Intelligent flue-cured tobacco lamina maintenance system based on Internet of Things

Through the Internet of Things technology and CNN+LSTM model, real-time monitoring and precise control of the smoke environment are achieved, which solves the problems of inaccurate environmental regulation and insufficient data recording in traditional maintenance methods, improves the maintenance efficiency and quality of smoke, and prevents Mold and damp.

CN119024908APending Publication Date: 2024-11-26CHINA TOBACCO ZHEJIANG IND CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410987688.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional smoke maintenance methods are restricted by natural conditions and are difficult to accurately adjust the environment, resulting in mass fluctuations, lack of data recording and analysis methods, and cannot effectively evaluate the maintenance effect.

Method used

Adopt an intelligent maintenance system based on the Internet of Things, through the environmental information collection module, data processing module, intelligent maintenance module and remote monitoring module, real-time monitoring and accurate control of the smoke storage environment, automatic adjustment of temperature and humidity, combined with CNN+LSTM Trend prediction model predicts quality changes.

Benefits of technology

Real-time monitoring and precise control of the tablet smoke environment is achieved, maintenance efficiency and quality is improved, mold and moisture are prevented, workload is reduced, and energy waste is avoided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024908A_ABST
    Figure CN119024908A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent flue-cured tobacco lamina maintenance system based on the Internet of Things, and the system comprises an environment information collection module which is used for collecting internal environment information and external environment information of a flue-cured tobacco lamina storage warehouse, and the environment information comprises temperature information and humidity information; the communication module is used for transmitting the internal environment information to the data processing module; the data processing module is used for acquiring temperature control parameters and target humidification parameters of the tobacco lamina storage warehouse according to the temperature information and the humidity information acquired by the environment information acquisition module; the intelligent maintenance module is used for adjusting the environment of the flue-cured tobacco lamina storage warehouse according to the temperature control parameters and the target humidification parameters obtained by the data processing module and selecting an adjusting mode based on the external environment information; and a remote monitoring module. According to the invention, real-time monitoring and accurate control of the storage environment of the lamina are realized, temperature and humidity parameters are automatically adjusted, the maintenance efficiency is effectively improved, and the optimal maintenance condition of the tobacco is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of tobacco strip maintenance, and in particular relates to an intelligent tobacco strip maintenance system based on the Internet of Things. Background Art

[0002] Tobacco strips refer to tobacco leaves that have been destemmed and threshed to remove stems larger than 1.5 mm in diameter. Tobacco strips are an important raw material for the tobacco manufacturing industry. With the improvement of people's health awareness and the development of diversified consumption, cigarettes with stable quality have become an important factor in consumer choice. Therefore, the maintenance of tobacco strips is particularly important.

[0003] The maintenance of tobacco strips is to make the chemical composition and physical properties of the tobacco strips enter the warehouse under natural climatic conditions to change appropriately, so as to achieve the purpose of mildew prevention, dust removal, quality preservation, alcohol enhancement and flavor enhancement. Although the current tobacco strip maintenance work can automatically and frequently detect the temperature and humidity of the warehouse environment, the oxygen concentration during nitrogen filling and insecticide treatment, etc., which reduces the error of manual detection, the following problems still exist:

[0004] (1) The traditional tobacco curing environment is restricted by natural conditions. Changes in factors such as temperature, humidity and light will affect the curing effect of tobacco strips and cause quality fluctuations;

[0005] (2) Traditional curing methods are difficult to accurately adjust environmental conditions and cannot be adjusted in time according to the actual state of the tobacco leaves, resulting in poor curing effects;

[0006] (3) Under traditional maintenance methods, there is often a lack of means to record and analyze data during the maintenance process, making it impossible to conduct a comprehensive analysis and evaluation of the maintenance status of the tobacco leaves.

[0007] In summary, there are many problems with the traditional tobacco leaf maintenance method, and there is an urgent need to provide an intelligent tobacco leaf maintenance system based on the Internet of Things to improve the efficiency and quality of tobacco leaf maintenance. Summary of the invention

[0008] In order to solve the above-mentioned technical problems existing in the prior art, the present invention provides an intelligent tobacco leaf maintenance system based on the Internet of Things, which can realize real-time monitoring and precise control of the tobacco leaf storage environment, automatically adjust the temperature and humidity parameters, and effectively improve the maintenance efficiency and quality.

