A low-gram-weight high-strength composite corrugated paperboard micropore structure defect detection method and system

Abstract

The present application provides a kind of low gram weight high-strength composite corrugated paperboard micropore structure defect detection method and system, the method comprises: the image data of corrugated paperboard micropore structure is collected, and the fused corrugated paperboard image set is constructed;Based on the fused corrugated paperboard image set, the micropore defect in paperboard is identified, and the paperboard micropore defect binary mask chart is obtained;Based on the paperboard micropore defect binary mask chart, spatial relationship analysis and structure reconstruction are carried out, and the structure diagram of connected defect region is constructed;Based on the structure diagram of connected defect region and geometric feature triplets, the influence of micropore defect on the mechanical properties of paperboard material is analyzed, and the residual strength of paperboard material under micropore defect is predicted;Based on the residual strength of paperboard material under micropore defect, micropore defect grade evaluation and grading control strategy are made.The present application realizes the detection and performance evaluation of corrugated paperboard micropore defect, constructs micropore defect grading control mechanism, and meets the quality control needs of green paperboard weight reduction and reinforcement.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of packaging material quality detection, and in particular to a low-grammage high-strength composite corrugated paperboard micro-hole structure defect detection method and system. BACKGROUND

[0002] Under the general trend of continuously promoting green low-carbon and high-strength performance material application in the packaging industry, low-grammage high-strength composite corrugated paperboard gradually replaces traditional packaging materials due to its lightweight, high cost-effectiveness, and excellent mechanical properties, and is widely used in many fields such as transportation, warehousing, and e-commerce logistics. The industry has higher requirements for the quality and performance of corrugated paperboard, especially under the background of the widespread use of micro-hole structure design to improve the overall mechanical performance of the material. How to accurately detect micro-hole structure defects and effectively evaluate the mechanical properties of the material has become a key technical bottleneck to ensure the reliability and safety of corrugated paperboard materials.

[0003] Chinese patent application with publication number CN119860983B provides a corrugated paperboard strength detection method and system. The method first obtains the stress data of the corrugated paperboard at each time under different pressing speed tests and the grayscale image of the corrugated side, analyzes the deformation of each corrugated in the grayscale image at each time in each pressing speed test process, obtains the structure damage degree of the corrugated paperboard in each pressing speed test, and extracts the stress peak value of the corrugated paperboard in each pressing speed test. Then, the structure damage degree and stress peak value of each pressing speed test are linearly fitted to obtain the true flat pressure strength of the corrugated paperboard.

[0004] However, the current technology still faces many challenges. At present, the packaging industry generally adopts the design idea of introducing micro-hole structure in the paperboard interlayer of composite corrugated paper to improve the overall mechanical properties of the material. By using microstructure morphology regulation, the stress is effectively dispersed and the impact energy is gradually absorbed, thereby enhancing the compression strength, stiffness, and deformation resistance. However, in actual production, due to the influence of multiple factors such as the uniformity of paper raw materials, the precision control of molding process, and environmental humidity, micro-hole structure is prone to defects such as hole collapse, oversized connected hole size, uneven pore distribution, and interlayer peeling. These subtle defects are usually hidden inside the paperboard or appear as slight structural disturbances, which are difficult to identify through traditional visual inspection methods and can easily become a key cause of structural failure in subsequent use. Especially under low-grammage design conditions, such microstructure defects will directly weaken the high-strength carrying capacity of the paperboard, which is contrary to the design goal of "lightweight and high strength", and seriously affects the stability and safety of the product in complex transportation and stacking scenarios.

[0005] In addition, on the automated high-speed pressing production line, the unit time output of paperboard is large, the rhythm is fast, and once the continuity structure defect occurs in the production process, it is extremely likely to form batch quality hidden trouble in a short time. If the defect is not discovered in time and misflows into the downstream packaging and circulation link, it is extremely likely to induce microstructure stress concentration under extreme working conditions such as moisture, high pressure and impact, and then cause paperboard collapse, packaging damage and other failure events, causing goods damage, logistics interruption, and even serious consequences such as personnel injury, which not only violates the sustainable development concept of green packaging, but also poses a major threat to the reputation and economic benefits of enterprises.

[0006] The existing mainstream quality detection means still relies on manual visual inspection and offline destructive testing, which has the obvious disadvantages of low detection efficiency, strong subjectivity and inability to realize real-time monitoring of the whole process. Especially in the face of high-throughput production tasks, microscopic defects are easy to be ignored, and quality hidden troubles are difficult to be checked in time. SUMMARY

[0007] In order to overcome the above-mentioned defects of the prior art, the present application provides a low grammage high-strength composite corrugated paperboard micro-pore structure defect detection method and system. The method first uniformly cuts, cleans and fixes the composite corrugated paperboard sample to obtain a standardized sample of the composite corrugated paperboard; then configures the microscope acquisition parameters, adopts a multi-focus microscopic imaging technology to collect images layer by layer at different focal heights; then adopts a maximum gray scale fusion algorithm to fuse the multi-focus composite corrugated paperboard images to construct a set of fused high-resolution composite corrugated paperboard images.

[0008] Then, based on the set of fused high-resolution paperboard images, gray scale normalization and denoising preprocessing are performed to obtain a second set of composite corrugated paperboard images; subsequently, a trained convolutional neural network model is used to predict the micro-pore defect prediction of the second set of composite corrugated paperboard images to generate a composite corrugated paperboard micro-pore defect probability map; according to the set threshold, each pixel defect probability value in the composite corrugated paperboard micro-pore defect probability map is converted into a binary mask to obtain a composite corrugated paperboard micro-pore defect binary mask map.

[0009] Further, based on the composite corrugated paperboard micro-pore defect binary mask map, a connectivity clustering analysis of the defect area is performed to identify all independent connected defect areas; and the area, perimeter, equivalent circle diameter and geometric center coordinates of each connected defect area are calculated; at the same time, according to the geometric features of the connected defect area and its defect geometric center set, a triangular subdivision algorithm is used to construct a structure diagram of the connected defect area.

[0010] Subsequently, based on the structural diagram and geometric feature triplet of the connected defect region, the weighted porosity of the paperboard material under microporous defects is calculated; the strength attenuation factor of the paperboard material under microporous defects is derived through a nonlinear model using the weighted porosity; combined with the initial strength of the paperboard material, the residual strength of the paperboard material under microporous defects is predicted, thereby realizing a quantitative assessment of the mechanical properties of the paperboard material caused by defects.

[0011] Finally, based on the remaining strength of the paperboard material under micropore defects, the micropore defects are classified into levels according to three preset strength grading thresholds. Combining the process experience rule base and machine learning prediction model, process adjustment schemes for different defect levels are automatically generated and integrated. The parameters of the process adjustment schemes are legally verified and necessary corrections are made. Finally, the final set of process parameter adjustment suggestions is output to guide the production site to make targeted adjustments to key process parameters such as spraying volume, pressing pressure, and drying temperature, thereby controlling the impact of defects and maintaining the stable quality of composite corrugated paperboard.

[0012] To achieve the above objectives, the present invention provides the following technical solution:

[0013] A method for detecting microporous structure defects in low-basis-weight, high-strength composite corrugated cardboard includes:

[0014] High-quality image data of the microporous structure in low-basis-weight, high-strength composite corrugated cardboard were collected, and a fused high-resolution image set of composite corrugated cardboard was constructed. ;

[0015] Based on the fused high-resolution composite corrugated cardboard image set Micropore defects in composite corrugated cardboard are identified, and a binary mask image of micropore defects in composite corrugated cardboard is obtained. ;

[0016] Binary mask image based on micropore defects of composite corrugated cardboard Spatial relationship analysis and structural reconstruction were performed to construct a structural diagram connecting the defective regions. ;

[0017] Structural diagram based on connected defect regions and geometric feature triples of connected defect regions This study analyzes the impact of micropore defects on the mechanical properties of paperboard materials and predicts the residual strength of paperboard materials with micropore defects. ;

[0018] Residual strength of paperboard materials based on micropore defects To conduct micropore defect level assessment and formulate graded control strategies.

