A real-time improvement method, device and equipment for corrugated cardboard warping

Abstract

The present invention discloses a method, device and equipment for real-time improvement of the warping of corrugated cardboard. The method includes: determining the warping degree of corrugated paper blocks; obtaining a plurality of process parameters in the production of corrugated cardboard; training a gradient boosting decision tree algorithm using feature data to generate a warping degree prediction model; using temperature difference data, wrapping angle data and glue amount data as target tuning parameters, predicting the warping degree using the warping degree prediction model, and recording the optimal wrapping angle and the optimal glue amount; producing corrugated cardboard using a set of optimal parameters. The present invention can adjust the production process parameters of corrugated cardboard based on the constructed warping degree prediction model, and produce corrugated cardboard with the optimal warping degree using a set of optimal parameters, realizing automatic adjustment of the warping degree, without relying on human experience, improving the yield rate of corrugated cardboard production, and reducing labor costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of corrugated board manufacturing, and particularly relates to a method, device and equipment for real-time improvement of corrugated board warping. Background Art

[0002] A corrugated board production line is a combination of equipment for producing corrugated boards. When producing corrugated boards, corresponding control needs to be carried out on each piece of equipment. If any link in the cardboard production line shows abnormalities, such as abnormalities in the wrap angle of the preheating wheel, temperature difference data at the paper inlet and outlet of the preheating wheel, humidity data, etc., it will cause the corrugated board to warp.

[0003] In the prior art, usually, data such as the wrap angle, glue amount, and humidity are manually adjusted, relying on the experience of operators to improve the warping of the cardboard. However, this method has the following defects: First, the experience levels of operators vary, making it impossible to quantitatively set production process parameters, resulting in inaccurate results; Second, the warping of the cardboard is interfered by basic data such as cardboard material and required corrugation type, resulting in product defects. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device and equipment for real-time improvement of corrugated board warping, which are used to solve at least one technical problem existing in the prior art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention provides a method for real-time improvement of corrugated board warping, including:

[0007] Obtain the point cloud data of the corrugated board, perform curve fitting using the point cloud data, and determine the warping degree of the corrugated paper block according to the curve curvature;

[0008] Obtain multiple process parameters for corrugated board production, where the process parameters at least include temperature difference data, wrap angle data, and glue amount data;

[0009] Take the multiple process parameters as independent variables, and take the warping degree of the corrugated paper block as the dependent variable, extract feature data, and use the feature data to train the gradient boosting decision tree algorithm to generate a warping degree prediction model;

[0010] Input the temperature difference data, wrap angle data, and glue amount data as target tuning parameters into the warping degree prediction model for warping degree prediction. When the warping degree is optimal, record the optimal wrap angle and optimal glue amount at this time;

[0011] Send a set of optimal parameters including the optimal wrap angle and optimal glue amount to the corrugated board production system to obtain a corrugated paper block with the optimal warping degree.

[0012] In a possible design, obtaining the point cloud data of the corrugated cardboard, performing curve fitting using the point cloud data, and determining the warping degree of the corrugated paper block according to the curve curvature includes:

[0013] Receiving the first point cloud data of a plurality of corrugated cardboards, wherein the first point cloud data is the cardboard image data at the paper outlet of the corrugated cardboard production line;

[0014] Extracting multiple groups of second point cloud data row by row from the first point cloud data, wherein each group of the second point cloud data corresponds to the cross-sectional data of one of the corrugated cardboards;

[0015] Determining the cutting points of the corrugated cardboard according to the data distribution state of the second point cloud data, and determining the third point cloud data corresponding to each corrugated paper block according to the cutting points;

[0016] Performing curve fitting on the third point cloud data, and determining the warping degree of each corrugated paper block according to the curve curvature.

[0017] In a possible design, performing curve fitting on the third point cloud data, and determining the warping degree of each corrugated paper block according to the curve curvature includes:

[0018] Performing curve fitting on the third point cloud data by using the least squares method, and calculating the curvature of the midpoint of the curve;

[0019] When the curvature value of the midpoint of the curve is larger, the warping degree of the corrugated paper block is larger; when the curvature value of the midpoint of the curve is smaller, the warping degree of the corrugated paper block is smaller.

