A loosening and moisture-recovering method, device and medium for non-full formula tobacco sheets

Abstract

The present application discloses a loosening and rehydrating method, device and medium for non-full formula tobacco sheets; it relates to the field of tobacco processing and solves the problem of unstable moisture content at the loosening and rehydrating outlet of tobacco leaves. By obtaining the identification code of the tobacco package to be processed and parsing it to obtain the corresponding formula data; obtaining the production environment data and real-time detection data of the tobacco package to be processed; inputting the formula data, production environment data and real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; controlling the water addition equipment of the loosening and rehydrating drum to add water according to the adjusted water addition amount. The formula data of the tobacco leaves are classified and associated with the production environment data and real-time detection data. The water addition amount is corrected by the fully connected neural network model, and the water addition amount is corrected in advance before the tobacco leaves enter the drum, which greatly eliminates the influence of the different water absorption properties of non-full formula tobacco on the moisture content of the loosening and rehydrating outlet, thereby achieving stable control.

Description

Technical Field

[0001] The present application relates to the field of tobacco processing, and in particular to a method, device and medium for loosening and rehumidifying non-full formula tobacco sheets. Background Art

[0002] Loosening and conditioning is a critical process in tobacco production. Its purpose is to regulate the material's moisture content and enhance its workability. The stability of the moisture content at the exit of the conditioning drum directly impacts the stability of subsequent processing and also influences the filling value of the finished tobacco. The moisture content of tobacco leaves at the exit of the conditioning drum directly affects their workability in subsequent processes. Traditionally, the loosening and conditioning of full-formula tobacco leaves uses the same water addition for all tobacco leaves of the same type.

[0003] However, non-full formula tobacco leaves are made using different tobacco leaf formulas or proportions. The grades and origins of each package of loose and rehumidified non-full formula tobacco leaves are different, and the non-full formula tobacco leaf raw materials are not evenly blended, which makes the water absorption of the tobacco leaves vary significantly during the production process, resulting in drastic fluctuations in the outlet moisture content at the same proportion of water addition. Therefore, using a fixed proportion of water addition will make the outlet moisture content of the tobacco leaves unstable.

[0004] It can be seen from this that how to solve the unstable moisture content of loose tobacco leaves at the rehumidification outlet is a technical problem that needs to be solved urgently by people in this field. Summary of the Invention

[0005] The purpose of this application is to provide a method, device and medium for loosening and rehumidifying non-full formula tobacco leaves, so as to solve the problem of unstable moisture content at the loosening and rehumidification outlet of tobacco leaves.

[0006] In order to solve the above technical problems, the present application provides a method for loosening and rehumidifying non-full formula tobacco sheets, comprising:

[0007] Obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data;

[0008] Obtaining production environment data and real-time detection data of the cigarette packs to be processed;

[0009] The formula data, the production environment data, and the real-time detection data are input into a pre-trained fully connected neural network model to obtain an adjusted water addition amount;

[0010] The water adding device of the loosening and rehumidifying drum is controlled to add water according to the adjusted water adding amount.

[0011] Optionally, in the above-mentioned loosening and rehumidification method for non-full-formula tobacco sheets, the step of obtaining the identification code of the cigarette pack to be processed and parsing it to obtain the corresponding formula data includes:

[0012] Obtaining the identification code of the cigarette package to be processed;

[0013] The identification code is parsed to obtain the tobacco leaf origin, tobacco leaf year, tobacco leaf grade, tobacco leaf weight, and tobacco leaf average moisture content, and the information is written into a pre-recorded information database.

[0014] Optionally, in the above-mentioned loosening and rehumidification method for non-full formula tobacco sheets, the step of obtaining the production environment data and real-time detection data of the tobacco packs to be processed includes:

[0015] The loosening and moisture-conditioning return air temperature and the loosening and moisture-conditioning induced steam pressure of the loosening and moisture-conditioning drum are obtained.

[0016] The actual weight and actual measured moisture content of the cigarette packs to be processed before entering the loosening and rehumidification drum are obtained.

