Method for comprehensive evaluation of cigarette paper

Abstract

The application discloses a comprehensive evaluation method of cigarette paper, which comprises the following steps: S1, data collection; S2, batch judgment; S3, comprehensive evaluation; S4, abnormal early warning; and S5, abnormal analysis. As the comprehensive evaluation method of the cigarette paper, when the quality of the cigarette paper product changes, the abnormal early warning can be timely given, and the abnormal analysis can be given in combination with historical experience; when it is necessary to continuously improve the quality of the cigarette paper product, the evaluation data can be given based on the comprehensive evaluation method as the basis for improvement. The application provides a scientific and intelligent evaluation method for the cigarette paper which has passed the detection, and can be used for comprehensively evaluating the comprehensive quality of the cigarette paper, realizing quantitative analysis of the evaluation indexes, automatic abnormal early warning and judgment.

Description

Technical Field

[0001] This invention relates to the field of cigarettes, and more specifically to a method for comprehensively evaluating cigarette paper. Background Technology

[0002] Cigarette auxiliary materials include cigarette paper, tobacco tow, tipping paper, and forming paper. Cigarette paper, as one of the main auxiliary materials for cigarettes, although accounting for only 5% of the total weight of a cigarette, is an indispensable raw material in the cigarette manufacturing process. As is well known, smoking is essentially smoking the smoke produced by burning tobacco, and cigarette paper is the carrier of the tobacco. During the combustion process of cigarettes, cigarette paper is the only component besides the tobacco that directly participates in combustion. The cigarette paper's participation in the burning process directly affects the appearance of the cigarette's combustion, the composition of the smoke, and the smoking quality. Therefore, the quality of cigarette paper plays a crucial role in the overall quality of the cigarette.

[0003] During the testing process, cigarette paper undergoes 17 tests, 10 of which are quantifiable: basis weight, width, longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, whiteness, opacity, fluorescent whiteness, smoldering rate, and moisture content. The remaining 7 are non-quantifiable: odor, core damage, number of joints, appearance, and markings. Currently, cigarette paper testing results have two standards: qualified and unqualified. However, there is no scientific evaluation method or quantitative assessment for qualified cigarette paper, and no basis for further improvement of product quality. Furthermore, there is no quantitative assessment for cigarette paper of the same brand from different manufacturers; and there is no way to provide early warning or assessment when quality changes occur.

[0004] Therefore, there is an urgent need for a scientific method to determine the overall quality of cigarette paper. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a method for comprehensively evaluating cigarette paper, which can automatically perform quantitative analysis of evaluation indicators, automatically issue early warnings of anomalies, and make judgments.

[0006] The technical solution adopted by this invention to solve its technical problem is as follows:

[0007] A comprehensive evaluation method for cigarette paper, including

[0008] S1, Data Acquisition

[0009] Data was collected from several batches of cigarette paper to be evaluated.

[0010] The scope of data collection includes: quantitative (g / m³) 2 Width (mm), longitudinal tensile energy absorption (J / m) 2Ten quantitative indicators, including air permeability (cu), air permeability coefficient of variation (%), whiteness (%), opacity (%), fluorescent whiteness (%), smoldering rate (s / 150mm), and moisture content (%);

[0011] In addition, there are 7 non-quantifiable indicators, including odor, core damage, number of joints, appearance, markings, cigarette paper anion and cation content, and ash content.

[0012] S2, Batch Differential Detection

[0013] Enter the data collection results and determine the quality of each batch of cigarette paper according to the judgment rules;

[0014] When a batch of cigarette paper is determined to be substandard, an anomaly analysis is performed.

[0015] When a batch of cigarette paper is deemed qualified, a comprehensive evaluation is conducted.

[0016] Judgment rules and methods:

[0017] 1) Classify defects in the data collection indicators.

