A method and system for quantitatively predicting the resistance of a post-leaf bundle cigar to the passage of smoke

Abstract

This invention discloses a method and system for quantitatively predicting the draw resistance of in-wall tobacco after shaping in leaf-shaped cigars, relating to the field of tobacco production technology. The method includes: conducting experiments using physical indicators of in-wall tobacco, filler material, and rolling process as variables to obtain the draw resistance of the shaped in-wall tobacco; using physical indicators, filler material, and rolling process as influencing factors, quantifying the rolling process using dummy variable encoding; combining the draw resistance obtained from the experiments, constructing a prediction model using a stepwise multiple linear regression method, and determining the weight ranking of the influencing factors; applying the prediction model to the in-wall tobacco to be tested, determining the predicted draw resistance value, and judging whether the draw resistance meets the standard; if it does not meet the standard, adjusting the influencing factors according to the weight ranking, thereby determining the optimal combination of preparation processes. Based on multi-module orthogonal experiments and dummy variable encoding-stepwise multiple linear regression, this method achieves positive prediction of draw resistance and reverse optimization of process parameters, thereby reducing raw material consumption and improving the quality of the finished product.

Description

Technical Field

[0001] This invention relates to the field of tobacco production technology, and in particular to a method and system for quantitatively predicting the draw resistance of endofibril smoke after leaf bundle cigar shaping. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Bundle cigars consist of a wrapper, binder, and filler. There are typically 2-3 filler types, blended in a specific ratio, wrapped in the binder to form the inner tobacco. This inner tobacco is then shaped in a mold to create the final inner tobacco. Finally, the wrapper is applied to the inner tobacco to form the finished cigar. Because the draw resistance of the finished cigar is covered by the cap, it's impossible to directly test it. Testing the draw resistance of the finished cigar would require cutting the cap, a destructive process that wastes raw materials and labor. Therefore, the draw resistance of the final inner tobacco is generally used as an indicator of the finished cigar's draw resistance.

[0004] The draw resistance of the inner tobacco after the leaf bundle cigar is shaped is affected by multiple factors: first, the physical properties of the inner tobacco, including length, circumference and density; second, the filler material, including the origin of the filler, the proportion of filler and the thickness of the filler leaves; and third, the rolling technique and the skill level of the rolling personnel.

[0005] Currently, in actual R&D processes, it's impossible to simultaneously couple multiple factors such as physical indicators, tobacco raw materials, rolling techniques, and rolling personnel, making it difficult to effectively predict the draw resistance distribution of in-fabric cigars. Furthermore, the roller and rolling techniques are qualitative categorical variables and cannot be directly incorporated into linear regression models. The industry lacks standardized dummy variable quantification coding schemes, making it impossible to quantify draw resistance fluctuations caused by human intervention. New product development relies on repeated trials, resulting in high tobacco consumption and long development cycles. When draw resistance fluctuations are significant, it's difficult to quickly trace the causes of draw resistance defects, failing to meet the refined production control requirements for draw resistance in bundled cigars. Summary of the Invention

[0006] To address the aforementioned issues, this invention proposes a quantitative prediction method and system for the draw resistance of inner-embryo smoke after leaf bundle cigar shaping. Based on multi-module orthogonal experiments and dummy variable coding-stepwise multiple linear regression, it achieves positive prediction of draw resistance and reverse optimization of process parameters, thereby reducing raw material consumption and improving the quality of finished products.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for quantitatively predicting the draw resistance of endo-fabric smoke after the leaf bundle cigar has been shaped, comprising: Experiments were conducted with the physical properties of the inner-embryo tobacco, the eggplant core material, and the rolling process as variables, and the draw resistance of the inner-embryo tobacco was tested for each cigarette after shaping. Using physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors, the rolling process factors were quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a stepwise multiple linear regression method was used to construct a prediction model and determine the weight ranking of the influencing factors. For the endofibril tobacco after testing and shaping, a predictive model is used to determine the predicted value of the draw resistance, and the draw resistance is judged to determine whether it meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking, so as to determine the optimal combination of preparation processes.

[0008] As an alternative implementation method, the process of detecting the smoke resistance of the endoderm after shaping includes: Under the same rolling process and core weight ratio, and with different cigarette specifications, the draw resistance of the inner preform cigarette after shaping was determined. Under the experimental conditions of obtaining the same cigarette specifications and rolling process, and different filler weight ratios, the draw resistance of the inner preform cigarette after shaping was determined. Under experimental conditions of obtaining the same cigarette specifications and filler weight ratio, as well as different rolling processes, the draw resistance of the inner preform cigarette after shaping was determined.

