Warping classification and process control method, system and equipment for paperboard at tile line outlet

Abstract

The invention relates to the field of corrugated board production, and discloses a corrugated board production line outlet paperboard warping classification and process control method, system and equipment, and the method is used for collecting and analyzing the warping type in the paperboard production process in real time, and outputting production line control parameters according to the warping type. The method comprises the following steps: detecting a vertical curve contour image of a paperboard on line and judging the type of the paperboard; when the type of the paperboard is a non-L-shaped paperboard, calculating the warpage convexity of the paperboard on line; if the absolute value of the warpage convexity is not greater than a preset warpage threshold value, judging that the quality of the produced paperboard is qualified, and if the absolute value of the warpage convexity is greater than the preset warpage threshold value, determining and outputting the warpage type of the produced paperboard according to the value of the warpage convexity and preset range values of the warpage convexity corresponding to different warpage types; and inputting the paperboard warping type into a pre-trained neural network model to obtain production line control parameters output by the neural network model, and transmitting the production line control parameters to a production line control center to adjust and control the paperboard quality.

Description

Technical Field

[0001] The present invention relates to the technical field of cardboard production, and in particular to a method, system and equipment for warping classification and process control of cardboard at a corrugator line outlet. Background Art

[0002] Corrugated paper packaging is widely used in downstream consumer industries such as home appliances, electronic products, IT, food and beverages, books, daily chemicals, textiles, as well as logistics and express delivery companies.

[0003] The quality of corrugated cardboard production line products is mainly related to factors such as the material of the base paper, moisture content, and temperature control during production. The warpage of the exit cardboard is a crucial indicator of product quality. Process control on corrugated cardboard production lines primarily involves real-time online monitoring of the warpage of the exit cardboard to achieve effective feedback control of cardboard quality. Online detection and warpage level identification of the exit cardboard are key to achieving effective process control. Currently, corrugated cardboard production lines already in operation in China mainly rely on on-site engineers' visual judgment and identification for export product quality inspection and control, along with manual parameter input adjustments. However, the current production speed of corrugated cardboard production lines is generally only a few hundred meters per minute, making online detection and warpage level identification of the exit cardboard significantly difficult using manual methods. Furthermore, the rapid development of online shopping and express delivery industries has brought about customized and personalized market demands, leading to multiple batches and small production runs in corrugated cardboard production. The large number of orders and the high frequency of material changes during production result in high labor costs in the corrugated cardboard industry, impacting the automation and intelligence levels of the corrugated cardboard manufacturing sector. Summary of the Invention

[0004] The present invention provides a method, system and equipment for classifying and controlling the warping of cardboard at the exit of a corrugator line, which are used to collect and analyze the warping type of produced cardboard in real time and output corresponding production line control parameters according to the warping type.

[0005] A first aspect of the present invention provides a method for classifying and controlling warping of cardboard at the exit of a corrugator line, the method comprising: using a line structured light sensor to collect a vertical surface curve profile image of a produced cardboard, and determining the cardboard type of the produced cardboard based on the vertical surface curve profile image; when the type of the produced cardboard is non-L-shaped cardboard, calculating the warping convexity of the produced cardboard based on the vertical surface curve profile image; if the absolute value of the warping convexity is not greater than a preset warping threshold, determining that the quality of the produced cardboard is qualified; if the absolute value of the warping convexity is greater than the preset warping threshold, determining and outputting the warping type of the produced cardboard based on the warping convexity value and a preset range of warping convexity values ​​corresponding to different warping types; inputting the warping type of the produced cardboard into a pretrained neural network model to obtain production line control parameters output by the pretrained neural network model, and outputting the production line control parameters to a production line control center for adjustment to control the cardboard quality.

[0006] Preferably, the method of using a line structured light sensor to collect a vertical surface curve profile image of the production cardboard and determining the cardboard type of the production cardboard based on the vertical surface curve profile image comprises: using a line structured light sensor to collect vertical surface reflected light images of the production cardboard multiple times, and pre-processing the collected vertical surface reflected light images to obtain multiple pre-processed images; extracting and integrating the vertical surface curve profile image of the production cardboard from the multiple pre-processed images; performing data fitting on the extracted vertical surface curve profile image to obtain a cubic function of the horizontal pixel coordinates of the curve profile - the vertical pixel coordinates of the curve profile; and calculating the The number of extreme points of the univariate cubic function: when the number of extreme points of the univariate cubic function is 0, the produced cardboard is determined to be normal cardboard; when the number of extreme points of the univariate cubic function is 1, the produced cardboard is determined to be non-S-shaped cardboard; when the number of extreme points of the univariate cubic function is 2, the produced cardboard is determined to be S-shaped cardboard and an alarm is issued; when the produced cardboard is non-S-shaped cardboard, the difference between the derivatives on both sides of the produced cardboard is calculated based on the univariate cubic function; when the difference exceeds the preset range of the derivative, the produced cardboard is determined to be L-shaped cardboard and an alarm is issued; otherwise, the produced cardboard is determined to be non-L-shaped cardboard.

