CN112273695A - Method, device and equipment for predicting water content of loose moisture regain outlet - Google Patents
Method, device and equipment for predicting water content of loose moisture regain outlet Download PDFInfo
- Publication number
- CN112273695A CN112273695A CN202011193473.XA CN202011193473A CN112273695A CN 112273695 A CN112273695 A CN 112273695A CN 202011193473 A CN202011193473 A CN 202011193473A CN 112273695 A CN112273695 A CN 112273695A
- Authority
- CN
- China
- Prior art keywords
- variable
- outlet
- loose
- feeding
- water content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B3/00—Preparing tobacco in the factory
- A24B3/04—Humidifying or drying tobacco bunches or cut tobacco
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B9/00—Control of the moisture content of tobacco products, e.g. cigars, cigarettes, pipe tobacco
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and equipment for predicting the water content of a loose moisture regain outlet, which are based on the idea that a reverse prediction model is constructed from a loose moisture regain outlet to a moist leaf feed outlet instead of using a moist leaf feed inlet parameter as a prediction factor, and specific input characteristic variables are selected and matched in combination with production equipment parameters, so that the problems of parameter cooperation and quality index association matching between the water content of the moist leaf feed outlet and the water content of the loose moisture regain outlet can be effectively and accurately solved, the control of the water content of materials can be stably and reliably guided, the process production cooperation of a tobacco processing workshop is realized, and the homogenization of tobacco production and processing is finally ensured.
Description
Technical Field
The invention relates to the field of tobacco processing, in particular to a method, a device and equipment for predicting the moisture content of a loose moisture regain outlet.
Background
The moisture content of the moist leaf feeding outlet is an important process index in the production link of silk making, and the conformity and the stability of the moist leaf feeding outlet have important influence on the stability of the process control of the subsequent procedures. In the production process of the cut tobacco, tobacco leaf materials need to be sliced, loosened and remoistened, subjected to laser impurity removal and moistened and fed, the loosening and remoistening of the slices and the storage of the leaves are carried out, and the tobacco leaves are conveyed to a moistened and fed process and finally enter a leaf storage room for storage (the processes are collectively called as a feeding section, and are indicated by dotted lines in a figure 1). The loosening and conditioning process mainly comprises the steps of adding water into hot steam to increase the moisture and temperature of the tobacco leaves, fully loosening tobacco blocks and removing miscellaneous gases, then carrying out the subsequent leaf moistening and feeding process, uniformly applying sugar materials on the tobacco leaves, and finally entering a leaf storage room to store for a certain time to balance the moisture and temperature of the tobacco leaves. On one hand, the intermediate link is easy to cause water loss due to the influence of various factors; on the other hand, the moisture of the leaf materials is usually only regulated in the loosening and moisture regaining process, and only the feeding work is carried out in the leaf moistening and feeding process, so that the fixed moisture in the sugar materials is removed, and the moisture of the materials cannot be corrected in the process. Therefore, the consistency of the water content of the outlet of the loosening and moisture regaining process is ensured, and the direct influence on the water content of the outlet of the guide loosening and moisture regaining and the stable leaf moistening and feeding process is realized.
However, the moisture content value of the existing loose moisture regain outlet (at the moisture meter 1) is mainly estimated according to the standard value of the moisture content of the moist leaf feeding inlet (at the moisture meter 2) by means of manual experience, but the moisture content is influenced by a plurality of factors in actual operation, and the manual simple estimation mode cannot realize the cooperative control of the parameters of the front and the rear processes.
Disclosure of Invention
In order to ensure the water content of the feeding outlet of the moistening tobacco to be stable, the invention aims to provide a method, a device and equipment for predicting the water content of the loosening and conditioning outlet, wherein a reverse prediction model is adopted to replace manual estimation, and the problem of poor parameter cooperation of the previous and subsequent processes is effectively solved.
The technical scheme adopted by the invention is as follows:
in a first aspect, the invention provides a method for predicting moisture content of a loose moisture regain outlet, wherein the method comprises the following steps:
constructing a prediction model for reversely predicting the water content of the loose moisture regain outlet;
acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types; the variable types at least comprise standard values of the moisture content of the leaf moistening feeding outlet given according to process standards;
and obtaining a predicted value of the water content of the loose conditioning outlet according to the input variable and the prediction model.
In at least one possible implementation manner, the preset manners of the variable categories include:
determining an output variable and selecting a plurality of candidate input variables;
determining correlation coefficients of each candidate input variable and the output variable one by one;
and determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold value.
In at least one possible implementation, the original input variables include: the temperature of the loose conditioning piece area, the relative humidity of the loose conditioning piece area, the material flow of the leaf moistening feeding process, the feeding flow of the leaf moistening feeding process, the temperature of the leaf moistening feeding piece area, the relative humidity of the leaf moistening feeding piece area, the temperature of the leaf moistening feeding outlet, the hot steam adding value of the leaf moistening feeding, the water content of the leaf moistening feeding outlet and the water content of the slice.