[0019] Furthermore, the constructed fused high-resolution composite corrugated cardboard image set The steps include:

[0020] Preparation of a sample of the composite corrugated board, obtaining a standardized sample of the composite corrugated board ;

[0021] Based on the standardized sample of the composite corrugated board , configuring relevant parameters for microscope acquisition, completing microscopic imaging acquisition at different focal height, and obtaining a multi-focus composite corrugated board image ;

[0022] Based on the multi-focus composite corrugated board image , using a maximum gray scale fusion algorithm to construct a fused high-resolution composite corrugated board image set ;

[0023] The composite corrugated board sample includes but is not limited to paperboard batch number information for identifying different production batch samples; paperboard grammage for measuring the mass per unit area of the paperboard; forming process parameters including hot pressing temperature, pressing strength, forming time, and other key process control indicators.

[0024] Further, the step of obtaining a composite corrugated board micro-hole defect binary mask image includes:

[0025] Based on the fused high-resolution composite corrugated board image set , obtaining a second composite corrugated board image set ;

[0026] Based on the second composite corrugated board image set , using a convolutional neural network model to generate a composite corrugated board micro-hole defect probability map ;

[0027] Based on the composite corrugated board micro-hole defect probability map , performing threshold segmentation and binary defect region extraction to obtain a composite corrugated board micro-hole defect binary mask image ;

[0028] The threshold segmentation and binary defect region extraction are based on a preset threshold parameter, which discriminates the defect probability value of each pixel in the micro-hole defect probability map and performs binary processing.

[0029] Further, the step of spatial relationship analysis and structure reconstruction includes:

[0030] Based on the composite corrugated board micro-hole defect binary mask image , performing defect region spatial connectivity clustering analysis to extract a set of all independent connected defect sub-regions ;

[0031] based on the set of all independent connected defect sub-regions , quantitative analysis of geometric features and extraction of defect geometric center coordinates are performed to construct geometric feature triplets of connected defect regions and a set of defect geometric centers ;

[0032] based on the geometric features of the connected defect regions and the set of defect geometric centers , a structure diagram of the connected defect regions is constructed .

[0033] Further, the spatial connectivity clustering analysis of the defect regions uses the 8-neighbor connectivity rule to judge the connectivity of all foreground pixels (pixel value is 1) in the binary mask image of the composite corrugated paperboard micro-hole defects ;

[0034] The 8-neighbor connectivity judgment specifically includes: if a foreground pixel and any one of its adjacent upper, lower, left, right four basic direction neighbor pixels, or left upper, right upper, left lower, right lower four diagonal direction neighbor pixels is also a foreground pixel, then the two are regarded as the same connected region.

[0035] Further, the steps of constructing geometric feature triplets of connected defect regions and a set of defect geometric centers include:

[0036] traverse each defect sub-region in the set of all independent connected defect sub-regions in turn , and calculate the geometric features of each defect sub-region respectively;

[0037] based on the geometric features, construct a geometric feature triplet of a connected defect region and a set of defect geometric centers .

[0038] Further, the step of calculating the geometric features includes:

[0039] count the total number of all foreground pixels in each connected defect sub-region , calculate the area of each connected defect sub-region , and after the image is spatially calibrated, based on the area of each connected defect sub-region , the corresponding actual physical area of each connected defect sub-region is converted ;

[0040] ​A boundary extraction algorithm is used to extract each connected defect sub-region. set of boundary pixels The perimeter of each connected defect sub-region is calculated by accumulating the Euclidean distances between adjacent boundary points. ;

[0041] Each defect region is approximated as an ideal circular region of equal area, and the equivalent circle diameter of each connected defect sub-region is calculated accordingly. ;

[0042] Based on each connectivity defect sub-region Foreground pixels are analyzed, and the average of the x and y coordinates of each foreground pixel is calculated. The geometric center coordinates of each connected defect sub-region are then extracted. .

[0043] Furthermore, the structural diagram for constructing the connected defect region... The steps include:

[0044] Based on each connectivity defect sub-region Geometric center coordinates Each node is considered a node in the structural graph, and each graph node is bound to a corresponding geometric feature triple as a node attribute, thus forming a graph node. Construct a complete set of graph nodes. ;

[0045] Based on graph node set Coordinates of each geometric center The Delaunay triangulation algorithm is used to establish the connection relationship. If any two nodes... center point , If two elements are adjacent in the Delaunay grid, an undirected edge is created. Construct a complete graph edge set ;

[0046] Based on the Delaunay triangulation algorithm, any three nodes that are connected pairwise by edges... It can form a sheet Construct a complete set of facets ;

[0047] Graph-based node sets Edge set and noodle sets Construct a structural diagram connecting the defective regions. .

[0048] Furthermore, the residual strength of the paperboard material under predicted microporous defects... The step of calculating the weighted porosity of the paperboard material under the micro-hole defect comprises:

[0049] The geometric feature triplet of the connected defect region ;

[0050] The weighted porosity of the paperboard material , based on the weighted porosity of the paperboard material under the micro-hole defect ;

[0051] The strength attenuation factor of the paperboard material under the micro-hole defect , based on the weighted porosity of the paperboard material under the micro-hole defect ;

[0052] The strength attenuation factor of the paperboard material under the micro-hole defect is mapped to the strength attenuation factor of the paperboard material under the corresponding micro-hole defect , and a fitting parameter and are introduced, a nonlinear function relationship reflecting the influence of the defect on the material strength is constructed in combination with the Mohr-Coulomb empirical model;

[0053] The residual strength of the paperboard material under the micro-hole defect is predicted by multiplying the strength attenuation factor of the paperboard material under the micro-hole defect and the initial strength of the paperboard material .

[0054] Further, the step of calculating the weighted porosity of the paperboard material under the micro-hole defect comprises:

[0055] The physical area of all connected defect sub-regions in the geometric feature triplet of the connected defect region is accumulated and divided by the total detection area to obtain the unweighted porosity of the paperboard material ;

[0056] The node connectivity in the structure diagram of the connected defect region is introduced to structureally weight the physical area of each connected defect sub-region to obtain the weighted porosity of the paperboard material .

[0057] Further, the micro-hole defect level evaluation and grading control strategy making comprises:

[0058] ​​​​Remaining strength of paperboard material under micro-hole defect , micro-hole defect grading is performed to construct the quality grade of the composite corrugated paperboard ;

[0059] Based on the quality grade of the composite corrugated paperboard , the process adjustment scheme is fused with the process experience rule base and the machine learning prediction model, the process adjustment suggestion is corrected, and the final process parameter adjustment suggestion set is constructed ;

[0060] Further, the micro-hole defect grading includes:

[0061] Three strength grading thresholds are preset , and , satisfying the relationship ;

[0062] If the remaining strength of the paperboard material under the micro-hole defect is greater than or equal to , the quality grade of the composite corrugated paperboard is divided into , wherein indicates that the material strength of the composite corrugated paperboard is excellent, the defect impact is negligible, and the process parameters can be maintained as they are;

[0063] If the remaining strength of the paperboard material under the micro-hole defect is greater than or equal to and less than , the quality grade of the composite corrugated paperboard is divided into , wherein indicates that the material of the composite corrugated paperboard is qualified but there is a slight strength decrease, which can be compensated by small amplitude optimization of process parameters (such as pressure, temperature, glue ratio, etc.);

[0064] If the remaining strength of the paperboard material under the micro-hole defect is greater than or equal to and less than , the quality grade of the composite corrugated paperboard is divided into , wherein indicates that the material of the composite corrugated paperboard has obvious strength decrease, and it is suggested to adjust the key process parameters to improve the structural stability;

[0065] If the remaining strength of the paperboard material under the micro-hole defect is less than , the quality grade of the composite corrugated paperboard is divided into , wherein indicates that the material of the composite corrugated paperboard has serious defects or has exceeded the safe range of use, and it is suggested to be scrapped or to be subjected to major optimization adjustment of the process route.

[0066] Furthermore, the construction of the final process parameter adjustment suggestion set The steps include:

[0067] Quality grades based on composite corrugated cardboard Analyze the current quality grade information and determine the process adjustment goals accordingly: If the quality grade of the composite corrugated cardboard is... This indicates the residual strength of the paperboard material under microporous defects. If the quality grade of the composite corrugated cardboard is within the excellent range, no adjustment is needed, and the system will maintain the current process settings; or This indicates the residual strength of the paperboard material under microporous defects. If the strength is slightly or moderately low, the system needs to adjust the process parameters to restore the strength level; if the quality grade of the composite corrugated cardboard is... This indicates the residual strength of the paperboard material under microporous defects. If there is a serious deficiency, the system will initiate a severe repair process and simultaneously trigger a manual review prompt or a pause mechanism to prevent the continuous output of substandard products.