[0007] Preferably, a structured light sensor is used to collect reflected light images from the vertical surface of the production cardboard multiple times, and the collected reflected light images from the vertical surface are preprocessed to obtain multiple preprocessed images, including: projecting structured light onto the vertical surface of the production cardboard; using the structured light sensor to collect reflected light images from the vertical surface of the production cardboard multiple times; and preprocessing the collected reflected light images from the vertical surface to obtain multiple preprocessed images.

[0008] Preferably, extracting and integrating the vertical surface curve profile image of the produced cardboard from the multiple pre-processed images includes: extracting light streaks from the multiple pre-processed images to obtain multiple groups of light streaks; mapping the position of each group of light streaks to three-dimensional spatial coordinates using camera calibration parameters; converting and aligning the three-dimensional spatial coordinates of the multiple groups of light streaks and then fusing them to obtain the three-dimensional profile of the vertical surface of the produced cardboard; and processing the three-dimensional profile of the vertical surface of the produced cardboard to obtain the vertical surface curve profile image of the produced cardboard.

[0009] Preferably, the cubic function of the horizontal pixel coordinate of the curve profile - the vertical pixel coordinate of the curve profile is expressed as:

[0010] f1(x)=a1x 3 +b1x 2 +c1x+d

[0011] Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f1(x) represents the vertical pixel coordinate of the vertical surface curve profile at the corresponding position, and a1, b1, c1, and d represent fitting constants.

[0012] Preferably, the difference δ between the derivatives on both sides of the production board is expressed as:

[0013]

[0014] Where x i Represents the horizontal pixel coordinates of the vertical surface curve contour, x1,x2,x3...x n ...x m is the horizontal coordinate of all pixels, m represents the number of all pixel coordinate points, and f′1(x) represents the derivative function corresponding to x i Function value of position, x n Let f′1(x)=0.

[0015] Preferably, when the type of the produced cardboard is a non-L-shaped cardboard, the warping convexity of the produced cardboard is calculated based on the vertical surface curve profile image, including: when the type of the produced cardboard is a non-L-shaped cardboard, data fitting is performed based on the vertical surface curve profile image to obtain a quadratic function of the horizontal pixel coordinates of the vertical surface curve profile - the vertical pixel coordinates of the vertical surface curve profile, and the quadratic function relationship is:

[0016] f(x)=ax 2 +bx+c

[0017] Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f(x) represents the vertical pixel coordinate of the vertical surface curve profile corresponding to the x position, and a, b, and c represent constants.

[0018] According to the quadratic function, the warping convexity θ corresponding to the produced cardboard is calculated using the following formula. The warping convexity θ is expressed as:

[0019]

[0020] Where K(x) is the average value of the curvature at the three quarter points, f′(x) represents the slope, f′(x) is the derivative of the vertical surface curve profile, f″(x) represents the rate of change of curvature, f″(x) is the second-order derivative of the vertical surface curve profile, and x a and x b They represent the pixel coordinates of the two endpoints of the horizontal pixel coordinates of the quadratic function, and x1, x2, and x3 represent the pixel coordinates of the three quartered points of the horizontal pixel coordinates of the quadratic function, which are:

[0021]

[0022] Preferably, the method of inputting the warping type of the produced cardboard into a pretrained neural network model to obtain the production line control parameters output by the pretrained neural network model, and outputting the production line control parameters to the production line control center for adjustment and control of the cardboard quality includes: establishing an input and output data set through the cardboard warping type or warping degree and production line quality control parameters recorded on the corrugated cardboard production line, training the input and output data set using a neural network model to obtain a pretrained neural network model, wherein the pretrained neural network model establishes a correspondence between the warping type of the production line cardboard and the production line control parameters; inputting the warping type of the produced cardboard into the pretrained neural network model to obtain the production line control parameters output by the pretrained neural network model; and outputting the production line control parameters to the production line control center for adjustment and control of the cardboard quality.