[0017] Optionally, in the above-mentioned loosening and rehumidifying method for non-full formula tobacco sheets, the water adding device controlling the loosening and rehumidifying drum adds water according to the adjusted water addition amount, and the method further comprises:

[0018] Determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed;

[0019] If so, the step of controlling the water adding device of the loosening and rehydrating drum to add water according to the adjusted water adding amount is entered.

[0020] Optionally, in the above-mentioned loosening and conditioning method for non-full formula tobacco sheets, the step of determining whether the cigarette pack currently entering the loosening and conditioning drum is a cigarette pack to be processed includes:

[0021] Obtaining the weight of the cigarette pack to be processed before the slicer;

[0022] Get the accumulated weight of the flow before loosening and rewetting;

[0023] When the weight of the cigarette pack before the slicer is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidification drum is the cigarette pack to be processed;

[0024] If the weight of the cigarette pack before the slicer is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is not the cigarette pack to be processed.

[0025] Optionally, in the above-mentioned loosening and conditioning method for non-full formula tobacco sheets, the step of determining whether the cigarette pack currently entering the loosening and conditioning drum is a cigarette pack to be processed includes:

[0026] determining whether flakes will be added to the cigarette pack to be processed;

[0027] If yes, obtain the added weight of the flakes;

[0028] Obtaining the weight of the cigarette pack to be processed before the slicer;

[0029] Get the accumulated weight of the flow before loosening and rewetting;

[0030] When the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is the cigarette pack to be processed;

[0031] If the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is not the cigarette pack to be processed.

[0032] Optionally, the loosening and rehydration method of the non-full formula tobacco sheet further includes:

[0033] The corresponding average moisture content of the tobacco leaves in the pre-recorded information database is updated according to the actual measured moisture content.

[0034] Optionally, in the above-mentioned loosening and rehydration method for non-full formula tobacco sheets, if thin sheets are added to the tobacco pack to be processed, the step of obtaining the cumulative weight of the flow scale before loosening and rehydration includes:

[0035] Detecting the moisture content of the inlet of the loose rehumidification drum based on a change point detection algorithm to determine whether the cigarette pack contains flakes;

[0036] If so, the detection of the accumulated weight of the flow scale is started.

[0037] Optionally, the loosening and rehydration method of the non-full formula tobacco sheet further includes:

[0038] After the loosening and moisture conditioning of the cigarette packs to be processed is completed, the moisture content is obtained;

[0039] The fully connected neural network model is subjected to loss calculation, back propagation, and parameter update according to the resulting moisture content, the formula data, the production environment data, and the real-time detection data.

[0040] In order to solve the above technical problems, the present application also provides a loosening and moisture-recovering device for non-full formula tobacco sheets, comprising:

[0041] A first acquisition module is used to obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data;

[0042] A second acquisition module is used to obtain production environment data and real-time detection data of the cigarette pack to be processed;

[0043] An adjustment module, configured to input the formula data, the production environment data, and the real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount;

[0044] The execution module is used to control the water adding equipment of the loosening and rehumidifying drum to add water according to the adjusted water adding amount.

[0045] In order to solve the above technical problems, the present application also provides a loosening and moisture-recovering device for non-full formula tobacco sheets, comprising:

[0046] memory for storing computer programs;

[0047] The processor is used to implement the steps of the above-mentioned loosening and rehumidification method of non-full formula tobacco sheets when executing the computer program.

[0048] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for loosening and rehumidifying non-full formula tobacco sheets are implemented.

[0049] The loosening and rehydration method for non-full-formula tobacco sheets provided in this application obtains the identification code of the tobacco package to be processed and parses it to obtain the corresponding formula data; obtains the production environment data and real-time detection data of the tobacco package to be processed; inputs the formula data, production environment data, and real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; and controls the water addition equipment of the loosening and rehydration drum to add water according to the adjusted water addition amount. The tobacco leaf formula data is classified and associated with the production environment data and real-time detection data. The water addition amount is corrected using the fully connected neural network model. The water addition amount is corrected in advance before the tobacco leaves enter the drum, which greatly eliminates the impact of the different water absorption properties of non-full-formula tobacco on the moisture content at the loosening and rehydration outlet, thereby achieving stable control.

