CN114794521A - On-line moisture meter calibration method for tobacco shred making link - Google Patents
On-line moisture meter calibration method for tobacco shred making link Download PDFInfo
- Publication number
- CN114794521A CN114794521A CN202210276230.5A CN202210276230A CN114794521A CN 114794521 A CN114794521 A CN 114794521A CN 202210276230 A CN202210276230 A CN 202210276230A CN 114794521 A CN114794521 A CN 114794521A
- Authority
- CN
- China
- Prior art keywords
- moisture
- moisture meter
- moistening
- leaf
- hot air
- 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.)
- Granted
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
- A24B9/00—Control of the moisture content of tobacco products, e.g. cigars, cigarettes, pipe tobacco
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses an on-line moisture meter calibration method for a tobacco shred making link, which comprises the following steps of data acquisition; step two, setting a production line moisture meter; establishing a model, namely establishing a moisture meter calibration model in sections according to a definition result; establishing a moisture prediction module, namely performing real-time sectional prediction on the moisture of the material by combining historical batch parameters according to each moisture meter calibration model; and step five, establishing an early warning module, comparing and analyzing the predicted value and the measured value, and early warning and displaying a moisture meter with the predicted value exceeding the material moisture deviation requirement. The invention aims to provide an on-line and real-time checking means for a moisture meter on a tobacco shred production line so as to prevent tobacco shred quality accidents caused by instability of equipment.
Description
The application is as follows: 202010662317.7, title of the invention: the invention discloses a divisional application of an on-line moisture meter calibration system in a tobacco shred making link.
Technical Field
The invention relates to the tobacco industry, in particular to the field of on-line moisture meter calibration in a cigarette tobacco shred making link, and particularly relates to an on-line moisture meter calibration method in a cigarette tobacco shred making link.
Background
In the tobacco production process, the tobacco shred production process is a very important link, and is a process for making the tobacco leaves into qualified tobacco shreds gradually through various processing procedures according to the physicochemical characteristics of the tobacco leaf raw materials and a certain program. In the cigarette production process, the process flow of the tobacco shred manufacturing is longest, the working procedures are most complicated, and the equipment types are most. The production operation of the existing silk-making workshop is in a production line type, and the existing silk-making workshop comprises key equipment such as a vacuum moisture regaining machine, a loosening moisture regaining machine, a temporary storage cabinet, a feeding moisture regaining machine, a hot air leaf moistening machine, a filament cutter, a silk dryer and the like.
The key control index of the cigarette shred manufacturing link is the control of tobacco shred moisture, the production is organized according to whether the tobacco shred moisture is qualified or not in each production link, and the moisture meter is the only equipment gateway for detecting the moisture in online production, so the accuracy of the moisture meter is particularly important. The other processes except tobacco leaf shredding all comprise a plurality of thinning moisture control links, each moisture control link is provided with a moisture meter, and the number of the moisture meters related to the whole process is more than 30. The detection accuracy of any moisture meter directly determines the product quality of the cut tobacco.
The traditional control method of the moisture meter is to regularly perform oven comparison experiment detection on each using channel of the moisture meter, and the oven experiment time is 1 hour each time. And if the deviation exceeding the required range occurs between the detection value of the moisture meter and the experimental value of the oven, adjusting the moisture meter by taking the experimental value of the oven as a standard. However, the number of the field moisture meters is large, and a single moisture meter simultaneously comprises more than 8 detection channels, so that the regular detection interval time of the moisture meters is long, careless omission easily occurs in large data volume manual analysis and screening, and the real-time accuracy of moisture meter detection is difficult to ensure.
Publication No.: the invention application of CN110567836A discloses a method and a system for quickly checking and measuring an online moisture meter of cut tobacco. The method comprises the steps of measuring the water content of the cut tobacco of each grade under set humidity through a drying method, and forming a cut tobacco water content corresponding table; the cut tobacco of each brand is preset in a corresponding constant humidity check box independently; acquiring a current tobacco shred mark to be produced on a production line, and taking tobacco shreds in a constant humidity checking box corresponding to the current tobacco shred mark as a checking sample of a moisture meter; acquiring a current moisture detection value detected by the moisture meter on the check sample, and looking up a table according to the tobacco shred moisture correspondence table to obtain a moisture look-up table value corresponding to the current tobacco shred brand; and checking the measured value of the moisture meter according to the moisture look-up table value and the current moisture detection value. The invention can improve the production efficiency of the tobacco shred processing process and reduce the production cost.
The moisture meter calibration system disclosed in the above document has hysteresis, does not have the functions of predicting and early warning material moisture, cannot detect the accuracy of the moisture meter on line and in real time, and can find out the abnormal condition of the moisture meter in time. Because the online tobacco shred moisture meter is an infrared ray type detection device, a key part light source and a filter of the online tobacco shred moisture meter are fragile parts, and if the abnormal condition of the moisture meter cannot be found in time, the device is unstable, so that the tobacco shred quality accident can be caused.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides an on-line moisture meter calibration method for a tobacco shred making link.
