Tobacco leaf moisture prediction method, device, equipment, medium and product

Abstract

The invention discloses a tobacco leaf moisture prediction method, device and equipment, a medium and a product. The method comprises the following steps: acquiring environmental attributes of a tobacco storage area where a tobacco material to be detected is located, and determining tobacco material moisture corresponding to the tobacco material to be detected; inputting the environment attributes into the target kinetic parameter model to obtain drying characteristic kinetic parameters; according to the thin-layer drying mechanism model, based on the preset leaf storage duration, the drying characteristic kinetic parameters and the tobacco leaf material moisture, determining the material moisture content of the to-be-detected tobacco leaf material; when the water content of the material meets the first condition, the tobacco leaf material to be detected is used for cigarette production. The problems that the hysteresis quality of material moisture control exists and the cigarette production efficiency is influenced in a mode of determining whether the tobacco leaf material is used for cigarette production by measuring the moisture content of the material in real time are solved, the prediction precision of the moisture content of the tobacco leaf material in the stored leaf moisture loss process is improved, and the effect of improving the cigarette production efficiency is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette production, and in particular to a method, device, equipment, medium and product for predicting the moisture content of tobacco leaves. Background Art

[0002] In the field of cigarette production, the moisture content of tobacco leaf materials is a key quality indicator for measuring the cigarette production process. The moisture content of tobacco leaf materials will affect the flexibility, processing resistance and other properties of tobacco leaf materials, thereby affecting the consumption of tobacco leaf materials and the quality of cigarettes during the cigarette production process, and further affecting the production cost of cigarettes. Therefore, before cigarette production, it is necessary to determine the moisture content of tobacco leaf materials in order to determine whether the accepted materials can be used for cigarette production based on the moisture content of the tobacco leaf materials.

[0003] The existing method of determining the moisture content of tobacco materials is usually to measure the moisture content of tobacco materials in real time before cigarette production, and select tobacco materials that meet the requirements of cigarette production according to the moisture content. If they do not meet the requirements, the batch of tobacco materials needs to be reprocessed before cigarette production. This method of determining whether tobacco materials are used for cigarette production by measuring the moisture content of materials in real time has a lag in material moisture control, which affects the efficiency of cigarette production. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and product for predicting the moisture content of tobacco leaves, so as to improve the prediction accuracy of the moisture content of tobacco leaves during the process of moisture loss during leaf storage, improve the moisture control accuracy of the materials, and achieve the technical effect of improving the production efficiency of cigarettes.

[0005] Real-time moisture content of exported tobacco leaf materials improves the prediction accuracy and adaptability of moisture content of exported tobacco leaf materials, thereby guiding the process quality indicator management and control of cigarette production.

[0006] According to one aspect of the present invention, a method for predicting tobacco leaf moisture is provided, the method comprising:

[0007] Acquire the environmental properties of the tobacco storage area where the tobacco leaf material to be tested is located, and determine the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested; wherein the environmental properties include environmental temperature and environmental humidity;

[0008] The environmental attributes are input into a trained target kinetic parameter model to obtain drying characteristic kinetic parameters; wherein the target kinetic parameter model is obtained by training an initial kinetic parameter model based on training samples and a thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of tobacco leaf materials in a thin layer state;

[0009] According to the thin layer drying mechanism model, based on the preset leaf storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, the moisture content of the tobacco leaf material to be tested is determined;

[0010] When the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time is used for cigarette production.

[0011] According to another aspect of the present invention, a device for predicting tobacco leaf moisture is provided, the device comprising:

[0012] An environmental attribute determination module is used to obtain the environmental attributes of the tobacco storage area where the tobacco material to be tested is located, and determine the moisture content of the tobacco material corresponding to the tobacco material to be tested; wherein the environmental attributes include environmental temperature and environmental humidity;

[0013] A kinetic parameter determination module, used for inputting the environmental attributes into a trained target kinetic parameter model to obtain drying characteristic kinetic parameters; wherein the target kinetic parameter model is obtained by training an initial kinetic parameter model based on training samples and a thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of tobacco leaf materials in a thin layer state;

[0014] A material moisture content determination module, used to determine the material moisture content of the tobacco leaf material to be tested based on a preset leaf storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material;

[0015] The judgment module is used to use the tobacco leaf material to be tested whose actual storage time reaches the preset storage time for cigarette production when the moisture content of the material meets the first condition.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and a memory in communication with the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting tobacco leaf moisture as described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting tobacco moisture as described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the method for predicting tobacco leaf moisture as described in any embodiment of the present invention.

