actual degree of material heterogeneity, thereby improving die-cutting stability and product quality and resolving die-cutting issues caused by local structural heterogeneity.

[0065] In some preferred embodiments, step S41 includes: S411, performing Gaussian filtering on the thickness distribution data and the density distribution data to obtain smoothed thickness data and density distribution data; S412, calculating the first-order difference of the smoothed thickness data and density distribution data to obtain the thickness change rate and density change rate; S413. Count the number of local mutation points within a unit area, where a local mutation point is a location point where the thickness change rate is greater than a preset thickness change rate threshold and / or the density change rate is greater than a preset density change rate threshold; S414. Calculate the proportion of local mutation points and convert the proportion into a local structural heterogeneity characteristic of the material.

[0066] Specifically, step S411 performs Gaussian filtering on the thickness distribution data and the density distribution data respectively, with the purpose of smoothing the data, reducing the impact of measurement noise on subsequent analysis, and making the data more reflective of the structural trend of the material itself.

[0067] More specifically, step S412 calculates the first-order difference of the smoothed thickness data and density distribution data to detect the spatial variation rate or gradient of thickness and density, thereby identifying the location where the material structure changes significantly.

[0068] More specifically, local mutation points indicate the presence of local structural anomalies or uneven areas within the material; step S413, combined with step S414, counts the number of these local mutation points in the die-cutting area and calculates their proportion of the number of all position points in the die-cutting area, providing an objective and quantitative indicator to describe the degree of unevenness of the local structure of the material. This quantitative feature can more fully reflect the actual structural characteristics of the material, so that the subsequent mold parameter configuration can more accurately consider the microstructural differences of the material itself, thereby optimizing the die-cutting process and improving product consistency.

[0069] In some preferred embodiments, the local mutation point includes a thickness mutation point and a density mutation point. The thickness mutation point is a position point where the thickness change rate is greater than a preset thickness change rate threshold, and the density mutation point is a position point where the density change rate is greater than a preset density change rate threshold. Step S414 includes: The proportion of thickness mutation points and the proportion of density mutation points are calculated respectively, and the proportion of thickness mutation points and the proportion of density mutation points are weighted based on the preset weight coefficient to obtain the local structural heterogeneity characteristics of the material.

[0070] Specifically, the above processing method clearly distinguishes local mutation points into thickness mutation points and density mutation points. Thickness mutation points are locations where the rate of change in material thickness exceeds a preset threshold, and density mutation points are locations where the rate of change in material density exceeds a preset threshold. When calculating the local structural heterogeneity characteristics of the material, the total proportion of all mutation points is no longer simply counted. Instead, the proportion of thickness mutation points within the die-cutting area and the proportion of density mutation points within the die-cutting area are calculated separately. These two independent proportions are then weighted and summed using a preset weight coefficient to obtain the final local structural heterogeneity characteristics of the material.

[0071] More specifically, this differentiated and weighted approach more meticulously reflects the heterogeneity of a material's local structure, distinguishing the contributions of thickness and density variations to overall heterogeneity, overcoming the inaccurate assessment associated with simply combining these two factors. By adjusting the weighting coefficients, the material's local structural heterogeneity can be more accurately quantified based on the varying sensitivity of different materials or die-cutting processes to thickness and density heterogeneity, providing more differentiated input for subsequent adaptive mold parameter configuration.

[0072] In some preferred embodiments, step S5 includes: S51. Obtaining the cumulative die-cutting length, average die-cutting pressure, and overload frequency of the mold based on the mold usage history statistics; S52 : Calculate the fatigue value of the mold based on the preset wear model or wear mapping table according to the accumulated die-cutting length, average die-cutting pressure, and overload frequency as a mold wear state feature.

[0073] Specifically, step S51 involves performing statistical analysis based on the die's historical usage data to obtain key indicators reflecting the die's workload. This can be achieved by recording the length of each die-cutting operation, instantaneous pressure data collected by the pressure sensor, setting an overload threshold, and recording the number of times the threshold is exceeded in the die-cutting machine's control system. These statistical data provide a quantitative basis for subsequent assessment of the die's wear status.