[0050] In addition, the present application also provides a device and a medium, which correspond to the above-mentioned loosening and rehumidification method of non-full formula tobacco sheets, and the effect is the same as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to 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 any creative work.

[0052] Figure 1 A flow chart of a method for loosening and rehumidifying a non-full formula tobacco sheet provided in an embodiment of the present application;

[0053] Figure 2 A structural diagram of a loosening and moisture-recovering device for non-full-formula tobacco sheets provided in an embodiment of the present application;

[0054] Figure 3This is a structural diagram of another loosening and rehumidification device for non-full formula tobacco sheets provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] The core of this application is to provide a loosening and rehumidification method, device and medium for non-full formula tobacco sheets.

[0057] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0058] The loosening and rehydration process is the first moisture control process in the cigarette shred process. Its process purpose is to adjust the moisture content of the material and increase the processing resistance of the material. The stability of its outlet moisture is directly related to the stability of subsequent processing, and also affects the filling value of the finished tobacco. For non-full formula tobacco sheets, different tobacco leaf formulas or proportions are used for production. Each package of non-full formula tobacco leaves that enter the loosening and rehydration process has different grades and origins, and the non-full formula tobacco leaf raw materials are not evenly blended, which makes the water absorption of the tobacco sheets significantly different during the production process, resulting in drastic fluctuations in the outlet moisture content under the same proportion of water addition. Therefore, using a fixed proportion of water addition will make the outlet moisture content of the tobacco leaves unstable. This application does not limit the overall processing flow of the tobacco sheets, nor does it limit the formula information of the non-full formula tobacco sheets.

[0059] In order to solve the above problems, the present invention provides a method for loosening and rehumidifying non-full formula tobacco sheets. Figure 1 This is a flow chart of a method for loosening and rehumidifying a non-full formula tobacco sheet provided in an embodiment of the present application, such as Figure 1 As shown, including:

[0060] S11: Obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data;

[0061] S12: Obtaining production environment data and real-time detection data of the cigarette packs to be processed;

[0062] S13: inputting the formula data, production environment data, and real-time detection data into a pre-trained fully connected neural network model to obtain the adjusted water addition amount;

[0063] S14: Control the water adding device of the loosening and rehumidifying drum to add water according to the adjusted water adding amount.

[0064] The identification code of the cigarette pack to be processed is obtained and parsed to obtain the corresponding formula data, which includes but is not limited to the origin, grade, year and ratio of the tobacco leaves.

[0065] The production environment data for processed cigarette packs refers to environmental information about the processing equipment during the tobacco processing process, including but not limited to temperature and humidity. Real-time detection data refers to actual detection data about the tobacco during processing, including but not limited to actual weight and moisture content. Data acquisition software can be used to collect real-time production data from the equipment's PLC address.

[0066] A loosening and conditioning drum is a device used in the cigarette production process to condition tobacco leaves. The function of the loosening and conditioning drum is to expose the tobacco leaves to a high relative humidity through rotation and heating, allowing them to absorb the appropriate amount of moisture, thereby softening and loosening the leaves. This facilitates subsequent processing and cigarette making. In the loosening and conditioning drum, the tobacco leaves are placed inside the drum and continuously moved as the drum rotates. Simultaneously, the heating device inside the drum provides the appropriate temperature to promote moisture absorption. This allows the tobacco leaves to reach the desired humidity level after a period of treatment in the drum, preparing them for subsequent processing steps.

[0067] A fully connected neural network (FCN), also known as a multi-layer perceptron (MLP), is a common artificial neural network model. It consists of multiple neurons, each of which is connected to all neurons in the previous layer, forming a fully connected structure. A FCN typically consists of an input layer, several hidden layers, and an output layer. Each neuron is connected to all neurons in the previous layer, with weights used to adjust the strength of the connections. Each neuron also has an activation function, which performs a nonlinear transformation on the input signal.

[0068] When training the model, it is necessary to train the fully connected neural network model through the delay time. The time provided by the tobacco factory in the system from the loose recirculation momentum scale to the loose recirculation drum entrance is used through data alignment processing; if this delay time is not provided, the Pearson correlation coefficient of the loose recirculation drum entrance data and the loose recirculation momentum scale data is calculated, and after translation, the point with the maximum absolute value of the correlation coefficient is taken as the delay time.