[0021] The technical solution of the embodiment of the present invention obtains the environmental properties of the storage area where the tobacco leaf material to be tested is located, and determines the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested; inputs the environmental properties into the trained target kinetic parameter model to obtain the drying characteristic kinetic parameters; the target kinetic parameter model is obtained by training the initial kinetic parameter model based on the training samples and the thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of the tobacco leaf material in a thin layer state; according to the thin layer drying mechanism model, based on the preset storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, the material moisture content of the tobacco leaf material to be tested is determined; when the material moisture content meets the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time is used for cigarette production, which solves the problem in the prior art of measuring the moisture content of the material in real time. The method of determining whether tobacco leaf materials are used for cigarette production by the amount of material has the problem of lag in material moisture control, which affects the efficiency of cigarette production. It is realized that the final target kinetic parameter model is constructed by using the initial kinetic parameter model to be trained and the thin layer drying mechanism model, so as to improve the interpretability of the target kinetic parameter model, and the preset leaf storage time, tobacco leaf material moisture and the drying characteristic kinetic parameters predicted by the target kinetic parameter model are substituted into the thin layer drying mechanism model to predict the material moisture content of the tobacco leaf material to be tested, thereby improving the prediction accuracy of the moisture content of the tobacco leaf material in the process of leaf storage moisture loss, and enabling the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time to be used for cigarette production when the material moisture content meets the first condition, thereby improving the cigarette production efficiency, thereby achieving the technical effect of improving the accuracy of material moisture control.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a method for predicting tobacco leaf moisture according to Embodiment 1 of the present invention;

[0025] Figure 2 is a schematic diagram of a method for predicting tobacco leaf moisture according to Embodiment 1 of the present invention;

[0026] Figure 3 is a schematic diagram of the structure of a tobacco leaf moisture prediction device provided according to the second embodiment of the present invention;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the method for predicting the moisture content of tobacco leaves according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flow chart of a method for predicting tobacco leaf moisture according to the first embodiment of the present invention. This embodiment is applicable to predicting the loss process of tobacco leaf moisture content. The method can be executed by a tobacco leaf moisture prediction device. The tobacco leaf moisture prediction device can be implemented in the form of hardware and / or software. The tobacco leaf moisture prediction device can be configured in a computing device. Figure 1 As shown, the method includes:

[0032] S110, obtaining the environmental properties of the tobacco leaf storage area where the tobacco leaf material to be tested is located, and determining the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested.

[0033] Among them, the tobacco leaf material to be tested may be a batch of tobacco leaves whose tobacco leaf moisture loss process needs to be predicted, so as to evaluate whether the batch of tobacco leaves can be used for cigarette production based on the prediction results. The leaf storage area may refer to the location where the tobacco leaf material is stored. For example, the leaf storage area may be a warehouse or other location. Environmental attributes are used to characterize the characteristics of the leaf storage environment. It should be noted that the environmental attributes of leaf storage are key factors affecting the moisture loss of tobacco leaf materials. Different environmental attributes directly affect the degree of evaporation of water from tobacco leaf materials. Environmental attributes include ambient temperature and ambient humidity. The moisture content of tobacco leaf materials may be a moisture value related to the tobacco leaf material to be tested. For example, the moisture content of tobacco leaf materials may be the moisture content value of materials at the initial stage of leaf storage, or the moisture content value of materials at the middle or final stage of leaf storage, etc.

[0034] In this embodiment, the environmental properties such as the ambient temperature and humidity of the storage area where the tobacco leaf material to be tested is located can be measured in real time or periodically, and the moisture content of the tobacco leaf material related to the tobacco leaf material to be tested can be determined, so as to predict the moisture loss of the tobacco leaf material to be tested based on the environmental properties and the moisture content of the tobacco leaf material.

[0035] S120, inputting environmental attributes into the trained target kinetic parameter model to obtain drying characteristic kinetic parameters; wherein the target kinetic parameter model is obtained by training the initial kinetic parameter model based on the training samples and the thin layer drying mechanism model.

[0036] Among them, the target kinetic parameter model is used to describe the correlation between ambient temperature, ambient humidity and drying characteristic kinetic parameters. The drying characteristic kinetic parameters can be kinetic parameters in the relationship curve used to describe the change of moisture content of tobacco materials with drying time. For example, the drying characteristic kinetic parameters can be drying speed (i.e., moisture loss rate), moisture absorption rate, wind speed, etc. The thin layer drying mechanism model is used to describe the moisture loss process of tobacco materials stored in a thin layer state. The thin layer state refers to the state in which the surface of the material layer is completely exposed to the same environmental conditions. In this state, as the material is placed for a longer time, moisture will be lost.

[0037] In this embodiment, the environmental attributes can be input into the pre-trained target kinetic parameter model, the correlation between the drying characteristics and time changes under the changes in the environmental attributes can be analyzed, and the drying characteristics kinetic parameters in the process of storing the tobacco leaf material to be tested can be output. For example, the target kinetic parameter model can be a convolutional neural network, a recurrent neural network, or a graph neural network. In specific applications, the target kinetic parameter model can be used to predict the temperature and humidity changes in the future period of time based on the environmental attributes, and the changes in the drying characteristics of the material moisture content over time can be analyzed based on the changes in temperature and humidity to obtain the drying characteristics kinetic parameters.