In at least one possible implementation manner, the preset manner of the variable categories further includes: integrating variables related to the temperature and the relative humidity of the area in the original input variables based on a preset variable optimization strategy.
In at least one possible implementation manner, the integrating variables related to the temperature and the relative humidity of the area in the original input variables comprises:
acquiring the moisture air enthalpy of the loosening and conditioning sheet area by utilizing the temperature of the loosening and conditioning sheet area and the relative humidity of the loosening and conditioning sheet area; and/or
And calculating the humid air enthalpy of the moistening blade feeding area by utilizing the temperature of the moistening blade feeding area and the relative humidity of the moistening blade feeding area.
In at least one possible implementation, the predictive model includes a convert-XGBoost model.
In a second aspect, the present invention provides a device for predicting moisture content of a loose moisture regain outlet, wherein the device comprises:
the reverse model training module is used for constructing a prediction model for reversely predicting the water content of the loose moisture regain outlet;
the input variable determining module is used for acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types; the variable types at least comprise standard values of the moisture content of the leaf moistening feeding outlet given according to process standards;
and the prediction module is used for obtaining a prediction value of the water content of the loosening and conditioning outlet according to the input variable and the prediction model.
In at least one possible implementation manner, the input variable determining module includes a variable type presetting unit, where the variable type presetting unit specifically includes:
the initial variable determining component is used for determining output variables and selecting a plurality of candidate input variables;
a correlation determination component for determining a correlation coefficient of each of the candidate input variables with the output variable one by one;
and the original input variable determining component is used for determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold value.
In at least one possible implementation manner, the variable type presetting unit further includes:
and the variable integration component is used for integrating variables related to the temperature and the relative humidity of the area in the original input variables based on a preset variable optimization strategy.
In a third aspect, the present invention provides a prediction apparatus for moisture content of a loose moisture regain outlet, including:
one or more processors, memory which may employ a non-volatile storage medium, and one or more computer programs stored in the memory, the one or more computer programs comprising instructions which, when executed by the apparatus, cause the apparatus to perform the method as in the first aspect or any possible implementation of the first aspect.
The concept of the invention is that the parameters of the moist leaf feeding inlet are abandoned as prediction factors, a reverse prediction model is constructed from the loose moisture regain outlet to the moist leaf feeding outlet, and the selection and matching of specific input characteristic variables are carried out by combining the parameters of production equipment, so that the problems of parameter cooperation and quality index association matching between the moisture content of the moist leaf feeding outlet and the moisture content of the loose moisture regain outlet can be effectively and accurately solved, the control of the material moisture content can be stably and reliably guided, the process production cooperation of a silk making workshop is realized, and the homogenization of the production and processing of cut tobacco is finally ensured.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
FIG. 1 is a schematic view of a feeding and shredding process;
FIG. 2 is a flow chart of an embodiment of a method for predicting moisture content of a loose conditioning outlet according to the present invention;
FIG. 3 is a flow chart of an embodiment of an input variable presetting method provided by the present invention;
FIG. 4 is a schematic diagram of an embodiment of a moisture content prediction device for a loose moisture regain outlet according to the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
Before describing the specific technical scheme of the invention, the processing and derivation ideas of the inventors are explained as follows. The inventor firstly tries to adopt a mode of establishing a multiple linear regression model for solving to realize the prediction and control of the water content of the loose moisture regaining outlet, specifically, a reference value of the moisture proportion of the moisture regaining and water adding of the loose moisture regaining machine is calculated by giving a moisture value of a leaf moistening feeding inlet, but the practice shows that the mode has the following defects:
(1) the material is subjected to multiple processes of slicing, loosening and moisture regaining of blades, moistening the leaves, feeding and the like, factors influencing the water content of a moistening leaf feeding outlet are complex and have certain relevance, but the multiple linear regression model is low in interpretation degree and insufficient in information consideration, and is not reliable after actual verification.
(2) The inlet water of the leaf moistening and feeding process is directly used as a standard to calculate the moisture regaining and water adding proportion of the loosening and moisture regaining machine, but the feedback time between the two processes is long, so that the rapid adjustment of the moisture content of the loosening and moisture regaining outlet is not facilitated.
In view of the above, the inventors have determined that it is necessary to adjust the prediction strategy to provide adaptive and accurate optimization and improvement of the above-mentioned methods in combination with process equipment parameters. Therefore, the embodiment of the method for predicting the moisture content of the loose conditioning outlet provided by the invention, which is shown in fig. 2, may specifically include:
and step S1, constructing a prediction model for reversely predicting the water content of the loose moisture regaining outlet.