[0020] In a possible design, performing curve fitting on the third point cloud data, and determining the warping degree of each corrugated paper block according to the curve curvature includes:

[0021] Fitting the third point cloud data into a circle, and calculating the radius of curvature of the circle according to the cardboard width, the number of creases, and the height data of the cross-section of the corresponding corrugated paper block;

[0022] When the radius of curvature value of the circle is larger, the warping degree of the corrugated paper block is smaller; when the radius of curvature value of the circle is smaller, the warping degree of the corrugated paper block is larger.

[0023] In a possible design, the process parameters further include the preset corrugated cardboard material, corrugated cardboard width, corrugator flute profile, and corrugator speed.

[0024] In a possible design, the temperature difference data is obtained by calculating the temperature difference between the paper inlet and the paper outlet of the preheating wheel, wherein the temperature at the paper inlet and the temperature at the paper outlet are collected by temperature sensors.

[0025] In a possible design, after calculating the temperature difference data, the method further includes:

[0026] Construct a linear equation with two variables y = ax + b using multiple temperature difference data y and multiple included angle data x, and calculate the constant parameters a and b.

[0027] In a possible design, after inputting the target tuning parameter into the warping prediction model for warping prediction, the method further includes:

[0028] Use the predicted warping as the optimization index of the pruning algorithm to obtain the optimal warping.

[0029] In a second aspect, the present invention provides a device for real-time improvement of corrugated cardboard warping, including:

[0030] A warping determination module, configured to obtain the point cloud data of the corrugated cardboard, perform curve fitting using the point cloud data, and determine the warping of the corrugated paper block according to the curve curvature;

[0031] A parameter acquisition module, configured to obtain multiple process parameters in the production of corrugated cardboard, where the process parameters at least include temperature difference data, included angle data, and glue amount data;

[0032] A model training module, configured to use the multiple process parameters as independent variables and the warping of the corrugated paper block as the dependent variable, extract feature data, and train a gradient boosting decision tree algorithm using the feature data to generate a warping prediction model;

[0033] An optimal parameter acquisition module, configured to input the temperature difference data, included angle data, and glue amount data as target tuning parameters into the warping prediction model for warping prediction, and when the warping is optimal, record the optimal included angle and optimal glue amount at this time;

[0034] An optimal parameter sending module, configured to send a set of optimal parameters including the optimal included angle and optimal glue amount to the corrugated cardboard production system to obtain a corrugated paper block with optimal warping.

[0035] In a possible design, the warping determination module is specifically configured to:

[0036] Receive the first point cloud data of several corrugated cardboards, where the first point cloud data is the cardboard image data at the outlet of the corrugated cardboard production line;

[0037] Extract multiple groups of second point cloud data row by row from the first point cloud data, where each group of the second point cloud data corresponds to the cross-sectional data of one of the corrugated cardboards;

[0038] Determine the cutting points of the corrugated board according to the data distribution state of the second point cloud data, and determine the third point cloud data corresponding to each corrugated paper block according to the cutting points;

[0039] Perform curve fitting on the third point cloud data, and determine the warping degree of each corrugated paper block according to the curve curvature.

[0040] In a possible design, when performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, the warping degree determination module is specifically configured to:

[0041] Perform curve fitting on the third point cloud data by using the least squares method, and calculate the curvature of the midpoint of the curve;

[0042] When the curvature value of the midpoint of the curve is larger, the warping degree of the corrugated paper block is larger; when the curvature value of the midpoint of the curve is smaller, the warping degree of the corrugated paper block is smaller.

[0043] In a possible design, when performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, the warping degree determination module is specifically configured to:

[0044] Fit the third point cloud data into a circle, and calculate the curvature radius of the circle according to the cardboard width, the number of creases, and the height data of the cross-section of the corresponding corrugated paper block;

[0045] When the curvature radius value of the circle is larger, the warping degree of the corrugated paper block is smaller; when the curvature radius value of the circle is smaller, the warping degree of the corrugated paper block is larger.

[0046] In a possible design, the process parameters further include a preset corrugated board material, corrugated board width, corrugating machine corrugation type, and corrugating machine speed.

