Method, device, equipment and medium for predicting cigarette quality and controlling cigarette production

Abstract

Embodiments of the present application disclose a cigarette quality prediction and cigarette production control method, device, equipment and medium, and relate to the technical field of tobacco processing. The method comprises: obtaining measured data of a preset cigarette quality index of a cigarette sample, and converting the measured data into a standardized matching degree; processing the standardized matching degree based on the CRITIC method to obtain the weight of the preset cigarette quality index, and determining the weighted result of the preset cigarette quality index according to the standardized matching degree and the corresponding weight; processing the weighted result of the preset cigarette quality index based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette sample, and establishing a comprehensive quality matching degree prediction model to predict the comprehensive quality matching degree of the cigarette in real time based on the comprehensive quality matching degree prediction model during the cigarette production process and adjust the cigarette production parameters according to the prediction result. The present scheme realizes real-time and accurate prediction of the quality of the cigarette, and feedback adjustment of the cigarette production process.

Description

Technical Field

[0001] This invention relates to the field of tobacco processing technology, and in particular to a method, apparatus, equipment and medium for predicting cigarette quality and controlling cigarette production. Background Technology

[0002] Cigarette paper is a crucial component of cigarette products. Its physical parameters and chemical composition directly affect the combustion characteristics, smoke release, ash coating, and sensory quality of cigarettes, making it a key material determining the overall quality of cigarettes. As the cigarette industry develops towards higher speeds, greater precision, and higher quality, stricter requirements are being placed on key parameters of cigarette paper, such as basis weight, air permeability, combustion aid content, ash content, potassium-sodium ratio, and pulp proportions. Determining the impact of cigarette paper parameters on cigarette quality is a pressing technical problem that needs to be solved.

[0003] Currently, cigarette quality is usually evaluated based on the subjective feelings of testers. This results in highly subjective evaluation results with poor reference value. Furthermore, due to the lag in evaluation results, it cannot provide support for the production control of cigarettes. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for predicting cigarette quality and controlling cigarette production, which can accurately identify the impact of cigarette paper parameters on cigarette quality and improve cigarette production based on the identification results.

[0005] According to one aspect of the present invention, a method for predicting cigarette quality and controlling cigarette production is provided, the method comprising: Obtain measured data of preset cigarette quality indicators for cigarette samples and convert them into standardized matching degrees; The standardized matching degree of the preset cigarette quality indicators is processed based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and the weighted result of the preset cigarette quality indicators is determined according to the standardized matching degree and the corresponding weights. The weighted results of the preset cigarette quality indicators are processed based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples. A comprehensive quality matching degree prediction model is then established to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results. The comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes.

[0006] According to another aspect of the present invention, a device for predicting cigarette quality and controlling cigarette production is provided, comprising: The standardized matching degree determination module is used to obtain the measured data of the preset cigarette quality indicators of the cigarette samples and convert them into standardized matching degrees. The weight determination module is used to process the standardized matching degree of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and to determine the weighted result of the preset cigarette quality indicators based on the standardized matching degree and the corresponding weights. The module for establishing a comprehensive quality matching degree prediction model is used to process the weighted results of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and to establish a comprehensive quality matching degree prediction model so as to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results. The comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the cigarette quality prediction and cigarette production control method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the cigarette quality prediction and cigarette production control method according to any embodiment of the present invention.

[0009] The technical solution of this application includes: acquiring measured data of preset cigarette quality indicators for cigarette samples and converting them into standardized matching degrees; processing the standardized matching degrees of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and determining the weighted result of the preset cigarette quality indicators based on the standardized matching degrees and corresponding weights; processing the weighted result of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and establishing a comprehensive quality matching degree prediction model to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results; wherein, the comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes. This technical solution achieves a unified quantitative expression of cigarette quality through the CRITIC and TOPSIS methods, improves the stability and objectivity of the evaluation results, and provides real-time feedback adjustments to cigarette production based on the prediction results output by the prediction model, greatly improving cigarette quality.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a method for predicting cigarette quality and controlling cigarette production according to Embodiment 1 of this application; Figure 2 This is a flowchart of a method for predicting cigarette quality and controlling cigarette production according to Embodiment 2 of this application; Figure 3 This is a schematic diagram of the overall quality matching degree of a cigarette sample provided according to Embodiment 2 of this application.

[0013] Figure 4 This is a schematic diagram of a cigarette quality prediction and cigarette production control device provided according to Embodiment 3 of this application; Figure 5 This is a schematic diagram of the structure of an electronic device that implements a method for predicting cigarette quality and controlling cigarette production according to an embodiment of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of this application 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 should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises 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.

[0016] Example 1 Figure 1 This application provides a flowchart of a method for predicting cigarette quality and controlling cigarette production, as shown in Embodiment 1. This embodiment is applicable to situations where cigarette quality is predicted in real time and the cigarette production process is improved based on the prediction results. This method can be executed by a cigarette quality prediction and production control device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes: S110: Obtain the measured data of the preset cigarette quality indicators of the cigarette sample and convert them into standardized matching degree.

[0017] The cigarette sample can be a sample used to test cigarette quality. A cigarette sample refers to the product obtained by wrapping tobacco in cigarette paper, commonly known as a cigarette. The preset cigarette quality indicators can be pre-set indicators for evaluating cigarette quality, and these can be indicators related to the cigarette paper. For example, preset cigarette quality indicators include, but are not limited to: smoke indicators, ash performance indicators, and sensory quality indicators.

[0018] Furthermore, after obtaining the measured data of the preset cigarette quality indicators for the cigarette samples, it is necessary to standardize them to facilitate subsequent calculations. This is because some indicators may indicate better quality with higher values, some may show better quality within a certain range, and some may indicate better quality with lower values; moreover, some indicators may not be in numerical form, which is not conducive to subsequent calculations. Therefore, this application standardizes the indicators to obtain the standardized matching degree corresponding to each indicator.

[0019] S120, The standardized matching degree of the preset cigarette quality indicators is processed based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and the weighted result of the preset cigarette quality indicators is determined according to the standardized matching degree and the corresponding weights.

[0020] Among them, the CRITIC method is a multi-criteria decision-making method (CriteriaImportance Through Intercriteria Correlation) that calculates the weight of indicators based on the objective attributes of data. It is used to automatically determine the objective weight of each indicator in the comprehensive evaluation.

[0021] Specifically, after obtaining the standardized matching degree of the preset cigarette quality indicators, the CRITIC method is used to process the standardized matching degree of the preset cigarette quality indicators to obtain the weight of each preset cigarette quality indicator. Then, the weight is multiplied by the standardized matching degree to obtain the weighted result of the preset cigarette quality indicators.

[0022] S130, The weighted results of the preset cigarette quality indicators are processed based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and a comprehensive quality matching degree prediction model is established to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results.

[0023] Among them, the TOPSIS method (Technique for Order Preference by Similarity to Ideal Solution) is a ranking method that approximates the ideal solution (also known as the superior-inferior solution distance method), used to evaluate and rank the relative merits of a finite number of solutions under multiple indicators. The overall quality matching degree reflects the overall quality of the cigarette. The overall quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the overall quality matching degree of the cigarette.

[0024] Specifically, after obtaining the weighted results of the preset cigarette quality indicators, the distances of each indicator from the positive and negative ideal solutions are calculated based on the TOPSIS method, thereby obtaining the overall quality matching degree of the cigarette sample. Further, the overall quality matching degree of the cigarette sample is used as the dependent variable, and the cigarette paper parameters are used as the independent variables to solve for the overall quality matching degree prediction model. This model can process the cigarette paper parameters during the cigarette production process, output the overall quality matching degree of the cigarette, and then adjust the cigarette production parameters based on this overall quality matching degree, such as adjusting the batch size of cigarette paper and the amount of tobacco filling, until the overall quality matching degree meets the preset qualification conditions, and then continue cigarette production.

[0025] The technical solution of this application includes: acquiring measured data of preset cigarette quality indicators for cigarette samples and converting them into standardized matching degrees; processing the standardized matching degrees of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and determining the weighted result of the preset cigarette quality indicators based on the standardized matching degrees and corresponding weights; processing the weighted result of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and establishing a comprehensive quality matching degree prediction model to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results; wherein, the comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes. This technical solution achieves a unified quantitative expression of cigarette quality through the CRITIC and TOPSIS methods, improves the stability and objectivity of the evaluation results, and provides real-time feedback adjustments to cigarette production based on the prediction results output by the prediction model, greatly improving cigarette quality.

[0026] Example 2 Figure 2 This is a flowchart illustrating a method for predicting cigarette quality and controlling cigarette production, provided in Embodiment 2 of this application. This embodiment is an optimization based on the aforementioned embodiment. This application constructs a multi-dimensional evaluation system encompassing smoke indicators, ash performance, and sensory quality to achieve a unified quantitative expression of cigarette quality. Furthermore, it combines objective weighting and a comprehensive ranking model to improve the stability and objectivity of the evaluation results. Simultaneously, by establishing a mapping relationship between cigarette paper structural parameters and the overall quality matching degree, it achieves prediction and feedback control of cigarette quality, thereby providing data support for cigarette paper formulation optimization and quality control in high-speed cigarette production processes.

[0027] like Figure 2 As shown, the method in this embodiment of the application specifically includes the following steps: S210: Obtain measured data on the smoke indicators, ash performance indicators, and sensory quality indicators of cigarette samples.

[0028] For example, based on a benchmark cigarette paper sample, a single-factor variable control method was used to design the cigarette paper parameters. This involved changing only one structural parameter of the cigarette paper at a time, while keeping the other parameters constant, thus preparing different cigarette paper samples for cigarette rolling. The prepared cigarette samples were then equilibrated at (22±1)℃ and (60±2)% relative humidity for 48 hours, and then tested according to relevant standards to obtain measured data on the cigarette samples' smoke indicators, ash packing performance indicators, and sensory quality indicators.

[0029] In this embodiment, a total of 17 cigarette samples were set up, and the structural parameters of the cigarette paper are shown in Table 1.

[0030] Table 1. Cigarette Paper Sample Parameter Information The structural parameters of the cigarette paper include: basis weight, air permeability, combustion aid content, ash content, potassium-sodium ratio, and hemp content.

[0031] The flue gas indicators include, but are not limited to: tar release, nicotine release, and carbon monoxide release.

[0032] The ash-coating performance indicators include, but are not limited to: ash-coating value, ash value, carbonization ring width, ash-holding capacity, combustion completeness, cone height, cone area, cone apex angle, deviation angle, and free combustion rate.

[0033] The sensory quality indicators include, but are not limited to: the overall sensory score of cigarettes, which may be a score given by relevant personnel.

[0034] S220, perform fuzzy membership degree transformation on the measured data to obtain the standardized matching degree.

[0035] Furthermore, the measured data undergoes fuzzy membership transformation, that is, all the above indicators are uniformly converted into standardized matching degrees of 0.1-1.0. Specifically, the flue gas indicators are transformed using an inverse S-shaped fuzzy discriminant function, which is shown below: ; Where x represents the measured data; x1 and x2 are preset thresholds. To standardize the matching degree.

[0036] The performance indicators of the ash coating are transformed using inverse S-type, S-type, and trapezoidal membership functions according to the small, large, and large viewing sizes, respectively; the S-type function is shown below: ; Where x represents the measured data; x1 and x2 are preset thresholds. To standardize the matching degree.

[0037] The trapezoidal membership function is shown below: ; Where x is the measured data; a, b, m, x1, and x2 are preset thresholds. To standardize the matching degree.

[0038] Sensory quality indicators are transformed using linear normalization, and the transformation formula is shown below: (Linear normalization method) Where i can be the category number of the cigarette sample. The scores for sensory quality indicators. The maximum score for sensory quality indicators. The minimum score for sensory quality indicators.

[0039] The above transformation ensures that indicators across different dimensions are comparable. During the fuzzy transformation process, cigarette paper structural parameters are introduced as correlation variables to participate in the standardization process, characterizing the correspondence between cigarette paper structural parameters and quality indicators.

[0040] S230, obtain the correlation coefficient between any two preset cigarette quality indicators.

[0041] The correlation coefficient can be the Pearson correlation coefficient between index i and index j, denoted by rij. The larger the |rij| is, the more overlapping the information of the two indicators.

[0042] S240, for the target cigarette quality indicator, determine the conflict coefficient corresponding to the target cigarette quality indicator based on the correlation coefficient between the target cigarette quality indicator and other cigarette quality indicators.

[0043] For example, the conflict coefficient is determined according to the following formula: ; in, Let be the conflict coefficient of the j-th target cigarette quality indicator, and i represent other cigarette quality indicators.

[0044] S250, based on the conflict coefficient and variation coefficient corresponding to the target cigarette quality index, determine the weight of the target cigarette quality index, and determine the weighted result of the preset cigarette quality index based on the standardized matching degree and the corresponding weight.

[0045] The target cigarette quality index is any one of the preset cigarette quality indicators. We will only introduce the target cigarette quality index as an example.

[0046] The weights of the target cigarette quality indicators are determined according to the following formula: ; in, The weights of the target cigarette quality indicators. The coefficient of variation is the value corresponding to the target cigarette quality index.

[0047] For example, the variability and conflict of the evaluation indicators are calculated, and the weight coefficients are calculated comprehensively based on the variability and conflict of the evaluation indicators. Based on the CRITIC objective weight analysis method, the weights of each cigarette quality indicator are determined, and the calculation results are shown in Table 2. The weights of the three indicators are ranked as follows: smoke quality indicator (0.473) > sensory quality indicator (0.387) > ash performance indicator (0.141). The weighted result of the preset cigarette quality indicators for 17 samples is calculated by weighted summation, that is, the weighted result is equal to the weighted sum of each preset cigarette quality indicator. The calculation formula is as follows: Weighted result = 0.141 × ash performance standardized matching degree + 0.473 × smoke quality indicator standardized matching degree + 0.387 × sensory total score standardized matching degree.

[0048] Table 2. Calculation Results of Objective Weights for Cigarette Quality Indicators CRITIC S260, Based on the TOPSIS method, the weighted results of the preset cigarette quality indicators are processed to obtain the comprehensive quality matching degree of the cigarette samples. The cigarette paper parameters of the cigarette samples are used as independent variables, and the comprehensive quality matching degree of the cigarette samples is used as dependent variables. The comprehensive quality matching degree prediction model is obtained by solving the problem using a multiple linear regression algorithm.

[0049] In this embodiment of the application, optionally, the weighted results of the preset cigarette quality indicators are processed based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette sample, including: determining the positive ideal solution and the negative ideal solution; obtaining the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution; and determining the comprehensive quality matching degree based on the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution.

[0050] In this embodiment of the application, optionally, obtaining the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution includes: calculating the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution using weighted Euclidean distance for smoke indicators and sensory quality indicators; and calculating the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution using weighted Manhattan distance for ash performance indicators.

[0051] For example, different evaluation dimensions are calculated using a differentiated distance weighting method for TOPSIS. Smoke and sensory indicators are calculated using weighted Euclidean distance, while ash coating performance is calculated using weighted Manhattan distance, to enhance the ability to distinguish core quality differences. Euclidean distance is used to enhance the distinguishing ability of continuous indicators (smoke and sensory), while Manhattan distance is used to suppress the interference of local fluctuations in ash coating performance on the results. Since smoke indicators have continuous cumulative characteristics during cigarette combustion, while ash coating performance exhibits staged abrupt changes, differentiated distance metrics are used to match different physical evolution mechanisms.

[0052] For example, a weighted standardized decision matrix is ​​constructed to determine the positive and negative ideal solutions, calculated according to the following formula: ; ; in, Let be the distance of the cigarette sample from the positive ideal solution. Calculate the distance between each scheme and the ideal solution for the distance of the cigarette sample from the negative ideal solution. For the positive ideal solution, For a negative ideal solution, This is the weighted result of the j-th indicator for the i-th cigarette sample.

[0053] Further according to the following formula: ; Calculate the relative proximity as the overall quality matching degree of cigarettes; and classify the quality of cigarette samples based on the relative proximity.

[0054] Based on the obtained weights, the overall quality of the cigarettes was calculated using the TOPSIS method, and the quality of 17 groups of cigarette samples was graded based on their relative similarity. The calculation results are shown below. Figure 3 According to C i The samples were graded according to the values: samples 4#, 14#, 9#, and 0# were rated as superior, while samples 3#, 10#, 16#, and 7# were rated as good.

[0055] S270 inputs cigarette paper parameters into the comprehensive quality matching degree prediction model in real time during the cigarette production process to obtain the comprehensive quality matching degree prediction result.

[0056] For example, the process of determining the comprehensive quality matching degree prediction model includes: taking the cigarette paper parameters (basis weight, air permeability, combustion aid content, ash content, potassium-sodium ratio) corresponding to 17 groups of samples as independent variables, taking the comprehensive quality matching degree of cigarettes as the dependent variable, and using a multiple linear regression algorithm to establish and train the comprehensive quality matching degree prediction model of cigarettes.

[0057] In this embodiment, the prediction model obtained after stepwise regression analysis is: Y = -1.159 + 0.064 × Quantitative Amount - 0.008 × Air Permeability + 0.463 × Combustion Improver Content + 0.006 × Potassium-Sodium Ratio - 0.043 × Ash Content; the importance of the parameters is ranked as follows: Quantitative Amount > Combustion Improver Content > Air Permeability > Ash Content > Potassium-Sodium Ratio. Among them, Quantitative Amount and Combustion Improver Content have a significant positive impact on the overall quality, and the model has a good fit and high prediction accuracy.

[0058] Specifically, during the cigarette production process, cigarette paper parameters are acquired in real time and then input into a comprehensive quality matching degree prediction model to obtain the comprehensive quality matching degree prediction result. This scheme enables rapid and immediate evaluation of the overall quality of cigarettes.

[0059] S280, Adjust cigarette production parameters based on the comprehensive quality matching degree prediction results.

[0060] For example, after obtaining the comprehensive quality matching degree prediction result, the cigarette production parameters can be adjusted, such as adjusting the production parameters of cigarette paper, the batch of cigarette paper and / or the amount of tobacco filling, so that cigarette production can be carried out based on the new production parameters after the comprehensive quality matching degree prediction result meets the preset requirements.

[0061] The above embodiments demonstrate that this application can achieve a multi-dimensional unified quantitative evaluation of cigarette quality, and on this basis, can effectively model the mapping relationship between cigarette paper structural parameters and overall cigarette quality, thereby achieving accurate evaluation, rapid prediction and process optimization guidance of cigarette quality, and providing reliable technical support for cigarette paper formulation design, cigarette production process control and product quality management.

[0062] This application employs the CRITIC objective weighting analysis method to assign weights to indicators. Based on the variability and conflict of indicators, the weights are calculated, which can effectively reduce the impact of subjective human factors on the comprehensive quality evaluation results of cigarettes, improve the objectivity and stability of weight allocation, and thus enhance the reliability of the evaluation results.

[0063] Meanwhile, this application uses a fuzzy discrimination method to standardize multidimensional quality indicators, thereby achieving a unified expression of indicators of different types and dimensions. It also combines the TOPSIS method to construct a comprehensive evaluation model, enabling objective ranking and grading of cigarette samples, and giving the evaluation results good interpretability and quantification.

[0064] This application establishes a predictive model between the matching degree of cigarette paper structural parameters and the overall quality of cigarettes, enabling the direct prediction of the overall quality of cigarettes from cigarette paper parameters, reducing the number of repeated experiments, improving the efficiency of formula optimization and process adjustment, and providing data support for cigarette paper structural design, production process control and product quality evaluation.

[0065] Example 3 Figure 4 This is a schematic diagram of a cigarette quality prediction and cigarette production control device provided in Embodiment 3 of this application. This device can execute the cigarette quality prediction and cigarette production control method provided in any embodiment of this invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 4 As shown, the device includes: The standardized matching degree determination module 310 is used to obtain the measured data of the preset cigarette quality indicators of the cigarette sample and convert them into standardized matching degree. The weight determination module 320 is used to process the standardized matching degree of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and to determine the weighted result of the preset cigarette quality indicators according to the standardized matching degree and the corresponding weights. The comprehensive quality matching degree prediction model establishment module 330 is used to process the weighted results of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette sample, and establish a comprehensive quality matching degree prediction model so as to predict the comprehensive quality matching degree of the cigarette in real time during the cigarette production process based on the comprehensive quality matching degree prediction model and adjust the cigarette production parameters according to the prediction results. The comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes.

[0066] The technical solution of this application embodiment includes: a standardized matching degree determination module 310, used to acquire measured data of preset cigarette quality indicators of cigarette samples and convert them into standardized matching degrees; a weight determination module 320, used to process the standardized matching degree of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and to determine the weighted result of the preset cigarette quality indicators according to the standardized matching degree and the corresponding weights; and a comprehensive quality matching degree prediction model establishment module 330, used to process the weighted result of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and to establish a comprehensive quality matching degree prediction model, so as to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process based on the comprehensive quality matching degree prediction model and adjust the cigarette production parameters according to the prediction results; wherein, the comprehensive quality matching degree prediction model is a model for processing cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes. This technical solution achieves a unified quantitative expression of cigarette quality through the CRITIC and TOPSIS methods, improving the stability and objectivity of the evaluation results. Furthermore, it provides real-time feedback adjustments to cigarette production based on the prediction results output by the prediction model, thereby significantly improving cigarette quality.

[0067] Optionally, in this embodiment of the application, the standardized matching degree determination module 310 is specifically used for: Obtain measured data on the smoke indicators, ash coating performance indicators, and sensory quality indicators of cigarette samples; The measured data are subjected to fuzzy membership degree transformation to obtain the standardized matching degree.

[0068] Optionally, in this embodiment of the application, the weight determination module 320 is specifically used for: Obtain the correlation coefficient between any two preset cigarette quality indicators; For the target cigarette quality indicators, the conflict coefficient corresponding to the target cigarette quality indicators is determined based on the correlation coefficient between the target cigarette quality indicators and other cigarette quality indicators. The weights of the target cigarette quality indicators are determined based on the conflict coefficient and the coefficient of variation corresponding to the target cigarette quality indicators.

[0069] Optionally, in this embodiment of the application, the comprehensive quality matching degree prediction model establishment module 330 includes: Ideal solution determination unit, used to determine positive and negative ideal solutions; The distance determination unit is used to obtain the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution; The comprehensive quality matching degree determination unit is used to determine the comprehensive quality matching degree based on the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution.

[0070] Optionally, in this embodiment of the application, the distance determination unit is specifically used for: For smoke indicators and sensory quality indicators, weighted Euclidean distance is used to calculate the distance of cigarette samples from the positive ideal solution and the distance from the negative ideal solution. For the performance index of ash coating, the weighted Manhattan distance is used to calculate the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution.

[0071] Optionally, in this embodiment of the application, the process of establishing a comprehensive quality matching degree prediction model includes: The cigarette paper parameters of the cigarette samples were used as independent variables, and the overall quality matching degree of the cigarette samples was used as the dependent variable. The multiple linear regression algorithm was used to solve the problem and obtain the overall quality matching degree prediction model.

[0072] Optionally, in this embodiment of the application, the device further includes: The prediction module is used to input cigarette paper parameters into the comprehensive quality matching degree prediction model in real time during the cigarette production process, and obtain the comprehensive quality matching degree prediction result. The feedback adjustment module is used to adjust the cigarette production parameters based on the comprehensive quality matching degree prediction results.

[0073] The cigarette quality prediction and cigarette production control device provided in this application embodiment can execute the cigarette quality prediction and cigarette production control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0074] Example 4 Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0075] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0076] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0077] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for predicting cigarette quality and controlling cigarette production.

[0078] In some embodiments, the cigarette quality prediction and cigarette production control method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the cigarette quality prediction and cigarette production control method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the cigarette quality prediction and cigarette production control method by any other suitable means (e.g., by means of firmware).

[0079] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs 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 processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0083] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0084] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0085] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting cigarette quality and controlling cigarette production, characterized in that, include: Obtain measured data of preset cigarette quality indicators for cigarette samples and convert them into standardized matching degrees; The standardized matching degree of the preset cigarette quality indicators is processed based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and the weighted result of the preset cigarette quality indicators is determined according to the standardized matching degree and the corresponding weights. The weighted results of the preset cigarette quality indicators are processed based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples. A comprehensive quality matching degree prediction model is then established to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results. The comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes.

2. The method according to claim 1, characterized in that, Obtain measured data of preset cigarette quality indicators for cigarette samples and convert them into standardized matching degrees, including: Obtain measured data on the smoke indicators, ash coating performance indicators, and sensory quality indicators of cigarette samples; The measured data are subjected to fuzzy membership degree transformation to obtain the standardized matching degree.

3. The method according to claim 1, characterized in that, The standardized matching degree of the preset cigarette quality indicators is processed based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, including: Obtain the correlation coefficient between any two preset cigarette quality indicators; For the target cigarette quality indicators, the conflict coefficient corresponding to the target cigarette quality indicators is determined based on the correlation coefficient between the target cigarette quality indicators and other cigarette quality indicators. The weights of the target cigarette quality indicators are determined based on the conflict coefficient and the coefficient of variation corresponding to the target cigarette quality indicators.

4. The method according to claim 1, characterized in that, The weighted results of the preset cigarette quality indicators are processed based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, including: Determine the positive and negative ideal solutions; Obtain the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution; The overall quality matching degree is determined based on the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution.

5. The method according to claim 4, characterized in that, Obtain the distances of the cigarette sample from the positive ideal solution and from the negative ideal solution, including: For smoke indicators and sensory quality indicators, weighted Euclidean distance is used to calculate the distance of cigarette samples from the positive ideal solution and the distance from the negative ideal solution. For the performance index of ash coating, the weighted Manhattan distance is used to calculate the distance of the cigarette sample from the positive ideal solution and the distance from the negative ideal solution.

6. The method according to claim 1, characterized in that, The process of establishing a comprehensive quality matching degree prediction model includes: The cigarette paper parameters of the cigarette samples were used as independent variables, and the overall quality matching degree of the cigarette samples was used as the dependent variable. The multiple linear regression algorithm was used to solve the problem and obtain the overall quality matching degree prediction model.

7. The method according to claim 1, characterized in that, The method further includes: During the cigarette production process, cigarette paper parameters are input into the comprehensive quality matching degree prediction model in real time to obtain the comprehensive quality matching degree prediction results; The cigarette production parameters are adjusted based on the comprehensive quality matching degree prediction results.

8. A device for predicting cigarette quality and controlling cigarette production, characterized in that, include: The standardized matching degree determination module is used to obtain the measured data of the preset cigarette quality indicators of the cigarette samples and convert them into standardized matching degrees. The weight determination module is used to process the standardized matching degree of the preset cigarette quality indicators based on the CRITIC method to obtain the weights of the preset cigarette quality indicators, and to determine the weighted result of the preset cigarette quality indicators based on the standardized matching degree and the corresponding weights. The module for establishing a comprehensive quality matching degree prediction model is used to process the weighted results of the preset cigarette quality indicators based on the TOPSIS method to obtain the comprehensive quality matching degree of the cigarette samples, and to establish a comprehensive quality matching degree prediction model so as to predict the comprehensive quality matching degree of cigarettes in real time during the cigarette production process and adjust the cigarette production parameters according to the prediction results. The comprehensive quality matching degree prediction model is a model that processes cigarette paper parameters to obtain the comprehensive quality matching degree of cigarettes.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the cigarette quality prediction and cigarette production control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the cigarette quality prediction and cigarette production control method as described in any one of claims 1-7.

Images