[0023] A second aspect of the present invention provides a warping classification and process control system for cardboard at the exit of a corrugated line, comprising: an acquisition module for acquiring a vertical surface curve profile image of a produced cardboard using a line structured light sensor, and determining the cardboard type of the produced cardboard based on the vertical surface curve profile image; a calculation module for calculating the warping convexity of the produced cardboard based on the vertical surface curve profile image when the type of the produced cardboard is non-L-shaped cardboard; a judgment module for judging that the quality of the produced cardboard is qualified when the absolute value of the warping convexity is not greater than a preset warping threshold, and determining and outputting the warping type of the produced cardboard based on the warping convexity value and a preset range of warping convexity values ​​corresponding to different warping types when the absolute value of the warping convexity is greater than the preset warping threshold; and a control parameter output module for inputting the warping type of the produced cardboard into a pretrained neural network model to obtain production line control parameters output by the pretrained neural network model, and outputting the production line control parameters to a production line control center for adjustment to control the cardboard quality.

[0024] A third aspect of the present invention provides a device for classifying and controlling warping of cardboard at the exit of a corrugator line, comprising: a memory and at least one processor, wherein the memory stores computer-readable instructions, and the memory and the at least one processor are interconnected via a circuit; the at least one processor calls the computer-readable instructions in the memory to enable the device for classifying and controlling warping of cardboard at the exit of a corrugator line to perform each step of the method for classifying and controlling warping of cardboard at the exit of a corrugator line as described above.

[0025] In the technical solution provided by the present invention, by accurately capturing the vertical surface curve contour image of the cardboard, intelligently judging the cardboard type and calculating the warping convexity, a rapid and accurate assessment of the cardboard quality is achieved. When a warping problem is found, the warping type can be automatically classified, and targeted production line control parameters can be output based on the pre-trained neural network model, so as to adjust production in time, ensure stable cardboard quality, and improve overall production efficiency and intelligent management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A first flow chart of the method for warping classification and process control of cardboard at a corrugated line provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of the structure of a corrugator line outlet cardboard warping classification and process control system provided by an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of the structure of the corrugated board exit warping classification and process control equipment provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The terms "first," "second," "third," "fourth," and the like (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The method for classifying and controlling the warping of corrugated cardboard at the corrugated board production line in this embodiment of the invention includes:

[0031] S101, using a line structured light sensor to collect a vertical surface curve profile image of the production cardboard, and determining the cardboard type of the production cardboard based on the vertical surface curve profile image;

[0032] S102, when the type of the produced paperboard is non-L-shaped paperboard, calculating the warping convexity of the produced paperboard based on the vertical surface curve profile image;

[0033] S103: If the absolute value of the warping convexity is not greater than the preset warping threshold, the quality of the produced paperboard is determined to be qualified. If the absolute value of the warping convexity is greater than the preset warping threshold, the warping type of the produced paperboard is determined and output based on the warping convexity value and the preset warping convexity range values ​​corresponding to different warping types.

[0034] S104: Input the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and output the production line control parameters to the production line control center.

[0035] It is understandable that the execution subject of the present invention can be a corrugator line export cardboard warping classification and process control system, or a terminal or server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0036] In this embodiment, in step S101, a line structured light sensor is used to collect a vertical surface curve profile image of the production cardboard, and the cardboard type of the production cardboard is determined based on the vertical surface curve profile image, including: using the line structured light sensor to collect vertical surface reflected light images of the production cardboard multiple times, and preprocessing the collected vertical surface reflected light images to obtain multiple preprocessed images; extracting and integrating the vertical surface curve profile image of the production cardboard from the multiple preprocessed images; performing data fitting based on the extracted vertical surface curve profile image to obtain the horizontal pixel coordinates of the curve profile - the vertical pixel coordinates of the curve profile. a cubic function of one variable; calculate the number of extreme points of the cubic function; when the number of extreme points of the cubic function is 0, the produced cardboard is determined to be normal cardboard; when the number of extreme points of the cubic function is 1, the produced cardboard is determined to be non-S-shaped cardboard; when the number of extreme points of the cubic function is 2, the produced cardboard is determined to be S-shaped cardboard, and an alarm is issued; when the produced cardboard is non-S-shaped cardboard, the difference between the derivatives on both sides of the produced cardboard is calculated based on the cubic function; when the difference exceeds the preset range of the derivative, the produced cardboard is determined to be L-shaped, and an alarm is issued; otherwise, the produced cardboard is determined to be non-L-shaped.