[0068] According to the quality grade of composite corrugated cardboard The process parameter suggestion set for the corresponding level is retrieved from the pre-set process experience rule base to obtain the process parameter suggestion set of the process experience rule base. ;

[0069] The currently detected parameters are input into a trained machine learning model for prediction, and the output is a set of process parameter suggestions predicted by the machine learning model. ;

[0070] The set of process parameter recommendations in the computational process experience rule base Recommended set of process parameters based on machine learning predictions The deviation between the two ;

[0071] Based on a preset tolerance threshold and relative deviation Compare and execute different fusion strategies: if the relative deviation Less than This indicates the recommended value of the empirical rule. Compared with machine learning predictions relative deviation rate between Within the tolerance threshold range, a simple average value is used; if the relative deviation... Greater than This indicates the recommended value of the empirical rule. Compared with machine learning predictions relative deviation rate between larger, the fused process parameter suggestion value is obtained by confidence weighting fusion ;

[0072] checking the fused process parameter suggestion value whether it falls into the equipment control allowable interval , if the fused process parameter suggestion value is out of the equipment control allowable interval , a correction operation needs to be performed to obtain a corrected process parameter ;

[0073] based on the corrected process parameter , a final process parameter adjustment suggestion set is constructed ;

[0074] The equipment control allowable interval is obtained by comprehensively setting the equipment specifications, process technology standards, quality safety constraints, historical experience data statistics and expert process threshold.

[0075] A low-grammage high-strength composite corrugated paperboard micro-hole structure defect detection system for implementing the above-mentioned low-grammage high-strength composite corrugated paperboard micro-hole structure defect detection method, the system comprises:

[0076] A high-resolution composite corrugated paperboard image construction module for collecting high-quality image data of the micro-hole structure in the low-grammage high-strength composite corrugated paperboard, and constructing a fused high-resolution composite corrugated paperboard face sheet set ;

[0077] A composite corrugated paperboard micro-hole defect recognition module for recognizing micro-hole defects in the composite corrugated paperboard based on the fused high-resolution composite corrugated paperboard face sheet set , to obtain a composite corrugated paperboard micro-hole defect binary mask image ;

[0078] A composite corrugated paperboard micro-hole defect spatial relationship analysis and structure reconstruction module for performing spatial relationship analysis and structure reconstruction based on the composite corrugated paperboard micro-hole defect binary mask image , to construct a structure graph of connected defect regions ;

[0079] A micro-hole defect mechanical property prediction module for analyzing the influence of the micro-hole defect on the mechanical properties of the paperboard material based on the structure graph of the connected defect regions and the geometric feature triplets of the connected defect regions , to predict the residual strength of the paperboard material under the micro-hole defect ;

[0080] Micro-hole defect grade evaluation and process adjustment module based on residual strength of paperboard material with micro-hole defects Micro-hole defect grade evaluation and grading control strategy making are performed.

[0081] Compared with the prior art, the present application has the following beneficial effects:

[0082] The low-grammage high-strength composite corrugated paperboard micro-hole structure defect detection method and system of the present application first standardizes the pretreatment of the low-grammage high-strength composite corrugated paperboard sample, including cutting to a uniform size, cleaning the surface and cross-section, and fixing the sample position, to ensure that the sample size is consistent, there is no surface impurity, and the posture is stable during imaging; on this basis, using industrial multi-focus microscopic imaging technology, according to the preset microscope acquisition parameters, the paperboard micro-hole structure images are collected layer by layer at different focal levels to obtain multi-focus composite corrugated paperboard images; then, using the maximum gray scale fusion algorithm, the pixel gray scale values of the images at each focal level are taken maximum point by point to construct a fused high-resolution composite corrugated paperboard face sheet set. This step solves the problem of focal point misplacement caused by uneven micro-hole distribution in the thickness direction of the paperboard, significantly reduces the difficulty of micro-hole edge recognition caused by single-layer image blur or surface fiber impurity shielding, especially in the micro-hole structure area with small aperture, shallow depth or mixed in the fibers, the accurate presentation of the complete boundary can be realized, ensuring the accurate extraction of the number, size and boundary profile of the micro-holes in the subsequent defect recognition process, providing a high-fidelity image basis for material structure integrity analysis and strength calculation.

[0083] Then, based on the fused high-resolution composite corrugated paperboard face sheet set, first, the image is preprocessed through gray scale normalization and two-dimensional Gaussian filtering to enhance the image contrast, smooth the background and suppress random noise generated in the imaging process, obtaining a clearer second composite corrugated paperboard face sheet set; then, the trained convolutional neural network model is used to infer the second composite corrugated paperboard face sheet set, generating a micro-hole defect probability value corresponding to each pixel, thereby quantifying the position and range of the micro-hole defect in the image; finally, the composite corrugated paperboard micro-hole defect probability map is subjected to threshold segmentation operation, extracting the area with probability value higher than the set threshold and performing binaryzation processing, outputting the composite corrugated paperboard micro-hole defect binary mask map, realizing the automatic accurate positioning and area division of the micro-hole defect. This step eliminates the interference of uneven illumination, gray scale drift and microscopic particle noise in the collected image, ensuring the stability of the image quality input to the subsequent defect recognition model; further, the model inference replaces manual naked eye recognition, eliminating the visual omission and unclear boundary division caused by the small size of the micro-hole, the insignificant color difference or the dense distribution in traditional manual detection; at the same time, through the probability map and threshold segmentation, the continuity and integrity of the micro-hole boundary extraction are ensured, especially in the edge fuzzy or adjacent structure complex area.

[0084] Then, based on the composite corrugated board micro-hole defect binary mask image, all independent defect connected regions are identified by spatial connectivity clustering analysis, and then the geometric feature quantitative analysis is carried out on each connected region to calculate the parameters such as area, perimeter, equivalent circle diameter and geometric center coordinates. Finally, taking the defect geometric center of the connected defect region as the node in the graph structure, combining the corresponding geometric features, the structure graph of the connected defect region is constructed by using the Delaunay triangulation algorithm, and the structured modeling of the micro-hole defect is realized. This step realizes the conversion of the scattered and various micro-hole defects from the pixel-level binary image to the graph structure representation with spatial relationship and geometric information, and solves the problem that the mutual position relationship and morphological characteristics of the defect group are difficult to accurately describe in the traditional defect detection.

[0085] Further, based on the connected defect region structure graph and geometric feature triplets, the influence of micro-hole defects on the mechanical properties of paperboard material is analyzed, and the residual strength of paperboard material under micro-hole defects is predicted. First, the unweighted porosity of the paperboard material is calculated by accumulating the physical area of all connected defect sub-regions and combining the total detection area. Then, the weighted porosity reflecting the intensity of defect distribution is obtained by introducing the node connectivity of each defect region in the structure graph as the weight. Subsequently, based on the weighted porosity of the paperboard material and combined with the empirical model, the strength attenuation factor of the paperboard material under micro-hole defects is calculated, and the weakening degree of the defect on the strength of the paperboard material is quantitatively evaluated. Finally, according to the strength attenuation factor of the paperboard material under micro-hole defects and the initial strength of the paperboard material, the residual strength of the paperboard material under micro-hole defects is calculated, and the prediction and evaluation of the carrying capacity of the composite corrugated paperboard in the actual service condition are realized. This step solves the problem that the traditional method cannot effectively associate the defect distribution characteristics with the mechanical properties, especially suitable for online quality monitoring or product sampling scenarios, and early warning of local micro-defects significantly affecting the compressive strength of the material, so as to timely screen out potential failure products and reduce the risk of batch structure damage caused by local damage in stacking and transportation. Finally, based on the residual strength of the paperboard material under micro-hole defects, the mechanical properties of the composite corrugated paperboard are classified into different quality grades, and the composite corrugated paperboard is divided into different quality grades by setting three strength grading thresholds, and the specific influence degree of defects of different degrees on the carrying capacity of the paperboard material is clear. Then, according to the quality grade of the composite corrugated paperboard, the corresponding process parameter adjustment scheme is retrieved from the process experience rule base and the machine learning prediction model, including key process parameters such as shotcrete amount, pressing pressure, drying temperature, adhesive addition ratio and paper machine line speed, and the deviation analysis of the two is carried out to optimize and ensure that the adjustment suggestion takes into account long-term stability and real-time adaptability. Then, the legal verification and necessary correction of the fused process parameter suggestion value are performed to ensure that all the control parameters meet the operating range allowed by the equipment. Finally, the final process parameter adjustment suggestion set is output to guide the production line to dynamically adjust the key process flow according to different defect grades, such as increasing the shotcrete amount and reducing the paper machine line speed in the low-strength grade sample corresponding batch, to improve the fiber bonding strength and prolong the adhesive reaction time. This step effectively suppresses the strength decline of the material caused by micro-hole defects, avoids the flow of inferior products, reduces the frequency of low-strength paperboard batches from the source, and realizes quality closed-loop control and process precise optimization in the production process. BRIEF DESCRIPTION OF DRAWINGS

[0086] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, brief descriptions will be given to the drawings needed to be used in the embodiments or prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any inventive work.