[0009] As an alternative implementation, physical index factors include endoepithelial smoke length, endoepithelial smoke circumference, and the same endoepithelial smoke density. Eggplant core raw material factors include eggplant core mass ratio and eggplant core weighted average thickness; The rolling process factors include the rollr and the rolling technique.

[0010] As an alternative implementation method, a stepwise multiple linear regression backward elimination method is used for modeling to determine the output non-standardized coefficients and standardized regression coefficients. The standardized regression coefficients are used as the weights of the influencing factors, and significant influencing factors are determined to construct a prediction model. The significant influencing factors include the length of the inner tobacco, the circumference of the inner tobacco, the weight of the inner tobacco after shaping, the ratio of the core weight to the weight of the tobacco, the roller and the rolling technique.

[0011] As an alternative implementation method, the prediction model is: ; in: X1 represents the predicted smoke resistance of the inner embryo after shaping; X2 represents the length; X3 represents the circumference; X4, X5, and X6 represent the weight percentage of the eggplant core from different production areas. For the j-th volume creator dummy variable The non-standardized regression coefficients; For the k-th winding technique dummy variable The non-standardized regression coefficients are J and K, which represent the number of dummy variables for the roll maker and the roll making technique, respectively.

[0012] As an alternative implementation method, the method also includes production quality traceability based on a prediction model. When the draw resistance exceeds the standard during the batch production process, the quality ratio of the filler, the cigarette specifications, and the rolling process are checked in order of weight to quickly determine the cause of the fluctuation.

[0013] Secondly, the present invention provides a quantitative prediction system for the draw resistance of endofibril smoke after leaf bundle cigar shaping, comprising: The acquisition module is configured to conduct experiments with the physical properties of the inner tobacco, the core material, and the rolling process as variables, and to test the draw resistance of the inner tobacco after shaping one by one. The modeling module is configured to use physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors. The rolling process factors are quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a stepwise multiple linear regression method is used to construct a prediction model and determine the weight ranking of the influencing factors. The prediction module is configured to use a prediction model to determine the predicted value of the draw resistance of the endoderm tobacco to be tested and to determine whether the draw resistance meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking to determine the optimal combination of preparation processes.

[0014] Thirdly, the present invention provides an electronic device including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0015] Fourthly, the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in the first aspect.

[0016] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes a method and system for quantitatively predicting the draw resistance of the inner tobacco after the cigar is shaped into a bundle-type cigar. Based on multi-module orthogonal experiments and dummy variable coding-stepwise multiple linear regression, it incorporates three types of coupled factors—physical indicators, filler material, and qualitative variables related to the cigar roller and rolling technique—into the same quantitative prediction model. Dummy variable coding solves the problem of qualitative process parameters being unable to be modeled through regression, fully restoring the multi-variable coupled draw resistance variation law during the hand-rolling process of cigars. Furthermore, all factor weights are determined by measured data from orthogonal experiments, abandoning the subjective assignment of traditional process experience. The data is reproducible and highly objective. It allows for non-destructive prediction of the inner tobacco after shaping, with prediction accuracy superior to single-factor prediction methods. This significantly reduces the number of new product trial batches and eliminates the need for destructive testing of finished cigars, improving product yield, reducing cigar tobacco material loss, and lowering overall production costs.

[0018] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart of the quantitative prediction method for endoderm smoke absorption resistance after shaping, provided in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the model evaluation results provided in Embodiment 1 of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form as well. Furthermore, it should be understood that the terms “comprising” and “including”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0025] Example 1 This embodiment provides a quantitative prediction method for the draw resistance of inner-embedded tobacco in leaf-shaped cigars after shaping. Based on multi-module orthogonal experiments and dummy variable coding-stepwise multiple linear regression, it quantifies qualitative process parameters, objectively outputs factor weights, and provides stable and reliable prediction accuracy. It enables positive prediction of draw resistance before new product trial production and reverse optimization of process parameters given a target draw resistance, thereby reducing raw material consumption. This overcomes the technical shortcomings of existing draw resistance prediction methods, such as incomplete factor coverage, inability to quantify qualitative processes, subjective assignment of factor weights, large prediction bias, and high trial production costs.

