Method, device, electronic device and storage medium for controlling moisture content of cut tobacco before drying

Abstract

The embodiments of this specification disclose a method, device, electronic device, and storage medium for controlling the moisture content of tobacco before drying. The method includes obtaining the brand information of the current batch of tobacco and determining a target prediction model; obtaining the current environmental parameters, the current production parameters, and the current moisture content of the first tobacco, determining the target moisture content of the second tobacco, and calculating the expected moisture content of the tobacco at the rehumidification outlet; determining the current moisture content of the tobacco at the rehumidification outlet, calculating the difference in moisture content of the tobacco based on the current moisture content of the tobacco and the expected moisture content of the tobacco, and adjusting the amount of water added during the rehumidification process based on the difference in moisture content of the tobacco. The embodiments of this specification can adjust the amount of water added during the rehumidification process, and can continuously and timely adjust the moisture content of the tobacco after rehumidification, so that the moisture content of the tobacco before drying is maintained at the expected value, meeting the moisture standard requirements before drying, and ensuring the quality of the final product.

Description

Technical Field

[0001] One or more embodiments of this specification relate to tobacco processing technology, and in particular to a method, device, electronic device, and storage medium for controlling moisture in cut tobacco before drying. Background Art

[0002] During the tobacco heating process, tobacco shreds are rehumidified by adding water during the rehumidification stage before being stored in leaf storage cabinets. The stored tobacco is then sequentially conveyed to the infeed cabinets for drying in the drying equipment. After drying, it passes through the outfeed cabinets for delivery. Throughout this process, controlling the moisture content of the tobacco before drying is crucial to the quality of the final product. This pre-drying moisture content must be monitored and maintained at the desired value. Traditional moisture monitoring methods, which rely heavily on manual testing and empirical judgment, suffer from issues such as delayed response and insufficient accuracy. These methods struggle to meet the pre-drying moisture standards required by modern intelligent manufacturing, impacting final product quality. Summary of the Invention

[0003] In order to solve the above problems, one or more embodiments of this specification describe a method, device, electronic device and storage medium for controlling moisture in cut tobacco before drying.

[0004] According to a first aspect, a method for controlling moisture in cut tobacco before drying is provided, the method comprising:

[0005] receiving a moisture control instruction, responding to the moisture control instruction, obtaining brand information of a current batch of cut tobacco, and determining a target prediction model that matches the brand information, wherein input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment, and output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet, wherein the environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate;

[0006] obtaining current environmental parameters, current production parameters, and current first cut tobacco moisture content, determining a target second cut tobacco moisture content based on the target prediction model, and calculating an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet;

[0007] The current moisture content of the cut tobacco at the rehumidification outlet is determined, a difference in moisture content of the cut tobacco is calculated based on the current moisture content of the cut tobacco and the expected moisture content of the cut tobacco, and the amount of water added during the rehumidification process is adjusted based on the difference in moisture content of the cut tobacco.

[0008] Preferably, before determining the target prediction model that matches the brand information, the method further includes:

[0009] For any brand information, historical data matching the brand information is obtained, and the historical data is subjected to feature correlation analysis and preprocessing to obtain training data, wherein the preprocessing includes removing outliers and supplementing missing values;

[0010] Construct an initial model, train the initial model based on the training data, and obtain a prediction model corresponding to the brand information, wherein the initial model is an XGBoost model based on a gradient boosting decision tree algorithm.

[0011] Preferably, after performing feature correlation analysis and preprocessing on the historical data to obtain training data, the method further includes:

[0012] Date information is obtained, season information is determined based on the date information, a moisture adjustment parameter corresponding to the season information is obtained, and the moisture content of the second shredded tobacco in the training data is adjusted based on the moisture adjustment parameter.

[0013] Preferably, the training data includes environmental parameters, production parameters, first tobacco moisture content, second tobacco moisture content, third tobacco moisture content of tobacco discharged from a leaf storage cabinet, cabinet number code, and moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet, wherein the moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet is the mean difference between the historical first tobacco moisture content and the historical third tobacco moisture content, and the initial model includes a first initial model and a second initial model;

[0014] The step of training the initial model based on the training data to obtain a prediction model corresponding to the brand information includes:

[0015] The first initial model is trained based on the training data to obtain a trained first model, wherein the first model is used to calculate a third moisture content of cut tobacco based on the moisture content of the first cut tobacco, a moisture difference between stored and discharged tobacco, and a standard deviation, wherein the standard deviation is the difference between the moisture content of the first cut tobacco and a set moisture content of the cut tobacco corresponding to the inlet of the drying device;

[0016] training the second initial model based on the training data to obtain a trained second model, wherein the second model is used to calculate the moisture content of the second cut tobacco according to the moisture content of the third cut tobacco and the mean value of the change in the second moisture content, wherein the mean value of the change in the second moisture content is the mean of the differences between the moisture content of the second cut tobacco and the moisture content of the third cut tobacco in each historical period;

[0017] The first model and the second model are integrated to obtain a prediction model corresponding to the brand information.