[0009] The technical solution adopted by the present invention is:

[0010] An intelligent tobacco leaf maintenance system based on the Internet of Things, characterized by comprising:

[0011] An environmental information collection module is used to collect internal and external environmental information of the tobacco strip storage warehouse, wherein the environmental information includes temperature information and humidity information;

[0012] A communication module, used for transmitting internal environment information to a data processing module;

[0013] A data processing module, used to obtain temperature control parameters and target humidification parameters of the tobacco storage warehouse according to the temperature information and humidity information collected by the environmental information collection module;

[0014] An intelligent maintenance module is used to adjust the environment of the tobacco storage warehouse according to the temperature control parameters and target humidification parameters obtained by the data processing module, and select an adjustment method based on external environmental information;

[0015] And a remote monitoring module, used for remotely monitoring the temperature information, the humidity information, the temperature control parameters and the target humidification parameters.

[0016] Furthermore, the environmental information collection module includes:

[0017] A collection equipment deployment submodule is used to obtain the size information of the tobacco strip storage warehouse, establish a collection model, and supplement the collection equipment according to the established collection model;

[0018] and an information collection submodule, which is used to collect the temperature information and the humidity information through various collection devices.

[0019] Furthermore, the acquisition equipment deployment submodule includes:

[0020] An initial model building unit, used to build an initial model based on the size information of the tobacco strip storage warehouse, divide the initial model into an external area and an internal area, and supplement the collection equipment in the external area according to the preset influencing factors of tobacco strip storage;

[0021] and a collection model building unit, which is used to match the corresponding collection point spatial distribution model and standard warehouse size information according to the preset influencing factors of tobacco strip storage, set the point collection model, supplement the point collection model to the corresponding position in the initial model, and mark the current initial model as the collection model.

[0022] Furthermore, the data processing module includes:

[0023] A temperature control parameter acquisition submodule, for acquiring the current temperature based on the temperature data inside the tobacco strip storage warehouse, and acquiring the target heating temperature or the target cooling temperature of the temperature control device based on the current temperature and a preset target temperature range;

[0024] and a target humidification parameter submodule, which is used to obtain humidity data inside the tobacco storage warehouse, obtain the current humidity, and when the current humidity does not meet the preset target humidity range, determine the humidity cycle change, and obtain the target humidification parameters of the humidification equipment based on the current humidity and the humidity cycle change.

[0025] Furthermore, the target humidification parameter acquisition submodule includes

[0026] A humidity cycle variation acquisition unit, used to acquire the initial humidity and the end humidity of the tobacco storage warehouse in the current detection cycle, and determine the humidity cycle variation based on the initial humidity and the end humidity;

[0027] and a target humidification parameter acquisition unit, which is used to determine the target water extraction volume and target wind speed of the humidification equipment according to the current humidity and the humidity periodic change.

[0028] Further, determining the target water extraction volume and target wind speed of the humidification equipment includes:

[0029] determining a humidity difference between the current humidity and a target humidity;

[0030] Multiplying the humidity difference by a first weight value to obtain a first product, and multiplying the humidity periodic change by a second weight value to obtain a second product, and adding the first product and the second product to obtain a first adjustment ratio;

[0031] Multiplying the humidity difference by a third weight value to obtain a third product, and multiplying the humidity periodic change by a fourth weight value to obtain a fourth product, and adding the third product and the fourth product to obtain a second adjustment ratio;

[0032] The target water pumping amount of the humidifying device is determined by using the current water pumping amount and the first adjustment ratio, and the target wind speed of the humidifying device is determined by using the current wind speed and the second adjustment ratio.

[0033] Furthermore, the intelligent maintenance module includes

[0034] A comparison submodule, configured to compare the external environment information with the preset range when the internal environment information is not within the preset range;

[0035] and an environmental regulation submodule, which is used to regulate the internal environment through the external environment when the external environmental information is within the preset range, and to regulate the internal environment through the temperature control device and the humidification device when the external environmental information is not within the preset range.

[0036] Furthermore, the remote monitoring module includes a trend prediction submodule, which is used to use a CNN+LSTM trend prediction model to predict the quality change trend of tobacco leaves in an adjusted environment, wherein the quality is evaluated by the degree of mildew of the tobacco leaves. The CNN+LSTM trend prediction model is obtained by training through historical environmental information and the corresponding degree of mildew.