In this embodiment, according to the process route shown in fig. 1, a feeding section model is established at a feeding section (from a moisture meter 1 to a moisture meter 3), and the initial design of the model is to directly predict the water content of the loosening and dampening outlet from the water content of the leaf moistening feeding outlet in a reverse prediction mode. Specifically, a data set can be constructed by selecting appropriate process parameters and equipment parameters in advance through characteristic engineering analysis, a reverse model (preferably Converse-XGboost) is used for predicting the water content of the loose conditioning feeding outlet based on a machine learning algorithm, 80% of data samples can be selected as a training set for training the model, 20% of data samples can be used as a test set for verification, and meanwhile, a Bayesian parameter-adjusting mode can be used for optimizing model parameters. The selection of the model input data and the reverse XGBoost model mentioned in the preferred example will be described later, and here, taking actual operation as an example, a model prediction effect target that can be referred to is given in combination with the application scenario of the present invention: the error of the predicted value of the water content of the loosening and conditioning outlet is within +/-0.2 percent. Likewise, this technical goal is only schematic and not limiting.
And step S2, acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types.
Wherein, in order to realize the concept of inverse prediction, the variable category at least needs to comprise the moisture content of the leaf moistening feed outlet, so that a standard value of the moisture content of the leaf moistening feed outlet can be given according to the process standard in actual operation.
It should be noted that one of the prerequisites for replacing manual estimation by the prediction model is how to determine the appropriate feature variables, and therefore, various feature parameters as input variables need to be preset in the model training stage.
Regarding feature selection, after practical analysis of the inventor and in combination with each process of the feeding segment shown in fig. 1, the following 12 feature variables are selected from a large amount of relevant historical data, including: water content Y output variable of loose moisture regaining outlet and temperature X of loose moisture regaining sheet area1Relative humidity X of loose moisture regaining sheet area2Material flow X for moistening and feeding3Feeding flow X of wetting leaf feeding4Temperature X of leaf moistening feeding zone5Relative humidity X of leaf moistening feeding sheet area6Temperature X of leaf-moistening feeding outlet7Hot steam adding value X for wetting leaf and feeding8Moisture content X of leaf moistening feeding outlet9(corresponding to the standard value of the moisture content of the moistening leaf feeding outlet, corresponding historical data can be obtained in the training stage), and the moisture content of the slices X10Flake blending flow X11As candidate input variables.
The above variable data can be obtained as follows: the temperature and humidity parameters can be generally from a temperature and humidity sensor, the material flow and the blending flow can be generally from a metering scale, the hot steam addition value can be generally from control parameters of hot steam supply equipment, and the water content can be generally from a moisture meter; further, in some embodiments, the above equipment parameters and production parameters may also be taken from data stored in the MES system database through the data acquisition device, and may be queried and obtained through the MES system in actual operation.
It should be noted that the selection of the above variables is only a preliminary selection from the equipment production parameters, and in order to improve the model processing accuracy, the inventor proposes to perform further correlation analysis on the preliminarily selected parameters, so that after determining the output variables and selecting a plurality of candidate input variables, the inventor also proposes to analyze the correlations between the candidate input variables and the output variables (i.e. the moisture content of the loose conditioning outlet) one by one to determine the correlation coefficients. Here, in some embodiments, the Pearson correlation analysis is performed on the input variables and the output variables, and the correlation coefficient results are shown in the following table:
| variables of | X1 | X2 | X3 | X4 | X5 | X6 | X7 | X8 | X9 | X10 | X11 |
| Correlation | 0.39 | 0.42 | 0.74 | 0.66 | 0.52 | 0.1 | -0.23 | -0.16 | 0.72 | 0.13 | 0.03 |
According to the correlation coefficient and a preset coefficient threshold value (for example less than 0.1), wherein the flake blending flow rate X is11The correlation with the water content Y of the loose conditioning outlet is only 0.03 and is obviously smaller than the coefficient threshold value, so that the variable X in the various input variables selected preliminarily in the foregoing can be considered11The loose conditioning outlet water content has low relevance, and can be excluded from candidate input variables, namely, the original input variables can be determined to be 10 types through further analysis of the relevance: temperature X of loose moisture regaining sheet area1Relative humidity X of loose moisture regaining sheet area2Material flow X for moistening and feeding3Feeding flow X of wetting leaf feeding4Temperature X of leaf moistening feeding zone5Relative humidity X of leaf moistening feeding sheet area6Temperature X of leaf-moistening feeding outlet7Hot steam adding value X for wetting leaf and feeding8Moisture content X of leaf moistening feeding outlet9And sheet moisture content X10。
Therefore, model training can be carried out on the basis of a plurality of input variables determined by the characteristic selection part, and corresponding data can be obtained from equipment and production parameters according to the input variables in the actual testing and application stage.
However, the inventor further proposes a concept of feature reconstruction based on the original input variables, that is, a new variable is constructed from the original input variables determined through the preset process, so that, in conjunction with fig. 3, the present invention provides at least one more preferred input variable preset method, specifically including:
step S21, determining output variables and selecting a plurality of candidate input variables;
step S22, determining the correlation coefficient of each candidate input variable and the output variable one by one;
step S23, determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold;
and step S24, integrating variables related to the temperature and the relative humidity of the areas in the original input variables based on a preset variable optimization strategy.
