Method for eliminating finishing twill defect of galvanized strip steel

Abstract

The invention provides a method for eliminating a galvanized strip steel finishing twill defect, and belongs to the technical field of metal processing, and the method comprises the following steps: inputting fusion data into a twill defect analysis model to obtain a twill defect probability value of each area of the strip steel surface, the fusion data being strip steel thickness information and width information; determining a first adjustment strategy of the finishing equipment according to the twill defect probability value, and controlling the finishing equipment to perform primary finishing on the strip steel based on the first adjustment strategy to obtain first strip steel; and determining a target adjustment strategy of the finishing equipment according to the finishing result of the first strip steel, and controlling the finishing equipment to perform second finishing on the first strip steel based on the target adjustment strategy to obtain target strip steel. According to the method for eliminating the galvanized strip steel finishing twill defect, the twill defect risk of the strip steel is reduced through precise regulation and control over finishing equipment.

Description

Technical Field

[0001] The present disclosure belongs to the field of metal processing technology, and more specifically, relates to a method for eliminating skin-polished twill defects in galvanized steel strips. Background Art

[0002] After cold rolling, galvanized strip will have a certain degree of plate defects, such as single-edge waves or middle waves, which have a significant impact on the formation of skin-polishing twill in galvanized strip. The strip needs to be rolled in a skin-polishing mill to improve surface flatness, but if edge waves or middle waves are present, the roller gap pressure will fluctuate periodically in the waved area. Edge waves cause a sudden increase in the contact pressure between the strip edge and the roller, while middle waves cause an imbalance in the pressure distribution in the central area, resulting in directional twill defects in the zinc layer during the cooling and crystallization process. In addition, the wavy area is prone to local plastic deformation differences during the skin-polishing process, causing the thickness of the galvanized layer to be unevenly distributed along the diagonal direction, further exacerbating the visibility of the twill. The traditional solution is to solve the skin-polishing twill defect by adjusting the skin-polishing mill roller profile during the skin-polishing process, but this method cannot completely improve the skin-polishing twill caused by plate defects. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a method for eliminating the diagonal defects of galvanized steel strip during skin-finishing, thereby reducing the risk of diagonal defects in the steel strip through precise control of the skin-finishing equipment.

[0004] A first aspect of the embodiments of the present disclosure provides a method for eliminating skin-pass twill defects in galvanized steel strip, comprising: Inputting the fused data into a diagonal defect analysis model to obtain a diagonal defect probability value for each area on the strip surface, wherein the fused data is the thickness and width information of the strip; determining a first adjustment strategy for a finishing device according to the diagonal defect probability value; Based on the first adjustment strategy, control the skin-passing equipment to perform a first skin-pass on the steel strip to obtain a first steel strip; determining a target adjustment strategy for skin-passing equipment according to the skin-passing result of the first steel strip; Based on the target adjustment strategy, the skin-finishing equipment is controlled to perform second skin-finishing on the first steel strip to obtain a target steel strip.

[0005] A second aspect of the embodiments of the present disclosure provides a device for eliminating skin-pass twill defects in galvanized steel strips, comprising: a data processing module, configured to input the fused data into a diagonal grain defect analysis model to obtain a diagonal grain defect probability value for each area on the surface of the steel strip, wherein the fused data includes thickness and width information of the steel strip; A first strategy module, configured to determine a first adjustment strategy for a finishing device according to the diagonal defect probability value; a first execution module, configured to control the skin-passing equipment to perform a first skin-pass on the steel strip according to the first adjustment strategy, the first steel strip; a target strategy module, configured to determine a target adjustment strategy for a skin-passing device according to a skin-passing result of the first steel strip; The second execution module is used to control the skin-finishing equipment to perform second skin-finishing on the first steel strip according to the target adjustment strategy to obtain a target steel strip.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of the above-mentioned method for eliminating the smooth twill defects of galvanized strip steel are implemented.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for eliminating the skin-polished twill defects of galvanized strip are implemented.