[0037] Furthermore, the CNN+LSTM trend prediction model uses the mean absolute percentage error (MAPE) of the fit between the predicted value and the true value as an evaluation indicator to verify the accuracy of the prediction on the test set. The specific calculation of MAPE is as follows:

[0038]

[0039] Among them, A i is the ith actual value, F i is the ith predicted value and n is the total number of data points.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] 1. Based on the Internet of Things technology, the present invention can realize real-time monitoring and precise control of the storage environment of tobacco strips, automatically adjust the temperature and humidity parameters, effectively improve the curing efficiency, and ensure that the tobacco obtains the best curing conditions.

[0042] 2. Through real-time monitoring and intelligent adjustment of environmental conditions, the Internet of Things system can effectively prevent tobacco from getting damp, moldy, and other problems, thereby ensuring the quality and safety of tobacco leaves.

[0043] 3. The present invention realizes remote monitoring of the tobacco storage environment, reduces the workload of personnel on site, and improves work efficiency.

[0044] 4. The present invention not only provides a curing environment for the storage of tobacco slices through different environmental adjustment methods, but also avoids the waste of energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The figure is a structural diagram of an intelligent tobacco maintenance system based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0047] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0048] The present invention will be described in detail below in conjunction with exemplary embodiments with reference to the accompanying drawings.

[0049] refer to Figure 1 The present invention provides an intelligent tobacco maintenance system based on the Internet of Things, comprising:

[0050] An environmental information collection module is used to collect internal and external environmental information of the tobacco strip storage warehouse, wherein the environmental information includes temperature information and humidity information;

[0051] A communication module, used for transmitting internal environment information to a data processing module;

[0052] A data processing module, used to obtain temperature control parameters and target humidification parameters of the tobacco storage warehouse according to the temperature information and humidity information collected by the environmental information collection module;

[0053] An intelligent maintenance module is used to adjust the environment of the tobacco storage warehouse according to the temperature control parameters and target humidification parameters obtained by the data processing module, and select an adjustment method based on external environmental information;

[0054] And a remote monitoring module, used for remotely monitoring the temperature information, the humidity information, the temperature control parameters and the target humidification parameters.

[0055] Specifically, the environmental information collection module includes: a collection equipment deployment submodule and an information collection submodule;

[0056] The collection equipment layout submodule is used to obtain the size information of the tobacco storage warehouse, establish a collection model, and supplement the collection equipment according to the established collection model;

[0057] The information collection submodule is used to collect temperature information and humidity information through various collection devices.

[0058] The acquisition equipment layout submodule includes: an initial model building unit and an acquisition model building unit;

[0059] An initial model building unit is used to build an initial model based on the size information of the tobacco strip storage warehouse, divide the initial model into an external area and an internal area, and supplement the collection equipment in the external area according to the preset influencing factors of the tobacco strip storage;

[0060] The collection model construction unit is used to match the corresponding collection point spatial distribution model and standard warehouse size information according to the preset influencing factors of tobacco strip storage, set the point collection model, add the point collection model to the corresponding position in the initial model, and mark the current initial model as the collection model.

[0061] Specifically, the method of setting the point acquisition model includes:

[0062] Obtain the size information of the corresponding warehouse, establish a standard warehouse 3D model and a warehouse 3D model, compare the standard warehouse 3D model with the warehouse 3D model, determine the difference information of the difference parts, the difference information includes the position, shape, and spatial volume relative to the standard warehouse 3D model, set the corresponding difference coordinates based on the obtained difference information, draw a difference coordinate spatial distribution map, analyze the difference coordinate spatial distribution map, obtain a collection point adjustment table, adjust each collection point in the collection point spatial distribution model according to the obtained collection point adjustment table, and obtain a point collection model.

[0063] Specifically, the data processing module includes a temperature control parameter acquisition submodule and a target humidification parameter submodule;

[0064] The temperature control parameter acquisition submodule is used to obtain the current temperature based on the temperature data inside the tobacco storage warehouse, and obtain the target heating temperature or target cooling temperature of the temperature control device based on the current temperature and the preset target temperature range;

[0065] The target humidification parameter acquisition submodule is used to obtain the humidity data inside the tobacco storage warehouse, obtain the current humidity, and determine the humidity cycle change when the current humidity does not meet the preset target humidity range. Based on the current humidity and the humidity cycle change, the target humidification parameters of the humidification equipment are obtained.

[0066] The target humidification parameter acquisition submodule includes a humidity cycle change acquisition unit and a target humidification parameter acquisition unit;

[0067] A humidity cycle variation acquisition unit is used to acquire the initial humidity and the final humidity of the tobacco storage warehouse in the current detection cycle, and determine the humidity cycle variation based on the initial humidity and the final humidity;

[0068] The target humidification parameter acquisition unit is used to determine the target water extraction volume and target wind speed of the humidification equipment according to the current humidity and the humidity cycle change.