[0018] Preferably, the step of calculating the expected moisture content of the cut tobacco at the rehumidification outlet based on the first moisture content change mean and the target second cut tobacco moisture content includes:

[0019] The first moisture content change mean value corresponding to the brand information is obtained, and the difference between the target second cut tobacco moisture content and the first moisture content change mean value is calculated to obtain the expected cut tobacco moisture content at the rehumidification outlet.

[0020] Preferably, the method further comprises:

[0021] When the accumulated weight of the moisture regain electronic scale reaches a preset weight, the accumulated weight is reset and the production grade of the drying section is obtained;

[0022] When the production brand matches the brand information, real-time collected data of the tow drying section is acquired, and the target prediction model is updated based on the real-time collected data;

[0023] When the production brand does not match the brand information, a compensation value between the production brand and the brand information is obtained and determined, and the amount of water added is adjusted based on the compensation value.

[0024] Preferably, after adjusting the amount of water added in the rehumidification process based on the moisture content difference of the shredded tobacco, the method further comprises:

[0025] The variation interval of the moisture content of the first shredded tobacco is determined based on the moisture content difference of the shredded tobacco, the waiting time for the variation value of the moisture content of the first shredded tobacco to reach the variation interval is counted, and the waiting time is displayed.

[0026] According to a second aspect, a device for controlling moisture in cut tobacco before drying is provided, the device comprising:

[0027] a receiving module, configured to receive a moisture control instruction, respond to the moisture control instruction, obtain brand information of a current batch of cut tobacco, and determine a target prediction model that matches the brand information, wherein input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment, and output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet, wherein the environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate;

[0028] an acquisition module, configured to acquire current environmental parameters, current production parameters, and current first cut tobacco moisture content, determine a target second cut tobacco moisture content based on the target prediction model, and calculate an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet;

[0029] The adjustment module is used to determine the current moisture content of the tobacco cut at the rehumidification outlet, calculate the moisture content difference of the tobacco cut based on the current moisture content of the tobacco cut and the expected moisture content of the tobacco cut, and adjust the amount of water added in the rehumidification process based on the moisture content difference of the tobacco cut.

[0030] According to a third aspect, there is provided an electronic device comprising a processor and a memory;

[0031] The processor is connected to the memory;

[0032] The memory is used to store executable program code;

[0033] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0034] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, enable the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0035] The method provided in the embodiments of this specification can determine the corresponding target prediction model based on the brand information, and process the environmental parameters, production parameters and the moisture content of the first tobacco cut into pieces according to the target prediction model to obtain the moisture content of the second tobacco cut into pieces, and use the moisture content of the second tobacco cut into pieces to determine the expected moisture content of the tobacco cut into pieces at the rehumidification outlet, and adjust the amount of water added during the rehumidification process. It can continuously and timely adjust the moisture content of the tobacco cut into pieces after rehumidification, so that the moisture content of the tobacco cut into pieces before drying is maintained at the expected value, meeting the moisture standard requirements before drying, and ensuring the quality of the final product. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 It is a flow chart of a method for controlling moisture in cut tobacco before drying in one embodiment of this specification.

[0038] Figure 2 It is a structural schematic diagram of a moisture control device for cut tobacco before drying in one embodiment of this specification.

[0039] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0041] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application. Different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even though the embodiment may not be clearly described in the following text.

[0042] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the elements described without departing from the scope of the present application. Various examples may appropriately omit, replace, or add various processes or components. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted, or combined. In addition, features described in some examples may be combined in other examples.

[0043] See also Figure 1 , Figure 1 : is a flow chart of a method for controlling moisture content of cut tobacco before drying provided in an embodiment of the present application. In this embodiment of the present application, the method includes:

[0044] S101: Receive a moisture control instruction, respond to the moisture control instruction, obtain brand information of a current batch of cut tobacco, and determine a target prediction model that matches the brand information.