[0069] The amount of water added is adjusted to the amount of water added for the current cigarette pack to be processed, which solves the control deviation caused by the quality difference of non-full formula tobacco leaves, avoids the influence of tobacco leaf quality on the loosening and rehydration results as much as possible, and realizes stable control of the moisture content at the loosening and rehydration outlet.

[0070] The loosening and rehydration method for non-full-formula tobacco sheets provided in the embodiments of the present application obtains the identification code of the tobacco pack to be processed and parses it to obtain the corresponding formula data; obtains the production environment data and real-time detection data of the tobacco pack to be processed; inputs the formula data, production environment data, and real-time detection data into a pre-trained fully connected neural network model to adjust the water addition amount; and controls the water addition equipment of the loosening and rehydration drum to add water according to the adjusted water addition amount. The tobacco leaf formula data is classified and correlated with the production environment data and real-time detection data. The water addition amount is corrected using the fully connected neural network model, which greatly eliminates the impact of the different water absorption properties of non-full-formula tobacco on the moisture content of the loosening and rehydration outlet, thereby achieving stable control.

[0071] According to the above embodiment, in another specific embodiment, the loosening and rehumidification method of non-full formula tobacco sheets, wherein the identification code of the cigarette pack to be processed is obtained and parsed to obtain the corresponding formula data, includes:

[0072] Obtaining the identification code of the cigarette package to be processed;

[0073] The identification code is parsed to obtain the tobacco leaf origin, tobacco leaf year, tobacco leaf grade, tobacco leaf weight, and tobacco leaf average moisture content, and the information is written into a pre-recorded information database.

[0074] The identification code for non-full-blended tobacco packages is usually a barcode, which can reveal the blend information, including the origin of the leaves, the year of the tobacco leaves, the tobacco grade, the tobacco weight, and the average moisture content of the tobacco leaves. Entering this data can help trace the source and composition of the tobacco and provide detailed product information.

[0075] Origin: The origin of the tobacco leaf, which may include country, region or specific farm information.

[0076] Grade: The quality grade of tobacco leaves, usually assessed based on their appearance, color, texture and other characteristics.

[0077] Vintage: The year the tobacco leaves were harvested, which can affect the quality and taste of the tobacco leaves.

[0078] Ratio: The ratio of tobacco leaves, which indicates the proportion of different types of tobacco leaves in the formula.

[0079] This information can be encoded in a barcode and printed on the cigarette pack. When the cigarette pack barcode is scanned or read, the recipe information can be obtained and used for purposes such as product traceability, quality control and market analysis.

[0080] According to the above embodiment, in another specific embodiment, obtaining the production environment data and real-time detection data of the cigarette pack to be processed includes:

[0081] The loosening and moisture-conditioning return air temperature and the loosening and moisture-conditioning induced steam pressure of the loosening and moisture-conditioning drum are obtained.

[0082] The actual weight and actual measured moisture content of the cigarette packs to be processed before entering the loosening and rehumidification drum are obtained.

[0083] The return air temperature and induced steam pressure may be adjusted according to the specific type of smoke sheet, rehumidification requirements and production experience, so the parameter values ​​need to be updated and input into the model in a timely manner.

[0084] While the average moisture content of tobacco leaves can be determined from the tobacco pack identification code, moisture content can change during the production process, necessitating re-measurement. Model parameters are automatically updated as production progresses, ensuring the model's timeliness.

[0085] Specifically, the corresponding average moisture content of the tobacco leaves in the pre-recorded information database is updated according to the actually measured moisture content.

[0086] In addition, since the number of samples for the first manual entry of the average moisture content of cigarette packs is relatively small, there is a certain degree of randomness, and the average moisture content of cigarette packs affects the model results; therefore, in the actual production process, the average moisture content of cigarette packs needs to be updated in real time. The update formula is as follows:

[0087]

[0088] In the formula Measure the average moisture content of the current cigarette pack, To record the average moisture content of cigarette packs in the system, k is the update ratio. When the production batch is less than the threshold δ (set as needed), k = 1 / n, n is the number of production batches, and when the production batches are large enough, n = δ.

