Paperboard surface cling film laminating process and fresh-keeping carton

Abstract

The present invention belongs to the field of intelligent production technology, and in particular, relates to a paperboard surface cling film laminating process and a fresh-keeping carton, the process comprising: obtaining a target feature set of a target product, such as target product size, type of food to be packaged, and fresh-keeping requirements; performing quality problem analysis on the target product to obtain a problem feature set, such as water loss, gas permeation, etc.; based on the problem feature set, assigning a weight value to each feature in the target feature set to obtain a target revised feature set, the weight value will guide the setting of subsequent process parameters to ensure that quality problems are focused on; determining the laminating process parameter range according to the target revised feature set, including parameters such as temperature, pressure, and time; inputting the process parameter range into the equipment control system to implement the laminating process. The above process ensures that in the actual production process, the equipment can operate according to the set parameters, so that the laminating process can be ensured to meet expectations and produce products that meet the requirements.

Description

Technical Field

[0001] The invention belongs to the technical field of intelligent production, and in particular relates to a paperboard surface cling film laminating process and a fresh-keeping carton. Background Art

[0002] In order to optimize the functions of packaging materials, the following functions are often obtained by hot pressing of coating materials such as polyethylene (PE), polypropylene (PP), polyvinyl alcohol (EVOH) on the surface of paperboard used to form packaging boxes:

[0003] (1) Moisture-proof and fresh-keeping: The moisture-proof property of the coating material can effectively reduce the evaporation and penetration of water, and delay the water loss of vegetables, fruits or flowers.

[0004] (2) Gas barrier: The coating material has certain gas barrier properties, which can prevent the entry and exit of oxygen and carbon dioxide, slowing down biological respiration and bacterial growth.

[0005] (3) Retain moisture: The coating material can effectively retain moisture in vegetables, fruits or flowers, extending their shelf life.

[0006] However, in the actual production process, due to the lack of precise process parameter control, the following cardboard production problems often occur:

[0007] Uneven film coverage: If parameters such as temperature, pressure or time are not precisely controlled, the laminating material may not cover the paperboard surface evenly, with some areas appearing thinner and thicker, affecting the functionality and aesthetics of the packaging.

[0008] Unstable laminating quality: Imprecise parameter control may lead to unstable laminating quality. Some products may experience separation or detachment between the laminating material and the cardboard, which reduces the packaging effect and quality.

[0009] Increased product loss: Due to unstable lamination quality or uneven coverage, product loss may increase, such as low lamination material utilization rate, more cardboard required for re-lamination, etc., which increases production costs.

[0010] Degradation of functional performance: Accurate control of process parameters is the key to ensuring that the coating material can exert its functional performance. If the control is not accurate, it may lead to degradation of functional performance such as moisture resistance, gas barrier, and moisture retention, affecting the preservation effect of the product. Summary of the invention

[0011] The present invention provides a paperboard surface fresh-keeping film coating process and a fresh-keeping paper box, which can effectively solve the problems in the background technology.

[0012] In order to achieve the above object, the technical solution adopted by the present invention is:

[0013] The process of laminating paperboard surface with plastic wrap includes:

[0014] Get the target feature set of the cardboard target product;

[0015] Performing quality problem analysis on the target product to obtain a problem feature set;

[0016] Based on the problem feature set, assigning a weight value to each feature in the target feature set to obtain a target revised feature set;

[0017] Determining a lamination process parameter range according to the target revised feature set;

[0018] The process parameter range is input into the equipment control system to implement the coating process.

[0019] Furthermore, the paperboard surface cling film laminating process also includes:

[0020] Place the laminating material in the laminating position of the heat press;

[0021] The paperboards are sequentially transferred to the bottom workbench of the heat press to ensure that the relative position between the paperboard surface and the coating material is accurate;

[0022] Lowering the upper hot pressing plate of the hot pressing machine so that the hot pressing plate and the laminating material are attached to the surface of the paperboard;

[0023] Within the process parameter range, controlling the hot press plate to heat and apply a set pressure at the same time, and maintaining the heating and pressure for a set time to complete the curing;

[0024] After the curing is completed, the hot press plate is lifted up to allow the laminated paperboard to be taken out.

[0025] Furthermore, quality problem analysis is performed on the target product to obtain a problem feature set, including:

[0026] Traverse historical data, sort cardboard quality issues according to frequency of occurrence, and select important problem factors based on the sorting results;

[0027] Classify the important problem factors and describe the problem for each classification;

[0028] The description content is taken as a problem feature in the problem feature set.