[0038] For example, an artificial neural network can be used to construct an initial kinetic parameter model of ambient temperature, ambient humidity and drying characteristic kinetic parameters based on experimental data, and then the initial kinetic parameter model is trained using training samples and a thin layer drying mechanism model to obtain a target kinetic parameter model. For example, the model formula of the initial kinetic parameter model can be expressed as: k, n = f (T, H); wherein T and H are the ambient temperature and ambient humidity of the leaf storage process, respectively, and the f() function represents the artificial neural network; k and n are both represented as drying characteristic kinetic parameters.

[0039] In this embodiment, before the environmental attributes are input into the trained target kinetic parameter model to obtain the drying characteristic kinetic parameters, the method for predicting tobacco leaf moisture also includes: determining the theoretical values ​​of the kinetic parameters corresponding to the drying characteristic kinetic attributes based on the drying characteristic kinetic attributes in the thin layer drying mechanism model; constructing an initial kinetic parameter model based on the predetermined environmental attributes and the theoretical values ​​of the kinetic parameters, so as to train the initial kinetic parameter model based on the training samples and the thin layer drying mechanism model to obtain the target kinetic parameter model.

[0040] The initial kinetic parameter model is used to describe the correlation between the environmental attributes and the drying characteristic kinetic parameters. The drying characteristic kinetic attributes can be used to characterize the characteristics of the drying characteristic kinetic parameters, and the drying characteristic kinetic parameters are the specific values ​​of the drying characteristic kinetic attributes. The drying characteristic kinetic attributes include but are not limited to the drying speed (i.e., the water loss rate), the moisture absorption rate, the wind speed and other characteristic attributes.

[0041] In this embodiment, it is possible to predetermine which drying characteristic kinetic properties the thin layer drying mechanism model has, and then configure the theoretical value of the kinetic parameter corresponding to each drying characteristic kinetic property, and configure multiple environmental properties. Furthermore, an association rule algorithm (such as Apriori algorithm, FP-Growth algorithm, Eclat algorithm, and Hopfian-R leaking lake algorithm, etc.) or other algorithms with mining association relationships can be used to analyze the association relationship between the theoretical value of the kinetic parameter and each environmental attribute, and obtain an initial kinetic parameter model that can describe the association relationship between the environmental attributes and the drying characteristic kinetic parameters. This allows the initial kinetic parameter model to be trained based on the training samples and the thin layer drying mechanism model to obtain the target kinetic parameter model, thereby ensuring the accuracy of the model in predicting the drying characteristic kinetic parameters.

[0042] It should be noted that in the actual production process of leaf storage, there are certain uncertainties influencing factors within the system, and there are irregular disturbances in the external environment. Therefore, some kinetic parameters of the mechanism model are difficult to measure and evaluate, which leads to the problem of low precision when the mechanism model is used alone to predict the moisture content of the material. In order to solve this problem, the technical solution provided in this embodiment provides theoretical support for the target kinetic parameter model by using a thin layer drying mechanism model, improves the interpretability of the target kinetic parameter model, uses the target kinetic parameter model to predict the kinetic parameters in the process of water loss during leaf storage, and then combines the thin layer drying mechanism model to predict the moisture content of the material, thereby improving the prediction effect of the moisture content of the tobacco leaf material.

[0043] In this embodiment, an initial kinetic parameter model is trained based on training samples and a thin layer drying mechanism model to obtain a target kinetic parameter model, including: obtaining multiple training samples; the training samples include environmental attributes when storing historical tobacco leaf materials, tobacco leaf material moisture of historical tobacco leaf materials, and actual moisture loss process data of historical tobacco leaf materials during historical storage time; for each training sample, the environmental attributes in the training sample are input into the initial kinetic parameter model to obtain kinetic parameters to be used associated with the environmental attributes; the kinetic parameters to be used and the tobacco leaf material moisture in the training sample are input into the thin layer drying mechanism model to obtain predicted moisture loss process data; based on the predicted moisture loss process data and the actual moisture loss process data in the training sample, the model parameters in the initial kinetic parameter model are corrected to obtain a trained target kinetic parameter model.

[0044] The tobacco material moisture of the historical tobacco material includes the initial moisture of the material when the historical tobacco material is stored and the constant moisture of the material in the moisture balance state of the historical tobacco material. The moisture balance state may refer to a state in which the moisture content of the material is basically constant in a thin layer state. The actual moisture loss process data includes the moisture value of the material at each moment in the process of moisture loss of the material. The kinetic parameters to be used refer to the drying characteristic kinetic parameters to be used.