[0089] According to the above embodiment, in another specific embodiment, the water adding device for controlling the loosening and rehydrating drum adds water according to the adjusted water addition amount, and the method further includes:

[0090] Determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed;

[0091] If so, the step of controlling the water adding device of the loosening and rehydrating drum to add water according to the adjusted water adding amount is entered.

[0092] Since cigarette pack processing is an assembly line production, and the data of the material after slicing entering the drum is far apart from that before slicing, it is necessary to accurately judge whether the cigarette pack currently entering the loose rehumidification drum is the cigarette pack to be processed. If so, control the water adding equipment of the loose rehumidification drum to add water according to the adjusted water addition amount.

[0093] According to the above embodiment, in another specific embodiment, the step of determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed includes:

[0094] Obtaining the weight of the cigarette pack to be processed before the slicer;

[0095] Get the accumulated weight of the flow before loosening and rewetting;

[0096] When the weight of the cigarette pack before the slicer is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidification drum is the cigarette pack to be processed;

[0097] If the weight of the cigarette pack before the slicer is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is not the cigarette pack to be processed.

[0098] Because the cigarette pack barcode reader is located before the slicer, and the post-slicing material entering the drum is far away from the pre-slicing data, in practice, the cigarette pack barcode and the weight of the cigarette pack before the slicer are written into a queue in the form of a hash table. The accumulated weight on the flow scale before loosening is used as the standard to sequentially determine the type of material currently entering the loosening and rehydration process. This embodiment uses a weight queue matching mechanism for execution data, comparing the weight of the cigarette pack before the slicer with the accumulated weight on the flow scale before loosening and rehydration to confirm the raw materials currently being used for production.

[0099] According to the above embodiment, in another specific embodiment, the step of determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed includes:

[0100] determining whether flakes will be added to the cigarette pack to be processed;

[0101] If yes, obtain the added weight of the flakes;

[0102] Obtaining the weight of the cigarette pack to be processed before the slicer;

[0103] Get the accumulated weight of the flow before loosening and rewetting;

[0104] When the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is the cigarette pack to be processed;

[0105] If the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is not the cigarette pack to be processed.

[0106] Some tobacco leaves are added with flakes during the initial batching process, necessitating the inclusion of flake weight analysis during bale matching. When flakes are detected, the weight of the bales before the slicer is cumulatively added. For example, if the total weight of flakes is 100kg and each bale weighs 200kg, the average operator will add flakes to the first four bales, resulting in a cumulative weight of approximately 225kg. While this method may allow for errors in determining the first few bales of tobacco, it has minimal impact on actual control, ensuring accurate identification of subsequent leaves.

[0107] According to the above embodiment, in another specific embodiment, if a thin sheet is added to the cigarette pack to be processed, the step of obtaining the cumulative weight of the flow scale before loosening and rehydration includes:

[0108] Detecting the moisture content of the inlet of the loose rehumidification drum based on a change point detection algorithm to determine whether the cigarette pack contains flakes;

[0109] If so, the detection of the accumulated weight of the flow scale is started.

[0110] During the tobacco leaf headstock stage, flakes are often added to increase the softness and workability of the tobacco leaves. Flakes are a thin sheet-like material made from tobacco leaf fragments that can increase the bulk and improve the texture of the tobacco leaves.

[0111] To distinguish whether or not flakes have been added, a change point detection algorithm can be used. This algorithm is used to detect sudden changes or turning points in a signal. In this case, the loose inlet moisture content of the tobacco leaf can be used as the input signal, and the change point detection algorithm can be used to detect sudden changes in looseness.

[0112] Specifically, historical data on the loose inlet moisture content of tobacco leaves can be collected and used as an input sequence. A change point detection algorithm can then be applied to analyze the change points in the input sequence. If the loose inlet moisture content of the tobacco leaves undergoes a significant abrupt change when flakes are added, the change point detection algorithm should be able to detect this change point.