[0074] More specifically, step S52 involves calculating the mold fatigue value using statistically derived indicators combined with a pre-established wear model or mapping table. Specifically, a mathematical model based on material fatigue theory can be used. This model takes as input the cumulative die-cutting length, average die-cutting pressure, and overload frequency, and outputs a numerical value representing the degree of fatigue damage. Alternatively, a multidimensional lookup table can be used, which directly maps a fatigue value to different ranges of cumulative die-cutting length, average die-cutting pressure, and overload frequency. The calculated fatigue value is used as a characteristic of the mold's wear state, which can comprehensively reflect the damage accumulation of the mold under complex stress histories.

[0075] More specifically, steps S51 and S52 work together to transform the mold's usage history into a fatigue value signature that better represents its actual wear and fatigue state. This fatigue value signature, along with blade sharpness and material hard point characteristics derived from transient force distribution data, edge quality scores and dimensional deviation characteristics derived from material surface image data, and local structural heterogeneity characteristics derived from thickness and density distribution data, is fed as input into a pre-trained adaptive parameter configuration model. Compared to relying solely on simple usage history estimates, this approach, by introducing the concept of fatigue value, more deeply reflects the mold's actual damage state, improving the accuracy of determining mold wear factors and, consequently, enhancing the effectiveness of adaptive parameter adjustment.

[0076] In some preferred embodiments, the method further comprises the following steps performed after step S7: S8. According to the visual inspection system or offline quality inspection results, actual product die-cutting quality data is obtained and input into the adaptive parameter configuration model as a feedback signal, and the adaptive parameter configuration model is iteratively optimized.

[0077] Specifically, actual product die-cutting quality data can be collected in real time through visual inspection systems. For example, industrial cameras can be used to capture images of die-cut product edges. Image processing algorithms can then analyze edge features such as flatness, burrs, and chipping, quantifying them into quality scores or defect counts. Alternatively, actual product die-cutting quality data can be obtained through offline quality testing. For example, after die-cutting, products can be sent to specialized testing equipment (such as optical microscopes or profilometers) for precision measurement to obtain data such as edge dimensional deviation and breakpoint rate.

[0078] More specifically, in this step, the actual product die-cutting quality data obtained is used as a feedback signal to input into the adaptive parameter configuration model, allowing the adaptive parameter configuration model to use the feedback signal for iterative optimization. The iterative optimization process adjusts the model's internal parameters, such as the weights and biases of the neural network.

[0079] More specifically, through a repetitive process of die-cutting, quality inspection, feedback, and model optimization, the adaptive parameter configuration model learns the complex relationship between input features and actual die-cutting quality, and gradually refines its parameter output strategy. As a result, the die adjustment parameters output by the adaptive parameter configuration model can more accurately adapt to various variations in the actual die-cutting process, such as die wear and material batch differences, thereby improving the stability and consistency of die-cutting quality.

[0080] In some preferred embodiments, the method further comprises the following steps performed between step S5 and step S6: SA, the blade sharpness characteristics, material hard point characteristics, edge quality score, size deviation characteristics, material local structure heterogeneity characteristics, and mold wear state characteristics are normalized to form a feature vector for input into the adaptive parameter model.

[0081] Specifically, normalization is the process of scaling features of different dimensions and numerical ranges to a uniform range. For example, you can use the min-max scaling method to linearly transform feature values ​​to a preset range, such as 0 to 1. Or you can use the Z-score normalization method to transform feature values ​​into a distribution with a mean of 0 and a standard deviation of 1.

[0082] More specifically, step SA normalizes the previously acquired feature data, mapping them to a unified numerical space and eliminating dimensional differences. The adaptive parameter configuration model learns and predicts based on the normalized feature vectors, outputting die adjustment parameters. Normalization allows the model to treat each feature fairly, improving the efficiency and accuracy of model learning. This allows for more precise output of adjustment parameters tailored to the current die and material conditions, enhancing die-cutting quality.