[0045] In order to improve the accuracy of the model, as many and rich training samples as possible can be obtained. After determining the training samples, the environmental attributes in the training samples can be input into the initial kinetic parameter model to be trained to obtain the drying characteristic kinetic parameters as the kinetic parameters to be used. Furthermore, the kinetic parameters to be used and the initial moisture content of the material and the constant moisture content of the material in the training samples are input into the thin layer drying mechanism model, and the predicted moisture loss process data is obtained after being processed by the objective function of the thin layer drying mechanism model. Furthermore, the predicted moisture loss process data and the actual moisture loss process data in the training samples can be subjected to loss processing, so as to correct the model parameters of the initial kinetic parameter model to be trained according to the obtained loss results, and train the initial kinetic parameter model until a trained target kinetic parameter model is obtained.

[0046] In this embodiment, based on the predicted water loss process data and the actual water loss process data in the training samples, the model parameters in the initial kinetic parameter model are corrected to obtain a trained target kinetic parameter model, including: determining an error value based on the predicted water loss process data and the actual water loss process data in the training samples; determining a model training attribute based on the error value; when the model training attribute does not meet the second condition, optimizing the model parameters according to the particle swarm optimization algorithm and the variable constraint function corresponding to the model parameters in the initial kinetic parameter model to obtain optimized parameters; updating the model parameters based on the optimized parameters to obtain an updated initial kinetic parameter model; and continuing to train the updated initial kinetic parameter model based on the training samples to obtain a trained target kinetic parameter model.

[0047] Among them, the model training attributes include at least convergence and accuracy. Convergence can be used to characterize the degree to which the model gradually learns the patterns and characteristics of the data during the training process, and the adjustment of parameters gradually tends to be stable. Convergence can include parameter convergence, function value convergence, and distribution convergence. Accuracy can be used to characterize the degree of consistency between the model prediction results and the actual results. The second condition may refer to whether the model training attribute points meet the conditions required for model prediction. Model parameters include at least the number of hidden layers, the number of neurons, weights, learning rates, regularization parameters, etc. The variable constraint function may refer to a function used to constrain the selection of model parameters. For example, the variable constraint function may be an optional range of process parameter values, or upper and lower limits of neural network parameters.

[0048] In this embodiment, the difference between the predicted water loss process data and the actual water loss process data in the training sample can be calculated to obtain an error value. Then, according to the error value, the model training attribute is evaluated. For example, the smaller the error value, or the more stable the error value change, the better the convergence and the higher the accuracy. It is determined whether the model training attribute meets the second condition. For example, when the error value is less than the preset error or the error change trend is stable, or when the current number of iterations is equal to the preset number, it is determined that the model training attribute meets the second condition. Otherwise, the model training attribute does not meet the second condition. When the model training attribute does not meet the second condition, the particle swarm optimization algorithm and the variable constraint function corresponding to the model parameters in the kinetic parameter model can be used to optimize the model parameters, solve the optimal neural network parameters, and obtain the optimization parameters. The model parameters are updated by optimizing the parameters, and after the model parameters are updated, the updated initial kinetic parameter model is obtained. The updated initial kinetic parameter model is continuously trained using the training sample until the model training attribute meets the second condition, and the trained target kinetic parameter model is obtained.

[0049] For example, see Figure 2 , read in the relevant data of the field experiment, including leaf storage time, tobacco material related moisture, ambient temperature, ambient humidity and other leaf storage process parameters, and determine the training sample set according to these leaf storage process parameters. Next, obtain the initial values ​​of the model parameters such as the number of hidden layers and the number of neurons of the initial kinetic parameter model to be trained, and obtain the variable constraint function corresponding to the model parameters to form a complete parameter optimization problem. When the initial kinetic parameter model is trained using the training sample set, it is solved by the particle swarm optimization algorithm. According to the convergence and rationality of the model training calculated by the particle swarm optimization algorithm, it is judged whether to output the optimization result (i.e., the optimization parameter), and finally the best target kinetic parameter model is solved. According to the trained target kinetic parameter model and the thin layer drying mechanism model, a fusion model for predicting the moisture loss process of tobacco leaves is obtained. By inputting the environmental attributes into the target kinetic parameter model in the fusion model, the drying characteristic kinetic parameters are obtained, and the thin layer drying mechanism model in the fusion model is used to determine the moisture loss process data of the tobacco material to be tested within the preset storage time according to the drying characteristic kinetic parameters and the moisture of the tobacco material.

[0050] It should be noted that before the kinetic parameters to be used and the moisture content of tobacco leaf materials in the training samples are input into the thin layer drying mechanism model to obtain the predicted moisture loss process data, the thin layer drying mechanism model can also be fitted according to the leaf storage time and tobacco leaf material moisture-related data in the experiment associated with the leaf storage area, and the determination coefficient R2 and the root mean square error RMSE are used as fitting test indicators to measure the fitting degree and prediction accuracy of the thin layer drying mechanism model for the moisture loss process data. This enables the thin layer drying mechanism model to accurately predict the moisture loss process data of tobacco leaf materials stored in the leaf storage area.