[0008] The beneficial effect of the method for eliminating the twill defects in the skin-finishing of galvanized strip provided by the embodiment of the present disclosure is that: by inputting the fusion data into the twill defect analysis model, the twill defect probability value of each area on the surface of the strip can be accurately calculated, and the first adjustment strategy is determined based on the twill defect probability value, so that the skin-finishing equipment can perform differentiated operations for the potential twill risks in different areas when it is first working, thereby improving the inhibitory effect of the first skin-finishing on the twill defects; the present disclosure can also dynamically optimize the process according to the actual situation after the first skin-finishing, and accurately adjust the skin-finishing equipment to eliminate the twill defects in the strip for the twill defects that were not eliminated by the first skin-finishing. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 A schematic flow chart of a method for eliminating skin-pass twill defects in galvanized steel strip provided in one embodiment of the present disclosure; Figure 2 This is a structural block diagram of a device for eliminating skin-pass twill defects in galvanized steel strips provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided in one embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present disclosure with unnecessary detail.

[0012] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for eliminating skin-pass twill defects in galvanized steel strip provided in one embodiment of the present disclosure, the method comprising: S101: Input the fused data into the diagonal defect analysis model to obtain the diagonal defect probability value of each area on the strip surface. The fused data is the thickness information and width information of the strip.

[0014] In this example, high-precision measuring instruments are used to obtain precise strip thickness information at different locations, and laser scanning technology is used to obtain strip width information. The acquired strip thickness and width information are fused to form fused data, providing basic data support for subsequent analysis.

[0015] In this embodiment, the fusion method includes feature-level fusion and data fusion; Among them, the feature-level fusion method is to perform principal component analysis or independent component analysis on the strip thickness information and width information.

[0016] Data fusion methods include direct concatenation and weighted fusion. The direct concatenation method directly concatenates the strip thickness and width information into a new feature vector according to a specific sequence. For example, the values ​​of each measurement point in the thickness and width data are arranged sequentially to form a long vector containing both thickness and width information. This method is simple and direct, preserving all the information in the original data.

[0017] The weighted fusion method assigns different weights to thickness and width information based on their importance to twill defect analysis, then performs a weighted sum to generate fused data. For example, if experiments or empirical analysis show that thickness information has a greater impact on twill defects, a higher weight can be assigned to thickness information. The corresponding data points are then weighted and added together to generate the fused feature data.

[0018] In this embodiment, the diagonal defect analysis model selects appropriate algorithm models based on different fusion methods. For example, for feature-level fusion, a machine learning algorithm such as a support vector machine or random forest is selected. For data-level fusion, a deep learning algorithm such as a multi-layer perceptron or convolutional neural network is selected. The diagonal defect analysis model is trained using a deep learning algorithm using a large amount of strip sample data labeled with diagonal defects. The fused data is input into the diagonal defect analysis model, which then extracts and analyzes features using a complex neural network structure, ultimately outputting diagonal defect probability values ​​for each area on the strip surface.

[0019] For example, assume a galvanized strip production line is equipped with a high-precision thickness gauge and a laser width detector. At a specific moment, data is collected from a section of the strip. The thickness gauge records the strip thickness at preset intervals, generating thickness data. The laser width detector operates synchronously, acquiring strip width data at the same preset intervals. These thickness and width data are then sequentially organized into a fused data format, for example, a two-dimensional array with thickness data stored in the first column and width data stored in the second column. This fused data array is then input into a pre-trained convolutional neural network-based twill defect analysis model. The twill defect analysis model extracts features from the fused data, simulating the correlation between strip thickness and width information at various scales, from microscopic to macroscopic. The pooling layer further filters and reduces the dimensionality of the extracted features, reducing the data volume while retaining key features. After multiple layers of convolution and pooling operations, the data enters a fully connected layer, where all features are integrated and calculated. The final output is a one-dimensional array containing multiple elements, each corresponding to the probability of a twill defect at the corresponding measurement point on the strip. For example, the probability value of the diagonal defect in the area corresponding to the starting position is 0.05 (indicating a 5% probability of a diagonal defect), and the probability value of the area corresponding to the middle position is 0.12, which intuitively shows the distribution of diagonal defects in various areas of the strip surface.