[0029] Furthermore, based on the problem feature set, a weight value is assigned to each feature in the target feature set, including:

[0030] Establish a mapping relationship based on the correlation between the problem feature set and the target feature set;

[0031] Based on the mapping relationship, the influence of the associated problem features on the target features is evaluated and converted into weights;

[0032] The comprehensive weight of each target feature is calculated comprehensively as the final weight value.

[0033] Furthermore, it also includes: using a machine learning algorithm to analyze the traversed historical data to identify potential new problem factors of the cardboard, and taking the new problem factors as part of the problem feature set.

[0034] Furthermore, a machine learning algorithm is used to analyze the historical data to identify potential new problems of cardboard, including:

[0035] Select a machine learning algorithm to perform the analysis task:

[0036] Adjust model parameters based on the required analysis depth and data complexity;

[0037] The preprocessed data is used to train the selected machine learning model, and the trained model is applied to analyze the historical data to identify potential new problem factors.

[0038] Furthermore, the influence of the associated problem features on the target features is evaluated and converted into weights, including:

[0039] Building a hierarchical structure based on the problem features and the target features, using a comparison matrix to compare the problem features in pairs to obtain pairwise comparison results;

[0040] Constructing a judgment matrix, inputting the pairwise comparison results into the judgment matrix, and calculating the eigenvector of the judgment matrix;

[0041] According to the feature vector, the influence weight of the problem feature on the target feature is calculated by the eigenvalue method.

[0042] Furthermore, the comprehensive weight of each target feature is calculated comprehensively, including:

[0043] Determine the weight of the impact degree of the problem feature on the target feature, and score the impact degree;

[0044] Based on each target feature, a weighted sum of the target features is obtained by calculating a weighted average;

[0045] The weighted sum of the target features is normalized to obtain the comprehensive weight of the target features.

[0046] Furthermore, the target feature comprehensive weight calculation formula is:

[0047]

[0048] W Y is the comprehensive weight of the target feature, w ti is the weight of the influence of the problem feature on the target feature, x pi is the score of the impact degree, and n is the number of problem features.

[0049] The fresh-keeping paper box is assembled by a plurality of cardboards of set shapes, and the cardboards are obtained by the cardboard surface laminating process of the fresh-keeping film as described in any one of claims 1 to 9.

[0050] The technical solution of the present invention can achieve the following technical effects:

[0051] In the present invention, by acquiring the feature set of the target product and analyzing its quality problems, it is possible to fully understand the product needs and possible problems, so as to design the coating process in a targeted manner, which can maximize the quality of the product in terms of freshness preservation, moisture resistance, gas barrier, etc., and improve the market competitiveness of the product; by assigning a weight value to each feature in the target feature set, determining the target revised feature set, and determining the coating process parameter range based on the revised feature set, it is possible to ensure that the process parameters match the product quality requirements, avoid quality problems caused by improper parameter settings, and improve production efficiency and product quality.

[0052] The equipment control system can automatically adjust and control according to the input process parameter range, implement the lamination process, reduce manual intervention, improve production efficiency, and ensure the stability and consistency of the lamination process, thereby reducing production costs. During the implementation process, through the analysis of the target feature set and the problem feature set and the precise control of the process parameters, it can ensure that different batches of products have consistent quality and functional performance, thereby improving the reliability and predictability of the product.

[0053] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 It is a schematic diagram of the process of laminating the paperboard surface with plastic wrap;

[0056] Figure 2 A flow chart for analyzing quality issues of target products;

[0057] Figure 3 A schematic diagram of a process for assigning weight values ​​to each feature in a target feature set;

[0058] Figure 4 Schematic diagram of the process of using machine learning algorithms to analyze traversed historical data. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0061] Embodiment 1

[0062] like Figure 1 As shown, the paperboard surface cling film laminating process includes:

[0063] S1: Obtain a target feature set of the target paperboard product; for example, the target feature set includes target product size, food type to be packaged, freshness requirements, transportation environment, etc. These features will become the basis for designing the laminating process to ensure that the final product can meet the expected requirements;

[0064] S2: Analyze the quality problems of the target product and obtain a set of problem features. Possible problems include water loss, gas permeation, uneven coating, etc. By analyzing the set of problem features, we can determine the problems that need to be solved in the process.