[0047] In a possible design, the temperature difference data is obtained by calculating the temperature difference between the paper inlet and the paper outlet of the preheating wheel, wherein the paper inlet temperature and the paper outlet temperature are collected by temperature sensors.

[0048] In a possible design, after calculating the temperature difference data, the parameter acquisition module is further configured to:

[0049] Use a plurality of temperature difference data y and a plurality of wrap angle data x to construct a binary linear equation y = ax + b, and calculate the constant parameters a and b.

[0050] In a possible design, after inputting the target tuning parameter into the warping degree prediction model for warping degree prediction, the optimal parameter acquisition module is further configured to:

[0051] Use the predicted warpage as the optimization index of the pruning algorithm to obtain the optimal warpage.

[0052] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, they execute the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect.

[0054] In a fifth aspect, the present invention provides a computer program product containing instructions. When the instructions are run on a computer, the computer is made to execute the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect.

[0055] Beneficial effects:

[0056] The present invention calculates the warpage of corrugated cardboard and obtains multiple process parameters in the production of corrugated cardboard. Using the process parameters as independent variables and the warpage as the dependent variable, it trains the gradient boosting decision tree algorithm to generate a warpage prediction model; uses the warpage prediction model to optimize the parameters to obtain the optimal wrapping angle and the optimal glue amount. Finally, it uses a set of optimal parameters including the optimal wrapping angle and the optimal glue amount to produce corrugated paper blocks with the optimal warpage. That is, the present invention can adjust the production process parameters of corrugated cardboard based on the constructed warpage prediction model, and use a set of optimal parameters to produce corrugated cardboard with the optimal warpage, realizing the automatic adjustment of warpage, without relying on human experience, improving the yield rate of corrugated cardboard production, and reducing labor costs. Description of the drawings

[0057] Figure 1 It is a flowchart of the real-time warpage improvement method for corrugated cardboard in this embodiment. Detailed implementation manners

[0058] To make the objectives, technical solutions, and advantages of the embodiments of this specification clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are some, but not all, of the embodiments of this specification. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] Embodiment

[0060] To solve the technical problems existing in the prior art, such as the uneven experience levels of operators, which makes it impossible to quantitatively set the production process parameters, resulting in inaccurate results, etc., the embodiment of the present application provides a method for real-time improvement of the warping of corrugated cardboard. This method adjusts the production process parameters of corrugated cardboard through the constructed warping degree prediction model, and uses a set of optimal parameters to produce corrugated cardboard with the optimal warping degree, realizing the automatic adjustment of the warping degree, without relying on human experience, improving the yield rate of corrugated cardboard production, and reducing the labor cost.

[0061] As Figure 1 shown, in the first aspect, the embodiment provides a method for real-time improvement of the warping of corrugated cardboard, including but not limited to being implemented by steps S1 to S5, specifically as follows:

[0062] Step S1. Obtain the point cloud data of the corrugated cardboard, perform curve fitting using the point cloud data, and determine the warping degree of the corrugated paper block according to the curve curvature;

[0063] As a specific implementation manner of step S1, it includes:

[0064] Step S11. Receive the first point cloud data of several corrugated cardboards, where the first point cloud data is the cardboard image data at the cardboard outlet of the corrugated cardboard production line;

[0065] It should be noted that in this embodiment, preferably, the server receives the first point cloud data of several corrugated cardboards, and the 3D camera set at the cardboard outlet of the corrugated cardboard production line collects the point cloud data of the corrugated cardboard, and the controller set in the 3D camera uploads the point cloud data to the server; among them, since multiple corrugated cardboards are stacked flat together on the production line for cardboard outlet, the first point cloud data collected by the 3D camera at this time contains the cross-sectional point cloud data of multiple corrugated cardboards, and this cross-sectional point data is the height data relative to the conveyor belt. Preferably, the 3D camera includes but is not limited to structured light 3D cameras, coded light 3D cameras, stereo vision 3D cameras, TOF 3D cameras, etc., and no limitation is made here.