[0020] S102: Determine a first adjustment strategy for the skin-finishing equipment according to the probability value of the diagonal defect, and control the skin-finishing equipment to perform a first skin-finish on the steel strip based on the first adjustment strategy to obtain a first steel strip.

[0021] In this embodiment, the first adjustment strategy for the skin-pass equipment is determined based on the diagonal defect probability value and a pre-defined mapping table of defect probabilities and skin-pass equipment adjustment parameters. This mapping table, optimized through multiple experiments and actual production experience, covers parameters such as the skin-pass equipment's rolling force and tension, the work roll speed adjustment range, and the roll gap adjustment corresponding to different defect probability intervals.

[0022] Or the first adjustment strategy is: Calculating a compensation value for a base rolling pressure of the skin-pass equipment based on the distribution density and average probability value of the defect risk area, and calculating a first rolling pressure based on the compensation value and the base rolling pressure of the skin-pass equipment; Determine the roll gap inclination angle in the skin-pass equipment based on the lateral distribution offset of the defect risk area and the ratio of the strip width; The tension gradient value is determined based on the real-time collected strip running speed and rolling tension fluctuation standard deviation.

[0023] In this embodiment, the calculation formula of the rolling pressure compensation value ΔP is:

[0024] in, is the base rolling pressure of skin-pass equipment (typical value 800~1500kN), 5 / m² triggers compensation, is the average probability value; is the first probability threshold.

[0025] The calculation formula for the tilt angle is:

[0026] Where k is the correction coefficient, θ is the tilt angle, ΔW is the lateral distribution offset of the risk area (unit: mm), and the tilt adjustment is activated when ΔW ≥ 10 mm, and W0 is the strip width.

[0027] The calculation formula of tension gradient value is:

[0028] in, is the initial tension gradient setting value (N / mm²), V_max is the maximum allowable speed of the skin-pass machine (typical value m / min); is the strip running speed (unit: m / min), is the standard deviation of rolling tension fluctuation, is the first standard deviation threshold.

[0029] S103: Determine a target adjustment strategy for the skin-polishing equipment according to the skin-polishing result of the first steel strip, and control the skin-polishing equipment to perform a second skin-polishing on the first steel strip based on the target adjustment strategy to obtain a target steel strip.

[0030] In this embodiment, image data of the first steel strip is collected using an image acquisition device. An image recognition algorithm analyzes the presence of diagonal grain defects on the surface of the first steel strip. Based on production process requirements and quality standards, a target adjustment strategy for the skin-passing equipment is determined. This target adjustment strategy provides targeted optimization for diagonal grain defects present after the first skin-pass.

[0031] For example, the surface morphology data of the first strip is collected by a laser profiler, and the morphology characteristic value is calculated based on the morphology data; if the morphology characteristic value is less than the quality standard, the wavelength and amplitude characteristics of the residual twill defect in the morphology data are extracted; the residual twill defect characteristics are matched with the fusion data in time and space, where the time and space matching is time and space matching; the initial rolling pressure compensation value and the roll gap inclination value are dynamically corrected by the particle swarm optimization algorithm to generate a target adjustment strategy.

[0032] From the above, it can be concluded that by inputting fused data consisting of strip thickness and width information into the twill defect analysis model, the present disclosure can accurately calculate the twill defect probability value for each area on the strip surface, providing a precise data basis for the formulation of subsequent adjustment strategies, and changing the ambiguity of previous reliance on empirical judgment. The first adjustment strategy is determined based on the twill defect probability value, so that the finishing equipment can perform differentiated operations for the potential twill risks in different areas during initial operation, thereby improving the first twill defect suppression effect of the first twill finishing. The present disclosure can also dynamically optimize the process in real time based on the actual situation after the first twill finishing. In the actual production process, there are uncertainties in strip characteristics, equipment status, etc. The present disclosure accurately adjusts the finishing equipment to eliminate twill defects in the strip if the first twill finishing did not eliminate them.