[0045] Among them, the input data of the target prediction model include environmental parameters, production parameters and the first tobacco moisture content at the inlet of the drying equipment; the output data of the target prediction model includes the second tobacco moisture content before entering the leaf storage cabinet; the environmental parameters include ambient temperature and ambient humidity; and the production parameters include steam flow.

[0046] The execution entity of this application can be a cloud server.

[0047] In an embodiment of the present specification, when the tobacco starts the drying process and the moisture content of the tobacco needs to be controlled before drying, the staff will generate a moisture control instruction and send it to the cloud server through operations on mobile phones, computers and other terminals. After receiving the moisture control instruction, the cloud server will deem that it is necessary to control the moisture content of the tobacco before drying, and will respond to the moisture control instruction and determine the current tobacco batch that is currently undergoing the drying process based on the production information, and determine the corresponding brand information. Different varieties of tobacco have significant differences in moisture absorption and release characteristics, and different models need to be trained separately. Therefore, several prediction models are pre-trained and stored in the cloud server, and each prediction model can be used for the prediction process of tobacco with a certain brand information. The cloud server will determine a matching target prediction model based on the brand information, and use this model for the subsequent moisture prediction process.

[0048] The tobacco drying process generally includes adding water to the tobacco in the rehumidification equipment to rehumidify the tobacco, and then transporting it to the leaf storage cabinet for storage to balance the production process and ensure that the tobacco can maintain certain humidity and temperature conditions before entering the drying stage, thereby ensuring the consistency of the drying effect. Next, the tobacco in the leaf storage cabinet will be sent to the feed cabinet, and from the feed cabinet it will be sent to the drying equipment for drying. After drying is completed, it will be sent to the discharge cabinet to wait for discharge. In this process, the moisture content of the tobacco will be measured once before it is sent to the drying equipment for drying, that is, the first tobacco moisture content is measured. However, when it is found at this stage that the moisture content of the first tobacco does not match the set standard moisture content, it is difficult to adjust the moisture content of the tobacco. Therefore, the prediction model trained in this application needs to predict the moisture content of the second tobacco before entering the leaf storage cabinet based on the moisture content of the first tobacco, environmental parameters and production parameters, and then adjust the amount of water added to the tobacco during the rehumidification stage. Among them, the moisture content of the tobacco can be measured by an infrared rapid moisture meter, a microwave moisture meter, etc.

[0049] In one embodiment, before determining the target prediction model that matches the brand information, the method further includes:

[0050] For any brand information, historical data matching the brand information is obtained, and the historical data is subjected to feature correlation analysis and preprocessing to obtain training data, wherein the preprocessing includes removing outliers and supplementing missing values;

[0051] Construct an initial model, train the initial model based on the training data, and obtain a prediction model corresponding to the brand information, wherein the initial model is an XGBoost model based on a gradient boosting decision tree algorithm.

[0052] In the embodiments of this specification, a prediction model needs to be trained for each brand information. First, the historical data corresponding to the brand information is obtained. Since the historical data has many types of data, it is first necessary to perform feature correlation analysis on the historical data through methods such as Pearson correlation coefficient and principal component analysis to determine which features are redundant or highly relevant to the model. This process will focus on the relationship between environmental factors (such as ambient temperature, ambient humidity, etc.), production parameters (such as steam flow, etc.) and the moisture content of the second tobacco, ensuring that these parameters are incorporated into the model to improve the accuracy of the prediction. In addition, it is also necessary to pre-process the feature data with high correlation that has been screened out to eliminate outliers with obvious numerical abnormalities and to supplement missing values ​​according to the average value of adjacent data. After completing the above processing, the training data for training the model can be obtained. By training the initial model with the training data, the prediction model corresponding to the brand information can be obtained.

[0053] The initial model used for training can be the XGBoost model, which has the characteristics of high precision, strong generalization ability and fast training. Specifically, it can be based on the gradient boosting decision tree algorithm, improve prediction accuracy by integrating multiple weak learners, and effectively prevent overfitting through the regularization mechanism, adapting to complex nonlinear relationships and high-dimensional data. In addition, XGBoost can automatically handle missing values ​​and unbalanced data, reducing the complexity of data preprocessing, and has good computational efficiency, suitable for large-scale real-time data processing. In practical applications, XGBoost can also provide feature importance assessment to help identify and analyze key factors, thereby further optimizing the production process.

[0054] In one possible implementation, after performing feature correlation analysis and preprocessing on the historical data to obtain training data, the method further includes:

[0055] Date information is obtained, season information is determined based on the date information, a moisture adjustment parameter corresponding to the season information is obtained, and the moisture content of the second shredded tobacco in the training data is adjusted based on the moisture adjustment parameter.