[0083] In some preferred embodiments, the mold adjustment parameters include: die-cutting pressure, die-cutting speed, and die-cutting depth fine-tuning amount.

[0084] Specifically, die-cutting pressure can be achieved by controlling the die-cutting machine's pressure head using a hydraulic system or servo motor, with real-time monitoring and closed-loop control enabled by an array of force sensors installed in the die-cutting area. Die-cutting speed can be controlled by adjusting the speed of the drive motors for the material transport mechanism or the die motion mechanism. Fine-tuning of the die-cutting depth can be achieved using a fine-tuning mechanism driven by a high-precision Z-axis servo motor or stepper motor.

[0085] More specifically, to address quality fluctuations caused by individual die variations, localized material inhomogeneities, and die wear during die-cutting, this solution uses an adaptive parameter configuration model to output specific die-cutting pressure, speed, and die-cutting depth fine-tuning values. Die-cutting pressure directly affects the cutting depth and force distribution of the blade. Adjusting the pressure can compensate for localized blade dullness or material hard spots, ensuring complete cuts. Die-cutting speed affects the material's deformation behavior and the force rate applied to the blade at the moment of cutting. Optimizing speed can reduce burrs and tears. Die-cutting depth fine-tuning provides fine adjustment capabilities to compensate for die wear or minor fluctuations in material thickness, avoiding damage to underlying layers or incomplete cuts. These parameters are dynamically calculated by the adaptive parameter configuration model based on input characteristics such as blade sharpness, material hard spots, edge quality, dimensional deviation, localized material structural inhomogeneities, and die wear. These parameters are then transmitted to the die-cutting machine's actuators, such as the pressure control valve, motor drive, and depth adjustment mechanism, enabling real-time, adaptive control of the die-cutting process and improving product quality consistency.

[0086] In some preferred embodiments, in step S6, the adaptive parameter configuration model is a multi-layer perceptron (MLP) or a convolutional neural network (CNN).

[0087] Specifically, the multilayer perceptron learns the nonlinear mapping relationship between input features and output parameters through multiple neuron layers. The convolutional neural network extracts patterns from the input features through convolution and pooling operations, and then maps the extracted patterns to the output parameters through a fully connected layer. Both models have the ability to learn complex associations from high-dimensional input data, can process feature data of different sources and properties, and predict the required die-cutting pressure, die-cutting speed, and die-cutting depth fine-tuning based on these features. As a result, the adaptive parameter configuration model can dynamically adjust the mold parameters according to actual conditions, overcoming the limitations of traditional fixed parameters or simple models that cannot accurately capture the interactions between complex factors, improving the accuracy and adaptability of parameter adjustment, and thus stabilizing the die-cutting quality.

[0088] In some preferred embodiments, step S1 includes: S11, collecting transient pressure data of the die-cutting area during trial cutting of the edge through a force sensor array; S12, using a visual camera to obtain an image of the surface of the material after die-cutting at the die-cutting area; S13, using an ultrasonic sensor to scan the die-cutting area to obtain ultrasonic reflection signals, and calculating thickness distribution data and density distribution data by analyzing the amplitude and delay of the reflection signals; S14. Retrieve the mold usage history corresponding to the identifier of the currently used mold from the mold management database.

[0089] Specifically, transient pressure data is collected by a force sensor array positioned beneath the die-cutting area. This array, comprised of multiple independent force sensors, captures the time-varying pressure values ​​at different locations within the die-cutting area at the moment the die-cutting blade contacts and cuts the material, thereby providing information on the force distribution during the die-cutting process.

[0090] More specifically, the material surface image data is captured by a visual camera located downstream of the die-cutting station. After the test cut is completed, the camera takes a picture of the die-cut edge area, recording the visual characteristics of the material surface, including the shape of the cut edge and any possible defects.

[0091] More specifically, thickness and density distribution data are obtained by scanning the material surface with an ultrasonic sensor. The sensor transmits an ultrasonic pulse into the material, receives the reflected echo, and measures the echo's intensity and travel time to infer the material's thickness and density at the scan point.

