A method and system for evaluating the degree of printing defects of corrugated cartons

Abstract

The present invention discloses a method and system for evaluating the degree of printing defects of corrugated cartons, including detecting the flatness of the printed corrugated cartons to be tested, screening out the corrugated cartons to be tested that meet the preset conditions as the target detection objects, collecting their printing images, inputting them into X types of defect types in the clustering algorithm for clustering after feature extraction, determining the defect analysis results of the target features according to the clustering results. When the clustering result is X types of defect types, determining the corresponding defect types and quantities according to the clustering clusters where the target features are located; when the clustering result is more than X types of defect types, using spectral analysis to determine the defect types and quantities of the target features; calculating the degree of printing defects of the corrugated cartons to be tested, and feedback-adjusting the next printing parameters of the corrugated cartons. The present invention takes into account the influence of flatness, determines the defect types through the clustering algorithm to evaluate the defect degree, and feedback-adjusts the next printing parameters, improving the accuracy of defect evaluation and the yield rate of the next printing process.

Description

Technical Field

[0001] The present invention relates to the technical field of corrugated paper box defect detection, and in particular to a method and system for evaluating the degree of printing defects of corrugated paper boxes. Background Art

[0002] During the printing process of corrugated boxes, due to environmental factors or improper printing parameter settings, printing defects such as printing position deviation, uneven color, blurred handwriting, and large color difference are prone to occur. In order to ensure the product quality of corrugated boxes, it is necessary to perform defect detection on the printed patterns of corrugated boxes.

[0003] At present, commonly used defect detection methods include manual inspection and image inspection. Manual inspection mainly relies on the naked eye and manual experience to inspect the appearance of the carton to confirm whether there is a problem with the printed pattern. Image detection usually trains a defect recognition model, inputs the collected carton image into the model, and automatically identifies the defect type. However, relying on manual inspection is not only inefficient, but also has large errors in the detection results. Although image detection can improve detection accuracy to a certain extent compared to manual inspection, it requires the collection of a large amount of defect data to train the model in the early stage, and the generalization ability of the model is usually poor, so it is impossible to effectively identify complex and changeable printing defects. Summary of the invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present invention provides a method and system for evaluating the degree of printing defects of corrugated paper boxes.

[0005] In a first aspect, the present invention provides a method for evaluating the degree of printing defects of corrugated paper boxes, the method comprising:

[0006] Detect the flatness of the corrugated paper boxes to be tested after printing, and select the corrugated paper boxes to be tested whose flatness meets the preset conditions as the target detection objects;

[0007] Collect the printed image of the target detection object, extract the features of the printed image, input the extracted target features into the X defect types in the clustering algorithm for clustering, and obtain the clustering results;

[0008] Determine the defect analysis result of the target feature according to the clustering result, including when the clustering result is X defect types, determine the corresponding defect type and the number of defect features according to the clustering cluster where the target feature is located; when the clustering result is more than X defect types, use spectral analysis to determine the defect type and the number of defect features of the target feature;

[0009] The defect analysis results and the number of target detection objects are used to calculate the printing defect degree of the corrugated box to be tested, and the next printing parameters of the corrugated box are adjusted according to the feedback of the printing defect degree.

[0010] Preferably, detecting the flatness of the corrugated cardboard box after printing includes:

[0011]

[0012] In the formula, F fl represents the flatness factor, α and β are constant coefficients, satisfying 0 < α < 0.01, 0 < β < 1; T and P respectively represent the temperature and pressure during the printing of the corrugated cardboard box, W represents the water content of the corrugated cardboard box; H and L respectively represent the thickness and length of the corrugated cardboard of the corrugated cardboard box; E and I respectively represent the elastic modulus of the corrugated cardboard and the structural moment of inertia of the corrugated cardboard box, and e is the base of the natural logarithm.