[0056] In the embodiments of this specification, considering that seasonal variations may also affect the accumulation and volatilization rate of moisture in cut tobacco, different moisture adjustment parameters are pre-set based on experience for different seasons. The cloud server determines the season based on the current date and queries the moisture adjustment parameter corresponding to that season. Only after adjusting the moisture content of the second cut tobacco in the training data using that moisture adjustment parameter will the model be trained using the training data. This eliminates the seasonal influence on moisture content and further improves the prediction accuracy of the trained model.

[0057] In addition, in other embodiments, a manual intervention coefficient reflecting the impact of manual operation on moisture control during the production process may be set in the training data.

[0058] In one embodiment, the training data includes environmental parameters, production parameters, a first tobacco moisture content, a second tobacco moisture content, a third tobacco moisture content of tobacco discharged from a leaf storage cabinet, a cabinet number code, and a moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet, wherein the moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet is the average of the differences between the historical first tobacco moisture content and the historical third tobacco moisture content, and the initial model includes a first initial model and a second initial model;

[0059] The step of training the initial model based on the training data to obtain a prediction model corresponding to the brand information includes:

[0060] The first initial model is trained based on the training data to obtain a trained first model, wherein the first model is used to calculate a third moisture content of cut tobacco based on the moisture content of the first cut tobacco, a moisture difference between stored and discharged tobacco, and a standard deviation, wherein the standard deviation is the difference between the moisture content of the first cut tobacco and a set moisture content of the cut tobacco corresponding to the inlet of the drying device;

[0061] training the second initial model based on the training data to obtain a trained second model, wherein the second model is used to calculate the moisture content of the second cut tobacco according to the moisture content of the third cut tobacco and the mean value of the change in the second moisture content, wherein the mean value of the change in the second moisture content is the mean of the differences between the moisture content of the second cut tobacco and the moisture content of the third cut tobacco in each historical period;

[0062] The first model and the second model are integrated to obtain a prediction model corresponding to the brand information.

[0063] In the embodiments of this specification, considering that in actual situations, different leaf storage cabinets, feeding cabinets, etc. may have certain fluctuations in moisture content due to reasons such as age and location, the cabinet number code of the corresponding cabinet will also be used as a feature in the training data. The initial model can be composed of a first initial model and a second initial model. The first initial model is mainly used to estimate the moisture content of the third tobacco cut according to the moisture content of the first tobacco cut, that is, the moisture content of the tobacco cut after it leaves the leaf storage cabinet. The second initial model is mainly used to estimate the moisture content of the second tobacco cut according to the moisture content of the third tobacco cut, that is, the moisture content of the tobacco cut before it enters the leaf storage cabinet. Specifically, when other features such as environmental parameters, production parameters and cabinet number codes are fixed, the calculation formula for the moisture content of the third tobacco cut by the trained first model can be that the moisture content of the third tobacco cut is equal to the moisture content of the first tobacco cut minus the standard deviation value plus the moisture difference value of the leaves leaving the storage cabinet. The calculation formula for the moisture content of the second tobacco cut by the trained second model can be that the moisture content of the second tobacco cut is equal to the moisture content of the third tobacco cut minus the mean value of the second moisture content change.

[0064] S102. Obtain current environmental parameters, current production parameters, and current first cut tobacco moisture content, determine a target second cut tobacco moisture content based on the target prediction model, and calculate an expected cut tobacco moisture content at the rehumidification outlet based on the first moisture content change mean and the target second cut tobacco moisture content.

[0065] The first moisture content change mean value includes the difference mean value between the historical moisture content of the second tobacco cut and the historical moisture content of the rehumidified outlet tobacco cut.

[0066] In the embodiments of this specification, after determining the target prediction model, the current actual environmental parameters, production parameters, and first cut tobacco moisture content are obtained and input into the target prediction model to obtain the target second cut tobacco moisture content output by the target prediction model. This target second cut tobacco moisture content is the moisture content of the cut tobacco before entering the leaf storage cabinet, in order to meet the relevant standard requirements for pre-drying moisture. Considering that the cut tobacco will experience certain moisture changes during the process of transporting the cut tobacco from the rehumidification outlet of the rehumidification equipment to the leaf storage cabinet, the average first moisture content change is calculated based on historical data. Based on the first moisture content change average and the target second cut tobacco moisture content, the expected cut tobacco moisture content at the rehumidification outlet is calculated. The expected cut tobacco moisture content is subsequently used as the moisture content that the cut tobacco should maintain during the rehumidification process.