[0037] In this embodiment, multiple reflected light images of the vertical surface of the production cardboard are collected, and the collected reflected light images of the vertical surface are preprocessed to obtain multiple preprocessed images. The method includes: projecting structured light onto the vertical surface of the production cardboard; collecting multiple reflected light images of the vertical surface of the production cardboard using a structured light sensor; and preprocessing the collected reflected light images of the vertical surface to obtain multiple preprocessed images.

[0038] Optionally, the structured light may be a light source emitted by a linear laser, and the structured light sensor may be a camera device.

[0039] It is understandable that when collecting the vertical surface reflected light image of the production cardboard, there may be areas without pixels. Therefore, it is necessary to use a camera device to collect the vertical surface reflected light image of the production cardboard multiple times, and then use the multiple collected images for analysis and processing.

[0040] In this embodiment, extracting and integrating a vertical surface curve profile image of a produced cardboard from a plurality of preprocessed images includes: extracting light streaks from the plurality of preprocessed images to obtain a plurality of groups of light streaks; mapping the position of each group of light streaks to three-dimensional spatial coordinates using camera calibration parameters; converting and aligning the three-dimensional spatial coordinates of the plurality of groups of light streaks, and then fusing them to obtain a three-dimensional profile of the vertical surface of the produced cardboard; and processing the three-dimensional profile of the vertical surface of the produced cardboard to obtain a vertical surface curve profile image of the produced cardboard.

[0041] In this embodiment, image processing algorithms (such as edge detection, threshold segmentation, etc.) are used to identify light streaks in the image, and a Canny edge detector or a Sobel operator is used to detect edges in the image. By setting an appropriate threshold, the light streaks are separated from the background.

[0042] In this embodiment, before performing 3D reconstruction, the camera needs to be calibrated to obtain its intrinsic and extrinsic parameters. Then, using the camera calibration parameters and the positions of the light streaks in the image, the positions of the light streaks are mapped to 3D spatial coordinates using the principle of perspective projection.

[0043] In this embodiment, the three-dimensional spatial coordinates at different perspectives are transformed and aligned and then fused to obtain the three-dimensional contour of the vertical surface of the production cardboard. If overlapping areas are encountered, these overlapping areas are optimized using a point cloud fusion algorithm (such as the ICP algorithm) to ensure the continuity and accuracy of the three-dimensional contour.

[0044] In this embodiment, a slicing plane perpendicular to the paperboard plane is selected from the three-dimensional contour of the vertical surface of the production paperboard. This plane should be located at the expected cross-sectional location of the paperboard. Then, a contour extraction algorithm (such as Canny edge detection and Hough transform) is used on the slicing plane to extract the curved contour of the paperboard. This contour will reflect the shape and size of the paperboard at that location. Finally, the three-dimensional contour of the vertical surface of the production paperboard is smoothed using a filtering algorithm (such as Gaussian filtering and median filtering) to generate a vertical surface curved contour image. Smoothing the extracted contour using a filtering algorithm (such as Gaussian filtering and median filtering) can eliminate minor fluctuations caused by noise or measurement errors.

[0045] In this embodiment, the cubic function of the horizontal pixel coordinate of the curve profile minus the vertical pixel coordinate of the curve profile is expressed as:

[0046] f1(x)=a1x 3 +b1x 2 +c1x+d

[0047] In the formula, x represents the horizontal pixel coordinate of the curve profile, f1(x) represents the vertical pixel coordinate of the vertical plane curve profile at the corresponding position, and a1, b1, c1 and d represent fitting constants.

[0048] The difference δ between the derivatives on both sides of the paperboard production process is expressed as:

[0049]

[0050] Where xi represents the horizontal pixel coordinates of the vertical surface curve profile, x1,x2,x3...x n ...x m is the horizontal coordinate of all pixels, m represents the number of all pixel coordinate points, and f′1(x) represents the derivative function corresponding to x i Function value of position, x n Let f′1(x)=0.

[0051] It can be understood that by calculating the difference between the derivatives on both sides of the corrugated cardboard and comparing the calculated difference with the preset range of the derivative, the reason for judging whether the cardboard is L-shaped or non-L-shaped is that the L-shaped cardboard has a significant slope change at the bend (i.e., the corner of the L), while the non-L-shaped cardboard does not have such a feature.