[0033] In one embodiment of the present disclosure, determining a first adjustment strategy for a finishing device according to a diagonal defect probability value includes: When the probability value of the twill defect is greater than or equal to a first threshold, determining a defect level based on the fusion data and the rolling tension data of the skin-pass equipment; A first adjustment strategy for the finishing equipment is determined according to the defect data corresponding to the defect level.

[0034] In this embodiment, the defect level includes a first defect level, a second defect level, and a third defect level, the third defect level is higher than the second defect level, and the second defect level is higher than the first defect level; Determine defect levels based on fusion data and rolling tension data, including: Calculate defect assessment index based on fusion data and rolling tension data of skin-pass equipment; If the defect assessment index is less than the first defect threshold, determining the defect level to be the first defect level; If the defect assessment index is greater than or equal to the first defect threshold and less than the second defect threshold, the defect level is determined to be the second defect level; If the defect assessment index is greater than or equal to the second defect threshold, the defect level is determined to be a third defect level.

[0035] In this embodiment, the second defect threshold is greater than the first defect threshold, and the first defect threshold and the second defect threshold can be set based on historical data statistics.

[0036] The formula for calculating the defect assessment index is:

[0037] in, is the defect assessment index, ΔT is the standard deviation of thickness deviation (mm), σW is the width fluctuation variance (mm²), ΔS is the rolling tension fluctuation amplitude of the skin-passing equipment (N / mm²), α, β, and γ are the first weight coefficient, the second weight coefficient, and the third weight coefficient, respectively.

[0038] The present disclosure determines a first adjustment strategy based on the probability value of twill defects and different defect levels, and adopts different refined adjustment methods for different degrees of twill defects, which greatly improves the pertinence and effectiveness of eliminating twill defects. Compared with the traditional single adjustment method, it can more comprehensively deal with various complex defect situations.

[0039] In one embodiment of the present disclosure, determining a first adjustment strategy for a finishing device based on defect data corresponding to a defect level includes: Input defect data, fusion data and rolling tension data into the random forest model to obtain the defect type; A first adjustment strategy for the finishing equipment is determined according to the defect type and a first mapping table; the first mapping table is a mapping table between preset defect types and strategies.

[0040] In this example, a random forest model is derived from historical defect grade information, fused strip data (including detailed and accurate strip thickness and width information), and rolling tension data. During training, the random forest model constructs multiple decision trees for classification and prediction, demonstrating powerful data analysis and pattern recognition capabilities. Defect types include: Type A: periodic streak defects (wavelength λ = 10-50 mm); Type B: random network defects (no fixed wavelength); Type C: localized point defects (diameter d ≤ 5 mm); and Type D: composite defects (a combination of A+B or B+C).

[0041] In this embodiment, the mapping table between defect types and policies is shown in Table 1.

[0042] Table 1 Mapping table between defect types and strategies

[0043] Among them, V0 is the initial speed of the finishing equipment transmission.

[0044] In one embodiment of the present disclosure, the method for eliminating skin-pass twill defects of galvanized steel strip further includes: The fused data is input into a diagonal defect analysis model to obtain diagonal defect probabilities for various regions on the strip surface. The fused data includes strip thickness and width information. A first adjustment strategy for the skin-pass mill is determined based on the diagonal defect probability. When the diagonal defect probability is greater than or equal to a first threshold, the defect level is determined based on the fused data and the rolling tension data of the skin-pass mill. The parameters in the first adjustment strategy are adjusted based on the defect level to obtain a second adjustment strategy. The skin-pass mill is controlled based on the first adjustment strategy to perform a first skin-pass on the strip, obtaining a first strip. Specifically, for the first defect level, the first adjustment strategy increases the tension gradient compensation based on the first step length. For the second defect level, the second adjustment strategy increases the rolling pressure compensation based on the tension gradient compensation based on the second step length. For the third defect level, the first adjustment strategy increases the tension gradient compensation based on the third step length, with the third step length being greater than the first step length. The rolling pressure compensation is increased based on the fourth step length, with the fourth step length being greater than the second step length. The seam inclination angle is increased based on the fifth step length. The skin-pass mill speed is reduced based on the sixth step length.