The process of step S21 to step S23 is the process of filtering the original input variables from the candidate input variables, which is not described herein again. In step S24, a specific way of constructing new variables according to the existing variables is proposed. In the original input variables, X2And X6The relative humidity refers to the ratio of the partial pressure of water vapor in the current wet air to the partial pressure of water vapor in the saturated wet air at the same temperature, so that according to the knowledge of the drying theory, the material moisture loss is mainly related to the partial pressure of water vapor in the wet air, and the temperature and the relative humidity in the air are two variables which influence each other, therefore, the enthalpy value of the wet air can be calculated through the relative humidity of the plate area and the temperature of the plate area, and the further construction of the input variable is completed. That is, in actual practice, X can be passed as described above1X2Calculating the enthalpy of the moist air in the region of the loose moisture regain sheet, which can also be calculated by X as described above5X6Calculating the humid air enthalpy of the moist blade feeding area, and replacing the two humid air enthalpies with the original blade area temperature and relative humidity (integration can be carried out only based on a single blade area, and characteristic integration can also be carried out on two related blade areas), so that the optimal scheme can reduce the dimension and reduce the operation pressure on one hand, and can avoid inputting two variables with interactive influence when a model is applied and reduce the precision on the other hand; thus, the final input variable class determined by the preferred embodiment can be obtained:
moisture content X of loose moisture regain area1' moistening leaf feeding material flow X2' moistening leaf feeding flow X3', moist air enthalpy X of leaf-moistening feeding sheet area4' moistening leaf and feeding outlet temperature X5' moistening leaf feeding hot steam adding value X6' moisture content X of leaf-moistening feeding outlet7' thin slice water content X8’。
Further, in order to ensure that the final parameters after the variables are integrated still have validity, the correlation verification can be performed on the integrated input variables based on the foregoing concept, and the following table can be referred to:
| variables of | X1’ | X2’ | X3’ | X4’ | X5’ | X6’ | X7’ | X8’ |
| Correlation | 0.44 | 0.74 | 0.66 | 0.78 | -0.23 | -0.16 | 0.72 | 0.13 |
And step S3, obtaining a predicted value of the water content of the loosening and conditioning outlet according to the input variable and the prediction model.
After the feature selection and the model construction (described later) are completed, the input variables can be input into the prediction model for reverse prediction, and the predicted value of the water content of the target loose moisture regaining outlet is obtained. Particularly, in the actual production operation, a standard set value mu of the moisture content of the leaf moistening feeding outlet can be given according to the production requirement based on the process standard, namely the moisture content X of the leaf moistening feeding outlet in input variables9Or X7Mu, then obtaining the values of the above input variables except mu through the MES system, and inputting the values into the prediction model to obtain the water content Y of the loose moisture regaining outlet which meets the water content standard of the leaf moistening feed outlet.
With regard to the construction of the prediction model, reference may be made in particular to the following preferred examples:
the prediction model is established between the moisture meter 1 and the moisture meter 3 based on a convert-XGboost algorithm in a machine learning algorithm, and compared with a multiple regression idea tried at first, the stability and the accuracy of moisture content control can be effectively improved in the better implementation mode. The specific modeling and calculation process is as follows:
the construction model is as follows:
wherein, i is 1,2, …, n, n is the number of samples; f is the set of all regression trees, FkIs a function of F. The optimum parameter sought is the parameter that is satisfied when the objective function value is minimal, the objective function being expressed as:
fobj(θ)＝L(θ)+Ω(θ)
l is a loss function, Ω regular term, where:
adding a new function f on the basis of the original model during each training, and adding the function into the model if the target function is reduced by the newly added function, wherein the specific process can refer to the following steps:
...
wherein the content of the first and second substances,
denotes the predicted value of the t-th order, ft(xi) Representing the function of the t-th new join.
The objective function at this time can be expressed as:
wherein c represents a constant.
Taylor expansion of the objective function yields:
removing the constant term allows the objective function to rely on each data point for a first derivative and a second derivative in the error function.
Then defining the complexity of the model, thinning f in the model, and dividing the tree f into a structural part q and a leaf weight part omega, namely:
ft(x)＝ωq(x),ω∈RT,q:RT→{1,2,...,T}
the structural part q maps the input variable to the index number of the leaf, and the weight omega gives the real number fraction value of each index number corresponding to the leaf. And defining the complexity of the model as the square sum of the number of nodes in each regression tree and the real number fraction value corresponding to the leaf node. Namely:
where γ, λ are tuning parameters used to prevent over-fitting of the model.
The objective function can be further expressed as:
wherein Ij＝{i|q(xi) J represents the set of samples in each leaf in the jth tree, and if the structure q is known, the best ω and its pair can be found by this objective functionThe maximum gain of the objective function.