[0065] S3: Based on the problem feature set, assign a weight value to each feature in the target feature set to obtain a target revised feature set; in this step, assign a weight value to each feature in the target feature set according to the severity and impact scope of the problem. These weight values ​​will guide the setting of subsequent process parameters to ensure that quality problems are solved in a focused manner;

[0066] S4: Determine the lamination process parameter range according to the target revised feature set; including parameters such as temperature, pressure, time, etc., which will be used to participate in the lamination process;

[0067] S5: Input the process parameter range into the equipment control system to implement the laminating process. Ensure that in the actual production process, the equipment can operate according to the set parameters, so as to ensure that the laminating process meets expectations and produces products that meet the requirements.

[0068] In the above embodiment, by obtaining the feature set of the target product and analyzing its quality problems, it is possible to fully understand the product requirements and possible problems, so as to design the coating process in a targeted manner, so as to maximize the quality of the product in terms of freshness preservation, moisture resistance, gas barrier, etc., and improve the market competitiveness of the product. In the implementation process, by assigning a weight value to each feature in the target feature set, determining the target revised feature set, and determining the coating process parameter range based on the revised feature set, it is possible to ensure that the process parameters match the product quality requirements, avoid quality problems caused by improper parameter settings, and improve production efficiency and product quality.

[0069] The technical solution of the present invention, by acquiring the feature set of the target product and analyzing its quality problems, can fully understand the product needs and possible problems, so as to design the coating process in a targeted manner, which can maximize the quality of the product in terms of freshness preservation, moisture resistance, gas barrier, etc., and improve the market competitiveness of the product; by assigning a weight value to each feature in the target feature set, determining the target revised feature set, and determining the coating process parameter range based on the revised feature set, it can ensure that the process parameters match the product quality requirements, avoid quality problems caused by improper parameter settings, and improve production efficiency and product quality.

[0070] The equipment control system can automatically adjust and control according to the input process parameter range, implement the lamination process, reduce manual intervention, improve production efficiency, and ensure the stability and consistency of the lamination process, thereby reducing production costs. During the implementation process, through the analysis of the target feature set and the problem feature set and the precise control of the process parameters, it can ensure that different batches of products have consistent quality and functional performance, thereby improving the reliability and predictability of the product.

[0071] Furthermore, the paperboard surface cling film laminating process also includes:

[0072] Place the laminating material in the laminating position of the heat press;

[0073] Transfer the cardboard to the bottom workbench of the heat press in sequence, ensuring that the relative position between the cardboard surface and the laminating material is accurate;

[0074] Lower the upper hot press plate of the hot press so that the hot press plate and the laminating material are attached to the surface of the paperboard; the hot press plate of the hot press heats the laminating material and applies pressure to make the laminating material bond with the surface of the paperboard;

[0075] Within the process parameter range, the hot press plate is controlled to heat and apply a set pressure at the same time, and the heating and pressure are maintained within the set time to complete the curing;

[0076] After curing is completed, the hot press plate is lifted up to allow the laminated cardboard to be taken out.

[0077] The equipment control system can automatically adjust and control according to the input process parameter range to implement the lamination process, which can reduce manual intervention, improve production efficiency, ensure the stability and consistency of the lamination process, and reduce production costs. During the implementation process, through the analysis of the target feature set and the problem feature set and the precise control of the process parameters, it can ensure that different batches of products have consistent quality and functional performance, thereby improving the reliability and predictability of the product.

[0078] As a preferred embodiment of the above, Figure 2 As shown, quality problems of the target product are analyzed to obtain a set of problem features, including:

[0079] A1: Traverse the historical data, sort the cardboard quality problems according to the frequency of occurrence, and select the important problem factors based on the sorting results;

[0080] Historical data includes but is not limited to lamination temperature, pressure, time parameters and related product defect rates. Through data mining technology, such as frequent pattern mining algorithm, the frequency of problem occurrence is analyzed to determine the most frequent quality problems. For example, if the data shows that uneven lamination is the most frequent problem, then it is listed as the first problem to be solved. These problem factors often have a greater impact on product quality and production efficiency. The problem factors with higher frequency of occurrence are selected as important problem factors to provide a basis for subsequent classification and description;

[0081] A2: Classify the important problem factors and describe the problem for each category;

[0082] Specific categories include physical factors (temperature, pressure unevenness, etc.), chemical factors (material compatibility, etc.) and operational factors (improper operation, etc.). The problem factors under each category are further described in detail to clarify the specific manifestations and possible impacts of the problem. For example, under the classification of physical factors, uneven coating temperature can be further described as local overheating or overcooling caused by the instability of the temperature control system;

[0083] A3: Take the description content as a problem feature in the problem feature set.