[0045] In one embodiment of the present disclosure, the skin-passing result of the first steel strip includes image data of the first steel strip; Determine the target adjustment strategy for the skin-pass equipment based on the skin-pass results of the first strip, including: Processing the image data of the first steel strip to obtain image features; Based on the image features and the defect value calculation formula, the defect value of the first strip is obtained; If the defect value of the first steel strip is greater than a first preset value, selecting an adjustment strategy template corresponding to the image feature in the strategy rule library according to the image feature; The parameters in the adjustment strategy template are adjusted based on the first amplitude value to obtain a corresponding target adjustment strategy; a plurality of adjustment strategy templates are stored in the strategy rule library.

[0046] In this embodiment, the image data of the first steel strip is processed to obtain image features, including: The surface image of the first strip is collected by a linear array CCD camera, covering the entire width direction; The image is subjected to Gaussian filtering to remove noise and histogram equalization to enhance contrast, thus obtaining the second strip surface image. Calculate the contrast, energy, and correlation of the gray-level co-occurrence matrix of the second strip surface image, and obtain the texture complexity according to the texture complexity calculation formula; The Canny operator is used to detect the defect edge of the second strip surface image, and the edge length L (mm) and average curvature R (1 / mm) are extracted.

[0047] The defect value of the first strip is calculated based on texture complexity, edge length, average curvature and defect value calculation formula.

[0048] In this embodiment, the texture complexity calculation formula is: Ct=W d ×Contrast+W n ×Energy+W x ×Correlation; Among them, Ct is the texture complexity, W d is the contrast weight, W n is the energy weight, W x is the weight of the correlation.

[0049] In this embodiment, the defect value calculation formula is: D=W L ×L / L max +W Ct ×(1−Ct / Ct max )+W R ×R Where D is the defect value, W L is the first weight, W Ct is the second weight, W R is the third weight, L max is the maximum value of edge length, Ct max is the benchmark value of texture complexity normalization, D∈[0,1].

[0050] In this embodiment, the present disclosure determines whether to perform a second polishing based on the comparison result of the defect value of the first steel strip with the first preset value; if the defect value of the first steel strip is greater than the first preset value, it means that the polishing twill defect of the strip after the first polishing is more serious, and it is necessary to adjust the polishing equipment to perform a second polishing on the first steel strip after the first polishing. At this time, according to the image features, feature matching is performed in the strategy rule library to select the adjustment strategy template. The strategy rule library is constructed by the long-term accumulated polishing process data and the correlation between the equipment operating parameters and the strip defects, which stores a variety of adjustment strategy templates. In the matching process, a matching algorithm based on feature similarity is used, such as the cosine similarity algorithm, to calculate the similarity between the image features and the feature vectors corresponding to each adjustment strategy template, and select the adjustment strategy template with the highest similarity.

[0051] In this embodiment, the strategy rule base is shown in Table 2. The strategy rule base includes but is not limited to a pressure increment template, a tilt compensation template, and a speed-tension coupling template.

[0052] Table 2 Policy rule base

[0053] In one embodiment of the present disclosure, operating data of a finishing device is processed to obtain a health index of the finishing device; The first amplitude value is calculated based on the health index and environmental data by weight, where the environmental data is the temperature around the finishing device.

[0054] In this embodiment, the present disclosure utilizes a data acquisition system to collect real-time operating parameters of key components of the finishing equipment, including but not limited to motor current, voltage, and speed, and roller system vibration amplitude and temperature. A data filtering algorithm (such as a Kalman filter) is used to denoise the collected raw data. The filtered raw data is then processed using an equipment health assessment model (such as a neural network algorithm) to generate a health index representing the current health of the finishing equipment. The health index is expressed on a scale of 0-1, with higher values ​​indicating better equipment health.

[0055] Use temperature sensors to monitor the temperature data around the finishing equipment in real time to ensure the accuracy and real-time nature of the data, and calculate the environmental data (temperature) compensation coefficient based on the environment; the value range of the environmental data (temperature) compensation coefficient is 0-1.