[0113] Using a sliding window method with a fixed window length, the mean, deviation, distribution and other statistical features in the front and back windows are compared. When the change in the statistical features exceeds the specified threshold, it is determined that the material has changed, and the current material no longer contains flakes; for example, the threshold is set to 1.3 times the statistical value corresponding to the inlet moisture of the historical head material.

[0114] According to the above embodiment, in another specific embodiment, the method further includes:

[0115] After the loosening and moisture conditioning of the cigarette packs to be processed is completed, the moisture content is obtained;

[0116] The fully connected neural network model is subjected to loss calculation, back propagation, and parameter update according to the resulting moisture content, the formula data, the production environment data, and the real-time detection data.

[0117] During the neural network training process, loss calculation, backpropagation and parameter updates are usually performed after each batch based on the actual control effect.

[0118] First, after each batch, the neural network calculates the loss between the predicted output and the actual output for that batch. A loss function is typically used to measure the difference between the predicted output and the actual output. Common loss functions include mean squared error (MSE) and cross entropy.

[0119] Next, the neural network propagates the gradient from the output layer to the input layer layer by layer based on the gradient information calculated by the loss function through the backpropagation algorithm. This determines the contribution of each neuron to the loss and passes the gradient information back to the weights and bias parameters in the network.

[0120] Finally, based on the gradient information and an optimization algorithm (such as stochastic gradient descent, SGD), the neural network updates its parameters to reduce the value of the loss function. The parameter updating process usually involves selecting a learning rate to control the step size of the parameter update.

[0121] This batch training process will be repeated multiple times on the entire training dataset until a predetermined stopping condition is reached, such as reaching the maximum number of iterations or the loss function converges.

[0122] By continuously adjusting parameters, the neural network can gradually optimize the model and improve its prediction and response capabilities for actual control tasks.

[0123] In the above embodiments, a method for loosening and rehumidifying non-full-rice tobacco sheets is described in detail. This application also provides corresponding embodiments of a device for loosening and rehumidifying non-full-rice tobacco sheets. It should be noted that this application describes the embodiments of the device from two perspectives: one from the perspective of functional modules and the other from the perspective of hardware.

[0124] Based on the perspective of functional modules, Figure 2 This is a structural diagram of a loosening and moisture-recovering device for non-full-formula tobacco sheets provided in an embodiment of the present application, such as Figure 2 As shown, a loosening and rehumidifying device for non-full recipe tobacco sheets comprises:

[0125] A first acquisition module 21 is used to obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data;

[0126] A second acquisition module 22 is used to obtain production environment data and real-time detection data of the cigarette pack to be processed;

[0127] An adjustment module 23 is configured to input the formula data, the production environment data, and the real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount;

[0128] The execution module 24 is used to control the water adding equipment of the loosening and rehumidifying drum to add water according to the adjusted water adding amount.

[0129] The loosening and rehydration method for non-full-formula tobacco leaves involves obtaining the identification code of the tobacco bales to be processed and parsing it to obtain the corresponding formula data. The production environment data and real-time detection data of the tobacco bales to be processed are then obtained. The formula data, production environment data, and real-time detection data are input into a pre-trained fully connected neural network model to determine the adjusted water addition amount. The water addition equipment in the loosening and rehydration drum is then controlled to add water according to the adjusted water addition amount. The tobacco leaf formula data is classified and correlated with the production environment data and real-time detection data. The water addition amount is then adjusted using the fully connected neural network model. This adjustment is made before the tobacco leaves enter the drum, greatly eliminating the impact of the varying water absorption properties of non-full-formula tobacco leaves on the moisture content at the loosening and rehydration outlet, thereby achieving stable control.

[0130] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, and they will not be repeated here.

[0131] Figure 3 This is a structural diagram of another loosening and moisture-recovering device for non-full-formula tobacco sheets provided in an embodiment of the present application, such as Figure 3 As shown, the loosening and rehumidification device for non-full-mix tobacco sheets includes: a memory 30 for storing a computer program;

[0132] The processor 31 is used to implement the steps of the method for obtaining user operation habit information as described in the above embodiment (the method for loosening and rehumidifying non-full-blended tobacco sheets) when executing the computer program.