[0051] S130. According to the thin layer drying mechanism model, based on the preset leaf storage time, drying characteristic kinetic parameters and tobacco leaf material moisture, determine the material moisture content of the tobacco leaf material to be tested.

[0052] Among them, the preset leaf storage time may refer to the duration of the leaf storage process.

[0053] In this embodiment, the preset leaf storage time, drying characteristic kinetic parameters and tobacco leaf material moisture content can be input into the thin layer drying mechanism model, and the objective function of the thin layer drying mechanism model can be used to determine the moisture content of the tobacco leaf material to be tested at each moment within the preset leaf storage time.

[0054] Optionally, the moisture content of the tobacco leaf material includes the initial moisture content of the material when the tobacco leaf material to be tested is stored and the constant moisture content of the material when the tobacco leaf material to be tested is in a moisture equilibrium state. Accordingly, according to the thin layer drying mechanism model, based on the preset leaf storage time, the drying characteristic kinetic parameters and the tobacco leaf material moisture content, the material moisture content of the tobacco leaf material to be tested is determined, including: determining the expected export time in the preset leaf storage time; based on the objective function in the thin layer drying mechanism model, the expected export time, the drying characteristic kinetic parameters, the initial moisture content of the material and the constant moisture content of the material are processed to obtain the material moisture content of the tobacco leaf material to be tested at the expected export time, so that when the expected export time is reached, the tobacco leaf material to be tested can be used for cigarette production.

[0055] In this embodiment, any moment can be determined from the preset leaf storage time as the estimated export time; or a moment can be determined from the preset leaf storage time as the estimated export time according to the cigarette production requirements; or the last moment in the preset leaf storage time can be used as the estimated export time. The estimated export time, the drying characteristic kinetic parameters, the initial moisture content of the material and the constant moisture content of the material can be used as the input parameters of the objective function in the thin layer drying mechanism model. After solving the objective function, the moisture content of the tobacco leaf material to be tested at the estimated export time can be obtained. So that when the actual leaf storage time reaches the estimated export time, the tobacco leaf material to be tested at this time can be used for cigarette production.

[0056] Among them, the expression of the objective function is: Among them, M t It is expressed as the moisture content of tobacco leaves at time t (time t is a moment in the preset leaf storage time), M e represents the constant moisture content of the material, M0 represents the initial moisture content of the material, k and n represent the kinetic parameters of drying characteristics; e () Expressed as an exponential function.

[0057] S140. When the moisture content of the material satisfies the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time is used for cigarette production.

[0058] The first condition may refer to a condition for determining whether the moisture content of the material meets the requirements for cigarette production.

[0059] Specifically, the moisture content of the material can be compared with the preset moisture range. If the moisture content of the material is within the upper and lower fluctuation range of the preset moisture range, it can be confirmed that the moisture content of the material meets the first condition; if the moisture content of the material is not within the upper and lower fluctuation range of the preset moisture range, it can be confirmed that the moisture content of the material does not meet the first condition. When the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time can be used for cigarette production, thereby ensuring the quality of cigarettes produced.

[0060] In this embodiment, the method for predicting tobacco leaf moisture also includes: when the moisture content of the material does not meet the first condition, adjusting the initial moisture content of the material in the tobacco leaf material moisture content of the tobacco leaf material to be tested; based on the adjusted tobacco leaf material moisture content, performing an operation of determining the material moisture content of the tobacco leaf material to be tested, so that when the material moisture content meets the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time can be used for cigarette production.

[0061] In actual applications, if the moisture content of the material does not meet the first condition, it means that the tobacco leaf materials to be tested at the time of the initial moisture content of the material cannot meet the subsequent cigarette production requirements when the actual leaf storage time reaches the preset leaf storage time. At this time, the initial moisture adjustment strategy can be determined according to the moisture content of the material. For example, if the moisture content of the material is too high, it means that the initial moisture content of the material is too high. The processing parameters of the leaf moistening process can be adjusted to process the tobacco leaf materials to reduce the initial moisture content of the materials; for example, if the moisture content of the material is too low, it means that the initial moisture content of the material is too low. The processing parameters of the leaf moistening process can also be adjusted to increase the initial moisture content of the material, thereby controlling the moisture content of the tobacco leaves after moistening. Through the adjusted moisture content of the tobacco leaf materials, the operation of determining the moisture content of the tobacco leaf materials to be tested in S130 is re-executed, so that when the moisture content of the material meets the first condition, the tobacco leaf materials to be tested whose actual leaf storage time reaches the preset leaf storage time can be used for cigarette production. The effect of accurately controlling the moisture content of the material is achieved during the loss of moisture from leaf storage.