Finally, it can be supplemented that the water content of the loose moisture regain outlet predicted by the invention can be directly used as a target set value of the loose moisture regain intelligent water adding system, namely, the water content of the loose moisture regain intelligent water adding system for producing the silk is predicted in series, for example, the water content of the loose moisture regain outlet of the batch is predicted before production, the intelligent water adding system only needs to set the required target set value of the water content of the loose moisture regain outlet, and automatically learns and calculates the required water adding flow rate at regular intervals, so that the stability and the conformity of the water content of the stub bar can be effectively ensured in the time that the material reaches the leaf moistening feed outlet from the loose moisture regain outlet; therefore, when the feeding section starts to produce, relevant data are collected in real time and the prediction operation is carried out in cooperation with parameters among the working procedures, and the moisture content of the moisture regain outlet is rapidly adjusted through the intelligent loosening and moisture regain water adding system, so that the homogenization processing level can be improved.
In conclusion, the concept of the invention is that the parameters of the moist feed inlet are abandoned as prediction factors, a reverse prediction model is constructed from the loose moisture regain outlet to the moist feed outlet, and the selection of specific input characteristic variables is carried out by combining the parameters of production equipment, so that the problems of parameter cooperation and quality index association matching between the moisture content of the moist feed outlet and the moisture content of the loose moisture regain outlet can be effectively and accurately solved, the control of the material moisture content can be stably and reliably guided, the process production cooperation of a silk making workshop is realized, and the homogenization of the production and processing of the silk making tobacco is finally ensured.
The inventor also carries out practical experimental verification on the scheme provided by the invention and obtains the following conclusion:
specifically, the number K of the trees of the prediction model is 130 through computer solving, the maximum depth of the trees is 7, the sum of the weights of the minimum leaf node samples is 4, the minimum loss function reduction value gamma required by node splitting is 0.01, and the random sampling proportion subsample is 0.8, so that overfitting and under-fitting can be effectively prevented. Tests show that the curve goodness of fit of the predicted value and the actual value of the moisture content of the loose conditioning outlet is high, the model score is 92.37, the mean square error MSE is 0.005, the errors can be controlled within 0.4%, the accurate prediction accuracy is 86.49%, and the prediction effect is greatly improved.
According to the verification, the idea of the reverse prediction model provided by the invention effectively realizes that the water content is predicted by a computer instead of a manual method, and the prediction accuracy is obviously improved.
Corresponding to the above embodiments and preferred solutions, the present invention further provides an embodiment of a device for predicting moisture content of a loose moisture regain outlet, as shown in fig. 4, which may specifically include the following components:
the reverse model training module 1 is used for constructing a prediction model for reversely predicting the water content of the loose moisture regain outlet;
the input variable determining module 2 is used for acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types; the variable types at least comprise standard values of the moisture content of the leaf moistening feeding outlet given according to process standards;
and the prediction module 3 is used for obtaining a predicted value of the water content of the loose moisture regaining outlet according to the input variable and the prediction model.
In at least one possible implementation manner, the input variable determining module includes a variable type presetting unit, where the variable type presetting unit specifically includes:
the initial variable determining component is used for determining output variables and selecting a plurality of candidate input variables;
a correlation determination component for determining a correlation coefficient of each of the candidate input variables with the output variable one by one;
and the original input variable determining component is used for determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold value.
In at least one possible implementation manner, the variable type presetting unit further includes:
and the variable integration component is used for integrating variables related to the temperature and the relative humidity of the area in the original input variables based on a preset variable optimization strategy.
It should be understood that the division of each component in the loose moisture regain outlet moisture percentage prediction device shown in fig. 4 is merely a logical functional division, and the actual implementation may be wholly or partially integrated into a physical entity or physically separated. And these components may all be implemented in software invoked by a processing element; or may be implemented entirely in hardware; and part of the components can be realized in the form of calling by the processing element in software, and part of the components can be realized in the form of hardware. For example, a certain module may be a separate processing element, or may be integrated into a certain chip of the electronic device. Other components are implemented similarly. In addition, all or part of the components can be integrated together or can be independently realized. In implementation, each step of the above method or each component above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above components may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors (DSPs), one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, these components may be integrated together and implemented in the form of a System-On-a-Chip (SOC).
In view of the foregoing examples and preferred embodiments thereof, it will be appreciated by those skilled in the art that, in practice, the technical idea underlying the present invention may be applied in a variety of embodiments, the present invention being schematically illustrated by the following vectors:
(1) a prediction device for water content of a loose moisture regain outlet. The device may specifically include: one or more processors, memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions, which when executed by the apparatus, cause the apparatus to perform the steps/functions of the foregoing embodiments or an equivalent implementation.
Preferably, the device for predicting the moisture content of the loose moisture regaining outlet can refer to a central control machine or other management platforms and carriers involved in the cut tobacco processing and generating link.