[0066] Step S12. Extract multiple groups of second point cloud data row by row from the first point cloud data, where each group of the second point cloud data corresponds to the cross-sectional data of one of the corrugated cardboards;

[0067] It should be noted that, since the first point cloud data contains cross-sectional point cloud data of several corrugated cardboards, if it is necessary to analyze and calculate the warping of one of the corrugated cardboards, it is necessary to extract the cross-sectional point cloud data of each corrugated cardboard from the first point cloud data. Since the first point cloud data is regularly arranged horizontally, the second point cloud data can be extracted row by row from the first point cloud data to obtain the cross-sectional point cloud data of each corrugated cardboard.

[0068] Step S13. Determine the cutting points of the corrugated paperboard according to the data distribution state of the second point cloud data, and determine the third point cloud data corresponding to each corrugated paper block according to the cutting points;

[0069] Specifically, by detecting the height difference between consecutive points in the second point cloud data, when the height difference between two adjacent points exceeds a height threshold, it can be determined that the cutting point of the corrugated cardboard is located between the two adjacent points. Preferably, before determining the cutting point, the position interval of the cutting point can also be preliminarily located according to the cardboard width and the number of planers set by the production management system, so that the position of the cutting point can be determined more accurately.

[0070] It should be noted that, since the thickness of the corrugated cardboard is basically set uniformly, for example, the thickness of three-layer corrugated cardboard and five-layer corrugated cardboard is usually set to less than 3 mm, the height threshold can be set to 3 mm. In addition, the point interval of the 3D camera is usually less than 0.5 mm, and the cutting interval of the cutter is also greater than 0.5 mm. Therefore, if the height difference between two adjacent points collected is greater than 3 mm, it is considered that the cutting point of the corrugated cardboard is located between the two adjacent points.

[0071] It should be noted that the cardboard width refers to the width of the entire corrugated cardboard before it is cut, and the planing number refers to the number of corrugated cardboard blocks that the production management system pre-sets to cut the entire corrugated cardboard into. For example, the planing number is set to 3, 4 or 5, etc., which is not limited here.

[0072] Step S14: Perform curve fitting on the third point cloud data, and determine the warping degree of each corrugated paper block according to the curvature of the curve.

[0073] As a specific implementation of step S14, curve fitting is performed on the third point cloud data, and the curvature of each corrugated paper block is determined according to the curvature of the curve, including:

[0074] Step S141. Use the least square method to perform curve fitting on the third point cloud data and calculate the curvature of the midpoint of the curve;

[0075] It should be noted that the least squares method used in this embodiment is an existing algorithm, and its algorithm principle will not be specifically described here. In addition, the curvature of the midpoint of the curve can be calculated through existing curvature calculation formulas, and no further pursuit will be made here. Then, after the point cloud data of the cross-section of the corrugated paper block is fitted into a curve, the curvature of the curve can be used to characterize the warping degree of the corrugated paper block. Preferably, by using the curvature of the midpoint of the curve to characterize the warping degree of the corrugated paper block, the warping degree of the corrugated paper block can be accurately reflected.

[0076] Step S142. When the curvature value of the midpoint of the curve is larger, the warping degree of the corrugated paper block is larger; when the curvature value of the midpoint of the curve is smaller, the warping degree of the corrugated paper block is smaller.

[0077] As another specific implementation manner of step S14, curve fitting is performed on the third point cloud data, and the warping degree of each corrugated paper block is determined according to the curve curvature, including:

[0078] Step S143. Fit the third point cloud data into a circle, and calculate the radius of curvature of the circle according to the cardboard width, the number of creases, and the height data of the cross-section of the corresponding corrugated paper block.

[0079] Specifically, according to the cardboard width and the number of creases, that is, by dividing the cardboard width by the number of creases, the width of each corrugated paper block can be obtained. Through the height data of the cross-section of the corrugated paper block and the width data of the paper block, the radius of curvature of the circle can be obtained.

[0080] Step S144. When the radius of curvature value of the circle is larger, the warping degree of the corrugated paper block is smaller; when the radius of curvature value of the circle is smaller, the warping degree of the corrugated paper block is larger.

[0081] Step S2. Obtain multiple process parameters for corrugated cardboard production, where the process parameters at least include temperature difference data, wrap angle data, and glue amount data; preferably, the process parameters further include a preset corrugated cardboard material, corrugated cardboard width, corrugator flute profile, corrugator speed, and humidity data.