[0067] In one embodiment, the calculating the expected moisture content of the cut tobacco at the rehumidification outlet according to the first moisture content change mean and the target second cut tobacco moisture content includes:

[0068] The first moisture content change mean value corresponding to the brand information is obtained, and the difference between the target second cut tobacco moisture content and the first moisture content change mean value is calculated to obtain the expected cut tobacco moisture content at the rehumidification outlet.

[0069] In the embodiments of this specification, different tobacco brands may have different rates of moisture change, so it is necessary to precalculate the first moisture content mean change value for each brand. In practice, the first moisture content mean change value for the current brand is directly found, and the difference between the target second tobacco moisture content and the first moisture content mean change value is calculated. This difference is the desired tobacco moisture content.

[0070] S103: determining the current moisture content of the cut tobacco at the rehumidification outlet, calculating a difference in moisture content of the cut tobacco based on the current moisture content of the cut tobacco and an expected moisture content of the cut tobacco, and adjusting the amount of water added during the rehumidification process based on the difference in moisture content of the cut tobacco.

[0071] In the embodiment of this specification, the rehumidification outlet can also detect the current moisture content of the tobacco. By calculating the difference between the current moisture content of the tobacco and the expected moisture content of the tobacco, it can be known how much water the current rehumidification equipment needs to increase or decrease to ensure that the moisture standard requirements are met during subsequent drying. The amount of water added during the rehumidification process can be adjusted accordingly to achieve control of the moisture content of the tobacco before drying.

[0072] In one embodiment, the method further comprises:

[0073] When the accumulated weight of the moisture regain electronic scale reaches a preset weight, the accumulated weight is reset and the production grade of the drying section is obtained;

[0074] When the production brand matches the brand information, real-time collected data of the tow drying section is acquired, and the target prediction model is updated based on the real-time collected data;

[0075] When the production brand does not match the brand information, a compensation value between the production brand and the brand information is obtained and determined, and the amount of water added is adjusted based on the compensation value.

[0076] In the embodiments of this specification, the conditioning equipment is equipped with an electronic conditioning scale that records the total weight of tobacco cuts that have undergone the conditioning process. A preset weight (e.g., 2000 kg) is set in the cloud server, and this preset weight is used as a data processing cycle. Whenever the cumulative weight reaches the preset weight again, the production information is used to determine the production grade of the tobacco cuts within the drying section (i.e., the section where the drying equipment is drying the tobacco cuts) and compare it with the grade information. If the two match, it indicates that tobacco cuts of the type corresponding to the grade information are still being dried. At this time, real-time data collected from the tobacco cuts within the drying section can be obtained. This real-time data can include the current moisture content of the tobacco cuts, ambient temperature, and ambient humidity. This real-time data is used to retrain the target prediction model, optimize, and update the model parameters to better reflect actual production conditions. If the production grade does not match the grade information, it indicates that the staff has forgotten to update the target prediction model, the tobacco cuts have changed, and the water addition amount of the conditioning equipment may be inaccurate. The cloud server pre-stores the prediction result difference of each prediction model determined by the staff when testing the trained prediction models. The prediction result difference will be used as a compensation value for the amount of water added to adjust the amount of water added to improve the accuracy of the prediction of the moisture content of the second tobacco.

[0077] In one embodiment, after adjusting the amount of water added during the rehumidification process based on the moisture content difference of the cut tobacco, the method further comprises:

[0078] The variation interval of the moisture content of the first shredded tobacco is determined based on the moisture content difference of the shredded tobacco, the waiting time for the variation value of the moisture content of the first shredded tobacco to reach the variation interval is counted, and the waiting time is displayed.

[0079] In the embodiment of the present specification, the target prediction model determines the expected moisture content of the tobacco shreds based on the moisture content of the first tobacco shreds, and then adjusts the amount of water added in the rehumidification process based on this, which takes a certain amount of time. During this period of time, a portion of the tobacco shreds has been processed. If the quality requirements of the tobacco shreds for the current production batch are very high, this portion of the tobacco shreds should be distinguished and processed separately. Therefore, the cloud server will determine the variation interval of the moisture content of the first tobacco shreds based on the difference in the moisture content of the tobacco shreds combined with the preset error fluctuation interval, and calculate the waiting time required for the change value of the moisture content of the first tobacco shreds to change to the variation interval. The tobacco shreds within this waiting time are tobacco shreds that do not strictly meet the moisture requirements before drying. Based on the production information, the real-time position of these dried tobacco shreds within the waiting time can be determined and marked so that the staff can quickly screen out these unqualified tobacco shreds.