[0013] Preferably, calculating the printing defect degree of the corrugated cardboard box to be measured by using the defect analysis result, the number of target features, and the number of target detection objects includes:

[0014]

[0015] In the formula, Q represents the printing defect degree, M0 represents the number of target detection objects, M represents the number of corrugated cardboard boxes to be measured, represents the sum of the average distances from all pixel points in the feature to their respective centroids, D i represents the distance from the i-th sample point to its respective centroid, and there are N sample points in total; Var(C), Var(G), and Var(B) respectively represent the variances of the color feature, texture feature, and edge feature, and Z represents the number of defect types obtained by clustering; γ1, γ2, and γ3 are respectively weight factors.

[0016] Preferably, feedback-adjusting the next printing parameter of the corrugated cardboard box according to the printing defect degree includes:

[0017] Adopt a reinforcement learning algorithm to learn the printing defect degree and historical printing parameters, train an adaptive adjustment model, and dynamically adjust the next printing parameter according to the adaptive adjustment model.

[0018] Preferably, extracting features from the printed image includes:

[0019] Preprocess the printed image, including converting the printed image to the Lab color space, and performing image enhancement, median filtering, and size unification processing;

[0020] Based on the preprocessed printed picture, extract the target features of the printed image, and the target features include color features, texture features, and edge features.

[0021] Preferably, inputting the extracted target features into X defect types in the clustering algorithm for clustering to obtain a clustering result, including:

[0022] The dimensionality reduction of the extracted target features is carried out using the PCA algorithm, and the dimensionality-reduced target features are fitted using the random forest algorithm. According to the screening indicators after fitting, the feature quantity with the largest correlation is screened out;

[0023] The K-means algorithm is used to cluster the screened feature quantities to generate a clustering result.

[0024] In a second aspect, the present invention also provides a corrugated cardboard printing defect degree evaluation system, and the system includes:

[0025] A target screening unit, configured to detect the flatness of the printed corrugated cardboard to be tested, and screen out the corrugated cardboard to be tested with flatness meeting the preset conditions as the target detection object;

[0026] A clustering unit, configured to collect the printed images of the target detection object, extract features from the printed images, and input the extracted target features into X types of defect types in the clustering algorithm for clustering to obtain a clustering result;

[0027] A defect analysis unit, configured to determine the defect analysis result of the target features according to the clustering result, including when the clustering result is X types of defect types, determining the corresponding defect type and the number of defect features according to the clustering cluster where the target features are located; when the clustering result is more than X types of defect types, using spectral analysis to determine the defect type and the number of defect features of the target features;

[0028] A parameter adjustment unit, configured to calculate the printing defect degree of the corrugated cardboard to be tested by using the defect analysis result and the number of target detection objects, and feedback and adjust the next printing parameter of the corrugated cardboard according to the printing defect degree.

[0029] In a third aspect, the present invention also provides an electronic device, including: a processor and a memory, where the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the method according to the first aspect and any one of its possible implementation manners as described above.

[0030] In a fourth aspect, the present invention also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by the processor of the electronic device, the processor is caused to execute the method according to the first aspect and any one of its possible implementation manners as described above.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0032] 1) Before detecting printing defects, the present invention first detects the flatness of the corrugated cardboard box to be tested after printing, and screens out the corrugated cardboard box to be tested with flatness meeting the preset conditions as the target detection object. Since flatness problems usually directly affect the printing results, it can be directly considered that there are printing defects for cardboard boxes with flatness defects, thus greatly improving the detection efficiency. For the detection of flatness, currently, it is usually carried out by scanning the surface of the cardboard with an instrument, which is not only costly but also inefficient. Therefore, when the present invention detects flatness, it mainly constructs a calculation model of the flatness factor according to printing parameters and material property parameters. By inputting the printing parameters and the parameters of the material itself into the calculation model, the flatness can be quickly predicted, which has the advantages of low cost, high efficiency, and high prediction accuracy.