(2) A readable storage medium, on which a computer program or the above-mentioned apparatus is stored, which, when executed, causes the computer to perform the steps/functions of the above-mentioned embodiments or equivalent implementations.
In the several embodiments provided by the present invention, any function, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on this understanding, some aspects of the present invention may be embodied in the form of software products, which are described below, or portions thereof, which substantially contribute to the art.
(3) A computer program product (which may include the above apparatus) when run on a terminal device, causes the terminal device to perform the method for predicting moisture content of loose conditioning outlet of the foregoing embodiment or an equivalent embodiment.
From the above description of the embodiments, it is clear to those skilled in the art that all or part of the steps in the above implementation method can be implemented by software plus a necessary general hardware platform. With this understanding, the above-described computer program products may include, but are not limited to, refer to APP; in the foregoing, the device/terminal may be a computer device, and the hardware structure of the computer device may further specifically include: at least one processor, at least one communication interface, at least one memory, and at least one communication bus; the processor, the communication interface and the memory can all complete mutual communication through the communication bus. The processor may be a central Processing unit CPU, a DSP, a microcontroller, or a digital Signal processor, and may further include a GPU, an embedded Neural Network Processor (NPU), and an Image Signal Processing (ISP), and may further include a specific integrated circuit ASIC, or one or more integrated circuits configured to implement the embodiments of the present invention, and the processor may have a function of operating one or more software programs, and the software programs may be stored in a storage medium such as a memory; and the aforementioned memory/storage media may comprise: non-volatile memories (non-volatile memories) such as non-removable magnetic disks, U-disks, removable hard disks, optical disks, etc., and Read-Only memories (ROM), Random Access Memories (RAM), etc.
In the embodiments of the present invention, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, and means that there may be three relationships, for example, a and/or B, and may mean that a exists alone, a and B exist simultaneously, and B exists alone. Wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.
Those of skill in the art will appreciate that the various modules, elements, and method steps described in the embodiments disclosed in this specification can be implemented as electronic hardware, combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In addition, the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other. In particular, for embodiments of devices, apparatuses, etc., since they are substantially similar to the method embodiments, reference may be made to some of the descriptions of the method embodiments for their relevant points. The above-described embodiments of devices, apparatuses, etc. are merely illustrative, and modules, units, etc. described as separate components may or may not be physically separate, and may be located in one place or distributed in multiple places, for example, on nodes of a system network. Some or all of the modules and units can be selected according to actual needs to achieve the purpose of the above-mentioned embodiment. Can be understood and carried out by those skilled in the art without inventive effort.
The structure, features and effects of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the above embodiments are merely preferred embodiments of the present invention, and it should be understood that technical features related to the above embodiments and preferred modes thereof can be reasonably combined and configured into various equivalent schemes by those skilled in the art without departing from and changing the design idea and technical effects of the present invention; therefore, the invention is not limited to the embodiments shown in the drawings, and all the modifications and equivalent embodiments that can be made according to the idea of the invention are within the scope of the invention as long as they are not beyond the spirit of the description and the drawings.
Claims (10)
1. A method for predicting the moisture content of a loose moisture regain outlet is characterized by comprising the following steps:
constructing a prediction model for reversely predicting the water content of the loose moisture regain outlet;
acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types; the variable types at least comprise standard values of the moisture content of the leaf moistening feeding outlet given according to process standards;
and obtaining a predicted value of the water content of the loose conditioning outlet according to the input variable and the prediction model.
2. The method for predicting the moisture content of the loose conditioning outlet of claim 1, wherein the preset modes of the variable types comprise:
determining an output variable and selecting a plurality of candidate input variables;
determining correlation coefficients of each candidate input variable and the output variable one by one;
and determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold value.
3. The method of predicting moisture content at a loose conditioning outlet of claim 2, wherein the raw input variables comprise: the temperature of the loose conditioning piece area, the relative humidity of the loose conditioning piece area, the material flow of the leaf moistening feeding process, the feeding flow of the leaf moistening feeding process, the temperature of the leaf moistening feeding piece area, the relative humidity of the leaf moistening feeding piece area, the temperature of the leaf moistening feeding outlet, the hot steam adding value of the leaf moistening feeding, the water content of the leaf moistening feeding outlet and the water content of the slice.
4. The method for predicting the moisture content of the loose conditioning outlet according to claim 3, wherein the presetting mode of a plurality of variable types further comprises: integrating variables related to the temperature and the relative humidity of the area in the original input variables based on a preset variable optimization strategy.
5. The method of claim 4, wherein the integrating variables related to the sheet zone temperature and the sheet zone relative humidity in the raw input variables comprises:
acquiring the moisture air enthalpy of the loosening and conditioning sheet area by utilizing the temperature of the loosening and conditioning sheet area and the relative humidity of the loosening and conditioning sheet area; and/or
And calculating the humid air enthalpy of the moistening blade feeding area by utilizing the temperature of the moistening blade feeding area and the relative humidity of the moistening blade feeding area.