[0133] The loosening and moisture-recovering device for the non-full formula tobacco sheet provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.

[0134] Among them, the processor 31 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 31 can be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic array (PLA). The processor 31 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 31 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 31 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0135] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 30 is at least used to store the following computer program 301, wherein, after the computer program is loaded and executed by the processor 31, it can implement the relevant steps of the loosening and rehumidification method of the non-full formula tobacco sheet disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 30 may also include an operating system 302 and data 303, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 302 may include Windows, Unix, Linux, etc. The data 303 may include but is not limited to data involved in implementing the loosening and rehumidification method of the non-full formula tobacco sheet.

[0136] In some embodiments, the loosening and rehumidification device for non-full formula tobacco sheets may further include a display screen 32 , an input and output interface 33 , a communication interface 34 , a power supply 35 and a communication bus 36 .

[0137] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the loose rehumidification device for non-full-formulation tobacco sheets, and may include more or fewer components than shown in the figure.

[0138] The loosening and rehydrating device for non-full-formula tobacco sheets provided in an embodiment of the present application includes a memory and a processor. When executing a program stored in the memory, the processor can implement the following method: a loosening and rehydrating method for non-full-formula tobacco sheets, obtaining an identification code of a tobacco pack to be processed and parsing it to obtain corresponding recipe data; obtaining production environment data and real-time detection data of the tobacco pack to be processed; inputting the recipe data, production environment data, and real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; and controlling the water addition equipment of the loosening and rehydrating drum to add water according to the adjusted water addition amount. The recipe data of the tobacco leaves is classified and associated with the production environment data and real-time detection data. The water addition amount is corrected using the fully connected neural network model. The water addition amount is corrected in advance before the tobacco leaves enter the drum, which greatly eliminates the influence of different water absorption properties of non-full-formula tobacco on the moisture content at the loosening and rehydrating outlet, thereby achieving stable control.

[0139] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the embodiment of the loosening and rehumidification method for non-full-blended tobacco sheets.

[0140] It is understandable that if the method in the above embodiment 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 storage medium. 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, which is stored in a storage medium and executes all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0141] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the program implements the following method: a method for loosening and rehydrating non-full-formula tobacco sheets, comprising obtaining an identification code of a tobacco pack to be processed and parsing it to obtain corresponding formula data; obtaining production environment data and real-time detection data of the tobacco pack to be processed; inputting the formula data, production environment data, and real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; and controlling the water addition equipment of the loosening and rehydrating drum to add water according to the adjusted water addition amount. The tobacco leaf formula data is classified and associated with the production environment data and real-time detection data. The water addition amount is corrected using the fully connected neural network model. This correction is made in advance before the tobacco leaves enter the drum, thereby significantly reducing the impact of the varying water absorption properties of non-full-formula tobacco on the moisture content at the loosening and rehydrating outlet, thereby achieving stable control.

[0142] The above is a detailed introduction to the loosening and rehumidification method, device and medium for non-full formula tobacco sheets provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

[0143] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

Claims

1. A method for loosening and rehumidifying non-full formula tobacco sheets, characterized in that: include: Obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data; Obtaining production environment data and real-time detection data of the cigarette packs to be processed; The formula data, the production environment data, and the real-time detection data are input into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; Controlling the water adding device of the loosening and rehydrating drum to add water according to the adjusted water adding amount; Before the water adding device for controlling the loosening and moisture-replenishing drum adds water according to the adjusted water addition amount, the device further comprises: Determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed; If so, the step of controlling the water adding device of the loosening and rehydrating drum to add water according to the water adding amount is performed; The step of judging whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed includes: determining whether flakes will be added to the cigarette pack to be processed; If yes, obtain the added weight of the flakes; Obtaining the weight of the cigarette pack to be processed before the slicer; Get the accumulated weight of the flow before loosening and rewetting; When the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is the cigarette pack to be processed; If the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidification drum is not the cigarette pack to be processed; If thin sheets are added to the cigarette pack to be processed, the method of obtaining the cumulative weight of the flow before loosening and rehydration includes: Detecting the moisture content of the inlet of the loose rehumidification drum based on a change point detection algorithm to determine whether the cigarette pack contains flakes; If so, the detection of the accumulated weight of the flow scale is started.