[0026] like Figure 1 As shown, it mainly includes: Experiments were conducted with the physical properties of the inner-embryo tobacco, the eggplant core material, and the rolling process as variables, and the draw resistance of the inner-embryo tobacco was tested for each cigarette after shaping. Using physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors, the rolling process factors were quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a stepwise multiple linear regression method was used to construct a prediction model and determine the weight ranking of the influencing factors. For the endofibril tobacco after testing and shaping, a predictive model is used to determine the predicted value of the draw resistance, and the draw resistance is judged to determine whether it meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking, so as to determine the optimal combination of preparation processes.

[0027] In this embodiment, experiments were conducted using the physical properties of the inner-embryo tobacco, the filler material, and the rolling process as variables. The process of testing the draw resistance of each inner-embryo tobacco after shaping included: Using the same rolling process and the same ratio of filler weight to cigarette weight, as well as different cigarette specifications as experimental conditions, the draw resistance of the inner preform cigarette after shaping was obtained for each cigarette. Using the same cigarette specifications and rolling process, and different filler weight ratios as experimental conditions, the draw resistance of the inner cigarette after shaping was obtained for each cigarette. Using the same cigarette specifications and filler weight ratio, as well as different rolling processes as experimental conditions, the draw resistance of the inner preform cigarette after shaping was obtained for each cigarette.

[0028] Specifically, it includes the following:

[0029] 1. Gradient test of physical indicators (groups A11 to A33).

[0030] Using the same raw material formula, with length gradients of 130mm, 140mm, and 150mm, and circumferential gradients of 47mm, 56mm, and 65mm, the reference density (300.4mg / cm³) was calculated based on the center weight value (10.5g) of a certain brand. 3 This is then converted into the weight of cigarettes of corresponding length and circumference. Based on the baseline density, the target weight of each group is calculated. The same rolling worker rolls the cigarettes using the tubular method and the same core weight ratio. A total of 9 groups of samples are produced, with no less than 30 cigarettes in each group. The draw resistance of the inner sheet cigarettes after shaping is tested for each cigarette.

[0031] The experimental group settings and the results of the draw resistance of the in-plant cigarettes after shaping are shown in Table 1. For example, in group A11, the in-plant cigarette length was 140mm (design value of physical properties after wrapping + 10mm), the circumference was 47mm, and the weight was 6.9g. The average weight after shaping was the measured weight of 30 in-plant cigarettes after shaping, and the average draw resistance of 30 in-plant cigarettes after shaping was 1221.90Pa. This pattern is consistent in other rows of the data table.

[0032] Table 1. Gradient test of physical properties;

[0033] 2. Multi-origin eggplant core quality ratio test (groups B1 to B10).

[0034] Each group of cigarettes has a specification of 140mm×56mm and a target weight of 10.5g. Ten groups of different filler weight ratios were designed for testing. The cigarettes were rolled by the same worker using the tubular method. Each group of samples had no less than 30 cigarettes, as shown in Table 2. The draw resistance of the inner liner after shaping was tested.

[0035] The experimental group setup and the results of the draw resistance of the rolled inner cigarettes after shaping are shown in Table 2. For example, in group B1, the proportions (weights) of the eggplant fillers from the three origins A, B, and C were 30% (3.2g), 40% (4.2g), and 30% (3.2g), respectively. After rolling and shaping with an inner cigarette length of 150mm, the average weight of the 30 rolled inner cigarettes was 10.78g, and the average draw resistance was 709.4Pa. This pattern is consistent across the other rows in the data table.

[0036] Table 2. Test on the proportion of eggplant cores from multiple production areas;

[0037] Before rolling, the thicknesses of the eggplant cores from the three origins (A, B, and C) were measured using a thickness gauge and found to be 0.21 mm, 0.14 mm, and 0.12 mm, respectively. The single-material smoke resistance of the eggplant core from origin A was 437 Pa, that of origin B was 486 Pa, and that of origin C was 1012 Pa.

[0038] 3. Orthogonal experiment on the rolling master and rolling method (groups C11 to C34).

[0039] To investigate the effects of different rolling techniques and the rolling master on suction resistance, an orthogonal experiment was conducted.

[0040] Each group of cigarettes has a specification of 140mm×56mm and a target weight of 10.5g. They were rolled by 3 senior cigarette makers using 4 rolling techniques (tubular method, book roll method, folding fan method, and grasping method) and according to the same filler weight ratio. A total of 12 groups of 3×4 orthogonal combinations were carried out, with no less than 30 cigarettes in each group, as shown in Table 3. The draw resistance of the inner liner after shaping was tested.