[0018] Eight major defects: longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, fluorescent whiteness, smoldering rate, odor, core damage, and cigarette paper anion and cation (not tested);

[0019] Six serious defects: basis weight, width, whiteness, moisture content, number of joints, and ash content (not tested);

[0020] Three common defects: opacity, appearance, and markings;

[0021] 2) Judgment method

[0022] ① Judgment of non-quantifiable indicators (external quality: odor, core damage, number of joints, appearance, markings):

[0023] External quality assessment is conducted on a batch of cigarette paper, using units of 5 rolls as a group.

[0024] If there is a serious defect ≥ 1 roll, or a more serious defect ≥ 2 rolls, or a general defect ≥ 3 rolls, or both a more serious defect and a general defect ≥ 2 rolls, then 5 rolls will be drawn.

[0025] If the batch of materials still falls within the above-mentioned scope of rejection, then the batch of materials is deemed unqualified.

[0026] If it does not meet the above rejection criteria, then 5 more volumes will be sampled, and the results of the second sampling inspection will be used as the basis for judgment.

[0027] If the remaining number of volumes is less than the number of additional samples to be drawn, no further sampling will be conducted, and the result of the first inspection will be used for judgment.

[0028] ② Determination of quantitative indicators (physicochemical judgment: quantitative value, width, longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, whiteness, opacity, hygiene indicators (fluorescent whiteness), smoldering rate, moisture content):

[0029] Physicochemical tests were conducted on a batch of cigarette paper:

[0030] If one or more major defects are found to be non-compliant, the batch of materials shall be deemed non-compliant.

[0031] If two or more serious defects are found to be unqualified, the batch of materials shall be deemed unqualified.

[0032] If three or more general defects fail to meet the standard, the batch of materials is deemed unqualified.

[0033] If one major defect and two minor defects are present at the same time, the batch of materials shall be deemed unqualified.

[0034] If the detected defects are in longitudinal tensile energy absorption or air permeability, a re-inspection is required:

[0035] Re-inspection method:

[0036] If the re-inspection still fails, the batch of materials is deemed unqualified.

[0037] If the re-inspection is qualified, a second re-inspection will be conducted, and the result of this re-inspection will be used as the basis for judgment.

[0038] S3, Overall Evaluation

[0039] Using principal component analysis, a comprehensive evaluation model was constructed for 10 quantitative indicators of a batch of cigarette paper to conduct a comprehensive evaluation.

[0040] S3.1, Data Standardization

[0041] Standardize the data for 10 quantitative indicators;

[0042] S3.2, Extract principal components

[0043] Calculate eigenvalues ​​and eigenvectors:

[0044] The standardized data is represented as a k*p matrix (k = 1, 2, ..., n+1; p = 1, 2, ..., N), and its corresponding eigenvalues ​​λ i Principal component variance contribution, orthogonalized unit eigenvector Z i The variance contribution rate is calculated using the following formula:

[0045]

[0046] Z iThe magnitude of the value indicates the ability of the component to provide information about the reaction; principal components are extracted based on their numerical values.

[0047] S3.3, Create a comprehensive evaluation model

[0048] Establish a principal component evaluation sub-model;

[0049] F m =a 1m ×X1+a 2m ×X2+a 3m ×X3+……+a nm ×X n ;

[0050] Among them, a 1m a 2m a 3m ...a nm Principal component score coefficients;

[0051] m is the sequence number of the extracted principal components;

[0052] X = (X1, X2, ..., X...) n Let X1, X2, X3...X be an n-dimensional random variable. 10 These represent quantitative amounts (g / m³) in sequence. 2 Width (mm), longitudinal tensile energy absorption (J / m) 2 ), air permeability (cu), air permeability coefficient of variation (%), whiteness (%), opacity (%), fluorescent whiteness (%), smoldering rate (s / 150mm), moisture content (%);

[0053] Based on the variance contribution rate of each principal component and the principal component evaluation sub-model, a principal component comprehensive evaluation model is established:

[0054] F = Z1F1 + Z2F2 + ... + Z m F m ;

[0055] Among them, Z1, Z2, Z3, ... Z m The variance contribution rate for extracting principal components;

[0056] Using the comprehensive evaluation model F for cigarette paper quality, the comprehensive score of each batch of cigarette paper is automatically calculated and sorted.