[0087] Figure 1 is a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method principle flow chart of the application;

[0088] Figure 2 is a method flow chart of constructing a fused high-resolution composite corrugated paperboard face sheet set in a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method of the application;

[0089] Figure 3 is a method flow chart of obtaining a composite corrugated paperboard micro-pore defect binary mask map in a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method of the application;

[0090] Figure 4 is a method flow chart of constructing a structure map of connected defect regions in a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method of the application;

[0091] Figure 5 is a method flow chart of predicting the residual strength of the paperboard material under the micro-pore defect in a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method of the application;

[0092] Figure 6 is a method flow chart of performing micro-pore defect grade evaluation and grading control strategy formulation in a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method of the application;

[0093] Figure 7 is a functional module diagram of a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection system of the application. DETAILED DESCRIPTION

[0094] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the application.

[0095] Embodiment 1

[0096] Please refer to Figure 1 The embodiment provides a low gram weight high strength composite corrugated paperboard micro-pore structure defect detection method, which comprises the following steps:

[0097] Step S1000, high-quality image data of the micro-pore structure in the low gram weight high strength composite corrugated paperboard is collected, and a fused high-resolution composite corrugated paperboard face sheet set is constructed .

[0098] Specifically, this step aims to acquire high-quality image data of the microporous structure in low-grammage, high-strength composite corrugated cardboard through standardized sample preprocessing and industrial-grade multifocal microscopy imaging technology, providing a stable and reliable visual information basis for subsequent microporous defect analysis and structural design.

[0099] Furthermore, such as Figure 2 As shown, step S1000 includes:

[0100] Step S1100: Preparation of composite corrugated cardboard samples, obtaining standardized samples of composite corrugated cardboard. .

[0101] In the specific implementation process, the first step is to obtain the parameter set of the composite corrugated cardboard sample, denoted as: .in, (in ) indicates the first Key structural and process attribute information of a composite corrugated cardboard sample, including but not limited to: cardboard batch number information, used to identify different production batches of samples; cardboard basis weight (unit: g / m²), used to measure the mass of cardboard per unit area, affecting material thickness and strength; molding process parameters, including key process control indicators such as hot pressing temperature, pressure intensity, and molding time. This indicates the total number of composite corrugated cardboard samples that need to be collected.

[0102] Next, based on the composite corrugated cardboard sample parameter set A standardized pretreatment process is performed on cardboard samples of different batches and weights, specifically including but not limited to the following steps: First, cutting: the original composite corrugated cardboard samples are cut to predetermined dimensions to ensure that the cross-sectional area of ​​the sample is representative and that the size is suitable for the clamping platform of the microscopic imaging equipment; Second, surface cleaning: the sample surface and cross-section are cleaned with a lint-free cloth and appropriate solvent to remove dust, fiber debris, or other adhering impurities to improve image clarity during imaging; Third, fixing and clamping: the processed cardboard samples are securely mounted on the platform of the microscopic imaging device to ensure that the posture remains stable during imaging and to avoid image blurring or structural displacement. After the above series of processing operations (cutting, cleaning, and fixing), standardized samples of composite corrugated cardboard are obtained. Standardized sample of the composite corrugated cardboard. It has the following three advantages: First, the size specifications are consistent and meet the clamping accuracy requirements of microscopic imaging equipment; second, the surface and cross-section are clean and free from contamination and obstruction by impurities; third, it is stable and prevents sample movement or tilting.

[0103] Finally, standardized samples of composite corrugated cardboard were prepared. The processing parameters and state parameters of the standardization sample of the corrugated paperboard form structured data for recording, facilitating subsequent tracing and automatic management, and the specific expression form is as follows:

[0104]

[0105] Each of the standardization samples of the corrugated paperboard includes a plurality of image layers. The image layers are represented by the formula: (i = 1, 2, 3, …, n) where i represents the image layer number, and n represents the total number of image layers. The pre-processed standardization sample includes the cutting size (length, width, and thickness), the cleaning state identifier (such as the cleanliness level), and the fixation method and stability indicator (clamping strength, position deviation, etc.). The image layers are represented by the formula: (i = 1, 2, 3, …, n) where i represents the image layer number, and n represents the total number of image layers.

[0106] Step S1200, based on the standardization sample of the corrugated paperboard , configuring the relevant parameters of the microscope for image acquisition, and completing microscopic imaging acquisition at different focal heights to obtain a multi-focal corrugated paperboard image .

[0107] In the specific implementation process, first, the core parameters of the microscopic imaging equipment are automatically configured, including the starting focal position (the height at which the first focal layer of the microscope lens is aligned with the sample), the focal step distance (the fixed distance by which the lens moves vertically each time), and the number of focal layers (the number of different focal layers into which the corrugated paperboard sample is divided in the vertical direction for imaging, used to obtain image data for different depth-of-field regions layer by layer), the total depth-of-field range (the physical distance spanned from the first image focal point to the last image focal point), and the focal height of the i-th layer (the focal depth at which the lens moves vertically from the initial position , representing the focal position at which the i-th image is captured), and the specific process formula is as follows:

[0108]

[0109]

[0110] wherein, i represents the image layer number, and n represents the total number of image layers. The image layers are represented by the formula: (i = 1, 2, 3, …, n) where i represents the image layer number, and n represents the total number of image layers.

[0111] After the above core parameter configuration is completed, based on each standardization sample of the corrugated paperboard, an image is collected at each set focal height , and the specific process formula is as follows:

[0112] ​

[0113] in, Indicates the first A standardized sample of composite corrugated cardboard At focal length Images collected at the location; This indicates an image acquisition operation used to acquire images at a specified sample and focal length height. The index representing the standardized sample image of composite corrugated cardboard, i.e., the index of the currently acquired composite corrugated cardboard image; This indicates the image layer number, which is the focal layer corresponding to the currently acquired composite corrugated cardboard image.

[0114] Ultimately, based on each For each composite corrugated cardboard image, construct its corresponding multifocal composite corrugated cardboard image, denoted as . Each of them (in ; ) indicates the first A standardized sample of composite corrugated cardboard. A collection of multifocal facets, Indicates the first A standardized sample of composite corrugated cardboard was taken at the first... The focal layer corresponding to the image of the composite corrugated cardboard.

[0115] For example, taking the photograph of a composite corrugated cardboard sample as an example, the starting focus position is set. Focal length step spacing and focal length layer The focal length height of the first layer Second layer focal length height And so on. Final total depth of field That is, the position of the microscope lens from its initial focal point. Starting from [the beginning], a total of 6 images with different focal layers were acquired in the vertical direction, comprehensively covering the microporous structure of the composite corrugated cardboard in the thickness direction. The vertical depth area. Simultaneously, multi-focus composite corrugated cardboard images. ,image The focus is on ,image The focus is on And so on. In the above multifocal composite corrugated cardboard images, each image focuses on the microporous structure of the cardboard sample at a certain focal depth.

[0116] Step S1300, based on the multi-focus composite corrugated cardboard image , the maximum gray scale fusion algorithm is adopted to construct a fused high-resolution corrugated paperboard surface sheet set .

[0117] In the specific implementation process, in order to obtain an image with optimal clarity and pore structure details, the maximum gray scale fusion algorithm is adopted to process the multi-focus corrugated paperboard image . The algorithm realizes the fusion of multi-layer focus information by selecting the maximum gray scale value in each pixel position in the multi-focus layer, and the specific process formula is as follows:

[0118]

[0119] Among them, represents the th fused corrugated paperboard image; represents the pixel position coordinate in the image, which is distributed to the horizontal and vertical pixel positions; represents the th fused high-resolution image of the corrugated paperboard image sample in the pixel position ; represents the maximum value operator; represents the th standard sample of the corrugated paperboard in the th corrugated paperboard image corresponding to the focus position gray value; represents the paperboard sample index number, and there are paperboard samples in total; represents the focal length layer index number, and there are images of different focal length layers in total.