[0052] Calculate the difference between the derivatives on both sides of the corrugated cardboard. That is, calculate the derivative (slope) on both sides of the suspected L-shaped area (i.e., the area where the corner may exist) of the corrugated cardboard. Then, calculate the difference between the derivatives on these two sides. This difference reflects the degree of change in the slope in this area.

[0053] In this embodiment, before formal production, the corrugated cardboard is trial-produced. After the trial production is completed, the difference between the derivatives on both sides of the non-L-shaped cardboard during the trial production is taken as the maximum value of the derivative preset range value, and the difference between the derivatives on both sides of the L-shaped cardboard during the trial production is taken as the minimum value of the derivative preset range value.

[0054] In this embodiment, in step S102, when the type of the produced paperboard is a non-L-shaped paperboard, the warping convexity of the produced paperboard is calculated based on the vertical surface curve profile image, including:

[0055] When the type of paperboard produced is non-L-shaped paperboard, data fitting is performed based on the vertical surface curve profile image to obtain a one-variable quadratic function of the vertical surface curve profile horizontal pixel coordinates minus the vertical surface curve profile vertical pixel coordinates. The quadratic function relationship is:

[0056] f(x)=ax 2 +bx+c

[0057] Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f(x) represents the vertical pixel coordinate of the vertical surface curve profile corresponding to the x position, and a, b, and c represent constants.

[0058]

[0059] Where K(x) is the average value of the curvature at the three quarter points, f′(x) represents the slope, f′(x) is the derivative of the vertical surface curve profile, f″(x) represents the rate of change of curvature, f″(x) is the second-order derivative of the vertical surface curve profile, and x a and x b They represent the pixel coordinates of the two endpoints of the horizontal pixel coordinates of the quadratic function, and x1, x2, and x3 represent the pixel coordinates of the three quartered points of the horizontal pixel coordinates of the quadratic function, which are:

[0060]

[0061] In this embodiment, step S103, the method for determining the preset range value of warpage convexity specifically includes: acquiring cross-sectional images of non-L-shaped cardboard with different warpage directions and degrees as samples; identifying the warpage direction and degree of warpage of the samples, and classifying the samples according to different warpage types to obtain classification results; establishing sub-image libraries corresponding to different warpage types and warpage levels according to the classification results; calculating the warpage convexity of each sample in each sub-image library one by one; and determining the warpage convexity range value corresponding to the warpage type and warpage level of each sub-image library according to the minimum and maximum values ​​of the warpage convexity of the samples in each sub-image library.

[0062] It can be understood that the method for calculating the warping convexity of each sample in each sub-image library can adopt the method for calculating the warping convexity θ as described above, which will not be described in detail here.

[0063] Exemplarily, when identifying the warping direction and degree of a sample and classifying the sample according to different warping types and warping levels to obtain a classification result, the classification result formed includes upwarping-type 1, upwarping-type 2, upwarping-type 3, downwarping-type 1, downwarping-type 2, and downwarping-type 3, and then six sub-image libraries are established based on the classification results, each image library corresponding to upwarping-type 1, upwarping-type 2, upwarping-type 3, downwarping-type 1, downwarping-type 2, and downwarping-type 3, and then the warping convexity of each sample in the six sub-image libraries is calculated one by one, and then the warping convexity range values ​​of upwarping-type 1, upwarping-type 2, upwarping-type 3, downwarping-type 1, downwarping-type 2, and downwarping-type 3 are determined, including: determining the warping convexity range value corresponding to upwarping-type 1 based on the minimum and maximum values ​​of the warping convexity of the samples in the image library corresponding to upwarping-type 1 The range of warp convexity corresponding to type 2 is determined based on the minimum and maximum values ​​of warp convexity of samples in the image library corresponding to type 2. Determine the warping convexity range value corresponding to upwarping-type 3 according to the minimum and maximum values ​​of the warping convexity of the samples in the upwarping-type 3 corresponding image library The range of warp convexity corresponding to type 1 is determined based on the minimum and maximum values ​​of warp convexity of the samples in the image library corresponding to type 1. The range of warp convexity corresponding to type 2 is determined based on the minimum and maximum values ​​of warp convexity of the samples in the image library corresponding to type 2. The range of warp convexity corresponding to type 3 is determined based on the minimum and maximum values ​​of warp convexity of the samples in the image library corresponding to type 3.