[0062] The technical solution provided in the present embodiment obtains the environmental properties of the storage area where the tobacco leaf material to be tested is located, and determines the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested; inputs the environmental properties into the trained target kinetic parameter model to obtain the drying characteristic kinetic parameters; the target kinetic parameter model is obtained by training the initial kinetic parameter model based on the training samples and the thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of the tobacco leaf material in a thin layer state; according to the thin layer drying mechanism model, based on the preset storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, the moisture content of the tobacco leaf material to be tested is determined; when the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time is used for cigarette production, which solves the problem in the prior art of measuring the moisture content of the material in real time. The method of determining whether tobacco leaf materials are used for cigarette production by the amount of material has the problem of lag in material moisture control, which affects the efficiency of cigarette production. It is realized that the final target kinetic parameter model is constructed by using the initial kinetic parameter model to be trained and the thin layer drying mechanism model, so as to improve the interpretability of the target kinetic parameter model, and the preset leaf storage time, tobacco leaf material moisture and the drying characteristic kinetic parameters predicted by the target kinetic parameter model are substituted into the thin layer drying mechanism model to predict the material moisture content of the tobacco leaf material to be tested, thereby improving the prediction accuracy of the moisture content of the tobacco leaf material in the process of leaf storage moisture loss, and enabling the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time to be used for cigarette production when the material moisture content meets the first condition, thereby improving the cigarette production efficiency, thereby achieving the technical effect of improving the accuracy of material moisture control.

[0063] Embodiment 2

[0064] Figure 3 Schematic diagram of a tobacco leaf moisture prediction device according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an environmental attribute determination module 210, a kinetic parameter determination module 220, a material water content determination module 230 and a judgment module 240.

[0065] Among them, the environmental attribute determination module 210 is used to obtain the environmental attributes of the storage area where the tobacco material to be tested is located, and determine the moisture content of the tobacco material corresponding to the tobacco material to be tested; wherein the environmental attributes include environmental temperature and environmental humidity; the dynamic parameter determination module 220 is used to input the environmental attributes into the trained target dynamic parameter model to obtain the drying characteristic dynamic parameters; wherein the target dynamic parameter model is obtained by training the initial dynamic parameter model based on the training sample and the thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the water loss process of the tobacco material stored in a thin layer state; the material moisture content determination module 230 is used to determine the material moisture content of the tobacco material to be tested based on the thin layer drying mechanism model, the preset storage time, the drying characteristic dynamic parameters and the tobacco material moisture. The judgment module 240 is used to use the tobacco material to be tested whose actual storage time reaches the preset storage time for cigarette production when the material moisture content meets the first condition.

[0066] The technical solution of the present embodiment is to obtain the environmental properties of the storage area where the tobacco leaf material to be tested is located, and determine the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested; input the environmental properties into the trained target kinetic parameter model to obtain the drying characteristic kinetic parameters; the target kinetic parameter model is obtained by training the initial kinetic parameter model based on the training samples and the thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of the tobacco leaf material in a thin layer state; according to the thin layer drying mechanism model, based on the preset storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, the moisture content of the tobacco leaf material to be tested is determined; when the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time is used for cigarette production, which solves the problem in the prior art of measuring the moisture content of the material in real time. The method of determining whether tobacco leaf materials are used for cigarette production has the problem of lag in material moisture control, which affects the efficiency of cigarette production. It is realized that the final target kinetic parameter model is constructed by using the initial kinetic parameter model to be trained and the thin-layer drying mechanism model, so as to improve the interpretability of the target kinetic parameter model, and the preset leaf storage time, tobacco leaf material moisture and the drying characteristic kinetic parameters predicted by the target kinetic parameter model are substituted into the thin-layer drying mechanism model to predict the material moisture content of the tobacco leaf material to be tested, thereby improving the prediction accuracy of the moisture content of the tobacco leaf material in the process of leaf storage moisture loss, and enabling the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time to be used for cigarette production when the material moisture content meets the first condition, thereby improving the cigarette production efficiency, thereby achieving the technical effect of improving the accuracy of material moisture control.

[0067] On the basis of the above device, optionally, the moisture content of the tobacco leaf material includes the initial moisture content of the material when the tobacco leaf material to be tested is stored and the constant moisture content of the material when the tobacco leaf material to be tested is in a moisture equilibrium state.

[0068] Based on the above device, optionally, the material moisture content determination module 230 includes:

[0069] An estimated exit time determination unit, used to determine an estimated exit time in a preset leaf storage time;

[0070] The material moisture content determination unit is used to process the expected outlet time, the drying characteristic kinetic parameters, the material initial moisture content and the material constant moisture content based on the objective function in the thin layer drying mechanism model to obtain the material moisture content of the tobacco leaf material to be tested at the expected outlet time, so that the tobacco leaf material to be tested can be used for cigarette production when the expected outlet time is reached.