[0120] Finally, based on each fused corrugated paperboard image, a fused high-resolution corrugated paperboard surface sheet set is constructed.

[0121] Step S2000, based on the fused high-resolution corrugated paperboard surface sheet set , the micro-hole defects in the corrugated paperboard are identified, and a corrugated paperboard micro-hole defect binary mask image is obtained.

[0122] Specifically, this step aims to automatically identify the defect area of the fused high-resolution corrugated paperboard surface sheet set constructed in step S1300, and output a binary defect image , which can be used for subsequent statistical analysis and structure evaluation.

[0123] Further, as Figure 3As shown, step S2000 includes:

[0124] Step S2100, based on the fused high-resolution composite corrugated paper board face piece set , a second composite corrugated paper board face piece set is obtained .

[0125] Specifically, this step mainly pre-processes the fused high-resolution composite corrugated paper board face piece set , aiming to improve image quality and provide more stable and high-quality input for subsequent deep learning models. The preprocessing process includes two sub-processes of gray scale normalization and noise removal filtering.

[0126] In the specific implementation process, first, the fused high-resolution composite corrugated paper board face piece set is subjected to gray scale normalization processing, linearly mapping its image pixel gray scale value from to the interval to obtain a first composite corrugated paper board face piece set , and the specific process formula is as follows:

[0127]

[0128] wherein represents the gray scale value of the normalized paper board face piece set at pixel point , and the pixel gray scale value ranges from ; represents the gray scale value of the fused high-resolution composite corrugated paper board face piece set at pixel point , and the pixel gray scale value ranges from .

[0129] Subsequently, based on the normalized first composite corrugated paper board face piece set , a two-dimensional Gaussian filter is used for noise suppression and image smoothing processing to obtain a second composite corrugated paper board face piece set , to remove high-frequency noise (such as salt and pepper noise, acquisition interference, etc.) in the image while preserving the edge structure of the image as much as possible. The specific process formula is as follows:

[0130]

[0131]

[0132] wherein represents the gray scale value of the Gaussian filter de-noised paper board face piece set at pixel point ; represents a two-dimensional Gaussian kernel function, which is used to take pixel point as the center and perform weighted average on the surrounding neighborhood. denotes a convolution operator; denotes the standard deviation of the Gaussian kernel, controlling the spread and smoothness of the kernel function; denotes the natural exponential function, used to realize the Gaussian decay property.

[0133] Step S2200, based on the second composite corrugated paper sheet set , using the convolutional neural network model U-Net, a composite corrugated paper micro-hole defect probability map is generated.

[0134] In the specific implementation process, the trained convolutional neural network model U-Net is used to perform inference operation on the second composite corrugated paper sheet set to generate the corresponding composite corrugated paper defect probability map . The probability map gives each pixel position in the image a defect probability value while keeping the resolution consistent with the input image, which is used to quantify the possibility of the pixel belonging to the micro-hole structure defect area, and provides a probability basis for the subsequent defect area accurate extraction. The specific process formula is as follows:

[0135]

[0136] wherein, denotes the composite corrugated paper micro-hole defect probability map, each pixel value is the defect probability value at the pixel position , with a value range of , and denote the height and width of the defect probability map, respectively; denotes the trained convolutional neural network model U-Net, which is composed of an encoder, a decoder and an activation function; denotes the parameter set of the network model, including convolution kernel weights, bias terms, etc., which is learned from the model training stage; denotes the Sigmoid activation function, which is used to limit the network output to the interval to realize probability normalization; denotes the decoder function, which contains deconvolution or upsampling and skip connection structure, used to gradually restore the spatial resolution; denotes the encoder function, which is composed of multiple layers of convolution and pooling, and extracts multi-scale semantic features of the image.

[0137] Step S2300, based on the composite corrugated paper micro-hole defect probability map , threshold segmentation and binary defect area extraction are performed to obtain a composite corrugated paper micro-hole defect binary mask map .

[0138] In the implementation process, based on the composite corrugated paper micro-hole defect probability map generated in step S2200 , a suitable threshold parameter is set , the defect probability value of each pixel in the micro-hole defect probability map is discriminated, and binary processing is performed accordingly to obtain a composite corrugated paper micro-hole defect binary mask map , which provides a basis for subsequent micro-hole defect morphology analysis. The specific process formula is as follows:

[0139]

[0140] , wherein represents the composite corrugated paper micro-hole defect binary mask map, that is, the pixel value 1 in the map represents that the pixel is judged as a defect area, and the pixel value 0 represents that the pixel belongs to a normal area; represents the probability value of the corresponding pixel in the composite corrugated paper micro-hole defect probability map; represents the threshold parameter, which is used as the decision boundary for defect judgment, and its value can be adjusted and optimized on the validation set according to experimental data, actual detection requirements and model performance, taking into account the sensitivity and accuracy of defect detection.

[0141] Step S3000, based on the composite corrugated paper micro-hole defect binary mask map , spatial relationship analysis and structure reconstruction are performed to construct a structure map of connected defect regions .

[0142] Specifically, this step aims to perform spatial relationship analysis and structure reconstruction on the composite corrugated paper micro-hole defect binary mask map extracted in step S2300, and sequentially complete the identification, geometric feature quantization and structure modeling based on the features of the composite corrugated paper micro-hole defect connected region. The output can be used for composite corrugated paper micro-hole defect morphology modeling, virtual material reconstruction and structure reliability evaluation.

[0143] Further, as shown in Figure 4 , step S3000 includes:

[0144] Step S3100, based on the composite corrugated paper micro-hole defect binary mask map , spatial connectivity clustering analysis of the defect region is performed to extract a set of all independent connected defect sub-regions .

[0145] Specifically, this step aims to perform spatial relationship analysis and structure reconstruction on the composite corrugated paper micro-hole defect binary mask map All the "foreground" pixels (i.e. the region with pixel value of 1, indicating potential defect region) in the image are subjected to spatial connectivity clustering analysis to identify all the defect regions in the image that are spatially independent of each other, i.e. connected components, laying the foundation for subsequent defect region morphological feature extraction and accurate analysis.

[0146] In the specific implementation process, the connectivity judgment criterion is 8-neighbor connectivity. That is, if a foreground pixel and any one of its adjacent upper, lower, left, right four basic direction neighborhood pixels, or left upper, right upper, left lower, right lower four diagonal direction neighborhood pixels is also a foreground pixel (pixel value is 1), then the two are regarded as the same connected region.

[0147] After the above analysis, the set of all independent connected defect sub-regions is extracted , and the specific expression formula is as follows:

[0148]

[0149] Among them, represents the set of all independent connected defect sub-regions; represents the total number of connected defect sub-regions detected; represents the connected defect sub-region, which contains a set of pixel coordinates connected thereto, i.e. ; represents the pixel point in the connected defect sub-region , and represents the horizontal coordinate (column index), represents the vertical coordinate (row index); represents the total number of pixels in the connected region, i.e. the number of pixel points contained in .

[0150] For example, taking a composite corrugated board defect image as an example, assuming that the set of all independent connected defect sub-regions extracted is , four connected defect sub-regions are extracted, which are specifically: connected region is located at the top left corner of the image, showing an "L" shape structure; connected region is distributed in the middle right of the image, showing a vertical line segment shape; connected region forms a compact square region; and connected region is located at the bottom left of the image, showing a horizontal band distribution.

[0151] Step S3200, based on the set of all independent connected defect sub-regions , quantitative analysis of geometric features and extraction of defect geometric center coordinates are performed to construct the geometric feature triplets of connected defect regions and the set of defect geometric centers .

[0152] Specifically, this step aims to perform quantitative analysis of geometric dimensions based on each connected defect sub-region extracted in step S3100 , calculate its core geometric parameters including pixel area, boundary perimeter, and equivalent circular aperture, etc., and construct the resulting defect geometric feature set to provide quantitative basis for subsequent defect recognition, severity discrimination, and quality evaluation.

[0153] In the specific implementation process, each defect sub-region in the set of all independent connected defect sub-regions is traversed in turn , and the following geometric feature calculations are performed for each defect sub-region

[0154] : First, area calculation. The total number of all foreground pixel points in each connected defect sub-region is counted to obtain the area of the th connected defect sub-region , and the specific expression formula is as follows:

[0155]

[0156] wherein represents the area of the th connected defect sub-region, which is the area of the defect sub-region calculated in pixels, with the unit of square pixels.