[0084] The problem description of each category is used as a feature in the problem feature set. These descriptions can help understand and identify product quality problems and become the basis for subsequent quality improvement and process optimization. Each feature in the problem feature set represents an aspect of the product quality problem. By comprehensively considering these features, product quality problems can be analyzed and solved more comprehensively.

[0085] In the above preferred scheme, by traversing historical data and sorting problems according to frequency of occurrence, it is possible to systematically understand the occurrence of product quality problems, rather than just relying on individual cases or incidental events. This method can ensure the comprehensiveness of problem analysis and help identify important problem factors that have a greater impact on product quality and production efficiency. By counting the frequency of occurrence of each problem factor in historical data, the severity and impact of the problem can be objectively quantified, making the problem analysis more objective and accurate and avoiding the influence of subjective bias.

[0086] During the implementation process, by classifying and describing important problem factors, the problems can be made clearer and more specific. This classification and description method helps to deeply understand the nature and characteristics of each problem factor, and provides a more specific basis and direction for subsequent problem solving. Using the problem description as a feature in the problem feature set helps to transform the lessons learned from historical data into practical actions, thereby providing clear goals and directions for subsequent quality improvement and process optimization, making improvement measures more targeted and effective.

[0087] As a preferred embodiment of the above, Figure 3 As shown in the figure, based on the problem feature set, a weight value is assigned to each feature in the target feature set, including:

[0088] B1: Establish a mapping relationship based on the correlation between the problem feature set and the target feature set;

[0089] In this step, firstly, various potential problem characteristics in the process of laminating the paperboard surface are collected and analyzed, such as uneven temperature and unstable pressure of the laminating material, and at the same time, the potential impact of these problem characteristics on the target characteristics of the laminating product (such as moisture resistance, gas barrier performance, etc.) is determined; using expert system or decision tree method, a mapping relationship is established based on the correlation between the problem characteristics and the target characteristics. This mapping relationship will guide the subsequent analysis and weight assignment to ensure that the key problem characteristics are effectively identified and processed;

[0090] B2: Based on the mapping relationship, evaluate the impact of the associated problem features on the target features and convert them into weights. Statistical analysis methods, such as regression analysis, variance analysis or machine learning models, can be used to quantify the specific impact of the problem features on the target features. This may include calculating correlation coefficients, importance scores or weights of prediction models. These quantitative indicators help determine which problem features have a significant impact on product quality and should be prioritized.

[0091] B3: Comprehensively calculate the comprehensive weight of each target feature as the final weight value. As a specific implementation paradigm, the influence of each problem feature on a single target feature can be integrated, and the final weight value can be determined by weighted average or other appropriate mathematical models. These comprehensive weights will guide the setting and adjustment of process parameters during the production process, such as adjusting the coating temperature, pressure and time, to ensure that each target feature can be optimally achieved.

[0092] During the implementation process, as a specific example: the fresh-keeping packaging of vegetables and fruits is coated. By applying the above method, the selection of coating materials and coating parameters are adjusted according to the fresh-keeping requirements of different vegetables and fruits. For example, for fruits that are easy to dehydrate, such as apples, the weight adjustment of moisture-proof performance is increased to optimize the fresh-keeping effect. Before production, the simulation software can be used to predict the specific impact of the adjusted process parameters on product quality to ensure that the adjustment can achieve the expected effect, thereby reducing the trial and error costs in actual production.

[0093] Furthermore, it also includes: using a machine learning algorithm to analyze the traversed historical data to identify potential new problem factors of the cardboard, and taking the new problem factors as part of the problem feature set.

[0094] Through the above methods, the plastic wrap coating process on the cardboard surface can continuously adapt to new problems and challenges arising in the production process, improve overall production efficiency and product quality. In addition, the introduction of machine learning algorithms makes the problem identification process more automated and intelligent, and improves the scientific and technological content of process control and future adaptability.

[0095] As a preferred embodiment of the above, Figure 4 As shown, a machine learning algorithm is used to analyze the traversed historical data to identify potential new problems of cardboard, including:

[0096] C1: Select a machine learning algorithm to perform the analysis task:

[0097] In the implementation process, you can consider using algorithms such as decision trees, random forests, support vector machines (SVM), or neural networks, which are able to process large amounts of data and identify complex data patterns and relationships. When selecting an algorithm, consider the algorithm's interpretability, accuracy, and computational complexity to ensure that the analysis results are both accurate and reliable.