[0064] In this embodiment, the preset warping threshold is If the absolute value of the warpage convexity is not greater than The quality of the produced cardboard is judged to be qualified.

[0065] 9. In this embodiment, in step S104, the warping type of the produced cardboard is input into a pretrained neural network model to obtain production line control parameters output by the pretrained neural network model, and the production line control parameters are output to the production line control center for adjustment and control of the cardboard quality. Specifically, the steps include: establishing an input and output data set using the cardboard warping type or warping degree recorded on the corrugated cardboard production line and the production line quality control parameters; training the input and output data set using a neural network model to obtain a pretrained neural network model, wherein the pretrained neural network model establishes a correspondence between the warping type of the production line cardboard and the production line control parameters; inputting the warping type of the produced cardboard into the pretrained neural network model to obtain the production line control parameters output by the pretrained neural network model; and outputting the production line control parameters to the production line control center for adjustment and control of the cardboard quality.

[0066] In this embodiment, different warping types correspond to different production line control parameters. The correspondence between warping types and production line control parameters is learned through a pre-trained neural network model, and the prediction is fed back to the production line control center to control product quality.

[0067] In this embodiment, the neural network model uses a convolutional neural network model, which consists of an input layer, a hidden layer, and an output layer. The input layer receives the cardboard warp type as an input feature. The hidden layer contains multiple layers of neurons, which are used to extract useful information from the input features and learn the complex relationship between the warp type and production line control parameters. The output layer outputs the predicted production line control parameters.

[0068] Before training the neural network model, the input and output data sets are established through the cardboard warping type or warping degree and production line quality control parameters (such as temperature, pressure, speed, etc.) recorded on the corrugated cardboard production line, and the collected data are preprocessed by cleaning, normalization, etc. to ensure the quality and consistency of the data.

[0069] In this example, a neural network model is trained using preprocessed cardboard production data to produce a pretrained neural network model. During the training process, the model learns the correspondence between different warpage types and production line control parameters and adjusts its internal parameters (such as weights and biases) to minimize prediction error.

[0070] Optionally, as the production process progresses, new data can be continuously collected and the neural network model can be continuously optimized and updated. This can be achieved through methods such as incremental learning and transfer learning to improve the model's predictive performance and adaptability.

[0071] In this embodiment, the predicted production line control parameters are fed back to the production line control center in real time. The production line control center adjusts the operation of the production line according to these parameters, such as adjusting the temperature, pressure, speed, etc., to achieve precise control of the cardboard quality.

[0072] This embodiment provides a method for classifying and controlling the warpage of corrugated cardboard at the production line exit. By accurately acquiring the vertical curve contour image of the cardboard, it intelligently determines the cardboard type and calculates the warpage convexity, achieving rapid and accurate assessment of cardboard quality. When a warpage problem is detected, it can automatically classify the warpage type and output targeted production line control parameters based on a pre-trained neural network model, thereby adjusting production in a timely manner, ensuring stable cardboard quality, and improving overall production efficiency and intelligent management level.

[0073] The above describes the warping classification and process control method of the corrugated board outlet in the embodiment of the present invention. The following describes the device in the embodiment of the present invention. Figure 2 In an embodiment of the present invention, the warpage classification and process control system for cardboard at the exit of a corrugator line is used to implement the warpage classification and process control method for cardboard at the exit of a corrugator line. The implementation of the warpage classification and process control system for cardboard at the exit of a corrugator line includes:

[0074] The acquisition module 201 is used to acquire the vertical surface curve contour image of the produced paperboard using a line structured light sensor, and to determine the paperboard type based on the vertical surface curve contour image.

[0075] Calculation module 202 is used to calculate the warpage of the produced paperboard based on the vertical plane curve profile image when the type of the produced paperboard is not L-shaped paperboard.

[0076] The judgment module 203 is configured to determine that the quality of the produced paperboard is qualified when the absolute value of the warping convexity is not greater than the preset warping threshold. When the absolute value of the warping convexity is greater than the preset warping threshold, the judgment module 203 is configured to determine and output the warping type of the produced paperboard based on the warping convexity value and the preset warping convexity range values ​​corresponding to different warping types.

[0077] The control parameter output module 204 is used to input the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and output the production line control parameters to the production line control center for adjustment to control the cardboard quality.