[0082] Among them, the temperature difference data is obtained by calculating the temperature difference between the paper inlet and paper outlet of the preheating wheel, where the paper inlet temperature and the paper outlet temperature are collected by temperature sensors; preferably, the temperature sensors can be installed at the paper inlet and paper outlet positions of the preheating wheels of the first pit machine on the production line, the paper inlet and paper outlet positions of the preheating wheels of the second pit machine, the paper inlet and paper outlet positions of the triple preheating wheel, etc., and the temperature sensors are used to collect the temperature data of the corrugated paper at the paper inlet and paper outlet positions of the preheating wheels.

[0083] Among them, the wrap angle data and the glue amount data can be collected by a programmable logic controller; preferably, after calculating the temperature difference data, the method further includes:

[0084] Construct a linear equation of two variables \(y = ax + b\) using multiple temperature difference data \(y\) and multiple wrap angle data \(x\), and calculate the constant parameters \(a\) and \(b\).

[0085] It should be noted that the construction of the linear equation of two variables \(y = ax + b\) can be used in subsequent target tuning parameters, which will be specifically described below and will not be elaborated here.

[0086] Step S3. Use the multiple process parameters as independent variables and the warping degree of the corrugated paper block as the dependent variable to extract feature data, and use the feature data to train the gradient boosting decision tree algorithm to generate a warping degree prediction model.

[0087] Specifically, use temperature, humidity, wrap angle data, glue amount data, corrugated paper material, corrugated cardboard width, corrugating machine corrugation type, and corrugating machine speed as independent variables, use the warping degree of the corrugated paper block as the dependent variable, and process the independent variable data and the dependent variable data into feature data suitable for the gradient boosting decision tree algorithm.

[0088] Step S4. Input the temperature difference data, wrap angle data, and glue amount data as target tuning parameters into the warping degree prediction model for warping degree prediction. When the warping degree is optimal, record the optimal wrap angle and the optimal glue amount at this time. Among them, the closer the warping degree value is to 0, the better the warping degree.

[0089] Specifically, since a linear equation of two variables of temperature difference data and wrap angle has been constructed before, then, in step S4, the temperature difference data can be calculated according to each wrap angle data and input into the prediction model for parameter tuning to obtain the optimal warping degree.

[0090] Preferably, after inputting the target tuning parameters into the warping degree prediction model for warping degree prediction, the method further includes:

[0091] Use the predicted warping degree as the optimization index of the pruning algorithm to obtain the optimal warping degree.

[0092] Step S5. Send a set of optimal parameters including the optimal wrap angle and the optimal glue amount to the corrugated cardboard production system to obtain a corrugated paper block with the optimal warping degree, that is, the optimal process parameters can be used to produce corrugated cardboard to obtain a corrugated paper block with the optimal warping degree.

[0093] Based on the above - disclosed content, in this embodiment, by calculating the warping degree of the corrugated board and obtaining multiple process parameters of corrugated board production, taking the process parameters as independent variables and the warping degree as the dependent variable to train the gradient - boosting decision - tree algorithm, a warping - degree prediction model is generated; using the warping - degree prediction model for parameter tuning to obtain the optimal wrapping angle and the optimal glue amount, and finally using a set of optimal parameters including the optimal wrapping angle and the optimal glue amount to produce corrugated paper blocks with the optimal warping degree. That is, the present invention can adjust the production process parameters of the corrugated board based on the constructed warping - degree prediction model, and use a set of optimal parameters to produce corrugated boards with the optimal warping degree, realizing the automatic adjustment of the warping degree, without relying on human experience, improving the yield rate of corrugated board production and reducing the labor cost.

[0094] In a second aspect, the present invention provides a device for real - time improvement of corrugated board warping, including:

[0095] A warping - degree determination module, configured to obtain the point - cloud data of the corrugated board, perform curve fitting using the point - cloud data, and determine the warping degree of the corrugated paper block according to the curve curvature;

[0096] A parameter acquisition module, configured to obtain multiple process parameters of corrugated board production, where the process parameters at least include temperature difference data, wrapping angle data, and glue amount data;

[0097] A model training module, configured to take the multiple process parameters as independent variables and the warping degree of the corrugated paper block as the dependent variable, extract feature data, and use the feature data to train the gradient - boosting decision - tree algorithm to generate a warping - degree prediction model;

[0098] An optimal - parameter acquisition module, configured to input the temperature difference data, wrapping angle data, and glue amount data as target tuning parameters into the warping - degree prediction model for warping - degree prediction, and when the warping degree is optimal, record the optimal wrapping angle and the optimal glue amount at this time;

[0099] An optimal - parameter sending module, configured to send a set of optimal parameters including the optimal wrapping angle and the optimal glue amount to the corrugated board production system to obtain corrugated paper blocks with the optimal warping degree.