[0080] The following will be combined with the Figure 2 , the tobacco moisture control device before drying provided by the embodiment of the present application is introduced in detail. Figure 2 The tobacco moisture control device before drying is used to implement the present application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0081] See Figure 2 , Figure 2 This is a schematic diagram of the structure of a tobacco moisture control device before drying provided by the embodiment of the present application. Figure 2 As shown, the device includes:

[0082] Receiving module 201 is configured to receive a moisture control instruction, respond to the moisture control instruction, obtain brand information of a current batch of cut tobacco, and determine a target prediction model that matches the brand information. Input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment. Output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet. The environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate.

[0083] an acquisition module 202 for acquiring current environmental parameters, current production parameters, and current first cut tobacco moisture content, determining a target second cut tobacco moisture content based on the target prediction model, and calculating an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet;

[0084] The adjustment module 203 is configured to determine the current moisture content of the cut tobacco at the rehumidification outlet, calculate the moisture content difference between the cut tobacco and the desired moisture content, and adjust the amount of water added during the rehumidification process based on the moisture content difference.

[0085] In one embodiment, the receiving module 201 is further configured to:

[0086] For any brand information, historical data matching the brand information is obtained, and the historical data is subjected to feature correlation analysis and preprocessing to obtain training data, wherein the preprocessing includes removing outliers and supplementing missing values;

[0087] Construct an initial model, train the initial model based on the training data, and obtain a prediction model corresponding to the brand information, wherein the initial model is an XGBoost model based on a gradient boosting decision tree algorithm.

[0088] In one embodiment, the receiving module 201 is further configured to:

[0089] Date information is obtained, season information is determined based on the date information, a moisture adjustment parameter corresponding to the season information is obtained, and the moisture content of the second shredded tobacco in the training data is adjusted based on the moisture adjustment parameter.

[0090] In one embodiment, the training data includes environmental parameters, production parameters, a first tobacco moisture content, a second tobacco moisture content, a third tobacco moisture content of tobacco discharged from a leaf storage cabinet, a cabinet number code, and a moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet, wherein the moisture difference between tobacco stored in a leaf storage cabinet and tobacco discharged from a leaf storage cabinet is the average of the differences between the historical first tobacco moisture content and the historical third tobacco moisture content, and the initial model includes a first initial model and a second initial model;

[0091] The receiving module 201 is further configured to:

[0092] The first initial model is trained based on the training data to obtain a trained first model, wherein the first model is used to calculate a third moisture content of cut tobacco based on the moisture content of the first cut tobacco, a moisture difference between stored and discharged tobacco, and a standard deviation, wherein the standard deviation is the difference between the moisture content of the first cut tobacco and a set moisture content of the cut tobacco corresponding to the inlet of the drying device;

[0093] training the second initial model based on the training data to obtain a trained second model, wherein the second model is used to calculate the moisture content of the second cut tobacco according to the moisture content of the third cut tobacco and the mean value of the change in the second moisture content, wherein the mean value of the change in the second moisture content is the mean of the differences between the moisture content of the second cut tobacco and the moisture content of the third cut tobacco in each historical period;

[0094] The first model and the second model are integrated to obtain a prediction model corresponding to the brand information.

[0095] In one embodiment, the acquisition module 202 is specifically configured to:

[0096] The first moisture content change mean value corresponding to the brand information is obtained, and the difference between the target second cut tobacco moisture content and the first moisture content change mean value is calculated to obtain the expected cut tobacco moisture content at the rehumidification outlet.

[0097] In one embodiment, the adjustment module 203 is further configured to:

[0098] When the accumulated weight of the moisture regain electronic scale reaches a preset weight, the accumulated weight is reset and the production grade of the drying section is obtained;

[0099] When the production brand matches the brand information, real-time collected data of the tow drying section is acquired, and the target prediction model is updated based on the real-time collected data;

[0100] When the production brand does not match the brand information, a compensation value between the production brand and the brand information is obtained and determined, and the amount of water added is adjusted based on the compensation value.

[0101] In one embodiment, the adjustment module 203 is further configured to:

[0102] The variation interval of the moisture content of the first shredded tobacco is determined based on the moisture content difference of the shredded tobacco, the waiting time for the variation value of the moisture content of the first shredded tobacco to reach the variation interval is counted, and the waiting time is displayed.