[0078] This embodiment accurately captures the vertical curve profile of the cardboard, intelligently determines the cardboard type, and calculates the degree of warping. This enables rapid and accurate assessment of cardboard quality. When warping is detected, the system automatically classifies the warping type and outputs targeted production line control parameters based on a pre-trained neural network model. This allows for timely production adjustments, ensuring stable cardboard quality and improving overall production efficiency and intelligent management.

[0079] Figure 2 The structure of the corrugated board exit warpage classification and process control system shown does not constitute a limitation on the corrugated board exit warpage classification and process control system, and can realize the steps of the corrugated board exit warpage classification and process control methods provided in the above-described method embodiments.

[0080] above Figure 2 The corrugated board exit warpage classification and process control system in this embodiment of the invention is described in detail from the perspective of modular functional entities. The corrugated board exit warpage classification and process control equipment in this embodiment of the invention is described in detail from the perspective of hardware processing.

[0081] Figure 3 This is a schematic diagram of the structure of a corrugator export cardboard warping classification and process control device provided by an embodiment of the present invention. The device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more mass storage devices) storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 can be temporary storage or permanent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations in the device 300. Furthermore, the processor 310 may be configured to communicate with the storage medium 330 to execute a series of instruction operations in the storage medium on the device 300.

[0082] Device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input / output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0083] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc., various media that can store program code.

[0085] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for classifying and controlling the warping of cardboard for export from a corrugated line, characterized in that: The method for classifying and controlling warping of cardboard exported from a corrugated line comprises: Using a line structured light sensor to collect a vertical surface curve profile image of the produced cardboard, and judging the cardboard type of the produced cardboard according to the vertical surface curve profile image; When the type of the produced cardboard is non-L-shaped cardboard, the warping convexity of the produced cardboard is calculated based on the vertical surface curve profile image; If the absolute value of the warping convexity is not greater than the preset warping threshold, the quality of the produced paperboard is determined to be qualified. If the absolute value of the warping convexity is greater than the preset warping threshold, the warping type of the produced paperboard is determined and output according to the value of the warping convexity and the preset range of the warping convexity corresponding to different warping types; The warping type of the produced cardboard is input into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and the production line control parameters are output to the production line control center for adjustment to control the cardboard quality.

2. The method for warping classification and process control of corrugated board export according to claim 1 is characterized in that: The method of collecting a vertical surface curve profile image of the production paperboard using a line structured light sensor and determining the paperboard type of the production paperboard according to the vertical surface curve profile image includes: A line structured light sensor is used to collect vertical surface reflected light images of the production cardboard for multiple times, and the collected vertical surface reflected light images are preprocessed to obtain multiple preprocessed images; Extract and integrate the vertical surface curve profile image of the produced paperboard from multiple pre-processed images; Data fitting is performed based on the extracted vertical surface curve profile image to obtain a univariate cubic function of the curve profile transverse pixel coordinates-curve profile longitudinal pixel coordinates; Calculate the number of extreme points of the one-variable cubic function. When the number of extreme points of the one-variable cubic function is 0, determine that the produced cardboard is a normal cardboard. When the number of extreme points of the one-variable cubic function is 1, determine that the produced cardboard is a non-S-shaped cardboard. When the number of extreme points of the one-variable cubic function is 2, determine that the produced cardboard is an S-shaped cardboard, and issue an alarm to remind the staff; When the production paperboard is a non-S-shaped paperboard, the difference of the derivatives on both sides of the production paperboard is calculated based on the univariate cubic function; When the difference exceeds the preset range of the derivative, the produced cardboard is determined to be an L-shaped cardboard and an alarm is issued. Otherwise, the produced cardboard is determined to be a non-L-shaped cardboard.

3. The method for warping classification and process control of corrugated board export according to claim 2 is characterized in that: The structured light sensor is used to collect vertical surface reflected light images of the production cardboard multiple times, and the collected vertical surface reflected light images are preprocessed to obtain multiple preprocessed images, including: Projecting structured light onto the vertical surface of the production board; Use a structured light sensor to collect reflected light images of the vertical surface of the production cardboard multiple times; The collected vertical surface reflected light images are preprocessed to obtain a plurality of preprocessed images.