[0157] If the image has undergone spatial calibration processing, the area of the th connected defect sub-region can be further converted into the actual physical area of the th connected defect sub-region to facilitate size evaluation consistent with the actual standard, and the specific process formula is as follows:

[0158]

[0159] wherein represents the physical area of the th connected defect sub-region, which is the area after conversion to actual physical dimensions, with the unit of square millimeters. This represents the conversion factor for the physical size of a pixel, i.e., the side length represented by each pixel in the actual physical size, in millimeters per pixel.

[0160] Secondly, perimeter extraction. A boundary extraction algorithm (such as the findContours method in OpenCV) is used to extract each connected defect sub-region. set of boundary pixels , and then calculate the first Perimeter of each connected defect subregion The specific process formula is as follows:

[0161]

[0162] in, Indicates the first A connected defect sub-region The set of boundary points; Indicates the first A connected defect sub-region The number of boundary points; Represents the set of boundary points The first in The coordinates of each boundary pixel point Represents the x-coordinate (column index). Represents the vertical axis (row index); Indicates the first Perimeter estimates of each connected defective sub-region, in pixels; Indicates from the boundary point arrive Euclidean distance.

[0163] Third, calculation of the equivalent circle diameter. Each defect region is approximated as an ideal circular region of equal area, and its equivalent circle diameter is calculated. The specific process formula is as follows:

[0164]

[0165] Fourth, geometric center coordinate extraction. Based on each connected defect sub-region. The geometric center coordinates of the foreground pixels are extracted using the following formula:

[0166]

[0167] in, Indicates the first A connected defect sub-region The geometric center coordinates; Indicates the first A connected defect sub-region The number of pixels in the image; Indicates the first A connected defect sub-region The index of the pixel, ranging from ; Indicates the first A connected defect sub-region The The x-coordinate (column index) of each pixel; Indicates the first A connected defect sub-region The The ordinate (row index) of each pixel.

[0168] Finally, based on the above geometric features, a geometric feature triplet for a connected defect region is constructed. and the set of defect geometric centers The specific formula is as follows:

[0169]

[0170]

[0171] in, Indicates the first The physical area of ​​each connected defective sub-region; Indicates the first The perimeter of a connected defective sub-region; Indicates the first The equivalent circle diameter of a connected defect sub-region; Indicates the first A connected defect sub-region The geometric center coordinates; This represents the total number of detected connected defect sub-regions.

[0172] Step S3300, based on the geometric features of the connected defect region and its defect geometric center set Construct a structural diagram connecting the defective regions. .

[0173] Specifically, this step aims to leverage the geometric features of the connected defect region. and its defect geometric center set Based on the geometric feature information of each defect region, a structural diagram that can quantify the spatial layout and topological structure of defects is established. .

[0174] In the specific implementation process, the structure diagram of the connected defect region The construction includes the following three steps:

[0175] First, the construction of the graph node set. This begins with each connected defect sub-region... Geometric center coordinates Each node is considered a node in the structural graph, and each graph node is bound to a corresponding geometric feature triplet. As a node attribute, it forms a graph node. Finally, a complete set of graph nodes is constructed. .

[0176] Secondly, the construction of the graph edge set. First, based on the graph node set... Coordinates of each geometric center The Delaunay triangulation algorithm is used to establish the connection relationship. If any two nodes... center point , If two elements are adjacent in the Delaunay grid, an undirected edge is created. Finally, a complete set of graph edges is constructed. ,in .

[0177] Third, the construction of the face set. Based on the Delaunay triangulation algorithm, any three nodes connected pairwise by edges... It can form a sheet Finally, a complete set of facets is constructed. .in, Represents the first in the set of facets Each facet is an ordered triplet consisting of three nodes, which are nodes. and .

[0178] Finally, based on the node set, edge set, and face set of the above graph, a structure graph of the connected defect region is constructed. The specific formula is as follows:

[0179]

[0180] Step S4000: Structural diagram based on connected defect regions and geometric feature triples of connected defect regions This study analyzes the impact of micropore defects on the mechanical properties of paperboard materials and predicts the residual strength of paperboard materials with micropore defects. .

[0181] Specifically, this step aims to refine the structural diagram of the connected defect region constructed in step S3300. and the geometric feature triplet of the connected defect region constructed in step S3200 A mechanical property prediction model for structure-sensitive analysis is established. This is achieved by introducing a weighted porosity of the paperboard material under microporous defects. Strength attenuation factor of paperboard materials under microporous defects Residual strength of paperboard materials under microporous defects This allows for the quantitative assessment of the remaining load-bearing capacity of composite corrugated cardboard materials under conditions of microporous defects, thereby enabling a structured and intelligent determination of the impact of defects on the mechanical properties of the material.

[0182] Furthermore, such as Figure 5 As shown, step S4000 includes:

[0183] Step S4100, based on the geometric feature triples of the connected defect region Calculate the weighted porosity of paperboard material with micropore defects. .

[0184] Specifically, this step aims to assess the proportion of microporous defect regions in the overall material as a basic input parameter for predicting mechanical properties.

[0185] In the specific implementation process, firstly, the geometric feature triples connecting the defective regions are... Physical area of ​​all connected defect subregions Accumulate the results and divide by the total area of ​​the detection area. The unweighted porosity of the paperboard material was obtained. The specific process formula is as follows:

[0186]

[0187] in, This represents the unweighted porosity of the paperboard material, which indicates the proportion of defective areas in the overall inspection area. Its value range is... ; Indicates the first The physical area of ​​each connected defective sub-region; This represents the total number of detected connected defect sub-regions; This indicates the total area of ​​the detection zone.

[0188] Furthermore, to enhance the responsiveness of the paperboard material's structural features to porosity calculation, a structural diagram of connected defect regions is introduced. Mid-node connectivity For each By performing structural weighting, the weighted porosity of the paperboard material is obtained. The specific process formula is as follows:

[0189]

[0190]

[0191] wherein, represents the weighted porosity of the paperboard material, used to reflect the weighted influence of defects on the material performance; represents the structure weighted factor, used to the first defect sub-region in the structure diagram to weight the importance of performance influence; represents the structure weight adjustment parameter, which needs to be obtained by experimental tuning (usually positive value); node connectivity represents the first defect sub-region in the structure diagram, used to count the number of adjacent edges of each node , that is, the connection activity of the structure diagram, if the boundary distance of any two defect sub-regions and is less than a certain threshold, there is adjacent edge number .

[0192] Step S4200, based on the weighted porosity of the paperboard material , calculate the strength attenuation factor of the paperboard material under the micro-hole defect. .

[0193] Specifically, this step aims to further evaluate the weakening degree of the micro-hole defect to the strength performance of the paperboard material based on the weighted porosity of the paperboard material calculated in step S4100 .

[0194] In the specific implementation process, the weighted porosity of the paperboard material is mapped to the strength attenuation factor of the paperboard material under the micro-hole defect , the fitting parameters and are introduced, and the nonlinear function relationship of the influence of defects on strength is constructed combined with the Mohr-Coulomb empirical model, to calculate the strength attenuation factor of the paperboard material under the micro-hole defect , which is used to quantify the weakening degree of the defect to the overall strength of the paperboard material, and the specific expression formula is as follows:

[0195]

[0196] wherein, represents the strength attenuation factor of the paperboard material under the micro-hole defect, used to represent the weakening proportion of the defect to the strength of the paperboard material, and the smaller the value, the more the strength decreases; represents the empirical attenuation coefficient, which is usually obtained by experiment or literature fitting; represents a nonlinear exponential parameter for controlling the nonlinear decay curvature, usually greater than 1, enhancing the sensitivity to high porosity, usually obtained by experimental or literature fitting.

[0197] Step S4300, predicting the residual strength of the paperboard material under the micro-hole defect based on the strength decay factor of the paperboard material under the micro-hole defect . .

[0198] Specifically, this step aims to calculate the effective residual carrying capacity of the paperboard material under the current defect condition based on the strength decay factor of the paperboard material under the micro-hole defect calculated in step S4200 , combined with the theoretical initial strength of the paperboard material in the ideal defect-free state.