6. The method for predicting the water content of the loose moisture regain outlet according to any one of claims 1 to 5, wherein the prediction model comprises a Converse-XGboost model.
7. A prediction device for water content of a loose moisture regain outlet is characterized by comprising:
the reverse model training module is used for constructing a prediction model for reversely predicting the water content of the loose moisture regain outlet;
the input variable determining module is used for acquiring corresponding equipment parameters and process parameters as input variables according to a plurality of preset variable types; the variable types at least comprise standard values of the moisture content of the leaf moistening feeding outlet given according to process standards;
and the prediction module is used for obtaining a prediction value of the water content of the loosening and conditioning outlet according to the input variable and the prediction model.
8. The method for predicting the moisture content of the loose conditioning outlet according to claim 7, wherein the input variable determining module comprises a variable type presetting unit, and the variable type presetting unit specifically comprises:
the initial variable determining component is used for determining output variables and selecting a plurality of candidate input variables;
a correlation determination component for determining a correlation coefficient of each of the candidate input variables with the output variable one by one;
and the original input variable determining component is used for determining the type of the original input variable according to the correlation coefficient and a preset coefficient threshold value.
9. The method for predicting moisture content of loose conditioning outlet according to claim 8, wherein the variable type presetting unit further comprises:
and the variable integration component is used for integrating variables related to the temperature and the relative humidity of the area in the original input variables based on a preset variable optimization strategy.
10. The utility model provides a loose moisture regain export moisture content prediction equipment which characterized in that includes:
one or more processors, memory, and one or more computer programs stored in the memory, the one or more computer programs comprising instructions which, when executed by the apparatus, cause the apparatus to perform the method of loose conditioning exit moisture content prediction of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193473.XA CN112273695A (en) | 2020-10-30 | 2020-10-30 | Method, device and equipment for predicting water content of loose moisture regain outlet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193473.XA CN112273695A (en) | 2020-10-30 | 2020-10-30 | Method, device and equipment for predicting water content of loose moisture regain outlet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112273695A true CN112273695A (en) | 2021-01-29 |
Family
ID=74353676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011193473.XA Pending CN112273695A (en) | 2020-10-30 | 2020-10-30 | Method, device and equipment for predicting water content of loose moisture regain outlet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112273695A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112931919A (en) * | 2021-02-02 | 2021-06-11 | 龙岩烟草工业有限责任公司 | Method and device for controlling moisture content of cut tobacco |
| CN113076309A (en) * | 2021-03-26 | 2021-07-06 | 四川中烟工业有限责任公司 | System and method for predicting water adding amount of raw tobacco shred |
| CN113515045A (en) * | 2021-07-12 | 2021-10-19 | 浙江中烟工业有限责任公司 | Loose leaf-moistening outlet moisture control method based on historical data prejudgment |
| CN113951533A (en) * | 2021-09-15 | 2022-01-21 | 深圳市信润富联数字科技有限公司 | Tobacco processing method, system, equipment and storage medium |
| CN114532564A (en) * | 2022-03-24 | 2022-05-27 | 河南中烟工业有限责任公司 | Method for controlling moisture content of tobacco shreds at loosening and conditioning outlet based on principal component analysis strategy |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1415180A (en) * | 1971-12-31 | 1975-11-26 | Hauni Werke Koerber & Co Kg | Method of and apparatus for assessing the moisture of tobacco or the like |
| CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method using processing parameter to predict control indexes during tobacco processing procedures |
| CN103222673A (en) * | 2013-05-06 | 2013-07-31 | 江苏中烟工业有限责任公司徐州卷烟厂 | Moisture control method for airflow cut-tobacco drier |
| CN108685142A (en) * | 2018-08-27 | 2018-10-23 | 红塔烟草(集团)有限责任公司 | Each process moisture content of outlet maintaining method in a kind of cigarette primary processing process |
| CN109674080A (en) * | 2019-03-07 | 2019-04-26 | 山东中烟工业有限责任公司 | Tobacco leaf conditioning amount of water prediction technique, storage medium and terminal device |
| CN110876481A (en) * | 2019-11-11 | 2020-03-13 | 张家口卷烟厂有限责任公司 | Control method and device for tobacco shred drying parameters |
| CN111184246A (en) * | 2018-11-14 | 2020-05-22 | 厦门邑通软件科技有限公司 | Method and system for controlling moisture content of cut tobacco drying inlet |
-
2020