[0057] S4, Abnormal Warning

[0058] Establish evaluation criteria and anomaly alarm rules;

[0059] When the comprehensive evaluation score of cigarette paper quality is greater than or less than 3σ, an abnormal warning will be issued for the quality data of that batch of cigarette paper.

[0060] Trend analysis is performed on the data of the comprehensive evaluation of daily cigarette paper quality, and trend warnings are issued when the trend changes.

[0061] When an alert is triggered, proceed to anomaly analysis;

[0062] S5, Anomaly Analysis

[0063] When a batch of cigarette paper is found to be substandard, or when the comprehensive quality evaluation score of the cigarette paper does not meet the evaluation standards or trend changes, an anomaly analysis will be automatically performed, and the inspection personnel will analyze the cause.

[0064] S6, Case Studies

[0065] The causes of abnormal warnings and trend warnings are classified and organized to form experience cases.

[0066] The beneficial effects of this invention are as follows:

[0067] This application provides a scientific and intelligent evaluation method for qualified cigarette paper, which can be used to comprehensively evaluate the overall quality of cigarette paper, realize automatic quantitative analysis of evaluation indicators, and automatically issue early warnings and judgments of anomalies.

[0068] As a comprehensive evaluation method for cigarette paper, this application can issue timely warnings of abnormalities when quality changes occur in cigarette paper products, and provide anomaly analysis based on historical experience; when it is necessary to continue to improve the quality of cigarette paper products, evaluation data can be provided as a basis for improvement based on this comprehensive evaluation method; at the same time, this application also provides a quantitative evaluation approach for cigarette paper of the same brand but from different manufacturers. Attached Figure Description

[0069] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0070] Figure 1 This is a system block diagram of the comprehensive evaluation method for this cigarette paper;

[0071] Figure 2 This is a feature value scree diagram of Example 2. Detailed Implementation

[0072] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] Example 1

[0074] A comprehensive evaluation method for cigarette paper, including

[0075] S1, Data Acquisition

[0076] Data was collected from several batches of cigarette paper to be evaluated.

[0077] The scope of data collection includes: quantitative (g / m³) 2 Width (mm), longitudinal tensile energy absorption (J / m) 2 Ten quantitative indicators, including air permeability (cu), air permeability coefficient of variation (%), whiteness (%), opacity (%), fluorescent whiteness (%), smoldering rate (s / 150mm), and moisture content (%);

[0078] In addition, there are 7 non-quantifiable indicators, including odor, core damage, number of joints, appearance, markings, cigarette paper anion and cation content, and ash content.

[0079] S2, Batch Differential Detection

[0080] Enter the data collection results and determine the quality of each batch of cigarette paper according to the judgment rules;

[0081] When a batch of cigarette paper is determined to be substandard, an anomaly analysis is performed.

[0082] When a batch of cigarette paper is deemed qualified, a comprehensive evaluation is conducted.

[0083] Judgment rules and methods:

[0084] 1) Classify defects in the data collection indicators.

[0085] Eight major defects: longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, fluorescent whiteness, smoldering rate, odor, core damage, and cigarette paper anion and cation (not tested);

[0086] Six serious defects: basis weight, width, whiteness, moisture content, number of joints, and ash content (not tested);

[0087] Three common defects: opacity, appearance, and markings;

[0088] 2) Judgment method

[0089] ① Judgment of non-quantifiable indicators (external quality: odor, core damage, number of joints, appearance, markings):

[0090] External quality assessment of a batch of cigarette paper is conducted on a per-roll basis:

[0091] If there is a serious defect ≥ 1 roll, or a more serious defect ≥ 2 rolls, or a general defect ≥ 3 rolls, or both a more serious defect and a general defect ≥ 2 rolls, then 5 rolls will be drawn.

[0092] If the batch of materials still falls within the above-mentioned scope of rejection, then the batch of materials is deemed unqualified.

[0093] If it does not meet the above rejection criteria, then 5 more volumes will be sampled, and the results of the second sampling inspection will be used as the basis for judgment.

[0094] If the remaining number of volumes is less than the number of additional samples to be drawn, no further sampling will be conducted, and the result of the first inspection will be used for judgment.

[0095] ② Determination of quantitative indicators (physicochemical judgment: quantitative value, width, longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, whiteness, opacity, hygiene indicators (fluorescent whiteness), smoldering rate, moisture content):

[0096] Physicochemical tests were conducted on a batch of cigarette paper:

[0097] If one or more major defects are found to be non-compliant, the batch of materials shall be deemed non-compliant.

[0098] If two or more serious defects are found to be unqualified, the batch of materials shall be deemed unqualified.

[0099] If three or more general defects fail to meet the standard, the batch of materials is deemed unqualified.

[0100] If one major defect and two minor defects are present at the same time, the batch of materials shall be deemed unqualified.

[0101] If the detected defects are in longitudinal tensile energy absorption or air permeability, a re-inspection is required:

[0102] Re-inspection method:

[0103] If the re-inspection still fails, the batch of materials is deemed unqualified.

[0104] If the re-inspection is qualified, a second re-inspection will be conducted, and the result of this re-inspection will be used as the basis for judgment.

[0105] S3, Overall Evaluation

[0106] Using principal component analysis, a comprehensive evaluation model was constructed by selecting 10 quantitative indicators for a certain batch of cigarette paper, and a comprehensive evaluation was conducted.

[0107] S3.1, Data Standardization

[0108] Standardize the data for 10 quantitative indicators;

[0109] S3.2, Extract principal components

[0110] Calculate eigenvalues ​​and eigenvectors:

[0111] The standardized data is represented as a k*p matrix (k = 1, 2, ..., n+1; p = 1, 2, ..., N), where N is the number of parallel experiments, and its corresponding eigenvalues ​​λ i Principal component variance contribution, orthogonalized unit eigenvector Z i The variance contribution rate is calculated using the following formula:

[0112]

[0113] Z i The magnitude of the value indicates the ability of the component to provide information about the reaction; principal components are extracted based on their numerical values.

[0114] S3.3, Create a comprehensive evaluation model

[0115] Establish a principal component evaluation sub-model;

[0116] F m =a 1m ×X1+a 2m ×X2+a 3m ×X3+……+a nm ×X n ;

[0117] Among them, a 1m a 2m a 3m ...a nm Principal component score coefficients;

[0118] m is the sequence number of the extracted principal components;

[0119] X = (X1, X2, ..., X...) n Let X1, X2, X3...X be an n-dimensional random variable. 10 These represent quantitative amounts (g / m³) in sequence. 2 Width (mm), longitudinal tensile energy absorption (J / m) 2 ), air permeability (cu), air permeability coefficient of variation (%), whiteness (%), opacity (%), fluorescent whiteness (%), smoldering rate (s / 150mm), moisture content (%);

[0120] Based on the variance contribution rate of each principal component and the principal component evaluation sub-model, a principal component comprehensive evaluation model is established:

[0121] F = Z1F1 + Z2F2 + ... + Z m F m ;

[0122] Among them, Z1, Z2, Z3, ... Z m The variance contribution rate for extracting principal components;

[0123] Using the comprehensive evaluation model F for cigarette paper quality, the comprehensive score of each batch of cigarette paper is automatically calculated and sorted.

[0124] S4, Abnormal Warning

[0125] Establish evaluation criteria and anomaly alarm rules;

[0126] When the comprehensive evaluation score of cigarette paper quality is greater than or less than 3σ, an abnormal warning will be issued for the quality data of that batch of cigarette paper.

[0127] Trend analysis is performed on the data of the comprehensive evaluation of daily cigarette paper quality, and trend warnings are issued when the trend changes.

[0128] When an alert is triggered, proceed to anomaly analysis;

[0129] S5, Anomaly Analysis

[0130] When a batch of cigarette paper is found to be substandard, or when the comprehensive quality evaluation score of the cigarette paper does not meet the evaluation standards or shows a trend change, an anomaly analysis will be automatically performed, and the inspection personnel will analyze the cause.

[0131] Example 2

[0132] The comprehensive evaluation method for cigarette paper shown in Example 1 is used to conduct a comprehensive quality evaluation of the cigarette paper.

[0133] S1, Data Acquisition

[0134] Data was collected from 57 batches of cigarette paper to be evaluated, and the results are shown in Table 1.

[0135] Table 1. Statistical table of quality data collection for different batches of cigarette paper

[0136]

[0137]

[0138] S2, Batch Differential Detection

[0139] Enter the data collection results and determine whether each batch of cigarette paper is qualified or not according to the judgment rules;

[0140] The assessment indicates that all batches of cigarette paper are of acceptable quality and can proceed with a comprehensive evaluation.

[0141] S3, Overall Evaluation

[0142] Standardize the data of 10 quantitative indicators for a selected batch of cigarette paper;

[0143] The formula for calculating data standardization is as follows:

[0144]

[0145] Where, x np Given the original data (n = 1, 2, ..., 10; p = 1, 2, ..., N), S is the average value of the nth indicator. n Let x' be the standard deviation of the data. np The data has been standardized.

[0146] Example: Table 2 shows the data standardization process for the "Width (mm)" indicator:

[0147] Table 2 Data Standardization - Width (mm)

[0148]

[0149]

[0150] Principal component analysis was performed using SPSS software, and the results are shown in Table 3.

[0151] Table 3 Principal Component Analysis Table

[0152]

[0153] Determined based on the principle that the eigenvalue is greater than 1:

[0154] There are 3 principal components, with contribution rates of 36.351%, 19.566%, and 14.020%, respectively. The cumulative variance contribution rate of the first 3 eigenvectors is 69.937%, and all eigenvalues ​​are greater than 1.

[0155] Combination Figure 2 The eigenvalue scree plot shows that the first three principal components contain most of the information for the 10 indicators of cigarette paper quality; therefore, it is feasible to use the first three principal components to evaluate the quality of different batches of cigarette paper in this embodiment.

[0156] Table 4 Principal Component Matrix

[0157]

[0158] Calculate the principal component score coefficients based on the principal component analysis table in Table 3 and the principal component matrix table in Table 4:

[0159] Principal component score coefficient = component values ​​of the principal component matrix / squared principal component eigenvalues;

[0160] For example: a 11 = -0.53 ÷ (3.635) 2 ) = -0.040;

[0161] Therefore, the evaluation models for each principal component are as follows:

[0162]

[0163]

[0164]

[0165] The three extracted principal components cover all the original variables. These three new indicators are used to replace the original ten indicators to establish a comprehensive evaluation model F for cigarette paper quality based on principal components.

[0166]

[0167] Using the comprehensive evaluation model F for cigarette paper quality, the comprehensive score of each batch of cigarette paper was automatically calculated and sorted. The results are shown in Table 5.

[0168] Table 5 shows the overall quality scores of some batches of cigarette paper.

[0169] Batch number F value 1 1772.818 2 1779.573 3 1764.695 4 1759.666 5 1762.774 6 1748.351 7 1759.788 8 1786.534 9 1772.416 10 1801.362 11 1758.708 12 1755.67 13 1716.806 14 1781.558 15 1823.945 16 1771.151 17 1784.452

[0170] S4, Abnormal Warning

[0171] Establish evaluation criteria and anomaly alarm rules;

[0172] When the comprehensive evaluation score of cigarette paper quality is greater than or less than 3σ, an abnormal warning will be issued for the quality data of that batch of cigarette paper.

[0173] Trend analysis is performed on the data of the comprehensive evaluation of daily cigarette paper quality, and trend warnings are issued when the trend changes.

[0174] Table 6 shows the abnormal warning situations for some batches in this embodiment. When a warning occurs, an abnormal analysis is initiated.

[0175] Table 6. Statistics on the Number of Abnormal Alarms

[0176] batch Is it abnormal? Number of alarms 1 no 0 2 no 0 3 no 0 4 no 0 5 no 0 6 no 0 7 no 0 8 no 0 9 yes 1 10 no 0 11 no 0 12 no 0 13 yes 1 14 no 0 15 no 0 16 no 0 17 no 0

[0177] S5, Anomaly Analysis

[0178] When a batch of cigarette paper is found to be substandard, or when the comprehensive quality evaluation score of the cigarette paper does not meet the evaluation standards or trend changes, an anomaly analysis will be automatically performed, and the inspection personnel will analyze the cause.

[0179] S6, Case Studies

[0180] The causes of abnormal warnings and trend warnings are classified and organized to form experience cases.

[0181] Example 3

[0182] Reference Figure 1A comprehensive evaluation system for cigarette paper, including:

[0183] The data acquisition module is used to collect data on several batches of cigarette paper to be evaluated; the scope of data collection includes quantitative and non-quantifiable indicators related to the quality of cigarette paper.

[0184] The judgment result input module is used to input the data collection results and judge the quality of each batch of cigarette paper according to the judgment rules.

[0185] When a batch of cigarette paper is determined to be substandard, an anomaly analysis is performed.

[0186] When a batch of cigarette paper is deemed qualified, a comprehensive evaluation is conducted.

[0187] The comprehensive evaluation module uses principal component analysis to construct a comprehensive evaluation model for n quantitative indicators of a batch of cigarette paper: First, a principal component evaluation sub-model is established;

[0188] F m =a 1m ×X1+a 2m ×X2+a 3m ×X3+……+a nm ×X n ;

[0189] Among them, a 1m a 2m a 3m ...a nm Principal component score coefficients;

[0190] m is the sequence number of the extracted principal components;

[0191] X = (X1, X2, ..., X...) n Let X1, X2, X3...X be an n-dimensional random variable. n These represent different quantitative indicators in sequence;

[0192] Secondly, based on the variance contribution rate of each principal component and the principal component evaluation sub-model, a principal component comprehensive evaluation model is established:

[0193] F = Z1F1 + Z2F2 + ... + Z m F m ;

[0194] Among them, Z1, Z2, Z3, ... Z m The variance contribution rate for extracting principal components;

[0195] Using the comprehensive evaluation model F for cigarette paper quality, the comprehensive score of each batch of cigarette paper is automatically calculated and sorted.

[0196] The anomaly warning module contains evaluation criteria and anomaly alarm rules.

[0197] When the comprehensive evaluation score of cigarette paper quality is greater than or less than 3σ, an abnormal warning will be issued for the quality data of that batch of cigarette paper.

[0198] Trend analysis is performed on the data of the comprehensive evaluation of daily cigarette paper quality, and trend warnings are issued when the trend changes.

[0199] When an alert is triggered, proceed to anomaly analysis;

[0200] The anomaly analysis module automatically performs anomaly analysis when there are unqualified batches of cigarette paper, or when the comprehensive quality evaluation score of cigarette paper does not meet the evaluation standards or trend changes. The inspection personnel analyze the causes, or the system automatically pushes the causes of the anomalies based on historical data and classic cases.

[0201] The experience case module is used to classify and organize the causes of anomaly warnings and trend warnings to form experience cases.

[0202] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A comprehensive evaluation method for cigarette paper, characterized by: include S1, Data Acquisition Data was collected from several batches of cigarette paper to be evaluated. Scope of data collection: quantitative and non-quantifiable indicators related to cigarette paper quality; The data collection scope includes 10 quantitative indicators: quantitative, width, longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, whiteness, opacity, fluorescent whiteness, smoldering rate, and moisture content. In addition, there are 7 non-quantifiable indicators, including odor, core damage, number of joints, appearance, markings, cigarette paper anion and cation content, and ash content. S2, Batch Differential Detection Enter the data collection results and determine the quality of each batch of cigarette paper according to the judgment rules; When a batch of cigarette paper is determined to be substandard, an anomaly analysis is performed. When a batch of cigarette paper is deemed qualified, a comprehensive evaluation is conducted. When determining the quality of each batch of cigarette paper according to the judgment rules, the judgment rules and methods include: S2.1 Classify defects in the data acquisition indicators. Eight major defects: longitudinal tensile energy absorption, air permeability, air permeability coefficient of variation, fluorescent whiteness, smoldering rate, odor, core damage, and anion and cation content of cigarette paper; Six major defects: basis weight, width, whiteness, moisture content, number of joints, and ash content; Three common defects: opacity, appearance, and markings; S2.2 Judgment Method (1) Determination of non-quantifiable indicators: External quality assessment of a batch of cigarette paper is conducted on a per-roll basis: If there is a serious defect ≥ 1 roll, or a more serious defect ≥ 2 rolls, or a general defect ≥ 3 rolls, or both a more serious defect and a general defect ≥ 2 rolls, then 5 rolls will be drawn. If the batch of materials still falls within the above-mentioned scope of rejection, then the batch of materials is deemed unqualified. If it does not meet the above rejection criteria, then 5 more volumes will be sampled, and the results of the second sampling inspection will be used as the basis for judgment. If the remaining number of volumes is less than the number of additional samples to be drawn, no further sampling will be conducted, and the result of the first inspection will be used for judgment. (2) Determination of quantitative indicators: Physicochemical tests were conducted on a batch of cigarette paper: If one or more major defects are found to be non-compliant, the batch of materials shall be deemed non-compliant. If two or more serious defects fail to meet the requirements, the batch of materials is deemed unqualified. If three or more general defects fail to meet the standard, the batch of materials is deemed unqualified. If one major defect and two minor defects are present at the same time, the batch of materials shall be deemed unqualified. If the detected defects are longitudinal tensile energy absorption or air permeability, they need to be re-inspected. S3, Overall Evaluation Principal component analysis was used to analyze a batch of cigarette paper. A comprehensive evaluation model is constructed using quantitative indicators to conduct a comprehensive evaluation. S3.1, Data Standardization right The quantitative indicator data are standardized. S3.2, Extract principal components Calculate eigenvalues ​​and eigenvectors: The standardized data is represented as matrix Its corresponding eigenvalues Principal component variance contribution, orthogonalized unit eigenvectors The variance contribution rate is calculated using the following formula: ； The magnitude of the value indicates the ability of the component to provide information about the reaction; principal components are extracted based on their numerical values. S3.3, Create a comprehensive evaluation model Establish a principal component evaluation sub-model; ； in, , , ... Principal component score coefficients; The calculation method for the principal component score coefficient is as follows: Principal component score coefficient = component value of principal component matrix / square of extracted principal component eigenvalues; m is the sequence number of the extracted principal components; yes 3D random variable, , , ... These represent different quantitative indicators in sequence; Based on the variance contribution rate of each principal component and the principal component evaluation sub-model, a principal component comprehensive evaluation model is established: ； in, , , ... The variance contribution rate for extracting principal components; Using the comprehensive evaluation model F for cigarette paper quality, the comprehensive score of each batch of cigarette paper is automatically calculated and sorted. S4, Abnormal Warning Establish evaluation criteria and anomaly alarm rules; When the comprehensive evaluation score of cigarette paper quality is greater than or less than 3 At that time, an abnormality warning was issued for the quality data of this batch of cigarette paper; Trend analysis is performed on the data of the comprehensive evaluation of daily cigarette paper quality, and trend warnings are issued when the trend changes. When an alert is triggered, proceed to anomaly analysis; S5, Anomaly Analysis When a batch of cigarette paper is found to be substandard, or when the comprehensive quality evaluation score of the cigarette paper does not meet the evaluation standards or shows a trend change, an anomaly analysis will be automatically performed, and the inspection personnel will analyze the cause.

2. The comprehensive evaluation method for cigarette paper according to claim 1, characterized in that: The comprehensive evaluation method also includes: S6, Case Studies The causes of abnormal warnings and trend warnings are classified and organized to form experience cases.

Images