[0100] In a possible design, the warping - degree determination module is specifically configured to:

[0101] Receive the first point - cloud data of several corrugated boards, where the first point - cloud data is the cardboard image data at the board - output position of the corrugated board production line;

[0102] Extract multiple groups of second point - cloud data row - by - row from the first point - cloud data, where each group of the second point - cloud data corresponds to the cross - sectional data of one of the corrugated boards;

[0103] Determine the cutting points of the corrugated cardboard according to the data distribution state of the second point cloud data, and determine the third point cloud data corresponding to each corrugated paper block according to the cutting points;

[0104] Perform curve fitting on the third point cloud data, and determine the warping degree of each corrugated paper block according to the curve curvature.

[0105] In a possible design, when performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, the warping degree determination module is specifically used for:

[0106] Perform curve fitting on the third point cloud data using the least squares method, and calculate the curvature of the midpoint of the curve;

[0107] When the curvature value of the midpoint of the curve is larger, the warping degree of the corrugated paper block is larger; when the curvature value of the midpoint of the curve is smaller, the warping degree of the corrugated paper block is smaller.

[0108] In a possible design, when performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, the warping degree determination module is specifically used for:

[0109] Fit the third point cloud data into a circle, and calculate the curvature radius of the circle according to the cardboard width, the number of creases, and the height data of the cross-section of the corresponding corrugated paper block;

[0110] When the curvature radius value of the circle is larger, the warping degree of the corrugated paper block is smaller; when the curvature radius value of the circle is smaller, the warping degree of the corrugated paper block is larger.

[0111] In a possible design, the process parameters further include a preset corrugated cardboard material, corrugated cardboard width, corrugating machine type, and corrugating machine speed.

[0112] In a possible design, the temperature difference data is obtained by calculating the temperature difference between the paper inlet and the paper outlet of the preheating wheel, wherein the paper inlet temperature and the paper outlet temperature are collected by temperature sensors.

[0113] In a possible design, after calculating the temperature difference data, the parameter acquisition module is further used for:

[0114] Use multiple temperature difference data y and multiple wrap angle data x to construct a binary linear equation y = ax + b, and calculate the constant parameters a and b.

[0115] In a possible design, after inputting the target tuning parameter into the warping degree prediction model for warping degree prediction, the optimal parameter acquisition module is further used for:

[0116] The predicted warpage is used as an optimization index for the pruning algorithm to obtain the optimal warpage.

[0117] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect.

[0118] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect is executed.

[0119] In a fifth aspect, the present invention provides a computer program product containing instructions. When the instructions are run on a computer, the computer is made to execute the real-time warpage improvement method for corrugated cardboard as described in any possible design of the first aspect.

[0120] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A real-time improvement method for corrugated cardboard warping, characterized in that, Including: Obtain the point cloud data of the corrugated board, perform curve fitting using the point cloud data, and determine the warping degree of the corrugated paper block according to the curve curvature, including: receiving the first point cloud data of a plurality of corrugated boards, where the first point cloud data is the cardboard image data at the board outlet of the corrugated board production line; extracting multiple groups of second point cloud data row by row from the first point cloud data, where each group of the second point cloud data corresponds to the cross-sectional data of one corrugated board; determining the cutting points of the corrugated board according to the data distribution state of the second point cloud data, and determining the third point cloud data corresponding to each corrugated paper block according to the cutting points; performing curve fitting on the third point cloud data, and determining the warping degree of each corrugated paper block according to the curve curvature; Obtain multiple process parameters for corrugated board production, where the process parameters at least include temperature difference data, wrap angle data, and glue amount data; Use the multiple process parameters as independent variables and the warping degree of the corrugated paper block as the dependent variable to extract feature data, and use the feature data to train the gradient boosting decision tree algorithm to generate a warping degree prediction model; Input the temperature difference data, wrap angle data, and glue amount data as target tuning parameters into the warping degree prediction model for warping degree prediction. When the warping degree is optimal, record the optimal wrap angle and optimal glue amount at this time; Send a set of optimal parameters including the optimal wrap angle and optimal glue amount to the corrugated board production system to obtain corrugated paper blocks with the optimal warping degree.