[0069] Specifically, determining the target water extraction volume and target wind speed of the humidification equipment includes:

[0070] Determine the humidity difference between the current humidity and the target humidity;

[0071] Multiplying the humidity difference by a first weight value to obtain a first product, and multiplying the humidity periodic change by a second weight value to obtain a second product, and adding the first product and the second product to obtain a first adjustment ratio;

[0072] Multiply the humidity difference by the third weight value to obtain a third product, and multiply the humidity periodic change by the fourth weight value to obtain a fourth product, and add the third product and the fourth product to obtain a second adjustment ratio;

[0073] The target water pumping amount of the humidification device is determined by using the current water pumping amount and the first adjustment ratio, and the target wind speed of the humidification device is determined by using the current wind speed and the second adjustment ratio.

[0074] Specifically, the intelligent maintenance module includes a comparison submodule and an environmental regulation submodule;

[0075] A comparison submodule, for comparing the external environment information with a preset range when the internal environment information is not within the preset range;

[0076] The environmental control submodule is used to control the internal environment through the external environment when the external environmental information is within the preset range, and to control the internal environment through the temperature control equipment and the humidification equipment when the external environmental information is not within the preset range.

[0077] Specifically, the remote monitoring module includes a trend prediction submodule, which is used to use the CNN+LSTM trend prediction model to predict the quality change trend of the tobacco leaves in the adjusted environment, where the quality is evaluated by the degree of mildew of the tobacco leaves, and the CNN+LSTM trend prediction model is obtained through historical environmental information and the corresponding degree of mildew training. The degree of mildew of the tobacco leaves corresponding to the quality is manually set, and the better the quality, the smaller the mildew area of ​​the tobacco leaves, and the mildew area is identified by the CCD visual system.

[0078] It should be noted that the CNN+LSTM trend prediction model uses the mean absolute percentage error (MAPE) of the predicted value and the true value as an evaluation indicator to verify the accuracy of the prediction on the test set. The specific calculation of MAPE is as follows:

[0079]

[0080] Among them, A i is the ith actual value, F i is the ith predicted value and n is the total number of data points.

[0081] The CNN structure used in this embodiment includes a convolutional layer, a pooling layer, a fully connected layer, and an output layer. After the convolutional layer performs feature extraction, the output feature map is passed to the pooling layer for feature selection and information filtering to enhance the translation invariance of the model. The pooling layer contains a pre-set pooling function, which replaces the result of a single point in the feature map with the feature map statistics of its adjacent area. The fully connected layer performs a nonlinear combination of the extracted features to obtain the output, and the obtained output is input into each LSTM node. Multiple LSTM cell units are used in the middle hidden layer for cyclic connection, and the output layer provides the prediction results. The network training uses the Adam algorithm to continuously adjust the parameters to optimize the prediction results.

[0082] The mathematical relationship of each layer in the LSTM network is:

[0083] ft=σ(Wf[ht-1,xt]+bf)

[0084] it=σ(Wi·[ht-1,xt]+bi)

[0085] ot=σ(Wo·[ht-1,xt]+bo)

[0086] ct=ftct-1+ittanh(Wc[ht-1,xt]+bc)

[0087] ht=ot*tanh(Ct)

[0088] Among them, ht-1 is the output value of the LSTM neural network at time t-1, h is the output value of the LSTM neural network at time t, Xt is the input value of the LSTM neural network at time t, Wi, Wf, Wo, Wc and bi, bf, bo, bc represent the weights and biases of the input gate, forget gate, output gate, and candidate memory respectively, it, ft, ot are the states of the input gate, forget gate, and output gate at time t respectively, Ct is the state of the memory unit at time t, σ is the Sigmoid activation function, and tanh(x) is the hyperbolic tangent function.

[0089] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent tobacco maintenance system based on the Internet of Things, characterized in that: include: An environmental information collection module is used to collect internal and external environmental information of the tobacco strip storage warehouse, wherein the environmental information includes temperature information and humidity information; A communication module, used for transmitting internal environment information to a data processing module; A data processing module, used to obtain temperature control parameters and target humidification parameters of the tobacco storage warehouse according to the temperature information and humidity information collected by the environmental information collection module; An intelligent maintenance module is used to adjust the environment of the tobacco storage warehouse according to the temperature control parameters and target humidification parameters obtained by the data processing module, and select an adjustment method based on external environmental information; And a remote monitoring module, used for remotely monitoring the temperature information, the humidity information, the temperature control parameters and the target humidification parameters.