[0092] More specifically, mold usage history data is obtained by querying a pre-established mold management database. The database stores a unique identifier for each mold and its corresponding usage records, such as the cumulative number of die-cutting operations and the type of processed materials.

[0093] More specifically, these multi-source data collection methods work together to comprehensively capture information on key factors affecting die-cutting quality, providing the necessary data input for subsequent adaptive parameter adjustments based on this data, thereby being able to cope with dynamic changes in molds and materials and improve product quality stability.

[0094] Second, please refer to Figure 3 and Figure 4 Some embodiments of the present application further provide a mold parameter adjustment system for use in a die-cutting machine, the system comprising: An acquisition module 201 is used to acquire transient force distribution data, material surface image data, thickness distribution data, density distribution data, and die usage history of a die-cutting area of ​​a workpiece; A first analysis module 202 is used to obtain blade sharpness characteristics and material hard point characteristics based on transient force distribution data; The second analysis module 203 is used to obtain the edge quality score and dimensional deviation characteristics of the cut edge based on the material surface image data; The third analysis module 204 is used to obtain the local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; A fourth analysis module 205 is configured to estimate mold wear characteristics based on the mold usage history; The parameter generation module 206 is used to input the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structure heterogeneity characteristics, and mold wear state characteristics into the pre-trained adaptive parameter configuration model to output mold adjustment parameters; The actuator control module 207 is used to control the actuator of the die-cutting machine to perform die-cutting based on the mold adjustment parameters.

[0095] The mold parameter adjustment system of the embodiment of the present application comprehensively perceives the various factors affecting the die-cutting quality by collecting transient forces, material images, local physical properties of the material, and mold history data during the die-cutting process, and generates mold adjustment parameters based on an adaptive parameter configuration model by integrating multi-source data to achieve adaptive adjustment control of the die-cutting machine, so that the die-cutting parameters are no longer fixed empirical values, but are dynamically adjusted according to the current mold state, material properties, and preliminary cutting results. This adaptive adjustment mechanism can effectively cope with quality fluctuations caused by individual differences in molds, wear, and local material inhomogeneities, and improve the stability of the die-cutting process and the consistency of product quality. The system of the present application realizes closed-loop control and optimization of the die-cutting process through perception, analysis, and intelligent decision-making.

[0096] In some preferred embodiments, the system further comprises: The model optimization module 208 is used to obtain actual product die-cutting quality data based on the visual inspection system or offline quality inspection results, input it into the adaptive parameter configuration model as a feedback signal, and iteratively optimize the adaptive parameter configuration model.

[0097] In some preferred embodiments, the system further comprises: The normalization processing module 209 is used to normalize the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structure heterogeneity characteristics, and mold wear state characteristics to form a feature vector for input into the adaptive parameter model.

[0098] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0100] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0101] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A mold parameter adjustment method, used in a die-cutting machine, characterized in that: The method comprises the steps of: S1. Obtaining transient force distribution data, material surface image data, thickness distribution data, density distribution data, and die usage history of the die-cutting area of ​​the workpiece; S2. Obtaining blade sharpness characteristics and material hard point characteristics based on the transient force distribution data; S3. Obtaining edge quality scores and dimensional deviation characteristics of the cut edges based on the material surface image data; S4. Obtaining local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; S5. estimating mold wear characteristics based on the mold usage history; S6. Inputting the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structure heterogeneity characteristics, and mold wear state characteristics into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; S7. Controlling the actuator of the die-cutting machine to perform die-cutting based on the die adjustment parameters.

2. The mold parameter adjustment method according to claim 1, characterized in that: Step S2 includes: S21. Perform force waveform analysis, peak value analysis, and distribution unevenness analysis on the transient force distribution data in sequence to extract blade sharpness characteristics and material hard point characteristics.