[0056] A first amplitude value is obtained by weighted calculation based on the health index and the environmental data (temperature) compensation coefficient.

[0057] Construct a weighted calculation model, where the weight of the health index is set to W j , the weight of the environmental data (temperature) compensation coefficient is set to W w , and W j +W w = 1. The weight setting is determined based on historical data statistical analysis and actual production experience. For example, under normal circumstances, W j =0.7, W w =0.3.

[0058] In this embodiment, the first amplitude value is dynamically adjusted through a comprehensive analysis of the operating data and environmental data of the finishing equipment, and then the adjustment strategy template is optimized, so that the finishing equipment can adjust parameters in a timely manner according to changes in the actual production process, adapt to different production conditions, and improve the stability of the finishing process and the consistency of product quality.

[0059] In one embodiment of the present disclosure, the method for eliminating skin-pass twill defects of galvanized steel strip further includes: If the health index of the finishing equipment decreases by a magnitude greater than or equal to a first magnitude within a preset time, adjusting the weight parameter of the health index according to a preset first weight adjustment coefficient; If the decline in the health index of the finishing equipment is less than the first decline within the preset time, the current weight parameter of the health index is maintained.

[0060] In this embodiment, when the health index of the finishing equipment decreases by an amount greater than or equal to a first threshold within a preset time period, it indicates a significant deterioration in the equipment's operating status. At this point, the weighting parameter for the health index used in calculating the first amplitude value is adjusted based on a pre-stored first weight adjustment coefficient. This first weight adjustment coefficient is derived based on the equipment's historical failure data and operational experience, and is both targeted and scientific. During the adjustment process, the weight of the health index is increased, making its impact on the calculation of the first amplitude value more significant. This allows for greater consideration of the equipment's health status when determining the target adjustment strategy, addressing potential equipment failure risks, ensuring the smooth progress of the finishing process, and effectively eliminating strip twill defects. When the health index of the finishing equipment decreases by less than the first threshold within a preset time period, it indicates that while the equipment's operating status has changed, it remains relatively stable. At this point, the current weighting parameter for the health index used in calculating the first amplitude value is maintained unchanged, ensuring the continued and effective elimination of strip twill defects and ensuring the quality of the strip finishing process.

[0061] From the above, it can be concluded that the present disclosure, by inputting the fused data consisting of strip thickness information and width information into the twill defect analysis model, can accurately calculate the twill defect probability value for each area on the strip surface, providing a precise data basis for the formulation of subsequent adjustment strategies, and changing the ambiguity of previous reliance on empirical judgment; determining the first adjustment strategy based on the twill defect probability value, so that the finishing equipment can perform differentiated operations for the potential twill risks in different areas during initial operation, thereby improving the first finishing's suppression effect on twill defects. The present disclosure can also dynamically optimize the process in real time based on the actual situation after the first finishing; in the actual production process, there are uncertainties in strip characteristics, equipment status, etc. The present disclosure can flexibly respond to these changes and accurately adjust the finishing equipment to eliminate twill defects in the strip if twill defects are not eliminated by the first finishing.

[0062] A method for eliminating skin-pass twill defects in galvanized steel strip corresponding to the above embodiment, Figure 2 This is a structural block diagram of a device for eliminating skin-wash twill defects in galvanized steel strips provided by an embodiment of the present disclosure. For ease of illustration, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The method device 20 for eliminating skin-pass twill defects of galvanized steel strip includes: a data processing module 21, a first strategy module 22 and a target strategy module 23.

[0063] in, The data processing module 21 is used to input the fused data into the diagonal defect analysis model to obtain the diagonal defect probability value of each area on the strip surface. The fused data is the thickness and width information of the strip; A first strategy module 22 is used to determine a first adjustment strategy for the skin-passing equipment according to the probability value of the diagonal defect, and is further used to control the skin-passing equipment to perform a first skin-pass on the strip according to the first adjustment strategy, the first strip; The target strategy module 23 is used to determine the target adjustment strategy of the skin-polishing equipment according to the skin-polishing result of the first steel strip, and is also used to control the skin-polishing equipment to perform the second skin-polishing on the first steel strip according to the target adjustment strategy to obtain the target steel strip.