[0098] C2: Adjust model parameters according to the required analysis depth and data complexity;

[0099] This includes setting the appropriate number of training iterations, learning rate, degree of regularization, etc. to optimize the performance of the model and avoid overfitting. When adjusting parameters, multiple experiments and verifications may be required to find the optimal parameter configuration to ensure that the model has good generalization ability on new data.

[0100] C3: Use the preprocessed data to train the selected machine learning model and apply the trained model to analyze historical data to identify potential new problem factors.

[0101] Use preprocessed historical data to train the selected machine learning model. The preprocessing steps include data cleaning (removing outliers and filling missing data), data transformation (such as normalization or standardization), and feature selection. During the training process, cross-validation techniques are applied to evaluate the stability and predictive ability of the model, which helps to ensure that the model not only performs well on the training data, but also maintains accuracy on unseen data. After training, the model is applied to the entire historical data set to identify new problem factors that have not been identified by previous process flows. By analyzing the results of the model output, these new problem factors are integrated into the problem feature set to provide support for subsequent process improvements.

[0102] Furthermore, the influence of the associated problem features on the target features is evaluated and converted into weights, including:

[0103] D1: Build a hierarchical structure based on problem features and target features, use a comparison matrix to compare problem features pairwise, and obtain pairwise comparison results;

[0104] During the implementation process, to evaluate the degree of influence of problem features on target features, we can first clarify the problem features and target features, and build the target features and problem features into a hierarchical structure, with the target features at the top level and the problem features at the next level, to facilitate subsequent processing. In order to determine the relative importance or degree of influence of the problem features with respect to the target features, for each problem feature, a pairwise comparison is made with another problem feature, and a standard hierarchical analysis method comparison matrix can be used. The elements of the matrix represent the relative importance of a problem feature relative to another problem feature, that is, the degree of influence of the feature on the target feature. The pairwise comparison results can provide a reliable basis and qualitative data for the subsequent allocation of the weight of the degree of influence of the problem feature on the target feature.

[0105] D2: Construct a judgment matrix, input the pairwise comparison results into the judgment matrix, and calculate the eigenvector of the judgment matrix;

[0106] D3: Based on the eigenvector, the eigenvalue method is used to calculate the influence weight of the problem feature on the target feature.

[0107] Specifically, the judgment matrix is ​​a matrix used to record the results of pairwise comparisons. Each element in the matrix represents the relative importance of one problem feature relative to another problem feature. The relative importance obtained through pairwise comparison can improve the accuracy of weight allocation, and the judgment matrix can convert these qualitative pairwise comparisons into quantitative data, thereby providing a reliable basis for subsequent weight allocation; the pairwise comparison results are input into the judgment matrix, and the judgment matrix is ​​subjected to eigenvalue decomposition to obtain eigenvectors. By calculating the eigenvectors, the relative importance obtained from the pairwise comparisons can be converted into weight ratios as the weights of the influence of the problem feature on the target feature. The judgment matrix is ​​a symmetric matrix. Before constructing the judgment matrix, a consistency test can be performed on the comparison matrix of each problem feature to verify the consistency of the judgment matrix. If the consistency test is passed, the eigenvector can be calculated and normalized to obtain the weight of the problem feature corresponding to the target feature. When performing a consistency test, the consistency index and the random consistency index can be used to evaluate the consistency of each problem feature comparison matrix, and the consistency ratio can be calculated to determine whether the matrix passes the consistency test. Through pairwise comparison and judgment matrix, the relationship between different problem features can be quantified, providing an objective basis for decision-making and ensuring that the weight of the impact of the associated problem features on the target features can accurately reflect their importance.

[0108] Furthermore, the comprehensive weight of each target feature is calculated comprehensively, including:

[0109] E1: Determine the weight of the impact of the problem feature on the target feature and score the impact;

[0110] E2: Based on each target feature, the weighted sum of the target features is obtained by calculating the weighted average;

[0111] E3: Normalize the weighted sum of the target features to obtain the comprehensive weight of the target features.

[0112] Specifically, the weight of the degree of influence of the problem feature on the target feature has been obtained in the above steps. Then, the degree of influence can be scored through questionnaires, expert evaluations, etc. The scoring can quantify the degree of influence of the problem feature on the target feature, making it comparable and quantifiable. By scoring the degree of influence, the degree of association between the problem feature and the target feature can be determined more accurately, so that the weight calculation can be performed more effectively. In order to assign weights to the target features, the comprehensive weight of the target features can be calculated by weighted average methods such as simple weighted average method, relative weighted average method, exponential weighted average method, etc. To ensure that the comprehensive weight of each target feature is within a certain range, the weighted sum of the target features can be normalized, including linear normalization, Z-score normalization, etc., to make it easier to understand.