2. The real-time improvement method for the warping of corrugated cardboard according to claim 1, wherein Performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, including: Performing curve fitting on the third point cloud data using the least squares method and calculating the curvature of the midpoint of the curve; When the curvature value of the curve midpoint is larger, the warping degree of the corrugated paper block is larger; when the curvature value of the curve midpoint is smaller, the warping degree of the corrugated paper block is smaller.

3. The real-time warping improvement method for corrugated cardboard according to claim 1, wherein Performing curve fitting on the third point cloud data and determining the warping degree of each corrugated paper block according to the curve curvature, including: Fitting the third point cloud data into a circle, and calculating the curvature radius of the circle according to the cardboard width, number of creases, and height data of the corresponding corrugated paper block cross-section; When the curvature radius value of the circle is larger, the warping degree of the corrugated paper block is smaller; when the curvature radius value of the circle is smaller, the warping degree of the corrugated paper block is larger.

4. The real-time warping improvement method for corrugated cardboard according to claim 1, wherein The process parameters further include the preset corrugated board material, corrugated board width, corrugator flute profile, and corrugator speed.

5. The real-time warping improvement method for corrugated cardboard according to claim 1, characterized in that, The temperature difference data is obtained by calculating the temperature difference between the paper inlet and paper outlet of the preheating wheel, where the paper inlet temperature and paper outlet temperature are collected by temperature sensors.

6. The real-time warping improvement method for corrugated cardboard according to claim 5, wherein, After calculating the temperature difference data, the method further includes: Constructing a binary linear equation y = ax + b using multiple temperature difference data y and multiple wrap angle data x, and calculating the constant parameters a and b.

7. The real-time warping improvement method for corrugated cardboard according to claim 1, wherein After inputting the target tuning parameters into the warping degree prediction model for warping degree prediction, the method further includes: Using the predicted warping degree as the optimization index of the pruning algorithm to obtain the optimal warping degree.

8. A real-time corrugated cardboard warping improvement device, characterized in that, Including: The warpage degree determination module is used to obtain the point cloud data of the corrugated cardboard, perform curve fitting using the point cloud data, and determine the warpage degree of the corrugated paper block according to the curve curvature, including: receiving the first point cloud data of a plurality of corrugated cardboard, wherein the first point cloud data is the cardboard image data at the paper outlet of the corrugated cardboard production line; extracting multiple groups of second point cloud data row by row from the first point cloud data, wherein each group of the second point cloud data corresponds to the cross-sectional data of one of the corrugated cardboard; determining the cutting points of the corrugated cardboard according to the data distribution state of the second point cloud data, and determining the third point cloud data corresponding to each corrugated paper block according to the cutting points; performing curve fitting on the third point cloud data, and determining the warpage degree of each corrugated paper block according to the curve curvature; The parameter acquisition module is used to obtain a plurality of process parameters for corrugated cardboard production, wherein the process parameters at least include temperature difference data, wrap angle data, and glue amount data; The model training module is used to use the plurality of process parameters as independent variables and the warpage degree of the corrugated paper block as the dependent variable, extract feature data, and train the gradient boosting decision tree algorithm using the feature data to generate a warpage degree prediction model; The optimal parameter acquisition module is used to input the temperature difference data, wrap angle data, and glue amount data as target tuning parameters into the warpage degree prediction model for warpage degree prediction, and record the optimal wrap angle and optimal glue amount at this time when the warpage degree is optimal; The optimal parameter sending module is used to send a set of optimal parameters including the optimal wrap angle and optimal glue amount to the corrugated cardboard production system to obtain corrugated paper blocks with the optimal warpage degree.

9. A computer device, characterized in that, It includes a memory, a processor, and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the real-time warpage improvement method for corrugated cardboard according to any one of claims 1-7.

Images