[0064] In one embodiment of the present disclosure, the first policy module 22 is specifically configured to: When the probability value of the twill defect is greater than or equal to a first threshold, determining a defect level based on the fusion data and the rolling tension data of the skin-pass equipment; A first adjustment strategy for the finishing equipment is determined according to the defect data corresponding to the defect level.

[0065] In one embodiment of the present disclosure, the first policy module 22 is specifically configured to: The defect level includes the first defect level, the second defect level and the third defect level, the third defect level is higher than the second defect level, and the second defect level is higher than the first defect level; Determine defect levels based on fused data and rolling tension data from the skin-pass equipment, including: Calculate defect assessment index based on fusion data and rolling tension data; If the defect assessment index is less than the first defect threshold, determining the defect level to be the first defect level; If the defect assessment index is greater than or equal to the first defect threshold and less than the second defect threshold, the defect level is determined to be the second defect level; If the defect assessment index is greater than or equal to the second defect threshold, the defect level is determined to be a third defect level.

[0066] In one embodiment of the present disclosure, the first policy module 22 is specifically configured to: Input defect data, fusion data and rolling tension data into the random forest model to obtain the defect type; A first adjustment strategy for the finishing equipment is determined according to the defect type and a first mapping table; the first mapping table is a mapping table between preset defect types and strategies.

[0067] In one embodiment of the present disclosure, the target policy module 23 is specifically configured to: The skin-passing result of the first steel strip includes image data of the first steel strip; Determine the target adjustment strategy for the skin-pass equipment based on the skin-pass results of the first strip, including: Processing the image data of the first steel strip to obtain image features; Based on the image features and the defect value calculation formula, the defect value of the first strip is obtained; If the defect value of the first steel strip is greater than a first preset value, selecting an adjustment strategy template corresponding to the image feature in the strategy rule library according to the image feature; The parameters in the adjustment strategy template are adjusted based on the first amplitude value to obtain a corresponding target adjustment strategy; a plurality of adjustment strategy templates are stored in the strategy rule library.

[0068] In one embodiment of the present disclosure, the target policy module 23 is specifically configured to: Process the operating data of the finishing equipment to obtain the health index of the finishing equipment; The first amplitude value is calculated based on the health index and environmental data by weight, where the environmental data is the temperature around the finishing device.

[0069] In one embodiment of the present disclosure, the target policy module 23 is specifically configured to: If the health index of the finishing equipment decreases by a magnitude greater than or equal to a first magnitude within a preset time, adjusting the weight parameter of the health index according to a preset first weight adjustment coefficient; If the decline in the health index of the finishing equipment is less than the first decline within the preset time, the current weight parameter of the health index is maintained.

[0070] From the above, it can be concluded that the present disclosure, by inputting the fused data consisting of strip thickness information and width information into the twill defect analysis model, can accurately calculate the twill defect probability value for each area on the strip surface, providing a precise data basis for the formulation of subsequent adjustment strategies, and changing the ambiguity of previous reliance on empirical judgment; determining the first adjustment strategy based on the twill defect probability value, so that the finishing equipment can perform differentiated operations for the potential twill risks in different areas during initial operation, thereby improving the first finishing's suppression effect on twill defects. The present disclosure can also dynamically optimize the process in real time based on the actual situation after the first finishing; in the actual production process, there are uncertainties in strip characteristics, equipment status, etc. The present disclosure can flexibly respond to these changes and accurately adjust the finishing equipment to eliminate twill defects in the strip if twill defects are not eliminated by the first finishing.

[0071] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of the data processing module 21, the first strategy module 22 and the target strategy module 23 are shown.

[0072] It should be understood that in the embodiments of the present disclosure, the processor 301 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0073] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0074] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0075] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of a method for eliminating smooth twill defects in galvanized strip provided by the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0076] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0077] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0078] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0079] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0081] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present disclosure.