[0071] Based on the above device, optionally, the expression of the objective function is: Among them, M t It is expressed as the moisture content of tobacco leaf material at time t, M e It represents the constant moisture content of the material, M0 represents the initial moisture content of the material, k and n represent the kinetic parameters of the drying characteristics, e () Expressed as an exponential function.

[0072] On the basis of the above device, optionally, the device further includes:

[0073] A material initial moisture adjustment module, used for adjusting the material initial moisture in the tobacco material moisture of the tobacco material to be tested when the moisture content of the material does not meet the first condition;

[0074] The re-execution module is used to determine the moisture content of the tobacco material to be tested based on the adjusted moisture content of the tobacco material, so that when the moisture content of the material meets the first condition, the tobacco material to be tested whose actual storage time reaches the preset storage time can be used for cigarette production.

[0075] On the basis of the above device, optionally, the device further includes:

[0076] A theoretical value determination module, for determining a kinetic parameter theoretical value corresponding to the drying characteristic kinetic attribute based on the drying characteristic kinetic attribute in the thin layer drying mechanism model;

[0077] A model determination module is used to construct an initial kinetic parameter model based on predetermined environmental attributes and the theoretical values ​​of the kinetic parameters, so as to train the initial kinetic parameter model based on training samples and a thin layer drying mechanism model to obtain the target kinetic parameter model; wherein the initial kinetic parameter model is used to describe the correlation between environmental attributes and drying characteristic kinetic parameters.

[0078] Based on the above device, optionally, the model determination module includes:

[0079] A training sample determination module is used to obtain multiple training samples; wherein the training samples include environmental attributes when storing historical tobacco leaf materials, tobacco leaf material moisture of historical tobacco leaf materials, and actual moisture loss process data of the historical tobacco leaf materials during the historical storage time;

[0080] A module for determining kinetic parameters to be used, for inputting, for each of the training samples, the environmental attributes in the training samples into the initial kinetic parameter model, to obtain kinetic parameters to be used associated with the environmental attributes;

[0081] A module for determining data of a predicted moisture loss process, for inputting the kinetic parameters to be used and the moisture content of the tobacco leaf material in the training sample into the thin layer drying mechanism model to obtain data of a predicted moisture loss process;

[0082] A parameter correction module is used to correct the model parameters in the initial kinetic parameter model based on the predicted water loss process data and the actual water loss process data in the training sample to obtain the trained target kinetic parameter model.

[0083] On the basis of the above device, optionally, the parameter correction module includes:

[0084] an error value determining unit, configured to determine an error value based on the predicted moisture loss process data and the actual moisture loss process data in the training sample;

[0085] A model training property determination unit, configured to determine a model training property based on the error value and / or the current number of iterations; wherein the model training property includes at least convergence and accuracy;

[0086] An optimization parameter determination unit, used for, when the model training attribute does not meet the second condition, optimizing the model parameters according to the particle swarm optimization algorithm and the variable constraint function corresponding to the model parameters in the initial dynamic parameter model to obtain the optimization parameters;

[0087] A parameter updating unit, used for updating the model parameters based on the optimization parameters to obtain an updated initial kinetic parameter model;

[0088] The continuing training unit is used to continue training the updated initial kinetic parameter model based on the training samples to obtain a trained target kinetic parameter model.

[0089] The tobacco leaf moisture prediction device provided in the embodiment of the present invention can execute the tobacco leaf moisture prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] Embodiment 3

[0091] Figure 4 It is a structural schematic diagram of an electronic device for implementing a method for predicting tobacco leaf moisture in an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0092] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting tobacco leaf moisture.

[0095] In some embodiments, the method for predicting tobacco moisture may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting tobacco moisture described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting tobacco moisture in any other appropriate manner (e.g., by means of firmware).

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0098] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0101] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0102] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting tobacco leaf moisture as provided in any embodiment of the present invention.

[0103] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting moisture loss in tobacco leaves, characterized in that: include: Acquire the environmental properties of the tobacco storage area where the tobacco leaf material to be tested is located, and determine the moisture content of the tobacco leaf material corresponding to the tobacco leaf material to be tested; wherein the environmental properties include environmental temperature and environmental humidity; The environmental attributes are input into a trained target kinetic parameter model to obtain drying characteristic kinetic parameters; wherein the target kinetic parameter model is obtained by training an initial kinetic parameter model based on training samples and a thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the moisture loss process of tobacco leaf materials stored in a thin layer state; According to the thin layer drying mechanism model, based on the preset leaf storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, the moisture content of the tobacco leaf material to be tested is determined; When the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual leaf storage time reaches the preset leaf storage time is used for cigarette production.

2. The method according to claim 1, characterized in that: The moisture content of the tobacco leaf material includes the initial moisture content of the material when the tobacco leaf material to be tested is stored and the constant moisture content of the material when the tobacco leaf material to be tested is in a moisture equilibrium state.