2. The intelligent tobacco leaf maintenance system based on the Internet of Things according to claim 1, characterized in that: The environmental information collection module includes: A collection equipment deployment submodule is used to obtain the size information of the tobacco strip storage warehouse, establish a collection model, and supplement the collection equipment according to the established collection model; and an information collection submodule, which is used to collect the temperature information and the humidity information through various collection devices.

3. The intelligent tobacco leaf maintenance system based on the Internet of Things as claimed in claim 2, characterized in that: The acquisition equipment layout submodule includes: An initial model building unit, used to build an initial model based on the size information of the tobacco strip storage warehouse, divide the initial model into an external area and an internal area, and supplement the collection equipment in the external area according to the preset influencing factors of tobacco strip storage; and a collection model building unit, which is used to match the corresponding collection point spatial distribution model and standard warehouse size information according to the preset influencing factors of tobacco strip storage, set the point collection model, supplement the point collection model to the corresponding position in the initial model, and mark the current initial model as the collection model.

4. The intelligent tobacco leaf maintenance system based on the Internet of Things according to claim 1, characterized in that: The data processing module comprises: A temperature control parameter acquisition submodule, for acquiring the current temperature based on the temperature data inside the tobacco strip storage warehouse, and acquiring the target heating temperature or the target cooling temperature of the temperature control device based on the current temperature and a preset target temperature range; and a target humidification parameter submodule, which is used to obtain humidity data inside the tobacco storage warehouse, obtain the current humidity, and when the current humidity does not meet the preset target humidity range, determine the humidity cycle change, and obtain the target humidification parameters of the humidification equipment based on the current humidity and the humidity cycle change.

5. The intelligent tobacco leaf maintenance system based on the Internet of Things as claimed in claim 4, characterized in that: The target humidification parameter acquisition submodule includes A humidity cycle variation acquisition unit, used to acquire the initial humidity and the end humidity of the tobacco storage warehouse in the current detection cycle, and determine the humidity cycle variation based on the initial humidity and the end humidity; and a target humidification parameter acquisition unit, which is used to determine the target water extraction volume and target wind speed of the humidification equipment according to the current humidity and the humidity periodic change.

6. The intelligent tobacco leaf maintenance system based on the Internet of Things as claimed in claim 5, characterized in that: Determining the target water extraction volume and target wind speed of the humidification device includes: determining a humidity difference between the current humidity and a target humidity; Multiplying the humidity difference by a first weight value to obtain a first product, and multiplying the humidity periodic change by a second weight value to obtain a second product, and adding the first product and the second product to obtain a first adjustment ratio; Multiplying the humidity difference by a third weight value to obtain a third product, and multiplying the humidity periodic change by a fourth weight value to obtain a fourth product, and adding the third product and the fourth product to obtain a second adjustment ratio; The target water pumping amount of the humidifying device is determined by using the current water pumping amount and the first adjustment ratio, and the target wind speed of the humidifying device is determined by using the current wind speed and the second adjustment ratio.

7. The intelligent tobacco leaf maintenance system based on the Internet of Things according to claim 1, characterized in that: The intelligent maintenance module includes A comparison submodule, configured to compare the external environment information with the preset range when the internal environment information is not within the preset range; and an environmental regulation submodule, which is used to regulate the internal environment through the external environment when the external environmental information is within the preset range, and to regulate the internal environment through the temperature control device and the humidification device when the external environmental information is not within the preset range.

8. The intelligent tobacco leaf maintenance system based on the Internet of Things according to claim 1, characterized in that: The remote monitoring module includes a trend prediction submodule, which is used to use a CNN+LSTM trend prediction model to predict the quality change trend of tobacco leaves in an adjusted environment, wherein the quality is evaluated by the degree of mildew of the tobacco leaves. The CNN+LSTM trend prediction model is obtained by training through historical environmental information and the corresponding degree of mildew.

9. The intelligent tobacco leaf maintenance system based on the Internet of Things according to claim 1, characterized in that: The CNN+LSTM trend prediction model uses the mean absolute percentage error (MAPE) of the predicted value and the true value as an evaluation indicator to verify the accuracy of the prediction on the test set. The specific calculation of MAPE is as follows: Among them, A i is the ith actual value, F i is the ith predicted value and n is the total number of data points.

Citation Information

Cited By

  • Nitrogen preparation and storage oxygen content automatic control system

    CN120315510A