[0082] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0083] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or replacements within the technical scope disclosed in this disclosure, and such modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for eliminating skin-pass twill defects in galvanized steel strip, characterized in that: include: Inputting the fused data into the diagonal defect analysis model to obtain the diagonal defect probability value of each area on the strip surface, wherein the fused data is the thickness and width information of the strip; determining a first adjustment strategy for a skin-finishing device according to the diagonal defect probability value, and controlling the skin-finishing device to perform a first skin-finish on the steel strip based on the first adjustment strategy to obtain a first steel strip; A target adjustment strategy for a skin-finishing device is determined according to the skin-finishing result of the first steel strip, and the skin-finishing device is controlled based on the target adjustment strategy to perform a second skin-finishing on the first steel strip to obtain a target steel strip.

2. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 1, characterized in that: The determining of a first adjustment strategy for a finishing device according to the diagonal defect probability value includes: When the twill defect probability value is greater than or equal to a first threshold, determining a defect level based on the fused data and the rolling tension data of the skin-passing equipment; A first adjustment strategy for the finishing equipment is determined according to the defect data corresponding to the defect level.

3. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 2, characterized in that: The defect level includes a first defect level, a second defect level, and a third defect level, wherein the third defect level is higher than the second defect level, and the second defect level is higher than the first defect level; The determining of the defect level based on the fusion data and the rolling tension data of the skin-passing equipment includes: Calculate defect assessment index based on fusion data and rolling tension data; If the defect assessment index is less than the first defect threshold, determining the defect level to be the first defect level; If the defect assessment index is greater than or equal to the first defect threshold and less than the second defect threshold, determining the defect level to be the second defect level; If the defect assessment index is greater than or equal to the second defect threshold, the defect level is determined to be a third defect level.

4. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 2, characterized in that: The step of determining a first adjustment strategy for the finishing equipment based on defect data corresponding to the defect level includes: Inputting the defect data, the fusion data and the rolling tension data into a random forest model to obtain a defect type; A first adjustment strategy for the finishing equipment is determined according to the defect type and a first mapping table; the first mapping table is a mapping table between preset defect types and strategies.

5. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 1, characterized in that: The skin-passing result of the first steel strip includes image data of the first steel strip; Determining a target adjustment strategy for skin-passing equipment based on the skin-passing result of the first steel strip includes: Processing the image data of the first steel strip to obtain image features; Obtaining a defect value of the first steel strip based on the image features and a defect value calculation formula; If the defect value of the first steel strip is greater than a first preset value, selecting an adjustment strategy template corresponding to the image feature in a strategy rule library according to the image feature; The parameters in the adjustment strategy template are adjusted based on the first amplitude value to obtain a corresponding target adjustment strategy; a plurality of adjustment strategy templates are stored in the strategy rule library.

6. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 5, characterized in that: Also includes: Processing the operating data of the finishing equipment to obtain a health index of the finishing equipment; A first amplitude value is calculated based on the health index and environmental data by weight, where the environmental data is the temperature around the finishing device.

7. The method for eliminating skin-pass twill defects of galvanized steel strip according to claim 6, characterized in that: Also includes: If the health index of the finishing equipment decreases by a magnitude greater than or equal to a first magnitude within a preset time, adjusting a weight parameter of the health index according to a preset first weight adjustment coefficient; If the health index of the finishing equipment decreases by less than a first decrease within a preset time, the current weight parameter of the health index is maintained.

8. A device for eliminating skin-wash twill defects on galvanized steel strip, characterized in that: include: a data processing module, configured to input the fused data into a diagonal grain defect analysis model to obtain a diagonal grain defect probability value for each area on the surface of the steel strip, wherein the fused data includes thickness and width information of the steel strip; a first strategy module, configured to determine a first adjustment strategy for a skin-passing device according to the diagonal defect probability value, and further configured to control the skin-passing device to perform a first skin-passing on the steel strip, the first steel strip, according to the first adjustment strategy; The target strategy module is used to determine the target adjustment strategy of the finishing equipment according to the finishing result of the first strip, and is also used to control the finishing equipment to perform a second finishing on the first strip according to the target adjustment strategy to obtain a target strip.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images