3. The method according to claim 2, characterized in that The method of determining the moisture content of the tobacco leaf material to be tested according to the thin layer drying mechanism model, based on the preset leaf storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material, includes: Determine the estimated exit time within the preset leaf storage time; Based on the objective function in the thin layer drying mechanism model, the expected outlet moment, the drying characteristic kinetic parameters, the initial moisture content of the material and the constant moisture content of the material are processed to obtain the moisture content of the tobacco leaf material to be tested at the expected outlet moment, so that the tobacco leaf material to be tested can be used for cigarette production when the expected outlet moment is reached.

4. The method according to claim 3, characterized in that The expression of the objective function is: Among them, M t It is expressed as the moisture content of tobacco leaf material at time t, M e It represents the constant moisture content of the material, M0 represents the initial moisture content of the material, k and n represent the kinetic parameters of the drying characteristics, e () Expressed as an exponential function.

5. The method according to claim 1, characterized in that After determining the moisture content of the tobacco leaf material to be tested, the method further comprises: When the moisture content of the material does not meet the first condition, adjusting the initial moisture content of the material in the tobacco material moisture of the tobacco material to be tested; Based on the adjusted moisture content of the tobacco leaf material, an operation of determining the moisture content of the tobacco leaf material to be tested is performed, so that when the moisture content of the material meets the first condition, the tobacco leaf material to be tested whose actual storage time reaches the preset storage time can be used for cigarette production.

6. The method according to claim 1, characterized in that Before inputting the environmental attributes into the trained target kinetic parameter model to obtain the drying characteristic kinetic parameters, the method further includes: Based on the drying characteristic kinetic properties in the thin layer drying mechanism model, determining a theoretical value of a kinetic parameter corresponding to the drying characteristic kinetic properties; Based on the predetermined environmental attributes and the theoretical values ​​of the kinetic parameters, an initial kinetic parameter model is constructed, and the initial kinetic parameter model is trained based on the training samples and the thin layer drying mechanism model to obtain the target kinetic parameter model; The initial kinetic parameter model is used to describe the correlation between environmental attributes and drying characteristic kinetic parameters.

7. The method according to claim 6, characterized in that The training of the initial kinetic parameter model based on the training sample and the thin layer drying mechanism model to obtain the target kinetic parameter model includes: Acquire multiple training samples; wherein the training samples include environmental attributes when storing historical tobacco leaf materials, tobacco leaf material moisture of historical tobacco leaf materials, and actual moisture loss process data of the historical tobacco leaf materials during the historical storage time; For each of the training samples, inputting the environmental attributes in the training sample into the initial kinetic parameter model to obtain the kinetic parameters to be used that are associated with the environmental attributes; Inputting the kinetic parameters to be used and the moisture content of the tobacco leaf material in the training sample into the thin layer drying mechanism model to obtain the predicted moisture loss process data; Based on the predicted water loss process data and the actual water loss process data in the training samples, the model parameters in the initial kinetic parameter model are modified to obtain the trained target kinetic parameter model.

8. The method according to claim 7, characterized in that The method of modifying the model parameters in the initial kinetic parameter model based on the predicted water loss process data and the actual water loss process data in the training sample to obtain the trained target kinetic parameter model includes: Determining an error value based on the predicted moisture loss process data and the actual moisture loss process data in the training sample; Determine a model training property based on the error value and / or the current number of iterations; wherein the model training property includes at least convergence and accuracy; When the model training attributes do not meet the second condition, optimizing the model parameters according to the particle swarm optimization algorithm and the variable constraint function corresponding to the model parameters in the initial dynamic parameter model to obtain the optimized parameters; Updating the model parameters based on the optimization parameters to obtain an updated initial kinetic parameter model; The updated initial kinetic parameter model is continuously trained based on the training samples to obtain a trained target kinetic parameter model.

9. A tobacco leaf moisture prediction device, characterized in that: include: An environmental attribute determination module is used to obtain the environmental attributes of the tobacco storage area where the tobacco material to be tested is located, and determine the moisture content of the tobacco material corresponding to the tobacco material to be tested; wherein the environmental attributes include environmental temperature and environmental humidity; A kinetic parameter determination module, used for inputting the environmental attributes into a trained target kinetic parameter model to obtain drying characteristic kinetic parameters; wherein the target kinetic parameter model is obtained by training an initial kinetic parameter model based on training samples and a thin layer drying mechanism model; the thin layer drying mechanism model is used to describe the drying process of tobacco leaf materials in a thin layer state; A material moisture content determination module, used to determine the material moisture content of the tobacco leaf material to be tested based on a preset leaf storage time, the drying characteristic kinetic parameters and the moisture content of the tobacco leaf material; The judgment module is used to use the tobacco leaf material to be tested whose actual storage time reaches the preset storage time for cigarette production when the moisture content of the material meets the first condition.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting tobacco leaf moisture according to any one of claims 1-8.

Images