4. The method for warping classification and process control of corrugated board export according to claim 3 is characterized in that: Extract and integrate the vertical surface curve profile image of the produced cardboard from multiple pre-processed images, including: Extracting light streaks from a plurality of preprocessed images to obtain a plurality of groups of light streaks; Using the camera calibration parameters, the position of each group of light fringes is mapped to three-dimensional spatial coordinates; The spatial three-dimensional coordinates of multiple groups of light stripes are transformed and aligned and then fused to obtain the three-dimensional contour of the vertical surface of the production cardboard; The three-dimensional contour of the vertical surface of the produced cardboard is processed to obtain a vertical surface curve contour image of the produced cardboard.

5. The method for warping classification and process control of corrugated board export according to claim 2 is characterized in that: The cubic function of the horizontal pixel coordinate of the curve profile - the vertical pixel coordinate of the curve profile is expressed as: f1(x)=a1x 3 +b1x 2 +c1x+d Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f1(x) represents the vertical pixel coordinate of the vertical surface curve profile at the corresponding position, and a1, b1, c1 and d represent fitting constants.

6. The method for warping classification and process control of corrugated board export according to claim 5 is characterized in that: The difference δ between the derivatives on both sides of the production board is expressed as: Where xi represents the horizontal pixel coordinates of the vertical surface curve profile, x1,x2,x3...x n ...x m is the horizontal coordinate of all pixels, m represents the number of all pixel coordinate points, and f1′(x) represents the derivative function corresponding to x i Function value of position, x n is the point where f1′(x)=0.

7. The method for warping classification and process control of corrugated board export according to claim 1, characterized in that: When the type of the produced cardboard is non-L-shaped cardboard, the warping convexity of the produced cardboard is calculated based on the vertical surface curve profile image, including: When the type of paperboard produced is non-L-shaped paperboard, data fitting is performed based on the vertical surface curve profile image to obtain a one-dimensional quadratic function of the vertical surface curve profile transverse pixel coordinates-vertical surface curve profile longitudinal pixel coordinates, and the one-dimensional quadratic function relationship is: f(x)=ax 2 +bx+c Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f(x) represents the vertical pixel coordinate of the vertical surface curve profile corresponding to the x position, and a, b, and c represent constants; According to the quadratic function, the warping convexity θ corresponding to the produced paperboard is calculated using the following formula, and the warping convexity θ is expressed as: Where K(x) is the average value of the curvature at the three quartered points, f′(x) is the slope, f′(x) is the derivative of the vertical surface curve profile, f″(x) is the rate of change of curvature, f″(x) is the second-order derivative of the vertical surface curve profile, and x a and x b They represent the pixel coordinates of the two endpoints of the horizontal pixel coordinates of the quadratic function of one variable, and x1, x2, and x3 represent the pixel coordinates of the three quarter-divided points of the horizontal pixel coordinates of the quadratic function of one variable, respectively:

8. The method for warping classification and process control of corrugated board export according to claim 1, characterized in that: The method of inputting the warping type of the produced paperboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and outputting the production line control parameters to the production line control center for adjustment to control the quality of the paperboard includes: An input-output data set is established through the cardboard warping type or warping degree recorded on the corrugated cardboard production line and the production line quality control parameters, and the input-output data set is trained using a neural network model to obtain a pre-trained neural network model. The pre-trained neural network model establishes a corresponding relationship between the cardboard warping type of the production line and the production line control parameters; Inputting the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model; The production line control parameters are output to the production line control center for adjustment to control the cardboard quality.

9. A corrugated board export warping classification and process control system, characterized in that: include: A collection module, used for collecting a vertical surface curve profile image of the production paperboard, and judging the paperboard type of the production paperboard according to the vertical surface curve profile image; A calculation module, used for calculating the warping convexity of the produced paperboard based on the vertical surface curve profile image when the type of the produced paperboard is non-L-shaped paperboard; A judgment module is used to judge that the quality of the produced paperboard is qualified when the absolute value of the warping convexity is not greater than the preset warping threshold value, and to determine and output the warping type of the produced paperboard according to the value of the warping convexity and the preset range value of the warping convexity corresponding to different warping types when the absolute value of the warping convexity is greater than the preset warping threshold value; The process control module is used to input the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and output the production line control parameters to the production line control center for adjustment to control the cardboard quality.

10. A corrugated board export warping classification and process control device, characterized in that: comprising a memory and at least one processor, wherein the memory has computer-readable instructions stored therein; The at least one processor calls the computer-readable instructions in the memory to execute the various steps of the corrugator line outlet cardboard warping classification and process control method as claimed in any one of claims 1-7.

Images