3. The mold parameter adjustment method according to claim 2, characterized in that: Step S21 includes: S211, performing force waveform analysis on the transient force distribution data using fast Fourier transform, extracting the main frequency component and each order harmonic component, and constructing a frequency spectrum; S212, calculating the spectrum energy concentration according to the spectrum graph, and converting the blade sharpness characteristics based on the spectrum energy concentration; S213, using a peak detection algorithm to identify peak points in the transient force distribution data, and recording the force value and position coordinates corresponding to each peak point; S214. Calculate the force distribution uniformity coefficient of the die-cutting area based on the force value and position coordinates of the peak point, and determine the hard point characteristics of the material based on the force distribution uniformity coefficient.

4. The mold parameter adjustment method according to claim 1, characterized in that: Step S3 includes: S31 , performing edge detection, defect recognition, and size measurement on the material surface image data in sequence to obtain edge quality scores and size deviation characteristics of the cut edges.

5. The mold parameter adjustment method according to claim 1, characterized in that: Step S4 includes: S41. Perform local change rate detection and mutation point detection on the thickness distribution data and the density distribution data in sequence to obtain the local structural inhomogeneity characteristics of the material.

6. The mold parameter adjustment method according to claim 5, characterized in that: Step S41 includes: S411, performing Gaussian filtering on the thickness distribution data and the density distribution data to obtain smoothed thickness data and density distribution data; S412, calculating the first-order difference of the smoothed thickness data and density distribution data to obtain a thickness change rate and a density change rate; S413, counting the number of the local mutation points within the unit area, where the local mutation points are locations where the thickness change rate is greater than a preset thickness change rate threshold and / or the density change rate is greater than a preset density change rate threshold; S414: Calculate the proportion of the local mutation points, and convert the proportion into a local structural heterogeneity characteristic of the material.

7. The mold parameter adjustment method according to claim 6, characterized in that: The local mutation points include thickness mutation points and density mutation points. The thickness mutation point is a position point where the thickness change rate is greater than a preset thickness change rate threshold, and the density mutation point is a position point where the density change rate is greater than a preset density change rate threshold. Step S414 includes: The proportion of thickness mutation points and the proportion of density mutation points are calculated respectively, and the proportion of thickness mutation points and the proportion of density mutation points are weighted based on a preset weight coefficient to obtain the local structural heterogeneity characteristics of the material.

8. The mold parameter adjustment method according to claim 1, characterized in that: Step S5 includes: S51, obtaining the cumulative die-cutting length, average die-cutting pressure, and overload frequency of the die according to the die usage history statistics; S52 : Calculate the fatigue value of the mold based on the accumulated die-cutting length, average die-cutting pressure, and overload frequency based on a preset wear model or wear mapping table, as a mold wear state feature.

9. The mold parameter adjustment method according to claim 1, characterized in that: The method further comprises the following steps performed after step S7: S8. According to the visual inspection system or offline quality inspection results, actual product die-cutting quality data is obtained, and the data is input into the adaptive parameter configuration model as a feedback signal, and the adaptive parameter configuration model is iteratively optimized.

10. A mold parameter adjustment system, used in a die-cutting machine, characterized in that: The system comprises: An acquisition module is used to obtain transient force distribution data of the die-cutting area of ​​the workpiece, material surface image data, thickness distribution data, density distribution data, and die usage history; A first analysis module is used to obtain blade sharpness characteristics and material hard point characteristics based on the transient force distribution data; a second analysis module, configured to obtain an edge quality score and a dimensional deviation characteristic of a cut edge based on the material surface image data; The third analysis module is used to obtain the local structural heterogeneity characteristics of the material based on the thickness distribution data and the density distribution data; a fourth analysis module, configured to estimate mold wear state characteristics based on the mold usage history; a parameter generation module for inputting the blade sharpness characteristics, material hard point characteristics, edge quality score, dimensional deviation characteristics, material local structural heterogeneity characteristics, and mold wear state characteristics into a pre-trained adaptive parameter configuration model to output mold adjustment parameters; An actuator control module is used to control the actuator of the die-cutting machine to perform die-cutting based on the mold adjustment parameters.

Images