[0199] In specific implementation process, combined with the strength decay factor of the paperboard material under the micro-hole defect and the initial strength of the paperboard material , the residual strength of the paperboard material under the micro-hole defect , that is, the effective carrying capacity of the paperboard material under the current defect condition, the specific process formula is as follows:

[0200]

[0201] wherein, represents the residual strength of the paperboard material under the micro-hole defect, for the effective carrying capacity of the material under the defect influence; represents the initial strength of the material, that is, the design theoretical strength of the material without defect influence, which can be obtained by standard mechanical test (such as compression test, tensile test and three-point bending test, etc.).

[0202] Step S5000, based on the residual strength of the paperboard material under the micro-hole defect , micro-hole defect grade evaluation and grading control strategy making.

[0203] Specifically, this step aims to grade the influence degree of the micro-hole defect based on the residual strength of the paperboard material under the micro-hole defect calculated in step S4300 , and accordingly generate the corresponding process adjustment suggestion, realizing the quality closed-loop control in the production process of low grammage high-strength composite corrugated paperboard.

[0204] Further, as shown in Figure 6 , step S5000 includes:

[0205] Step S5100, based on the residual strength of the paperboard material under the micro-hole defect , grade division of the micro-hole defect, construction of the quality grade of the composite corrugated paperboard .

[0206] Specifically, the step aims to determine the residual strength of the paperboard material under the micro-hole defect based on the calculation in step S4300 The mechanical properties of the current corrugated paperboard are classified to achieve hierarchical management of the defect evaluation results and process adjustment reference.

[0207] In the specific implementation process, three strength classification thresholds are preset 、 and , wherein the relationship is satisfied , and the classification thresholds can be obtained by fitting training sample data according to standards or production experience, for interval division of the residual strength of the paperboard material under the micro-hole defect Based on the strength classification thresholds 、 and , the quality classification rule of the corrugated paperboard is constructed, and the specific process formula is as follows:

[0208] If , the quality classification of the corrugated paperboard is . Among them, indicates that the material strength of the corrugated paperboard is excellent, the defect impact is negligible, and the process parameters can be maintained as they are;

[0209] If , the quality classification of the corrugated paperboard is . Among them, indicates that the material of the corrugated paperboard is qualified but there is a slight strength decrease, which can be compensated by small-scale optimization of process parameters (such as pressure, temperature, glue ratio, etc.);

[0210] If , the quality classification of the corrugated paperboard is . Among them, indicates that the material of the corrugated paperboard has obvious strength decrease, and it is suggested to adjust the key process parameters to improve the structural stability;

[0211] If , the quality classification of the corrugated paperboard is . Among them, indicates that the material of the corrugated paperboard has serious defects or has exceeded the safe range of use, and it is suggested to be scrapped or to make major optimization adjustment of the process route.

[0212] Finally, the quality classification of the corrugated paperboard is obtained.

[0213] Step S5200, based on the quality classification of the corrugated paperboard The process adjustment scheme is integrated with the process experience rule base and machine learning prediction model to revise the process adjustment suggestions and construct the final process parameter adjustment suggestion set. .

[0214] In the specific implementation process, based on the quality grade of the composite corrugated cardboard Depending on the differences, matching process adjustment schemes are retrieved from the process experience rule base and the trained machine learning prediction model to automatically generate a set of process parameter adjustment suggestions containing multiple control dimensions. The set of process parameter adjustment suggestions This involves controlling multiple key parameters, including the spraying system, pressure system, drying system, adhesive dosing system, and paper machine line speed, to suppress defects in composite corrugated board and improve its residual strength. The specific process is as follows:

[0215] Firstly, based on the quality grade of composite corrugated cardboard. Analyze the current quality grade information and determine the process adjustment goals accordingly: If the quality grade of the composite corrugated cardboard is... This indicates the residual strength of the paperboard material under microporous defects. If the quality grade of the composite corrugated cardboard is within the excellent range, no adjustment is needed, and the system will maintain the current process settings; or This indicates the residual strength of the paperboard material under microporous defects. If the strength is slightly or moderately low, the system needs to adjust the process parameters to restore the strength level; if the quality grade of the composite corrugated cardboard is... This indicates the residual strength of the paperboard material under microporous defects. If there is a serious deficiency, the system will initiate a severe repair process and simultaneously trigger a manual review prompt or a pause mechanism to prevent the continuous output of substandard products.

[0216] Secondly, based on the quality grade of composite corrugated cardboard. The process parameter suggestion set for the corresponding level is retrieved from the pre-set process experience rule base to obtain the process parameter suggestion set of the process experience rule base. This includes, but is not limited to, the following dimensions: shotcrete volume (unit: ), pressing pressure (Unit: MPa), Drying temperature (unit: Adhesive dosage ratio (unit: and paper machine line speed Empirical values ​​and adjustment ranges for parameters such as... Indicates the first Recommended values ​​based on empirical rules for each process parameter; This refers to the scenario of rule suggestion; This represents the total number of process parameters. The rule base is constructed based on historical production line experience, process engineer recommendations, and statistical analysis results, forming robust and reliable parameter adjustment ranges. For example, if the current quality grade of the composite corrugated cardboard is... The system can recommend increasing the shotcrete volume. The drying temperature increases And measures such as reducing the paper machine line speed by 2% were implemented.

[0217] Thirdly, to further enhance the personalization and adaptability of parameter recommendations, the system inputs currently detected physical parameters (such as cardboard moisture content, thickness, and initial strength), raw material information, and production environment parameters into a trained machine learning model for prediction. This model can be a multilayer perceptron (MLP), random forest (RF), or support vector machine (SVM) structure, and its training data comes from historical correlation samples between cardboard strength and process parameters. The prediction model outputs a set of process parameter suggestions predicted by machine learning. This serves as a supplement or correction to the rules of thumb, enhancing the dynamic responsiveness of the recommendations. Among these, Indicates the first Machine learning predictions of process parameters; This refers to a machine-based scenario; Indicates the total number of process parameters;

[0218] Fourth, the process parameter suggestion set from the process experience rule base. Recommended set of process parameters based on machine learning predictions The data is then integrated to generate a final set of process parameter adjustment recommendations. First, calculate the set of process parameter suggestions from the process experience rule base. Recommended set of process parameters based on machine learning predictions The deviation between the two The specific process formula is as follows:

[0219]

[0220] in, Indicates the first The relative deviation rate of each process parameter is used to measure the degree of similarity between the two (numerical range). ); Indicates the first Recommended values ​​based on empirical rules for each process parameter; Indicates the first Machine learning predictions of process parameters;

[0221] Then, based on the preset tolerance threshold The following fusion strategy is performed:

[0222] If , it indicates that the relative deviation rate between the experience rule recommended value and the machine learning predicted value is small, and a simple average value is adopted within the tolerance threshold range. The specific process formula is as follows:

[0223]

[0224] If , it indicates that the relative deviation rate between the experience rule recommended value and the machine learning predicted value is large, and a confidence weighted fusion is adopted. The specific process formula is as follows:

[0225]

[0226]

[0227] wherein, represents the weight of the experience rule recommended value; represents the weight of the machine learning predicted value; represents the success rate of the process parameter suggestion set of the process experience rule library based on historical data statistics, i.e. , represents the actual application times of the process parameter suggestion set of the process experience rule library, represents the number of times of reaching the expected effect in the process parameter suggestion set of the process experience rule library; represents the confidence index of the prediction result of the i-th process parameter in the process parameter suggestion set predicted by machine learning, which is used to measure the credibility of the prediction value, and is usually directly output or indirectly calculated by the machine learning model; represents the fused process parameter suggestion value.

[0228] Subsequently, parameter legality verification and correction are performed. It is checked whether the fused process parameter suggestion value falls within the equipment control allowable interval . The equipment control allowable interval is obtained by comprehensively setting the equipment specifications, process technical standards, quality safety constraints, historical experience data statistics, and expert process threshold.

[0229] If the fused process parameter suggestion value exceeds the equipment control allowable interval , the following correction operation needs to be performed:​​​

[0230]

[0231] If Then it will be forced to be set as the lower limit. ;like Then force it to be set to the upper limit. ;like If the value is within the range, no correction is needed.

[0232] For example, taking the photograph of a composite corrugated cardboard sample as an example, assuming the pressing pressure... The control range is The recommended values ​​for the process parameters of the system integration are: If so, a correction operation is performed, and the corrected process parameters are finally obtained. .