[0113] Furthermore, the target feature comprehensive weight calculation formula is:

[0114]

[0115] W Y is the comprehensive weight of the target feature, w ti is the weight of the influence of the problem feature on the target feature, x pi is the impact score, and n is the number of problem features.

[0116] Embodiment 2

[0117] The fresh-keeping paper box is assembled by a plurality of cardboards of set shapes, and the cardboards are obtained by the cardboard surface laminating process of the fresh-keeping film as claimed in any one of claims 1 to 9.

[0118] The technical effects achieved by this embodiment are as described in Embodiment 1 and will not be repeated here.

[0119] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A process for coating paperboard surface with plastic wrap, characterized in that: include: Obtain a target feature set of a cardboard target product, the target feature set including target product size, food type to be packaged, freshness requirements, and transportation environment; Analyze the quality problems of the target product to obtain a set of problem characteristics, including water loss, gas permeation, and uneven coating; Based on the problem feature set, assign a weight value to each feature in the target feature set according to the severity and impact scope of the problem, to obtain a target revised feature set; Determining a lamination process parameter range according to the target revised feature set; Inputting the process parameter range into the equipment control system, including temperature, pressure, and time, to implement the coating process; Analyzing the quality problems of the target product to obtain a problem feature set includes: traversing historical data, sorting the cardboard quality problems according to the frequency of occurrence, and selecting important problem factors according to the sorting results; classifying the important problem factors and describing the problem for each classification; and using the description content as a problem feature in the problem feature set; Based on the problem feature set, assigning a weight value to each feature in the target feature set, including: establishing a mapping relationship according to the correlation between the problem feature set and the target feature set; based on the mapping relationship, evaluating the influence of the associated problem feature on the target feature and converting it into a weight; and comprehensively calculating the comprehensive weight of each target feature as the final weight value; It also includes: using machine learning algorithms to analyze traversed historical data to identify potential new problem factors of cardboard and taking the new problem factors as part of the problem feature set.

2. The paperboard surface cling film coating process according to claim 1, characterized in that: Also includes: Place the laminating material in the laminating position of the heat press; The paperboards are sequentially transferred to the bottom workbench of the heat press to ensure that the relative position between the paperboard surface and the coating material is accurate; Lowering the upper hot pressing plate of the hot pressing machine so that the hot pressing plate and the laminating material are attached to the surface of the paperboard; Within the process parameter range, controlling the hot press plate to heat and apply a set pressure at the same time, and maintaining the heating and pressure for a set time to complete the curing; After the curing is completed, the hot press plate is lifted up to allow the laminated paperboard to be taken out.

3. The paperboard surface cling film coating process according to claim 1, characterized in that: Machine learning algorithms are used to analyze historical data to identify potential new problems with cardboard, including: Select a machine learning algorithm to perform the analysis task: Adjust model parameters based on the required analysis depth and data complexity; The preprocessed data is used to train the selected machine learning model, and the trained model is applied to analyze the historical data to identify potential new problem factors.

4. The paperboard surface cling film coating process according to claim 1, characterized in that: Evaluate the influence of the relevant problem features on the target features and convert them into weights, including: Building a hierarchical structure based on the problem features and the target features, using a comparison matrix to compare the problem features in pairs to obtain pairwise comparison results; Constructing a judgment matrix, inputting the pairwise comparison results into the judgment matrix, and calculating the eigenvector of the judgment matrix; According to the feature vector, the influence weight of the problem feature on the target feature is calculated by the eigenvalue method.

5. The paperboard surface cling film coating process according to claim 1, characterized in that: The comprehensive weight of each target feature is calculated comprehensively, including: Determine the weight of the impact degree of the problem feature on the target feature, and score the impact degree; Based on each target feature, a weighted sum of the target features is obtained by calculating a weighted average; The weighted sum of the target features is normalized to obtain the comprehensive weight of the target features.

6. The paperboard surface cling film coating process according to claim 5, characterized in that: The calculation formula of the comprehensive weight of target features is: W Y is the comprehensive weight of the target feature, w ti is the weight of the influence of the problem feature on the target feature, x pi is the score of the impact degree, and n is the number of problem features.

Images