[0041] Table 3. Orthogonal experiment between roll makers and roll maker techniques;

[0042] In this embodiment, the influencing factors are divided into three categories: physical indicators, filler raw materials, and rolling process, as shown in Table 4. Among them, physical indicators include the length of the inner tobacco, the circumference of the inner tobacco, and the weight of the inner tobacco after shaping; filler raw materials include the filler mass ratio and the weighted average thickness of the filler; and rolling process includes the rollr and rolling techniques.

[0043] For physical indicators and eggplant core raw materials, they can be directly used in the calculation as continuous variables. For rolling process classification variables (roller, rolling method), dummy variable coding and quantification are used. Dummy variable coding and quantification is the process of converting multi-category variables into binary variables with values ​​of 0 or 1. The 0 / 1 indicator indicates whether the sample belongs to a certain category.

[0044] The weighted average thickness of the eggplant core is: T avg =0.21w A +0.14w B +0.12w C In the formula, w A w represents the mass fraction of eggplant core A. B w represents the mass fraction of eggplant core B. C The mass fraction of eggplant core C.

[0045] Table 4. Classification of candidate impact factors;

[0046] In this embodiment, stepwise multiple linear regression (backward elimination method) is used to construct the predictive model. Stepwise multiple linear regression is a statistical method that automatically selects independent variables in multiple linear regression analysis. Its core idea is to ensure that only independent variables that have a significant impact on the dependent variable are retained in the final model by introducing or removing variables one by one, thereby solving the problem of multivariate collinearity and constructing the optimal regression equation.

[0047] This embodiment uses the backward elimination method, starting from all variables and eliminating insignificant variables one by one. Once eliminated, they are not introduced again. This method is mature and reliable in the field of tobacco physicochemical index prediction.

[0048] Specifically, it includes: (1) All candidate influencing factors were included in the initial prediction model with a significance level of α=0.05, and insignificant variables were removed.

[0049] (2) Output non-standardized coefficients (used for engineering prediction) and standardized regression coefficients (representing the objective influence weight of factors).

[0050] (3) Conduct multicollinearity diagnosis, F test, and residual test; use leave-one-out cross-validation to evaluate the model prediction accuracy.

[0051] (4) General form of the model: ; In the formula: P is the smoke absorption resistance of the endoderm after shaping; For constant terms; The regression coefficients are continuous independent variables; , The coefficients are dummy regression variables; ε is the random error term. The i-th continuous independent variable includes the influencing factors related to physical index factors and eggplant core raw material factors; Let j be the j-th volume dummy variable; Let I be the dummy variable for the k-th rolling technique; I, J, and K are the number of continuous independent variables, the number of rolling technique dummy variables, and the number of rolling technique dummy variables, respectively.

[0052] In this embodiment, the absolute value of the standardized regression coefficient represents the strength of the factor's influence on the suction resistance. This allows the weights of the influencing factors to be ranked, as shown in Table 5. Among them, the weighted average thickness X7 is highly collinear with the A / B / C eggplant core mass ratio, and the stepwise regression determination is not significant, so it is removed from the final model.

[0053] Table 5. Ranking of Influence Factor Weights;

[0054] ; In the formula: P is the smoke absorption resistance of the endoderm after shaping; For constant terms; The regression coefficients are continuous independent variables; , The coefficients are dummy regression variables; ε is the random error term. The i-th continuous independent variable includes the influencing factors related to physical index factors and eggplant core raw material factors; Let j be the j-th volume dummy variable; Let I be the dummy variable for the k-th rolling technique; I, J, and K are the number of continuous independent variables, the number of rolling technique dummy variables, and the number of rolling technique dummy variables, respectively.

[0055] Finally, based on stepwise multiple linear regression, and with length, circumference, weight after shaping, eggplant core quality ratio, roller, and rolling technique as significant influencing factors, the prediction model constructed is as follows: ; in: X1 represents the predicted smoke resistance of the inner embryo after shaping; X2 represents the length; X3 represents the circumference; X4, X5, and X6 represent the percentage of the core weight from origins A, B, and C. For the j-th volume creator dummy variable The non-standardized regression coefficients, with their own dimensions, are used to offset the conversion of the dimensions of the independent variables. They represent the amount of draw resistance correction brought by different roll makers relative to the benchmark roll maker (roll maker No. 1). That is, under the condition that other processes, raw materials and specifications are completely consistent, the average change in draw resistance of the inner preform smoke by this roll maker compared to the benchmark group (roll maker No. 1) after shaping. Corrections for the production staff; Dumb variables for rolling techniques The non-standardized regression coefficients have their own corresponding dimensions to offset the conversion of the dimensions of the independent variables. They represent the amount of suction resistance correction brought about by different rolling techniques relative to the benchmark rolling technique (tubular method). That is, under the same conditions, the average change in suction resistance of the rolling technique compared to the benchmark technique (tubular method). This is a correction item for the rolling technique.

[0056] Among them, the dummy variable benchmark group is No. 1 roll maker and tubular method; Dumb variables for the roll maker: No. 1 (D1=0, D2=0); No. 2 (D1=1, D2=0); No. 3 (D1=0, D2=1); Dumb variables for rolling techniques: tubular method (M1=0, M2=0, M3=0); scroll method (M1=1); folding fan method (M2=1); grasping and wrapping method (M3=1).

[0057] In this embodiment, as Figure 2As shown in Table 6, the comprehensive fitting accuracy of the finalized endomorph smoke absorption resistance multiple linear prediction model was evaluated using the coefficient of determination, adjusted coefficient of determination, mean absolute error, root mean square error, and mean relative error. The results show that the model is highly significant overall, with an average relative prediction error of 11.70% for all experimental samples.

[0058] Table 6. Average results of the model;

[0059] Taking the No. 2 roll maker and the grab-and-wrap method as an example, D1=1, D2=0; M1=0, M2=0, M3=1; ; In the formula: X1=140; X2=56; X3=10.83; X4=0.3; X5=0.4; X6=0.3; =652.10 556.53 = 95.57 Pa; (Difference between No. 2 and No. 1 rollers, both using the tubular method); =495.77 556.53= 60.76Pa (Tube method switched to gripping method, compared with the same personnel, selected No. 1 rolling technician); It can be obtained 591.34 Pa; Relative error: RE = 32.39 / 623.73 × 100% ≈ 5.19%; Prediction accuracy = 100% 5.19% = 94.81%.

[0060] Therefore, the accuracy rate of this prediction is 94.81%.

[0061] In this embodiment, based on the constructed prediction model, the following two-way industrial applications can be performed.

[0062] (1) Positive suction resistance prediction: Input the length, circumference, final weight, A, B and C origin eggplant core ratio, rolling personnel and rolling method of the product to be developed, substitute into the prediction model to output the predicted value of the inner curd smoke suction resistance after finalization, and judge in advance whether the inner curd smoke suction resistance meets the standard based on the set target suction resistance, thereby reducing the need for physical trial production.

[0063] (2) Reverse process optimization: Given the target shape and the inner curvature smoke absorption resistance, if the predicted value does not reach the target value or exceeds the target value, the parameters are adjusted according to the factor weight from high to low priority, with priority given to adjusting the proportion of C in the core and the circumference of the cigarette, and the optimal process combination is calculated iteratively.

[0064] (3) Production quality traceability: When the suction resistance exceeds the standard during the batch production process, the raw material ratio, cigarette geometric specifications, and rolling operation are investigated in order of weight to quickly determine the cause of the fluctuation.

[0065] The aforementioned solution incorporates three types of coupled factors—physical indicators, filler materials from various origins, and qualitative variables related to the cigar roller and the rolling process—into a single quantitative prediction model. By using dummy variable coding, it addresses the challenge of regression modeling for qualitative process parameters, fully reconstructing the multi-variable coupled draw resistance variation patterns during the hand-rolling process. Furthermore, all factor weights are determined by orthogonal experimental data, eliminating subjective assignments based on traditional process experience. This ensures data reproducibility and strong objectivity. It allows for non-destructive prediction of the inner tobacco after shaping, with prediction accuracy superior to single-factor prediction methods. This significantly reduces the number of batches required for new product trials and eliminates the need for destructive puncture testing of finished cigars, improving product yield, reducing cigar tobacco loss, and lowering overall production costs. In addition, the prediction equation is concise and can be quickly calculated directly in Excel, SPSS, Origin, and Python, making it suitable for implementation in both R&D laboratories and production workshops.

[0066] Example 2 This embodiment provides a quantitative prediction system for the draw resistance of endofibril smoke after leaf bundle cigar shaping, including: The acquisition module is configured to conduct experiments with the physical properties of the inner tobacco, the core material, and the rolling process as variables, and to test the draw resistance of the inner tobacco after shaping one by one. The modeling module is configured to use physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors. The rolling process factors are quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a stepwise multiple linear regression method is used to construct a prediction model and determine the weight ranking of the influencing factors. The prediction module is configured to use a prediction model to determine the predicted value of the draw resistance of the endoderm tobacco to be tested and to determine whether the draw resistance meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking to determine the optimal combination of preparation processes.

[0067] It should be noted that the above modules correspond to the steps described in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should also be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0068] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0069] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0070] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0071] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.

[0072] The method in Example 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0073] A computer program product includes a computer program that, when executed by a processor, implements the method described in Embodiment 1.

[0074] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0075] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0076] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0077] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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 beyond the scope of this invention.

[0078] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for quantitatively predicting the draw resistance of endo-embryonic smoke after leaf bundle cigar shaping, characterized in that, include: Experiments were conducted with the physical properties of the inner-embryo tobacco, the eggplant core material, and the rolling process as variables, and the draw resistance of the inner-embryo tobacco was tested for each cigarette after shaping. Using physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors, the rolling process factors were quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a predictive model was constructed using a stepwise multiple linear regression method, and the weight ranking of the influencing factors was determined. For the endofibril tobacco after testing and shaping, a predictive model is used to determine the predicted value of the draw resistance, and the draw resistance is judged to determine whether it meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking, so as to determine the optimal combination of preparation processes.

2. The method for quantitatively predicting the draw resistance of endofibril smoke after shaping a leaf-bundle cigar as described in claim 1, characterized in that, The process of testing the smoke resistance of endoderms after shaping includes: Under the same rolling process and core weight ratio, and with different cigarette specifications, the draw resistance of the inner preform cigarette after shaping was determined. Under the experimental conditions of obtaining the same cigarette specifications and rolling process, and different filler weight ratios, the draw resistance of the inner preform cigarette after shaping was determined. Under experimental conditions of obtaining the same cigarette specifications and filler weight ratio, as well as different rolling processes, the draw resistance of the inner preform cigarette after shaping was determined.

3. The method for quantitatively predicting the draw resistance of endofibril smoke after shaping a leaf-bundle cigar as described in claim 1, characterized in that, Physical index factors include endoderm length, endoderm circumference, and the same endoderm density; Eggplant core raw material factors include eggplant core mass ratio and eggplant core weighted average thickness; The rolling process factors include the rollr and the rolling technique.

4. The method for quantitatively predicting the draw resistance of endofibril smoke after shaping a leaf-bundle cigar as described in claim 3, characterized in that, The model was constructed using a stepwise multiple linear regression backward elimination method to determine the output non-standardized coefficients and standardized regression coefficients. The standardized regression coefficients were used as the weights of the influencing factors, and significant influencing factors were identified to construct the prediction model. The significant influencing factors included the length of the inner tobacco, the circumference of the inner tobacco, the weight of the inner tobacco after shaping, the ratio of the core weight to the total weight, the roller, and the rolling technique.

5. The method for quantitatively predicting the draw resistance of endo-fabric smoke after shaping a leaf-bundle cigar as described in claim 1, characterized in that, The prediction model is: ； in: X1 represents the predicted smoke resistance of the inner embryo after shaping; X2 represents the length; X3 represents the circumference; X4, X5, and X6 represent the weight percentage of the eggplant core from different production areas. For the j-th volume creator dummy variable The non-standardized regression coefficients; For the k-th winding technique dummy variable The non-standardized regression coefficients are J and K, which represent the number of dummy variables for the roll maker and the roll making technique, respectively.

6. The method for quantitatively predicting the draw resistance of endo-fabric smoke after shaping a leaf-bundle cigar as described in claim 1, characterized in that, The method also includes production quality traceability based on prediction models. When the draw resistance exceeds the standard during batch production, the quality ratio of the filler, cigarette specifications, and rolling process are investigated in order of weight to determine the cause of the fluctuation.

7. A quantitative prediction system for the draw resistance of endofibril smoke after leaf bundle cigar shaping, characterized in that, include: The acquisition module is configured to conduct experiments with the physical properties of the inner tobacco, the core material, and the rolling process as variables, and to test the draw resistance of the inner tobacco after shaping one by one. The modeling module is configured to use physical index factors, eggplant core raw material factors, and rolling process factors as influencing factors. The rolling process factors are quantified by dummy variable coding. Combined with the suction resistance obtained from the experiment, a stepwise multiple linear regression method is used to construct a prediction model and determine the weight ranking of the influencing factors. The prediction module is configured to use a prediction model to determine the predicted value of the draw resistance of the endoderm tobacco to be tested and to determine whether the draw resistance meets the standard. If it does not meet the standard, the influencing factors are adjusted according to the weight ranking to determine the optimal combination of preparation processes.

8. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the method described in any one of claims 1-6.

Images