- 2020-10-30 CN CN202011193473.XA patent/CN112273695A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1415180A (en) * | 1971-12-31 | 1975-11-26 | Hauni Werke Koerber & Co Kg | Method of and apparatus for assessing the moisture of tobacco or the like |
| CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method using processing parameter to predict control indexes during tobacco processing procedures |
| CN103222673A (en) * | 2013-05-06 | 2013-07-31 | 江苏中烟工业有限责任公司徐州卷烟厂 | Moisture control method for airflow cut-tobacco drier |
| CN108685142A (en) * | 2018-08-27 | 2018-10-23 | 红塔烟草(集团)有限责任公司 | Each process moisture content of outlet maintaining method in a kind of cigarette primary processing process |
| CN111184246A (en) * | 2018-11-14 | 2020-05-22 | 厦门邑通软件科技有限公司 | Method and system for controlling moisture content of cut tobacco drying inlet |
| CN109674080A (en) * | 2019-03-07 | 2019-04-26 | 山东中烟工业有限责任公司 | Tobacco leaf conditioning amount of water prediction technique, storage medium and terminal device |
| CN110876481A (en) * | 2019-11-11 | 2020-03-13 | 张家口卷烟厂有限责任公司 | Control method and device for tobacco shred drying parameters |
Non-Patent Citations (3)
| Title |
|---|
| 刘继辉等: "基于随机森林回归的制丝过程参数影响权重分析", 《烟草科技》 * |
| 常明彬等: "基于环境温湿度条件的松散回潮加水量预测模型研究", 《海峡科学》 * |
| 邱小梅: "环境温湿度对烟草制丝加工过程的影响研究", 《福建质量管理》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112931919A (en) * | 2021-02-02 | 2021-06-11 | 龙岩烟草工业有限责任公司 | Method and device for controlling moisture content of cut tobacco |
| CN113076309A (en) * | 2021-03-26 | 2021-07-06 | 四川中烟工业有限责任公司 | System and method for predicting water adding amount of raw tobacco shred |
| CN113076309B (en) * | 2021-03-26 | 2023-05-09 | 四川中烟工业有限责任公司 | System and method for predicting water addition amount of raw tobacco |
| CN113515045A (en) * | 2021-07-12 | 2021-10-19 | 浙江中烟工业有限责任公司 | Loose leaf-moistening outlet moisture control method based on historical data prejudgment |
| CN113515045B (en) * | 2021-07-12 | 2024-02-20 | 浙江中烟工业有限责任公司 | Loose moist leaf outlet water control method based on history data prejudgement |
| CN113951533A (en) * | 2021-09-15 | 2022-01-21 | 深圳市信润富联数字科技有限公司 | Tobacco processing method, system, equipment and storage medium |
| CN114532564A (en) * | 2022-03-24 | 2022-05-27 | 河南中烟工业有限责任公司 | Method for controlling moisture content of tobacco shreds at loosening and conditioning outlet based on principal component analysis strategy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112273695A (en) | Method, device and equipment for predicting water content of loose moisture regain outlet | |
| CN109674080B (en) | Tobacco leaf conditioning water adding amount prediction method, storage medium and terminal equipment | |
| CN111597729B (en) | Processing equipment technological parameter optimization method and system | |
| CN112273696B (en) | Method, device and equipment for controlling moisture after shredding | |
| CN110893001B (en) | Method and system for controlling water content of outlet of loosening and dampening process | |
| CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
| CN105341985A (en) | Moisture content control method and system of inlet cut tobaccos of cut-tobacco drier | |
| CN113128764A (en) | Generation of tobacco dryer outlet water content prediction model and regulation and control method based on same | |
| KR101432436B1 (en) | Apparatus and method for prediction of influent flow rate and influent components using nearest neighbor method | |
| CN112036701A (en) | Technological parameter optimization method for multi-process industrial production process | |
| CN114532564A (en) | Method for controlling moisture content of tobacco shreds at loosening and conditioning outlet based on principal component analysis strategy | |
| CN112257947A (en) | Method, device and equipment for predicting temperature and humidity of cigarette making environment | |
| CN113011491A (en) | Hot continuous rolling strip steel width prediction method based on principal component analysis and random forest cooperation | |
| CN115456460A (en) | Multi-quality index output prediction method and system for tobacco shred loosening and conditioning process | |
| CN114403487B (en) | Water adding control method for loosening and dampening | |
| CN114027539A (en) | Model prediction control-based loosening and conditioning quantitative water adding control method | |
| CN111695730A (en) | ARIMA and RNN-based vertical mill vibration prediction method and device | |
| CN108614536B (en) | Complex network construction method for key factors of cigarette shred making process | |
| CN115251445A (en) | Method for controlling moisture content of tobacco leaves at outlet of loosening and conditioning machine | |
| CN101320258A (en) | Two-stage virtual measurement method | |
| CN111524023A (en) | Greenhouse adjusting method and system | |
| CN113076309B (en) | System and method for predicting water addition amount of raw tobacco | |
| CN113876008B (en) | Method for controlling stability of moisture content of loose and moisture regained tobacco flakes | |
| CN115017700A (en) | Cigarette shred making process variable selection and weighting method based on SCAD algorithm | |
| CN114911169A (en) | Method, system, equipment and medium for optimizing desulfurization synergistic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |