Reconstituted tobacco sensory quality score determination method and system based on spreading rate

Abstract

The invention relates to the technical field of computer deep learning, in particular to a reconstituted tobacco sensory quality score determination method and system based on a spreading rate. The method comprises the following steps: acquiring the spreading rate of the reconstituted tobacco to be detected; inputting the spreading rate into a trained sensory quality scoring model; and obtaining a sensory quality score prediction value which is output by the sensory quality score model and is calculated based on the coating rate, and determining the sensory quality score prediction value as a sensory quality score value corresponding to the to-be-detected reconstituted tobacco. The invention aims to solve the problem of how to improve the product stability in the paper-making reconstituted tobacco production process.

Description

Technical Field

[0001] The present application relates to the field of computer deep learning technology, and in particular to a method and system for determining a sensory quality score of reconstituted tobacco leaves based on coating rate. Background Art

[0002] Reconstituted tobacco is an important part of the tobacco industry, and its quality directly affects the quality of tobacco products. The national standard GB 5606.4-2005 "Cigarettes Part 4: Sensory Technical Requirements" stipulates several rules for judging the sensory quality of cigarettes, and evaluates the sensory quality of cigarettes from aspects such as the appearance, smoke, and aroma of tobacco leaves.

[0003] However, manual smoking evaluation usually involves sampling several cigarettes from a production batch, testing the parameters related to the sensory quality of the cigarettes using chemical experiments, and then combining the subjective judgment of professional smoking testers on the appearance, smoke, aroma and other aspects of the tobacco leaves to score the sensory quality of the cigarettes. If the score is unqualified, all cigarettes in the production batch will be judged as unqualified.

[0004] Related technical solution 1, Chinese patent publication number CN117422330A discloses a method for evaluating the quality of ordinary cigarette tobacco, which discloses the following indicators for evaluating the quality of tobacco: 1. Leaf quality indicators (including leaf moisture content, leaf filling value, leaf whole rate and leaf broken rate); 2. Cigarette physical indicators (including cigarette unit weight, cigarette unit weight standard deviation, cigarette draw resistance, cigarette draw resistance standard deviation, cigarette filter ventilation rate and cigarette filter ventilation rate standard deviation); 3. Smoke indicators (including tar release extremes, carbon monoxide release extremes and smoke nicotine release extremes); 4. Sensory indicators (including gloss, aroma, harmony, miscellaneous smell, irritation and aftertaste). The score of each indicator corresponds to a different weight. The final comprehensive evaluation score of tobacco is obtained by multiplying each indicator by its own weight and adding them together.

[0005] Related technical solution 2, Chinese patent publication number CN110458474A discloses a comprehensive evaluation method for the physical quality of cigarette rolling, which discloses the following 7 indicators for evaluating the quality of cut tobacco: support weight, draw resistance, hardness, ventilation rate, end cut tobacco, dust content and empty head rate. Through data collection, data standardization processing, and principal component analysis of standardized data, a batch of cigarette comprehensive physical quality evaluation model is established, and the cigarette rolling quality is quantitatively scored through the evaluation model.

[0006] However, the above-mentioned related technical solutions all focus on analyzing the indicators of tobacco itself, and do not involve the research on the indicators and / or process steps that are correlated with the sensory quality of reconstituted tobacco in the preparation process of cigarettes, especially the preparation process of reconstituted tobacco.

[0007] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0008] The main purpose of this application is to provide a method for determining the sensory quality score of reconstituted tobacco based on coating rate, aiming to solve the problem of how to improve the product stability in the papermaking process of reconstituted tobacco.

[0009] To achieve the above-mentioned purpose, the present application provides a method for determining the sensory quality score of reconstituted tobacco leaves based on coating rate, the method comprising:

[0010] Obtaining the coating rate of the reconstituted tobacco leaves to be tested;

[0011] inputting the coating rate into the trained sensory quality scoring model;

[0012] The predicted sensory quality score value calculated based on the coating rate and output by the sensory quality score model is obtained, and the predicted sensory quality score value is determined as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested.

[0013] Optionally, the trained sensory quality scoring model includes a sensory quality scoring calculation module for coating rate, and the training process of the sensory quality scoring model includes:

[0014] Get a sample data set of coating rate;

[0015] The coating rate sample data set is normalized to speed up the convergence of the gradient descent of the coating rate data on the same scale;

[0016] Based on the normalized coating rate sample data set and the corresponding sensory quality score data set, a correlation data table is constructed;

[0017] Input the associated data table into the model with lightGBM architecture for training, and calculate the AUC value of the model after each training is completed;

[0018] After the AUC value reaches the preset AUC threshold, the training is completed.

[0019] Optionally, before the step of inputting the associated data table into a model with a lightGBM architecture for training, and calculating the AUC value of the model after each training is completed, the step further includes:

[0020] Calculating the observed frequency and expected frequency between the coating rate data and the sensory quality score in the associated data table, and calculating the chi-square statistic based on the observed frequency and the expected frequency;

[0021] According to the chi-square statistic and the degrees of freedom associated with the preset coating rate data set, a chi-square distribution table is searched, a p-value is calculated, and a coating rate with a p-value less than a significance level threshold is determined as a target coating rate;

[0022] The step of inputting the associated data table into a model with a lightGBM architecture for training, and calculating the AUC value of the model after each training is completed includes:

[0023] The associated data table of the filtered target coating rate is input into the model with lightGBM architecture for training.

[0024] Optionally, adjust the maximum depth and number of leaf nodes in the model hyperparameters during training.

[0025] Optionally, after the step of obtaining the predicted sensory quality score value calculated based on the coating rate output by the sensory quality score model, and determining the predicted sensory quality score value as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested, the step further includes:

[0026] During the process of executing the papermaking method reconstituted tobacco process, obtaining the sensory quality score value associated with the reconstituted tobacco in the current production line at every preset period;

[0027] Determine whether the sensory quality score is within a normal value range;

[0028] When it is detected that the sensory quality score value is not in the normal value interval, determining whether the coating rate in the current production line is in the standard coating rate interval;

[0029] If not, the abnormal target coating rate process equipment parameters among the coating rate process equipment parameters are determined and output.

[0030] Optionally, the abnormal target coating rate process equipment parameters include at least one of absolute dry weight before coating, absolute dry weight after coating, coating roller pressure, coating liquid concentration, paper machine speed and base absorption performance value.

[0031] In addition, to achieve the above-mentioned objectives, the present application also provides a papermaking method reconstituted tobacco system, the papermaking method reconstituted tobacco system comprising: a memory, a processor, and a reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory and executable on the processor, wherein the reconstituted tobacco sensory quality score determination program based on coating rate, when executed by the processor, implements the steps of the method for determining the sensory quality score of reconstituted tobacco based on coating rate as described in any of the above items.

[0032] This application has at least the following beneficial effects:

[0033] 1. The process parameters of reconstituted tobacco with strong correlation with sensory quality scores in the production process of papermaking reconstituted tobacco were explored, as well as the equipment parameters associated with the process parameters of reconstituted tobacco, so as to achieve the correlation between the sensory quality scores and the process parameters of reconstituted tobacco;

[0034] 2. Convert the sensory quality score obtained by traditional manual smoking evaluation into a value calculated by the system in real time based on process parameters, so as to realize the efficient application of sensory quality score in the industrial production of papermaking reconstituted tobacco leaves;

[0035] 3. Through the collection of reconstituted tobacco process parameters that have a strong correlation with the sensory quality score in the production process of papermaking reconstituted tobacco, the parameters are pre-processed and input into the sensory quality score model to simulate the predicted sensory quality score close to the actual manual smoking score, thereby realizing real-time simulation monitoring of the sensory quality score in the production process of reconstituted tobacco and ensuring the output stability of reconstituted tobacco in the production process of papermaking reconstituted tobacco. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of the architecture of the hardware operating environment of the papermaking process reconstituted tobacco system involved in the embodiment of the present application;

[0037] Figure 2 This is a flow chart of a first embodiment of a method for determining a sensory quality score of reconstituted tobacco leaves based on coating rate of the present application;

[0038] Figure 3 It is a schematic diagram of the fitting curve of the coating rate and the sensory evaluation score involved in the embodiments of the present application;

[0039] Figure 4 This is a schematic diagram of the association between the associated process parameters and the sensory quality scores of reconstituted tobacco leaves selected from the association table involved in the embodiments of the present application;

[0040] Figure 5 This is a flow chart of a second embodiment of the method for determining the sensory quality score of reconstituted tobacco leaves based on coating rate of the present application.

[0041] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0042] In order to better understand the above technical solution, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] As an implementation plan, Figure 1 This is a schematic diagram of the architecture of the hardware operating environment of the papermaking reconstituted tobacco system involved in the embodiment of the present application.

[0044] like Figure 1 As shown, the papermaking method reconstituted tobacco leaf system may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0045] Those skilled in the art will understand that Figure 1 The architecture of the reconstituted tobacco system for papermaking shown in the figure does not constitute a limitation on the reconstituted tobacco system for papermaking, and the system may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0046] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a program for determining the sensory quality score of reconstituted tobacco leaves based on the coating rate. The operating system is a program for managing and controlling the hardware and software resources of the papermaking process reconstituted tobacco leaf system, the program for determining the sensory quality score of reconstituted tobacco leaves based on the coating rate, and the operation of other software or programs.

[0047] exist Figure 1In the papermaking reconstituted tobacco system shown, the user interface 1003 is mainly used to connect to the terminal and communicate data with the terminal; the network interface 1004 is mainly used for the background server and communicates data with the background server; the processor 1001 can be used to call the reconstituted tobacco sensory quality score determination program based on the coating rate stored in the memory 1005.

[0048] In this embodiment, the papermaking process reconstituted tobacco system includes: a memory 1005, a processor 1001, and a reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory and executable on the processor, wherein:

[0049] When the processor 1001 calls the reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory 1005, the following operations are performed:

[0050] Obtaining the coating rate of the reconstituted tobacco leaves to be tested;

[0051] inputting the coating rate into the trained sensory quality scoring model;

[0052] The predicted sensory quality score value calculated based on the coating rate and output by the sensory quality score model is obtained, and the predicted sensory quality score value is determined as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested.

[0053] When the processor 1001 calls the reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory 1005, the following operations are performed:

[0054] Get a sample data set of coating rate;

[0055] The coating rate sample data set is normalized to speed up the convergence of the gradient descent of the coating rate data on the same scale;

[0056] Based on the normalized coating rate sample data set and the corresponding sensory quality score data set, a correlation data table is constructed;

[0057] Input the associated data table into the model with lightGBM architecture for training, and calculate the AUC value of the model after each training is completed;

[0058] After the AUC value reaches the preset AUC threshold, the training is completed.

[0059] When the processor 1001 calls the reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory 1005, the following operations are performed:

[0060] Calculating the observed frequency and expected frequency between the coating rate data and the sensory quality score in the associated data table, and calculating the chi-square statistic based on the observed frequency and the expected frequency;

[0061] According to the chi-square statistic and the degrees of freedom associated with the preset coating rate data set, a chi-square distribution table is searched, a p-value is calculated, and a coating rate with a p-value less than a significance level threshold is determined as a target coating rate;

[0062] The associated data table of the filtered target coating rate is input into the model with lightGBM architecture for training.

[0063] When the processor 1001 calls the reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory 1005, the following operations are performed:

[0064] During the process of executing the papermaking method reconstituted tobacco process, obtaining the sensory quality score value associated with the reconstituted tobacco in the current production line at every preset period;

[0065] Determine whether the sensory quality score is within a normal value range;

[0066] When it is detected that the sensory quality score value is not in the normal value interval, determining whether the coating rate in the current production line is in the standard coating rate interval;

[0067] If not, the abnormal target coating rate process equipment parameters among the coating rate process equipment parameters are determined and output.

[0068] Based on the hardware architecture of the above-mentioned papermaking reconstituted tobacco system based on computer deep learning technology, an embodiment of the method for determining the sensory quality score of reconstituted tobacco based on coating rate of the present application is proposed.

[0069] Reference Figure 2 In a first embodiment, the method for determining the sensory quality score of reconstituted tobacco leaves based on coating rate comprises the following steps:

[0070] Step S10, obtaining the coating rate of the reconstituted tobacco leaf to be tested;

[0071] In this embodiment, the coating rate of the reconstituted tobacco leaf to be tested is firstly obtained;

[0072] It should be noted that the reconstituted tobacco to be tested refers to the reconstituted tobacco that has gone through the reconstituted tobacco process and is waiting to be tested to see if its quality meets the sensory quality standards. Optionally, the reconstituted tobacco to be tested can be selected from a product batch previously produced in the production batch as the reconstituted tobacco to be tested.

[0073] The traditional way to score the sensory quality of reconstituted tobacco is to manually smoke the cigarettes made from the reconstituted tobacco and then evaluate and score them. Among the process parameters of the reconstituted tobacco itself, the parameters that affect the sensory quality score are still unclear.

[0074] In this embodiment, in order to study which parameters are strongly correlated with the sensory quality score of papermaking reconstituted tobacco, corresponding statistics are performed based on the existing production database Uniformence and combined with the actual sensory quality manual smoking scores, so as to determine the fitting curves in each process parameter.

[0075] For example, see Figure 3 The schematic diagram of the fitting curve of the coating rate and the sensory evaluation score is shown. The following relationship can be obtained through the fitting curve:

[0076] There was a positive correlation between coating rate and sensory quality score.

[0077] After determining the fitting curve, Minitab was further used to perform correlation analysis on the key process parameters involved, referring to the corresponding table between the correlation coefficient and the correlation strength shown in Table 1:

[0078] Table 1. Correspondence between correlation coefficient and correlation strength

[0079] Correlation coefficient Strength of association 0.8-10 Very strong correlation 0.6-0.8 Strong correlation 0.4-0.6 Moderately strong correlation 0.2-0.4 Weak correlation 0.0-0.2 Very weak or no correlation

[0080] Based on the relationship correspondence table given in Table 1, we screened out parameters with correlation coefficients close to 0.8 or above from various process parameters as process parameters with strong correlation.

[0081] Based on the relationship correspondence table given in Table 1, the correlation coefficient of the coating rate is 0.874, which is a process parameter with strong correlation.

[0082] Optionally, the coating rate is a value calculated by the absolute dry weight before coating and the absolute dry weight after coating, and the calculation formula is:

[0083] X=(A2-A1) / A2

[0084] Wherein, X is the coating rate, A2 is the absolute dry weight after coating, and A1 is the absolute dry weight before coating;

[0085] It applies the specific values ​​of the absolute dry weight before coating and the absolute dry weight after coating in the DCS human-machine interface, calculates in real time and collects them to the background production database Uniformance for call.

[0086] Among them, the absolute dry weight before coating and the absolute dry weight after coating are both detected by Kr-85 (Krypton 85) rays installed inside the QCS. The principle is: Kr-85 (Krypton 85) rays penetrate the paper to form ray changes, which are converted into current signals through circuit conversion amplifiers. OPCsmart is used to read the absolute dry weight current signal before coating of the QCS client, convert it into specific values ​​and display it on the DCS human-machine interface, and collect the values ​​to the background production database Uniformance for call.

[0087] Step S20, inputting the coating rate into the trained sensory quality scoring model;

[0088] Furthermore, after determining that the associated process parameter with a strong correlation with the sensory quality score is the coating rate, during the papermaking reconstituted tobacco production process, the system collects the coating rate in the reconstituted tobacco in real time, and inputs the coating rate into the trained sensory quality score calculation model constructed based on the deep learning model. The sensory quality score calculation module based on the coating rate in the sensory quality score calculation model simulates and predicts the sensory quality score value corresponding to the coating rate.

[0089] In order to ensure that the sensory quality score calculated by the model is close enough to the sensory quality score after manual smoking, during the training process, we collected the coating rates of a large number of reconstituted tobacco leaves produced in historical batches, and scored these reconstituted tobacco leaves through manual smoking, and obtained a correlation table covering the coating rate and sensory quality score of a large number of reconstituted tobacco leaves. Figure 4 This is a schematic diagram of the correlation between the coating rate and sensory quality score of reconstituted tobacco leaves selected from the correlation table (the specific values ​​of the sensory quality score are omitted due to industrial secrets). Using the data in this correlation table, multiple deep learning training and algorithm optimization were carried out. After testing, the accuracy of the final model reached 91.6%.

[0090] Step S30, obtaining the predicted sensory quality score value calculated based on the coating rate and output by the sensory quality score model, and determining the predicted sensory quality score value as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested.

[0091] In this embodiment, a predicted sensory quality score that is as consistent as possible with the actual smoking score is calculated based on the coating rate, and the predicted sensory quality score is determined as the sensory quality score corresponding to the reconstituted tobacco to be tested. Thus, by monitoring the sensory quality score, the coating rate link that affects the sensory quality score in the production process of the reconstituted tobacco is monitored in real time. When the sensory quality score is abnormal, the coating rate link that affects the sensory quality score is checked immediately.

[0092] Further and optionally, after obtaining the sensory quality score corresponding to the reconstituted tobacco leaves to be tested, it can be determined whether the reconstituted tobacco leaves to be tested are within a preset normal value range. When it is detected that the sensory quality score is not within the normal value range, it is then detected whether the coating rate associated with the sensory quality score is abnormal.

[0093] In addition, it should be noted that in this embodiment, after we found the coating rate that has a strong correlation with the sensory quality score, we did not directly monitor it based on the numerical value of the coating rate. The reason is that there are many quality monitoring indicators in the production process of reconstructed tobacco leaves, but the general monitoring indicators are only for assessing the output grade of the reconstructed tobacco leaves, which does not affect whether the reconstructed tobacco leaves are qualified; and the sensory quality score value is an indicator with a veto nature as to whether the production of reconstructed tobacco leaves is qualified.

[0094] In the actual papermaking process of reconstituted tobacco leaves, we allow a certain fluctuation in the numerical range of the coating rate. Therefore, even if the coating rate of a batch of reconstituted tobacco leaves deviates from the preset numerical range, but does not cause the sensory quality score value monitored by the system to deviate from the normal value range, we still regard the output of this batch of reconstituted tobacco leaves as qualified, and do not regard the fluctuating coating rate as an abnormal process parameter. In other words, it is only meaningful to judge whether the coating rate that affects the sensory quality score value is abnormal when the sensory quality score value is monitored to be abnormal.

[0095] In the technical solution provided in this embodiment, by finding the coating rate that is strongly correlated with the sensory quality score in the process parameters of papermaking reconstituted tobacco, the coating rate is input into the trained sensory quality score model, and the sensory quality score prediction value is calculated based on the coating rate and used as the sensory quality score value corresponding to the reconstituted tobacco to be tested, thereby achieving efficient application of the sensory quality score in the industrial production of papermaking reconstituted tobacco and ensuring the output stability of reconstituted tobacco in the production process of papermaking reconstituted tobacco.

[0096] Second embodiment

[0097] Based on the first embodiment, in this embodiment, the trained sensory quality scoring model includes a sensory quality scoring calculation module for coating rate, and the training process of the sensory quality scoring model includes:

[0098] Step S100, obtaining a coating rate sample data set;

[0099] Step S200, normalizing the coating rate sample data set to accelerate the convergence speed of the gradient descent of the coating rate data on the same scale;

[0100] Step S300, constructing a correlation data table based on the normalized coating rate sample data set and the corresponding sensory quality score data set;

[0101] Step S400, input the associated data table into a model with a lightGBM architecture for training, and calculate the AUC value of the model after each training is completed;

[0102] Step S500: After the AUC value reaches the preset AUC threshold, the training is completed.

[0103] In this embodiment, Figure 3 It can be seen that the distribution relationship between the coating rate and the sensory quality score is relatively close. Therefore, in the training process of the deep model of the sensory quality score calculation module of the coating rate, this embodiment adopts normalization processing to scale the characteristic values ​​of the coating rate samples to a specific range, eliminate the influence of the dimensional difference between the features, and enable the model to better learn the characteristic relationship between the coating rate samples and the sensory quality score data set.

[0104] Based on the normalized coating rate sample data set and the corresponding sensory quality score data set, an associated data table was constructed, and the associated data table was input into the model with the lightGBM architecture for training, and the AUC value of the model was calculated after each training was completed.

[0105] In this embodiment, AUC (Area Under Curve) is used to evaluate the performance index of the sensory quality scoring model. After each training is completed, the performance index of the current model, that is, the AUC value, can be calculated by calling the AUC function in Python. If the AUC value does not reach the preset AUC threshold after the training is completed, the hyperparameters in each model are adjusted and the training continues.

[0106] When the AUC value of the deep learning model with the lightGBM architecture in the sensory quality score calculation module of the coating rate reaches a preset AUC threshold, the training is terminated to obtain the trained sensory quality score calculation module of the coating rate.

[0107] Furthermore, before step S300, the following steps are further included:

[0108] Step S600, calculating the observed frequency and expected frequency between the coating rate data and the sensory quality score in the associated data table, and calculating the chi-square statistic according to the observed frequency and the expected frequency;

[0109] Step S700, searching the chi-square distribution table according to the chi-square statistic and the degrees of freedom associated with the preset coating rate data set, calculating the p-value, and determining the coating rate with a p-value less than a significance level threshold as the target coating rate;

[0110] The step S300 includes:

[0111] Step S301, filter out the associated data table of the target coating rate and input it into the model with the lightGBM architecture for training.

[0112] In order to further reduce the computing power overhead when the model is trained based on the constructed associated data table, feature selection is used to remove redundant coating rate sample data in the associated data table.

[0113] First, the observed frequency and expected frequency between each coating rate and the sensory quality score in the associated data table are calculated, and the chi-square statistic is calculated according to the observed frequency and the expected frequency. The calculation formula of the chi-square statistic is as follows:

[0114]

[0115] In the formula, O i is the observed frequency, is the collected value, E i is the expected frequency, is the calculated value;

[0116] Among them, E i The calculation formula is:

[0117]

[0118] Furthermore, according to the chi-square statistic and the degrees of freedom associated with the preset coating rate data set, the chi-square distribution table is searched to obtain the p-value.

[0119] Optionally, the degrees of freedom is the total number of eigenvalues ​​in the spread rate data set minus one.

[0120] Finally, the coating rate value with a p-value less than the significance level threshold is determined as the target coating rate, and the values ​​in the data set other than the target coating rate are removed as redundant data.

[0121] Optionally, the significance level threshold is set to 0.09.

[0122] Furthermore, in this embodiment, during the training process, the maximum depth (max_depth parameter) and the number of leaf nodes (num_leaves parameter) in the model hyperparameters are adjusted.

[0123] Optionally, the maximum depth (max_depth parameter) can be set to -1;

[0124] Optionally, the number of leaf nodes (num_leaves parameter) can be set to 30;

[0125] Finally, the associated data table of the target coating rate is screened out and input into the model with the lightGBM architecture for training. When the AUC value of the deep learning model with the lightGBM architecture in the sensory quality score calculation module of the coating rate reaches the preset AUC threshold, the training is terminated to obtain the trained sensory quality score calculation module of the coating rate.

[0126] Third embodiment

[0127] Based on any embodiment, refer to Figure 5 In this embodiment, after step S30, the following steps are further included:

[0128] Step S40, during the process of executing the papermaking method reconstituted tobacco process, obtaining the sensory quality score value associated with the reconstituted tobacco in the current production line at every preset period;

[0129] Step S50, determining whether the sensory quality score is within a normal value range;

[0130] Step S60, when it is detected that the sensory quality score value is not in the normal value range, determining whether the post-coating absolute dry weight in the current production line is in the standard post-coating absolute dry weight range;

[0131] Step S70: If not, determine and output the abnormal target post-coating absolute dry quantitative process equipment parameters among the post-coating absolute dry quantitative process equipment parameters.

[0132] In this embodiment, after the sensory quality score value corresponding to the absolute dry weight after coating is calculated by the deep learning model based on the first embodiment, during the execution of the papermaking method reconstituted tobacco process, the sensory quality score value associated with the reconstituted tobacco in the current production line is obtained every preset period.

[0133] Optionally, the preset period may be to obtain data once every 5 minutes.

[0134] After obtaining the sensory quality score value, determine whether the numerical interval of the sensory quality score value is in the normal value interval. When it is detected that the sensory quality score value is not in the normal value interval, it is determined that the absolute dry weight after coating of the reconstituted tobacco to be tested is abnormal, and the absolute dry weight after coating is used as the target tobacco process parameter to be tested. When it is determined that the absolute dry weight after coating is not in its corresponding standard absolute dry weight after coating interval, the abnormal target absolute dry weight after coating process equipment parameters among the absolute dry weight process equipment parameters after coating are determined and output.

[0135] Optionally, the normal value interval of the sensory quality score can be set to a fixed value of ±1; wherein the fixed value can be set according to the specific processing scenario of the reconstituted tobacco leaves.

[0136] Further and optionally, in this embodiment, when it is determined that the absolute dry weight after coating is not within the normal value range, the absolute dry weight after coating corresponds to one or more target absolute dry weight after coating process equipment parameters.

[0137] The target coating rate process equipment parameters include at least one of the absolute dry weight before coating, the absolute dry weight after coating, the coating roller pressure, the coating liquid concentration, the paper machine speed and the base absorption performance value.

[0138] For the absolute dry weight before coating, the absolute dry weight before coating will also affect the coating rate, and the two are positively correlated. When the coating rate value is abnormal, the equipment parameters affecting the absolute dry weight before coating can be detected, including at least one of the sizing amount, retention rate, and base uniformity. The absolute dry weight before coating is adjusted by adjusting the equipment parameters affecting the absolute dry weight before coating, and then the coating rate value is adjusted.

[0139] The sizing amount refers to the slurry flow rate required to meet the quantitative requirements. Optionally, a flow meter can be set in the slurry pipeline in the coating process, and the system can collect the sizing amount by collecting the flow data on the flow meter. Among them, the sizing amount is positively correlated with the absolute dry weight before coating within a certain numerical range.

[0140] Retention rate (also known as filler retention rate) refers to the proportion of fillers or fibers retained in paper during the papermaking process, that is, the percentage of fillers in paper to fillers in the slurry. Retention rate is positively correlated with the absolute dry weight before coating.

[0141] In addition, the retention rate is a calculated value, calculated as follows:

[0142] Retention rate = absolute dry weight of retained slurry / absolute dry weight of slurry * 100%

[0143] Among them, the absolute dry amount of retained slurry and the absolute dry amount of slurry are both the collection amounts of the system.

[0144] The base absorption performance value refers to the quantitative value of the base absorption performance, which is related to the material of the base and is positively correlated with the bulk thickness of the base within a certain numerical range. The base absorption performance value is a parameter value predetermined in the papermaking recycling process, and the base absorption performance value can be changed by changing the bulk thickness of the base. Under the same conditions, the better the base absorption performance, the higher the absolute dry weight before coating, but there is an extreme value. Therefore, the base absorption performance is positively correlated with the absolute dry weight before coating within a certain range.

[0145] For the absolute dry weight after coating, the absolute dry weight after coating will also affect the coating rate, and the two are positively correlated. When the coating rate value is abnormal, the equipment parameters affecting the absolute dry weight after coating can be detected, including at least one of the coating liquid concentration, coating roller pressure, additive usage, absolute dry weight before coating, paper machine speed, coating liquid temperature and base absorption performance value.

[0146] The coating liquid concentration can be a collected value or a calculated value. The Brix value is used to reflect the coating liquid concentration for monitoring and measurement, or it can be collected and converted by a mass transmitter and presented as a specific concentration value. There is a positive correlation between the coating liquid concentration and the absolute dry weight after coating.

[0147] The coating roller pressure refers to the pressure value when the coating roller applies the coating to the surface of the base material, which can be directly collected by the system. Among them, the coating roller pressure is negatively correlated with the absolute dry weight after coating.

[0148] The amount of additives used refers to all substances in the middle coating liquid except the concentrated liquid, including flavors and fragrances, calcium carbonate, propylene glycol, glycerin, etc. Among them, calcium carbonate in the additives will directly increase the absolute dry weight after coating. Therefore, the amount of additives used is positively correlated with the absolute dry weight after coating.

[0149] In addition, the absolute dry weight before coating will also affect the absolute dry weight after coating, and the two are positively correlated. When the absolute dry weight after coating is abnormal, the equipment parameters affecting the absolute dry weight before coating can be detected (see the equipment parameters affecting the absolute dry weight before coating mentioned above), and the absolute dry weight before coating can be adjusted by adjusting the equipment parameters affecting the absolute dry weight before coating, thereby adjusting the absolute dry weight before coating, and then adjusting the value of the absolute dry weight after coating.

[0150] Paper machine speed refers to the running speed of the paper machine, which is determined by the driving roller of the paper machine's fourdrinier wire and can be directly collected by the system. The paper machine speed is negatively correlated with the absolute dry weight after coating.

[0151] In addition, the coating liquid temperature will also affect the size of the absolute dry weight after coating. When the coating liquid temperature increases, the coating liquid viscosity increases, and the absolute dry weight after coating will also increase. Therefore, when the absolute dry weight after coating is abnormal, the equipment parameters affecting the coating liquid temperature can be detected. By adjusting the equipment parameters affecting the coating liquid temperature, the coating liquid temperature can be adjusted, and then the value of the absolute dry weight after coating can be adjusted.

[0152] As for the coating roller pressure, the coating roller pressure refers to the pressure value when the coating roller applies the coating to the surface of the base material, which can be directly collected by the system. Among them, the coating roller pressure is negatively correlated with the coating rate.

[0153] For the coating liquid concentration, paper machine speed and base absorption performance values, refer to the above and will not be repeated here. The paper machine speed is negatively correlated with the coating rate, the coating liquid concentration is positively correlated with the coating rate, and the base absorption performance is positively correlated with the coating rate within a certain range.

[0154] When an abnormality is detected in the coating rate value, based on the above-mentioned equipment parameters and the positive / negative correlation between these operating parameters and the coating rate, it is detected whether the above-mentioned target coating rate equipment parameters are too large / too small, and when it is found that the target coating rate equipment parameters are too large / too small, the parameters are quickly adjusted to regulate the coating rate of papermaking reconstituted tobacco leaves.

[0155] In the technical solution provided in this embodiment, after the sensory quality score value corresponding to the coating rate is calculated by the deep learning model, when an abnormal sensory quality score value is detected during the execution of the papermaking reconstituted tobacco process, it is determined whether the coating rate is abnormal, and when the coating rate is abnormal, the abnormal equipment parameters related to the coating rate are output, thereby realizing real-time monitoring of the key parameters affecting the sensory quality score in the papermaking reconstituted tobacco production process, and timely feedback when an abnormality occurs, thereby ensuring product stability in the papermaking reconstituted tobacco production process.

[0156] In addition, it can be understood by a person skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the papermaking process reconstituted tobacco system to implement the process steps of the embodiment of the above method.

[0157] Therefore, the present application also provides a computer-readable storage medium, which stores a program for determining the sensory quality score of reconstituted tobacco leaves based on coating rate. When the program for determining the sensory quality score of reconstituted tobacco leaves based on coating rate is executed by a processor, the various steps of the method for determining the sensory quality score of reconstituted tobacco leaves based on coating rate as described in the above embodiment are implemented.

[0158] The computer-readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which may store program codes.

[0159] It should be noted that since the storage medium provided in the embodiment of the present application is the storage medium used to implement the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the storage medium, so it is not repeated here. All storage media used in the method of the embodiment of the present application belong to the scope of protection of this application.

[0160] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0161] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0162] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0164] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present application may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0165] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0166] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for determining sensory quality score of reconstituted tobacco leaves based on coating rate, characterized in that: The method comprises the following steps: Obtaining the coating rate of the reconstituted tobacco leaves to be tested; inputting the coating rate into the trained sensory quality scoring model; The predicted sensory quality score value calculated based on the coating rate and output by the sensory quality score model is obtained, and the predicted sensory quality score value is determined as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested.

2. The method according to claim 1, characterized in that The trained sensory quality scoring model includes a sensory quality scoring calculation module for coating rate, and the training process of the sensory quality scoring model includes: Get a sample data set of coating rate; The coating rate sample data set is normalized to speed up the convergence of the gradient descent of the coating rate data on the same scale; Based on the normalized coating rate sample data set and the corresponding sensory quality score data set, a correlation data table is constructed; Input the associated data table into the model with lightGBM architecture for training, and calculate the AUC value of the model after each training is completed; After the AUC value reaches the preset AUC threshold, the training is completed.

3. The method according to claim 2, characterized in that The step of inputting the associated data table into a model with a lightGBM architecture for training, and calculating the AUC value of the model after each training is completed, further includes: Calculating the observed frequency and expected frequency between the coating rate data and the sensory quality score in the associated data table, and calculating the chi-square statistic based on the observed frequency and the expected frequency; According to the chi-square statistic and the degrees of freedom associated with the preset coating rate data set, a chi-square distribution table is searched, a p-value is calculated, and a coating rate with a p-value less than a significance level threshold is determined as a target coating rate; The step of inputting the associated data table into a model with a lightGBM architecture for training, and calculating the AUC value of the model after each training is completed includes: The associated data table of the filtered target coating rate is input into the model with lightGBM architecture for training.

4. The method according to claim 2, characterized in that During training, adjust the maximum depth and number of leaf nodes in the model hyperparameters.

5. The method according to any one of claims 1 to 4, characterized in that: After the step of obtaining the predicted sensory quality score value calculated based on the coating rate output by the sensory quality score model, and determining the predicted sensory quality score value as the sensory quality score value corresponding to the reconstituted tobacco leaf to be tested, the method further includes: During the process of executing the papermaking method reconstituted tobacco process, obtaining the sensory quality score value associated with the reconstituted tobacco in the current production line at every preset period; Determine whether the sensory quality score is within a normal value range; When it is detected that the sensory quality score value is not in the normal value interval, determining whether the coating rate in the current production line is in the standard coating rate interval; If not, the abnormal target coating rate process equipment parameters among the coating rate process equipment parameters are determined and output.

6. The method according to claim 5, characterized in that The abnormal target coating rate process equipment parameters include at least one of the absolute dry weight before coating, the absolute dry weight after coating, the coating roller pressure, the coating liquid concentration, the paper machine speed and the base absorption performance value.

7. A papermaking process reconstituted tobacco system, characterized in that: The papermaking reconstituted tobacco system comprises: a memory, a processor, and a reconstituted tobacco sensory quality score determination program based on coating rate stored in the memory and executable on the processor, wherein the reconstituted tobacco sensory quality score determination program based on coating rate, when executed by the processor, implements the steps of the reconstituted tobacco sensory quality score determination method based on coating rate as described in any one of claims 1 to 6.

Images