[0103] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field-programmable gate array (FPGA) or an integrated circuit (IC).

[0104] Each processing unit and / or module in the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0105] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0106] The communication bus 302 is used to implement the connection and communication between these components.

[0107] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0108] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0109] The processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and circuits to connect various components within the electronic device 300. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, and accesses data stored in the memory 305 to perform various functions and process data within the electronic device 300. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may also be implemented as a separate chip, rather than integrated into the processor 301.

[0110] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0111] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain user input data; and the processor 301 can be used to call the tobacco pre-drying moisture control application stored in the memory 305 and specifically perform the following operations:

[0112] receiving a moisture control instruction, responding to the moisture control instruction, obtaining brand information of a current batch of cut tobacco, and determining a target prediction model that matches the brand information, wherein input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment, and output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet, wherein the environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate;

[0113] obtaining current environmental parameters, current production parameters, and current first cut tobacco moisture content, determining a target second cut tobacco moisture content based on the target prediction model, and calculating an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet;

[0114] The current moisture content of the cut tobacco at the rehumidification outlet is determined, a difference in moisture content of the cut tobacco is calculated based on the current moisture content of the cut tobacco and the expected moisture content of the cut tobacco, and the amount of water added during the rehumidification process is adjusted based on the difference in moisture content of the cut tobacco.

[0115] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0116] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0117] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0119] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0120] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0122] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be performed by instructing related hardware through a program. The program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0123] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for controlling moisture in cut tobacco before drying, characterized in that: The method comprises: receiving a moisture control instruction, responding to the moisture control instruction, obtaining brand information of a current batch of cut tobacco, and determining a target prediction model that matches the brand information, wherein input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment, and output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet, wherein the environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate; obtaining current environmental parameters, current production parameters, and current first cut tobacco moisture content, determining a target second cut tobacco moisture content based on the target prediction model, and calculating an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet; determining a current moisture content of the cut tobacco at the rehumidification outlet, calculating a difference in moisture content of the cut tobacco based on the current moisture content of the cut tobacco and a desired moisture content of the cut tobacco, and adjusting an amount of water added during the rehumidification process based on the difference in moisture content of the cut tobacco; Wherein, before determining the target prediction model matching the brand information, the method further includes: For any brand information, historical data matching the brand information is obtained, and after feature correlation analysis and preprocessing of the historical data, training data is obtained; the training data includes environmental parameters, production parameters, first tobacco moisture content, second tobacco moisture content, third tobacco moisture content of tobacco discharged from a storage cabinet, cabinet number code, and moisture difference between tobacco stored and discharged from a storage cabinet, where the moisture difference between tobacco stored and discharged from a storage cabinet is the average of the difference between the moisture content of the first tobacco cut in history and the moisture content of the third tobacco cut in history; Constructing an initial model, training a first initial model based on the training data to obtain a trained first model, wherein the first model is used to calculate a third moisture content of cut tobacco based on the first moisture content of cut tobacco, a moisture difference between stored and discharged tobacco, and a standard deviation, wherein the standard deviation is the difference between the first moisture content of cut tobacco and a set moisture content of cut tobacco corresponding to an inlet of the drying device, and the trained first model calculates the moisture content of the third cut tobacco using a formula where the moisture content of the third cut tobacco is equal to the moisture content of the first cut tobacco minus the standard deviation plus the moisture difference between stored and discharged tobacco, and the initial model includes the first initial model and the second initial model; training the second initial model based on the training data to obtain a trained second model, wherein the second model is used to calculate the moisture content of the second cut tobacco based on the third cut tobacco moisture content and the mean value of the second moisture content change, wherein the mean value of the second moisture content change is the mean of the differences between the historical moisture contents of the second cut tobacco and the historical moisture contents of the third cut tobacco, and wherein the trained second model calculates the moisture content of the second cut tobacco using the formula: the moisture content of the second cut tobacco is equal to the moisture content of the third cut tobacco minus the mean value of the second moisture content change; The first model and the second model are integrated to obtain a prediction model corresponding to the brand information.

2. The method according to claim 1, characterized in that The preprocessing includes removing outliers and supplementing missing values; the initial model is an XGBoost model based on a gradient boosting decision tree algorithm.

3. The method according to claim 2, characterized in that After performing feature correlation analysis and preprocessing on the historical data to obtain training data, the method further includes: Date information is obtained, season information is determined based on the date information, a moisture adjustment parameter corresponding to the season information is obtained, and the moisture content of the second shredded tobacco in the training data is adjusted based on the moisture adjustment parameter.