[0033] 2) After determining the target detection object, the present invention collects the printing image of the target detection object, extracts the features of the printing image, and clusters the extracted target features into X types of defect types in the clustering algorithm to obtain the clustering result; if the collected printing image is directly clustered for defects, due to many interference factors, it usually affects the accuracy of the clustering result. Therefore, the present invention further extracts the target features in the image and performs defect clustering through the target features to improve the accuracy of the clustering result. When obtaining the clustering result, the defect analysis result of the target features is determined according to the clustering result, including when the clustering result is X types of defect types, determining the corresponding defect type and the number of defect features according to the clustering cluster where the target features are located; when the clustering result is more than X types of defect types, spectral analysis is used to determine the defect type and the number of defect features of the target features; compared with training a defect recognition model with a large amount of data, the present invention uses a clustering algorithm without collecting a large number of data labels to train the model, can quickly determine the defect type, and for defect types that cannot be recognized, spectral analysis is used, further ensuring the accuracy of the defect detection result.

[0034] 3) After obtaining the defect analysis result, the present invention calculates the printing defect degree of the corrugated cardboard box to be tested by using the defect analysis result and the number of target detection objects, and feedback-adjusts the next printing parameter of the corrugated cardboard box according to the printing defect degree. This can reduce the defect degree in the next printing process and is beneficial to improving the yield of cardboard box printing.

[0035] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the following will describe the drawings required to be used in the embodiments of the present invention or the background art.

[0037] The accompanying drawings here are incorporated into the specification and form a part of this specification. These drawings show embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure.

[0038] Figure 1 It is a schematic flowchart of a method for evaluating the degree of printing defects of a corrugated cardboard box provided by an embodiment of the present invention;

[0039] Figure 2 It is a schematic structural diagram of a system for evaluating the degree of printing defects of a corrugated cardboard box provided by an embodiment of the present invention. Detailed implementation manners

[0040] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] The terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0042] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set composed of A, B, and C.

[0043] Referring to "embodiments" in this article means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present invention. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0044] In addition, for a better illustration of the present invention, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present invention can still be implemented without certain specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail so as to highlight the gist of the present invention.

[0045] Currently, for the evaluation of corrugated cardboard box printing defects, manual inspection or defect model recognition is mostly adopted. The former has low efficiency, and the latter has a high cost for training the model and poor model generalization ability. Therefore, a method for evaluating the degree of corrugated cardboard box printing defects provided by the present invention can quickly identify the defect types through a clustering algorithm, takes into account the influence of flatness, and will feedback the printing parameters of the next printing process after identifying the defects, thereby improving the yield.

[0046] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of a method for evaluating the degree of corrugated cardboard box printing defects provided by an embodiment of the present invention. As Figure 1 shown, a method for evaluating the degree of corrugated cardboard box printing defects includes the following steps:

[0047] S10. Detect the flatness of the corrugated cardboard box to be tested after printing, and screen out the corrugated cardboard boxes to be tested with flatness meeting the preset conditions as the target detection objects;

[0048] The flatness problem of the cardboard box usually directly affects the printing quality. When the surface of the cardboard box is uneven, there is usually uneven contact between the paper and the printing plate during printing, resulting in a decrease in the overprint accuracy of the pattern during multi-color printing, and phenomena such as misalignment, ghosting, or blurred color edges occur. In some scenarios, the unevenness of the cardboard box surface may also cause ink scraping during the printing process, that is, after the ink accumulates on the raised part of the cardboard, it is transferred to the adjacent printing area, causing pollution in the non-printing area. Therefore, in this embodiment, before detecting the printing pattern defects, the influence of flatness is first considered. The flatness of the corrugated cardboard box to be tested after printing will be detected, and it will be judged whether the flatness meets the preset conditions. Those that do not meet the conditions will be excluded, and the remaining corrugated cardboard boxes to be tested that meet the conditions will be used as the target detection objects. It is equivalent to that those with flatness not meeting the conditions can be directly regarded as having printing defects. In this way, the detection efficiency of printing defects can be greatly improved.

[0049] Currently, when detecting the flatness of cardboard boxes, corresponding detection instruments are usually used. For example, flatness testers, thickness gauges, etc. When using instruments for detection, it is necessary to manually hold the instrument to detect the flatness of each cardboard box one by one. This method requires manual scanning and detection of all areas of the cardboard box. Once some positions are missed, the detection results cannot be guaranteed. Moreover, this method requires a large amount of manpower and material resources, resulting in high costs and low efficiency. In the face of the scenario with a large number of cardboard boxes to be detected in this embodiment, this method is obviously not applicable. To balance the detection efficiency and accuracy of flatness, the present invention considers constructing a calculation model of a flatness factor based on printing parameters and material parameters itself, and characterizing the flatness of the cardboard box through the flatness factor.

[0050] In one embodiment, detecting the flatness of the corrugated cardboard box after printing includes:

[0051]

[0052] In the formula, F fl represents the flatness factor, α and β are constant coefficients, satisfying 0 < α < 0.01, 0 < β < 1; T and P respectively represent the temperature and pressure during the printing process of the corrugated cardboard box, W represents the water content of the corrugated cardboard box; H and L respectively represent the thickness and length of the corrugated cardboard of the corrugated cardboard box; E and I respectively represent the elastic modulus of the cardboard of the corrugated cardboard box and the structural moment of inertia, and e is the base of the natural logarithm.

[0053] For the sake of helping understanding, specific values will be substituted below to illustrate this model:

[0054] Assume α = 0.001, β = 0.5, and obtain the printing parameters during this printing process: T = 120 °C, P = 5×10 5 N / m 2 ; obtain the parameters of the cardboard box material: W = 60%, H = 0.003 m, L = 0.5 m, E = 5×10 9 N / m 2 , I = 10 -6 m 4 . Substitute all the values into the above formula to calculate the flatness factor F fl is approximately 1.41×10 -6 . Generally, the smaller the flatness factor, the higher the corresponding flatness. Therefore, the preset threshold of the flatness factor can be set to 1×10 -6 . If the calculated 1.41×10 -6 exceeds 1×10 -6 , it is considered that the flatness of the cardboard box does not meet the preset conditions, and the corresponding cardboard box needs to be excluded; when the calculated flatness factor is less than or equal to 1×10 -6 , it is considered that the preset conditions are met, and these cardboard boxes that meet the conditions are used as the target detection objects.

[0055] Therefore, compared with the manual detection of flatness by instruments, in this embodiment, a calculation model of the flatness factor is constructed by combining printing parameters and material characteristics. When predicting flatness, only by obtaining the printing parameters and the material's own parameters and inputting them into the model, it is possible to quickly determine whether the flatness meets the preset conditions, taking into account both the detection quality and efficiency of flatness.

[0056] S20. Collect the printed image of the target detection object, extract features from the printed image, and cluster the extracted target features into X types of defect types in the clustering algorithm to obtain a clustering result;

[0057] Currently, in the process of image recognition using machine vision, if we want to recognize printing defects, a large amount of labeled data is required to train the defect recognition model, and the data collection, annotation difficulty, and training cost are all relatively high. Moreover, once a new defect appears, the model under this supervised learning cannot recognize it, and its generalization ability is poor. For this reason, the embodiment adopts an unsupervised learning clustering model. By extracting features from the printed image and then performing clustering operations, a clustering result can be generated quickly and accurately.

[0058] In one embodiment, the extracting features from the printed image includes:

[0059] Preprocess the printed image, including converting the printed image to the Lab color space and performing image enhancement, median filtering, and size unification processing;

[0060] Based on the preprocessed printed picture, extract the target features of the printed image, where the target features include color features, texture features, and edge features.

[0061] It should be noted that before extracting features, in order to ensure the quality of the extracted features, it is necessary to preprocess the image first. The Lab color space is more suitable for visual perception than RGB or CMYK. The L component represents brightness, and the a and b components represent the color changes from green to red and from blue to yellow, respectively. Converting to the Lab space helps to separate color and brightness information, facilitating subsequent feature extraction and analysis. Image enhancement includes contrast, brightness, or sharpening processing, which can improve the visibility and distinguishability of features, especially in the case of uneven light or poor printing quality. It includes rotating the image, contrast stretching, etc. to remove salt-and-pepper noise and small particle interference in the image while keeping the edge information relatively intact. Median filtering can remove salt-and-pepper noise and small particle interference in the image while keeping the edge information relatively intact. Finally, scale all the images to be processed to the same size to ensure the consistency of feature extraction and the feasibility of comparison, so as to avoid the scale effect caused by different image sizes.

[0062] After preprocessing, target feature extraction is performed, including color features, texture features, and edge features. In the Lab color space, statistical measures such as color histograms, color means, and standard deviations can be calculated as features. Color features reflect the overall tone and color uniformity of the print and are crucial for identifying defects such as uneven color and color deviation. Texture features can be extracted through gray-level co-occurrence matrices and wavelet transforms, which describe the spatial distribution pattern of pixel values in the image and are very effective for identifying texture defects such as uneven stripes and halftone dots. Edge features are extracted using edge detection algorithms such as Canny and Sobel operators to obtain the boundary information in the image. Edge features can reveal the shape and structure in the image and are very effective for identifying issues such as the integrity and blurriness of printed patterns.

[0063] Therefore, in this embodiment, through image preprocessing, the effectiveness of feature extraction is ensured. By using color features, texture features, and edge features, defects can be identified from multiple perspectives, which is beneficial to improving the accuracy of defect recognition results.

[0064] In one embodiment, the extracted target features are input into X types of defect types in a clustering algorithm for clustering to obtain a clustering result, including:

[0065] The PCA algorithm is used to reduce the dimension of the extracted target features, and the random forest algorithm is used to fit the target features after dimension reduction. According to the screening index after fitting, the feature quantity with the largest correlation is selected;

[0066] The K-means algorithm is used to cluster the selected feature quantities to generate a clustering result.

[0067] In this embodiment, by performing a PCA transformation on the extracted target feature matrix, a new feature coordinate system can be found, where the first few principal components can explain most of the data variance. These principal components are the new features after dimension reduction. The random forest algorithm is used to fit the features after dimension reduction, and then the feature with the largest correlation is selected according to the feature importance. These features will be used in subsequent clustering analysis to ensure the accuracy and efficiency of the clustering effect.

[0068] Furthermore, based on the feature quantity with the largest correlation selected previously, the K-means algorithm is applied for clustering. First, the value of K needs to be determined, that is, the expected number of clustering categories, corresponding to X types of defect types. The algorithm iteratively optimizes the positions of the cluster centers until the stopping condition is met, such as the change in the cluster centers is less than the threshold or the maximum number of iterations is reached. Finally, X clustering results are obtained, and each cluster represents one or a class of printing defects.

[0069] Therefore, in this embodiment, through feature dimension reduction, the interference of invalid features can be reduced, and the computational complexity can be lowered. By screening the feature quantities with large correlations, the accuracy of the clustering result is further improved.

[0070] S30. Determine the defect analysis result of the target feature according to the clustering result, including when the clustering result is X types of defect types, determining the corresponding defect type and the number of defect features according to the cluster where the target feature is located; when the clustering result is more than X types of defect types, use spectral analysis to determine the defect type and the number of defect features of the target feature.

[0071] It can be understood that after obtaining the clustering result, only the number of types of defect types in the clustering result needs to be judged. Assuming that the clustering result is X types of defect types, it means that no new defect types have appeared. At this time, only the corresponding defect type and the number of defect features need to be determined according to the cluster where the target feature is located. Assuming that the clustered defect types are more than X types of defect types, it means that new defect types have appeared. At this time, the corresponding defect type and the number of defect features can be determined according to the clusters where some of the target features are located first, and for the new defects, spectral analysis can be directly used to determine the new defect type and the number of defect features. Finally, the identified new defect type data can be added to the clustering algorithm for data update. In the next clustering, the algorithm can identify the defects newly generated this time, which is equivalent to an adaptive iterative process of unsupervised learning.

[0072] S40. Calculate the printing defect degree of the corrugated cardboard box to be measured by using the defect analysis result and the number of target detection objects, and feedback and adjust the next printing parameter of the corrugated cardboard box according to the printing defect degree.

[0073] In one embodiment, the calculating the printing defect degree of the corrugated cardboard box to be measured by using the defect analysis result, the number of target features, and the number of target detection objects includes:

[0074]

[0075] In the formula, Q represents the printing defect degree, M0 represents the number of target detection objects, M represents the number of corrugated cardboard boxes to be measured, represents the sum of the average distances from all pixel points in the feature to the centroid to which they belong, D i represents the distance from the i-th sample point to the centroid to which it belongs, and there are N sample points in total; Var(C), Var(G), and Var(B) respectively represent the variances of color features, texture features, and edge features, Z represents the number of defect types obtained by clustering; γ1, γ2, and γ3 are weight factors respectively.

[0076] In the above formula, first, M0 / M is used to determine the qualified rate of the flatness meeting the conditions. Then, based on this, the defect degree is evaluated according to the clustering result. γ1, γ2, and γ3 are weight factors respectively, each value not exceeding 1, and the sum of the three weight factors is 1. Specifically, it can be adjusted according to the application scenario and experience, for example, taking the values of 0.4, 0.4, and 0.2 respectively. Var(C), Var(G), and Var(B) represent the variances of color features, texture features, and edge features respectively. A large variance indicates a high degree of dispersion of the features, usually meaning more inconsistencies or complexities, thus reflecting the defect degree. When calculating the variance of color features, the variances of the three components L, a, and b in the Lab color space can be calculated and then averaged. When calculating the variance of texture features, taking the gray-level co-occurrence matrix (GLCM) as an example, assuming several texture features such as contrast, energy, and entropy are extracted, then the variance of each feature can be calculated independently, or the joint variance of these feature vectors can be calculated. Edge features may be based on the edge strength or direction after an edge detection algorithm. If the edge strength is quantified as the intensity value of each edge pixel in the image, the variance of the edge features can be calculated according to the intensity value of each edge pixel. Therefore, through the above formula for calculating the defect degree, the defect degree can be quickly and accurately evaluated for use in feedback regulation of the printing parameters in the next printing process.

[0077] In one embodiment, feedback regulation of the next printing parameters of the corrugated cardboard box according to the printing defect degree includes:

[0078] Using a reinforcement learning algorithm to learn the printing defect degree and historical printing parameters, training an adaptive adjustment model, and dynamically adjusting the next printing parameters according to the adaptive adjustment model.

[0079] Specifically, the process of using the intensity learning algorithm for feedback regulation of parameters includes the following:

[0080] Define the environment (Environment):

[0081] State: The current set of printing parameters, including printing speed, ink amount, printing pressure, etc., and possible historical printing defect feedback information.

[0082] Action: A change within the range of adjustable printing parameters, such as increasing or decreasing the percentage of printing pressure, adjusting the ink supply amount, etc.

[0083] Reward: The feedback given according to the printing result. A low printing defect degree results in a high reward, and a high defect degree results in a low reward. Specifically, it can be a negative defect metric (such as the negative value of defect count or defect severity score), with the aim of minimizing this value.

[0084] Observation: After performing an action, the current degree of printing defects and other relevant status information feedback by the environment.

[0085] Selection algorithm: Select Q-Learning. This algorithm is applicable to discrete action spaces and learns an action-value function Q(s,a), which represents the expected return of taking action a in state s. It is more applicable when the action space is continuous or very large. Directly learn the policy π(s) to select actions and estimate the value of this action at the same time.

[0086] Initialization and exploration:

[0087] Initialization of the policy: At the beginning, the initial printing parameters can be randomly selected or set according to existing experience.

[0088] Exploration and exploitation: Introduce the ε-greedy policy or other exploration mechanisms to balance the need to explore new parameter combinations and exploit the known best policy.

[0089] Training process:

[0090] Observe the current state: Obtain the current printing parameters and historical printing defect feedback from the environment.

[0091] Select and execute an action: Select an action (adjust the printing parameters) according to the current policy and execute it.

[0092] Receive the reward and observe the new state: After completing a printing, calculate the reward according to the defect detection result and observe the new state information.

[0093] Update the model: Update the Q value or policy parameters according to the reward and the old and new states, and optimize the model to expect higher rewards in the future.

[0094] Adaptive adjustment: As learning progresses, the model gradually learns to select the optimal or near-optimal printing parameters in different situations, achieving adaptive adjustment and reducing printing defects. Finally, the trained reinforcement learning model can be deployed to the actual printing system to monitor the printing quality and defect feedback in real time and continuously optimize the model performance.

[0095] In summary, the present invention learns the degree of defects through a reinforcement learning algorithm and adjusts the next printing parameters of the corrugated box according to the feedback of the printing defect degree. In this way, the defect degree of the next printing process can be reduced, which is beneficial to improving the yield rate of carton printing.

[0096] See Figure 2 , in one embodiment, the present invention also provides a corrugated box printing defect degree evaluation system, and the system includes:

[0097] A target screening unit 100 is configured to detect the flatness of a corrugated cardboard box to be tested after printing, reject the corrugated cardboard boxes to be tested with a flatness less than a preset threshold, and use the remaining corrugated cardboard boxes to be tested as target detection objects;

[0098] A clustering unit 200 is configured to collect a printed image of a target detection object, extract features from the printed image, and cluster the extracted target features into X types of defect types in a clustering algorithm to obtain a clustering result;

[0099] A defect analysis unit 300 is configured to determine a defect analysis result of the target features according to the clustering result, including when the clustering result is X types of defect types, determining the corresponding defect type and the number of defect features according to the clustering cluster where the target features are located; when the clustering result is more than X types of defect types, using spectral analysis to determine the defect type and the number of defect features of the target features;

[0100] A parameter adjustment unit 400 is configured to calculate the printing defect degree of the corrugated cardboard box to be tested by using the defect analysis result and the number of target detection objects, and feedback and adjust the next printing parameter of the corrugated cardboard box according to the printing defect degree.

[0101] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0102] The present invention also provides an electronic device, including: a processor and a memory. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the method in any of the above possible implementation manners.

[0103] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor is caused to execute the method in any of the above possible implementation manners.

[0104] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0105] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. Those skilled in the art can also clearly understand that each embodiment of the present invention has different emphases in description. For the convenience and brevity of description, the same or similar parts may not be elaborated in different embodiments. Therefore, for the parts not described or not described in detail in a certain embodiment, reference can be made to the descriptions of other embodiments.

[0106] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0107] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0109] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital versatile disc (DVD)), or a semiconductor medium (e.g., solid state disk (SSD)), etc.

[0110] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware with a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage medium includes: various media that can store program codes such as read-only memory (ROM) or random access memory (RAM), magnetic disks, or optical discs.

Claims

1. A method for evaluating the degree of printing defects of corrugated paper boxes, characterized in that: The method comprises: Detect the flatness of the corrugated paper boxes to be tested after printing, and select the corrugated paper boxes to be tested whose flatness meets the preset conditions as the target detection objects; The method of detecting the flatness of the printed corrugated paper box to be tested comprises: In the formula, F fl represents the flatness factor, α and β are constant coefficients, satisfying 0<α<0.01, 0<β<1; T and P represent the temperature and pressure during the printing process of the corrugated box, respectively, and W represents the moisture content of the corrugated box; H and L represent the thickness and length of the corrugated box paperboard, respectively; E and I represent the elastic modulus and structural moment of inertia of the corrugated box paperboard, respectively, and e is the base of the natural logarithm; Collect the printed image of the target detection object, extract the features of the printed image, input the extracted target features into the X defect types in the clustering algorithm for clustering, and obtain the clustering results; Determine the defect analysis result of the target feature according to the clustering result, including when the clustering result is X defect types, determine the corresponding defect type and the number of defect features according to the clustering cluster where the target feature is located; when the clustering result is more than X defect types, use spectral analysis to determine the defect type and the number of defect features of the target feature; The defect analysis results and the number of target detection objects are used to calculate the printing defect degree of the corrugated box to be tested, and the next printing parameters of the corrugated box are adjusted according to the feedback of the printing defect degree.

2. The method for evaluating the degree of printing defects of corrugated paper boxes according to claim 1, characterized in that: The method of calculating the printing defect degree of the corrugated paper box to be tested by using the defect analysis result and the number of target detection objects includes: In the formula, Q represents the degree of printing defects, M0 represents the number of target detection objects, and M represents the number of corrugated boxes to be tested. Represents the sum of the average distances of all pixels in the feature to their centroids, D i Indicates the distance from the i-th sample point to its centroid, there are N sample points in total; Var(C), Var(G), and Var(B) represent the variances of color features, texture features, and edge features, respectively; Z represents the number of defect types obtained by clustering; γ1, γ2, and γ3 are weight factors, respectively.

3. The method for evaluating the degree of printing defects of corrugated paperboard according to claim 1, characterized in that: The method of adjusting the next printing parameters of the corrugated box according to the feedback of the printing defect degree includes: A reinforcement learning algorithm is used to learn the degree of printing defects and historical printing parameters, train the adaptive adjustment model, and dynamically adjust the next printing parameters according to the adaptive adjustment model.

4. The method for evaluating the degree of printing defects of corrugated paperboard according to claim 1, characterized in that: The feature extraction of the printed image comprises: Preprocess the printed image, including converting the printed image to Lab color space, and performing image enhancement, median filtering and size unification; Based on the preprocessed printed image, target features of the printed image are extracted, wherein the target features include color features, texture features and edge features.

5. The method for evaluating the degree of printing defects of corrugated paper boxes according to claim 4, characterized in that: The extracted target features are input into the X defect types in the clustering algorithm for clustering to obtain clustering results, including: The PCA algorithm is used to reduce the dimension of the extracted target features, and the random forest algorithm is used to fit the reduced target features. According to the fitted screening indicators, the feature quantity with the greatest correlation is screened out; The K-means algorithm is used to cluster the selected features and generate clustering results.

6. A corrugated box printing defect assessment system, characterized in that: The system comprises: The target screening unit is used to detect the flatness of the corrugated paper boxes to be tested after printing, and screen out the corrugated paper boxes to be tested whose flatness meets the preset conditions as the target detection objects; The method of detecting the flatness of the printed corrugated paper box to be tested comprises: In the formula, F fl represents the flatness factor, α and β are constant coefficients, satisfying 0<α<0.01, 0<β<1; T and P represent the temperature and pressure during the printing process of the corrugated box, respectively, and W represents the moisture content of the corrugated box; H and L represent the thickness and length of the corrugated box paperboard, respectively; E and I represent the elastic modulus and structural moment of inertia of the corrugated box paperboard, respectively, and e is the base of the natural logarithm; A clustering unit is used to collect a printed image of a target detection object, extract features from the printed image, input the extracted target features into the X defect types in the clustering algorithm for clustering, and obtain a clustering result; A defect analysis unit, used to determine the defect analysis result of the target feature according to the clustering result, including when the clustering result is X defect types, determining the corresponding defect type and the number of defect features according to the clustering cluster where the target feature is located; when the clustering result is more than X defect types, using spectral analysis to determine the defect type and the number of defect features of the target feature; The parameter adjustment unit is used to calculate the printing defect degree of the corrugated paper box to be tested by using the defect analysis results and the number of target detection objects, and adjust the next printing parameters of the corrugated paper box according to the feedback of the printing defect degree.

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and when the processor executes the computer instructions, the electronic device executes the method for evaluating the degree of printing defects of corrugated paperboard as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the method for evaluating the degree of printing defects of corrugated paper boxes according to any one of claims 1 to 5.

Images