[0233] Ultimately, based on the revised process parameters Construct a final set of process parameter adjustment suggestions. As a basis for recommending automatic or manual process adjustments on-site, it guides the control of key links such as spraying, pressurization, drying, bonding and running speed, so as to achieve stable recovery of cardboard strength and quality improvement.

[0234] Example 2

[0235] This embodiment, based on Embodiment 1, provides a system for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard, such as... Figure 7 As shown, it includes:

[0236] The high-resolution composite corrugated cardboard image construction module is used to acquire high-quality image data of the microporous structure in low basis weight high strength composite corrugated cardboard, and construct a fused high-resolution composite corrugated cardboard face sheet set. ;

[0237] The micropore defect identification module for composite corrugated cardboard is based on a fused high-resolution set of composite corrugated cardboard face sheets. Micropore defects in composite corrugated cardboard are identified, and a binary mask image of micropore defects in composite corrugated cardboard is obtained. ;

[0238] The module for spatial relationship analysis and structural reconstruction of micropore defects in composite corrugated cardboard is based on the binary mask image of micropore defects in composite corrugated cardboard. Spatial relationship analysis and structural reconstruction were performed to construct a structural diagram connecting the defective regions. ;

[0239] The micropore defect mechanical property prediction module is based on the structural diagram of the connected defect region. and geometric feature triples of connected defect regions , analyze the influence of micro-hole defects on the mechanical properties of paperboard materials, and predict the residual strength of paperboard materials under micro-hole defects ;

[0240] Micro-hole defect grade evaluation and process adjustment module based on the residual strength of paperboard materials under micro-hole defects , micro-hole defect grade evaluation and grading control strategy making.

[0241] The part of the above technical solution provided in the embodiments of the present application which is consistent with the implementation principle of the corresponding technical solution in the prior art is not described in detail to avoid excessive repetition.

[0242] The specific embodiments described above further illustrate the purposes, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting microporous structure defects in low-basis-weight, high-strength composite corrugated cardboard, characterized in that, include: High-quality image data of the microporous structure in low basis weight high strength composite corrugated cardboard were collected, and a fused high-resolution composite corrugated cardboard image set was constructed. Based on the fused high-resolution composite corrugated cardboard image set, micropore defects in composite corrugated cardboard are identified, and a binary mask image of micropore defects in composite corrugated cardboard is obtained. Based on the binary mask image of micropore defects in composite corrugated cardboard, spatial relationship analysis and structural reconstruction are performed to construct a structural diagram of connected defect regions. Based on the structural diagram and geometric feature triplet of the connected defect region, the influence of micropore defects on the mechanical properties of paperboard is analyzed, and the residual strength of paperboard under micropore defects is predicted. The steps for predicting the residual strength of paperboard material under microporous defects include: calculating the weighted porosity of the paperboard material under microporous defects based on the geometric feature triplet of the connected defect region; calculating the strength attenuation factor of the paperboard material under microporous defects based on the weighted porosity of the paperboard material; and predicting the residual strength of the paperboard material under microporous defects based on the strength attenuation factor of the paperboard material under microporous defects. The steps for calculating the weighted porosity of the paperboard material under microporous defects include: summing the physical areas of all connected defect sub-regions in the geometric feature triplet of the connected defect region and dividing it by the total detection area to obtain the unweighted porosity of the paperboard material; introducing the node connectivity in the structural graph of the connected defect region and performing structural weighting on the physical area of ​​each connected defect sub-region to obtain the weighted porosity of the paperboard material. Based on the residual strength of paperboard materials with micropore defects, we conduct micropore defect level assessment and formulate graded control strategies.

2. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 1, characterized in that, The steps for constructing the fused high-resolution composite corrugated cardboard image set include: Obtain standardized samples of composite corrugated cardboard to obtain multifocal images of the composite corrugated cardboard; Based on multifocal composite corrugated cardboard images, a set of fused high-resolution composite corrugated cardboard images is constructed using the maximum grayscale fusion algorithm.

3. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 1, characterized in that, The steps for obtaining the binary mask image of micropore defects in composite corrugated cardboard include: Based on the fused high-resolution composite corrugated cardboard image set, a second composite corrugated cardboard image set is obtained; Based on the second composite corrugated cardboard image set, a convolutional neural network model is used to generate a probability map of micropore defects in the composite corrugated cardboard. Based on the probability map of micropore defects in composite corrugated cardboard, threshold segmentation and binary defect region extraction are performed to obtain a binary mask map of micropore defects in composite corrugated cardboard.

4. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 1, characterized in that, The steps of spatial relationship analysis and structural reconstruction include: Based on the binary mask image of micropore defects in composite corrugated cardboard, spatial connectivity clustering analysis of defect regions is performed to extract the set of all independent connected defect sub-regions; Based on the set of all independent connected defect sub-regions, quantitative analysis of geometric features and extraction of defect geometric center coordinates are performed to construct geometric feature triples and defect geometric center sets for connected defect regions. Based on the geometric features of the connected defect region and the set of its defect geometric centers, a structural diagram of the connected defect region is constructed.

5. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 4, characterized in that, The spatial connectivity clustering analysis of the defect region uses 8-neighborhood connectivity judgment to determine the connectivity of all foreground pixels in the binary mask image of micropore defects in composite corrugated cardboard. The 8-neighborhood connectivity determination specifically includes: if a foreground pixel and any one of its four basic directional neighboring pixels (up, down, left, and right) or four diagonal directional neighboring pixels (upper left, upper right, lower left, and lower right) are also foreground pixels, then the two are considered to be in the same connected region.

6. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 4, characterized in that, The calculation steps for the geometric features include: The total number of all foreground pixels in each connected defect sub-region is counted, the area of ​​each connected defect sub-region is calculated, and after the image is spatially calibrated, the actual physical area of ​​each connected defect sub-region is obtained based on the area of ​​each connected defect sub-region. A boundary extraction algorithm is used to extract the set of boundary pixels of each connected defect sub-region, and the perimeter of each connected defect sub-region is calculated based on the cumulative Euclidean distance between adjacent boundary points. Each defect region is approximated as an ideal circular region of equal area, and the equivalent circle diameter of each connected defect sub-region is calculated accordingly. Based on the foreground pixels in each connected defect sub-region, the average values ​​of the x-coordinate and y-coordinate of each foreground pixel are calculated, and the geometric center coordinates of each connected defect sub-region are extracted.

7. The method for detecting microporous structural defects in low-basis-weight, high-strength composite corrugated cardboard according to claim 1, characterized in that, The steps for constructing the structural diagram of the connected defect region include: Based on the geometric center coordinates of each connected defect sub-region, it is regarded as a node of the structural graph, and each graph node is bound to the corresponding geometric feature triple as a node attribute to form a graph node and construct a complete graph node set. Based on the coordinates of the geometric centers in the graph node set, the Delaunay triangulation algorithm is used to establish the connection relationship. If the center points of any two nodes are adjacent in the Delaunay grid, an undirected edge is established to construct a complete graph edge set. Based on the Delaunay triangulation algorithm, any three nodes connected in pairs by edges can form a patch, thus constructing a complete set of patches. Based on the set of nodes, edges, and faces of the graph, a structural graph of the connected defect region is constructed.

8. A system for detecting microporous structural defects in low-basis-weight high-strength composite corrugated cardboard, used to implement the method for detecting microporous structural defects in low-basis-weight high-strength composite corrugated cardboard according to any one of claims 1-7, characterized in that, The system includes: The high-resolution composite corrugated cardboard image construction module is used to acquire high-quality image data of the microporous structure in low basis weight high strength composite corrugated cardboard and construct a fused high-resolution composite corrugated cardboard image set. The composite corrugated cardboard micropore defect identification module identifies micropore defects in the composite corrugated cardboard based on a fused high-resolution composite corrugated cardboard image set and obtains a binary mask image of the micropore defects in the composite corrugated cardboard. The module for spatial relationship analysis and structural reconstruction of micropore defects in composite corrugated cardboard performs spatial relationship analysis and structural reconstruction based on the binary mask image of micropore defects in composite corrugated cardboard, and constructs a structural diagram of connected defect regions. The micropore defect mechanical property prediction module analyzes the influence of micropore defects on the mechanical properties of paperboard materials based on the structural diagram of the connected defect region and the geometric feature triplet of the connected defect region, and predicts the residual strength of the paperboard material under micropore defects. The micropore defect level assessment and process adjustment module assesses the micropore defect level and formulates graded control strategies based on the residual strength of the paperboard material under micropore defects.

Images