4. The method according to claim 1, wherein The calculating the expected moisture content of the cut tobacco at the rehumidification outlet according to the first moisture content change mean value and the target second cut tobacco moisture content includes: The first moisture content change mean value corresponding to the brand information is obtained, and the difference between the target second cut tobacco moisture content and the first moisture content change mean value is calculated to obtain the expected cut tobacco moisture content at the rehumidification outlet.

5. The method according to claim 1, wherein The method further comprises: When the accumulated weight of the moisture regain electronic scale reaches a preset weight, the accumulated weight is reset and the production grade of the drying section is obtained; When the production brand matches the brand information, real-time collected data of the tow drying section is acquired, and the target prediction model is updated based on the real-time collected data; When the production brand does not match the brand information, a compensation value between the production brand and the brand information is obtained and determined, and the amount of water added is adjusted based on the compensation value.

6. The method according to claim 1, characterized in that After adjusting the amount of water added during the rehumidification process based on the moisture content difference of the cut tobacco, the method further includes: The variation interval of the moisture content of the first shredded tobacco is determined based on the moisture content difference of the shredded tobacco, the waiting time for the variation value of the moisture content of the first shredded tobacco to reach the variation interval is counted, and the waiting time is displayed.

7. A device for controlling moisture in cut tobacco before drying, characterized in that: The device comprises: a receiving module, configured to receive a moisture control instruction, respond to the moisture control instruction, obtain brand information of a current batch of cut tobacco, and determine a target prediction model that matches the brand information, wherein input data of the target prediction model includes environmental parameters, production parameters, and the moisture content of the first cut tobacco at the inlet of the drying equipment, and output data of the target prediction model includes the moisture content of the second cut tobacco before entering the leaf storage cabinet, wherein the environmental parameters include ambient temperature and ambient humidity, and the production parameters include steam flow rate; an acquisition module, configured to acquire current environmental parameters, current production parameters, and current first cut tobacco moisture content, determine a target second cut tobacco moisture content based on the target prediction model, and calculate an expected cut tobacco moisture content at the rehumidification outlet based on a first moisture content change mean value and the target second cut tobacco moisture content, wherein the first moisture content change mean value includes a mean difference between historical second cut tobacco moisture contents and historical cut tobacco moisture contents at the rehumidification outlet; an adjustment module, configured to determine a current moisture content of the cut tobacco at the rehumidification outlet, calculate a difference in moisture content of the cut tobacco based on the current moisture content of the cut tobacco and a desired moisture content of the cut tobacco, and adjust an amount of water added during the rehumidification process based on the difference in moisture content of the cut tobacco; The receiving module is further configured to: For any brand information, historical data matching the brand information is obtained, and after feature correlation analysis and preprocessing of the historical data, training data is obtained; the training data includes environmental parameters, production parameters, first tobacco moisture content, second tobacco moisture content, third tobacco moisture content of tobacco discharged from a storage cabinet, cabinet number code, and moisture difference between tobacco stored and discharged from a storage cabinet, where the moisture difference between tobacco stored and discharged from a storage cabinet is the average of the difference between the moisture content of the first tobacco cut in history and the moisture content of the third tobacco cut in history; Constructing an initial model, training a first initial model based on the training data to obtain a trained first model, wherein the first model is used to calculate a third moisture content of cut tobacco based on the first moisture content of cut tobacco, a moisture difference between stored and discharged tobacco, and a standard deviation, wherein the standard deviation is the difference between the first moisture content of cut tobacco and a set moisture content of cut tobacco corresponding to an inlet of the drying device, and the trained first model calculates the moisture content of the third cut tobacco using a formula where the moisture content of the third cut tobacco is equal to the moisture content of the first cut tobacco minus the standard deviation plus the moisture difference between stored and discharged tobacco, and the initial model includes the first initial model and the second initial model; training the second initial model based on the training data to obtain a trained second model, wherein the second model is used to calculate the moisture content of the second cut tobacco based on the third cut tobacco moisture content and the mean value of the second moisture content change, wherein the mean value of the second moisture content change is the mean of the differences between the historical moisture contents of the second cut tobacco and the historical moisture contents of the third cut tobacco, and wherein the trained second model calculates the moisture content of the second cut tobacco using the formula: the moisture content of the second cut tobacco is equal to the moisture content of the third cut tobacco minus the mean value of the second moisture content change; The first model and the second model are integrated to obtain a prediction model corresponding to the brand information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or processor to execute the steps of the method according to any one of claims 1 to 6.

Images