2. The method for loosening and rehumidifying non-full formula tobacco sheets according to claim 1, characterized in that: The step of obtaining the identification code of the cigarette pack to be processed and parsing the code to obtain the corresponding recipe data includes: Obtaining the identification code of the cigarette package to be processed; The identification code is parsed to obtain the tobacco leaf origin, tobacco leaf year, tobacco leaf grade, tobacco leaf weight, and tobacco leaf average moisture content, and the information is written into a pre-recorded information database.

3. The method for loosening and rehumidifying non-full formula tobacco sheets according to claim 2, characterized in that: The obtaining of the production environment data and real-time detection data of the cigarette pack to be processed includes: Obtaining the loosening and moisture-conditioning return air temperature and the loosening and moisture-conditioning induced steam pressure of the loosening and moisture-conditioning drum; The actual weight and actual measured moisture content of the cigarette packs to be processed before entering the loosening and rehumidification drum are obtained.

4. The method for loosening and moistening non-full formula tobacco sheets according to claim 1, characterized in that: The step of judging whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed includes: Obtaining the weight of the cigarette pack to be processed before the slicer; Get the accumulated weight of the flow before loosening and rewetting; When the weight of the cigarette pack before the slicer is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidification drum is the cigarette pack to be processed; If the weight of the cigarette pack before the slicer is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is not the cigarette pack to be processed.

5. The method for loosening and rehydrating non-full formula tobacco sheets according to claim 3, characterized in that: Also includes: The corresponding average moisture content of the tobacco leaves in the pre-recorded information database is updated according to the actual measured moisture content.

6. The method for loosening and rehumidifying non-full formula tobacco sheets according to claim 1, characterized in that: Also includes: After the loosening and moisture conditioning of the cigarette packs to be processed is completed, the moisture content is obtained; The fully connected neural network model is subjected to loss calculation, back propagation, and parameter update according to the resulting moisture content, the formula data, the production environment data, and the real-time detection data.

7. A loosening and moisture-reinforcing device for non-full-formula tobacco sheets, characterized in that: include: A first acquisition module is used to obtain the identification code of the cigarette pack to be processed and parse it to obtain the corresponding recipe data; A second acquisition module is used to obtain production environment data and real-time detection data of the cigarette pack to be processed; An adjustment module, configured to input the formula data, the production environment data, and the real-time detection data into a pre-trained fully connected neural network model to obtain an adjusted water addition amount; An execution module, configured to control the water adding device of the loosening and rehumidifying drum to add water according to the adjusted water adding amount; The loosening and rehumidification device for non-full formula tobacco sheets is also used for: Before controlling the water adding device of the loosening and rehumidifying drum to add water according to the adjusted water adding amount, determining whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed; If so, the execution module is triggered; The step of judging whether the cigarette pack currently entering the loosening and rehumidifying drum is a cigarette pack to be processed includes: determining whether flakes will be added to the cigarette pack to be processed; If yes, obtain the added weight of the flakes; Obtaining the weight of the cigarette pack to be processed before the slicer; Get the accumulated weight of the flow before loosening and rewetting; When the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is consistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidifying drum is the cigarette pack to be processed; If the sum of the weight of the cigarette pack before the slicer and the weight of the added slices is inconsistent with the accumulated weight of the flow scale, it is determined that the cigarette pack currently entering the loosening and rehumidification drum is not the cigarette pack to be processed; If thin sheets are added to the cigarette pack to be processed, the method of obtaining the cumulative weight of the flow before loosening and rehydration includes: Detecting the moisture content of the inlet of the loose rehumidification drum based on a change point detection algorithm to determine whether the cigarette pack contains flakes; If so, the detection of the accumulated weight of the flow scale is started.

8. A loosening and moisture-reinforcing device for non-full-formula tobacco sheets, characterized in that: include: memory for storing computer programs; A processor is used to implement the steps of the loosening and rehumidification method of non-full formula tobacco sheets as described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for loosening and rehumidifying non-full-formula tobacco sheets according to any one of claims 1 to 6.

Images