The invention aims to provide an on-line and real-time checking means for a moisture meter on a tobacco shred production line so as to prevent tobacco shred quality accidents caused by instability of equipment.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the on-line moisture meter calibration system for the cigarette tobacco shred making link comprises an information management system, wherein historical production data are stored in the information management system, the historical production data comprise historical batch parameters, and the system further comprises a calibration device which is in communication connection with the information management system
The moisture meter setting module is used for setting a moisture meter at the front end of each process of the silk production line and defining each moisture meter in sections;
the modeling module is used for establishing a moisture meter calibration model in sections according to the definition result;
the moisture prediction module is used for performing real-time sectional prediction on the moisture of the material according to the moisture meter calibration models and in combination with historical batch parameters;
and the early warning module is used for comparing and analyzing the predicted value and the measured value and carrying out early warning and display on a moisture meter with the predicted value exceeding the material moisture deviation requirement.
As the improvement of the technical scheme, the moisture meter setting module sets the moisture meters at the front ends of the procedures of loosening and dampening, temporary storage cabinet, moistening and feeding, premixing cabinet, hot air moistening, shredding and shred drying on the shred production line, and defines each moisture meter:
a first stage: comprises a moisture meter for the stage of the tobacco leaf coming material to the loosening and moisture regaining outlet;
and (2) second stage: a moisture meter comprising a stage from a leaf moistening feed inlet to a leaf moistening feed outlet;
and (3) three stages: a moisture meter which is arranged from a leaf moistening feeding outlet to a hot air leaf moistening outlet;
and a fourth stage: comprises a moisture meter from a loosening and conditioning inlet to a cut tobacco drying inlet.
As an improvement of the technical scheme, the modeling module comprises a loose moisture regaining instrument calibration model, a leaf moistening and feeding moisture meter calibration model and a hot air leaf moistening moisture meter calibration model which are established in a segmented mode.
As an improvement of the technical scheme, the loose moisture regaining instrument calibration model is a multiple regression model established by taking the water content at the loose moisture regaining inlet, the total water pumping amount, the steam opening compensation amount, the time from vacuum moisture regaining to loose moisture regaining as influence factors and the water content at the loose moisture regaining outlet as a dependent variable.
As an improvement of the technical scheme, the verification model of the moistening leaf feeding moisture meter is a neural network model established by taking moistening leaf feeding inlet moisture as input, moistening leaf feeding outlet moisture as output, and taking the storage time of a temporary storage cabinet, the compensation steam opening degree and the moistening leaf feeding and moisture discharging opening degree as influence factors.
As an improvement of the technical scheme, the hot air leaf moistening moisture meter calibration model is a neural network model established by taking hot air leaf moistening inlet moisture as input and hot air leaf moistening outlet moisture as output, and taking hot air leaf moistening compensating steam opening as an influence factor through a premixing cabinet.
As an improvement of the technical scheme, the early warning module is provided with the predicted moisture deviation requirement of each section of moisture meter, namely an early warning threshold value, wherein
A first stage: the moisture deviation requirement of the loosening and moisture regaining instrument is +/-1%;
and (2) second stage: the moisture deviation requirement of the leaf moistening and feeding moisture meter is +/-1 percent;
and (3) three stages: the moisture deviation requirement of the hot air leaf moistening moisture meter is +/-0.5%.
As an improvement of the technical scheme, a feedback loop is arranged between the modeling module and the early warning module.
The invention also provides an on-line moisture meter calibration method for the tobacco shred making link, which is applied to any one of the on-line moisture meter calibration systems for the tobacco shred making link and comprises the following steps:
step one, data acquisition
The data source is as follows: corresponding historical production data in the silk-making line information management system;
step two, setting a production line moisture meter
Setting a moisture meter setting module at the front end of the loosening and dampening, temporary storage cabinet, leaf moistening and feeding, premixing cabinet, hot air leaf moistening, shredding and shred drying processes of a shred production line, and defining each moisture meter;
step three, establishing a model
Establishing a loose moisture regaining instrument calibration model, a leaf moistening and feeding moisture instrument calibration model and a hot air leaf moistening moisture instrument calibration model in sections through a modeling module;
wherein:
the loose conditioning moisture meter calibration model is a multiple regression model established by taking the water content at a loose conditioning inlet, the total water pumping amount, the compensated steam opening degree and the time from vacuum conditioning to loose conditioning as influence factors and taking the water at a loose conditioning outlet as a dependent variable;
the verification model of the leaf moistening feeding moisture meter is a neural network model established by taking leaf moistening feeding inlet moisture as input, leaf moistening feeding outlet moisture as output, and taking temporary storage cabinet storage time, compensation steam opening and leaf moistening feeding and moisture removing opening as influence factors;
the hot air leaf moistening moisture meter calibration model is a neural network model established by taking hot air leaf moistening inlet moisture as input and hot air leaf moistening outlet moisture as output, and taking hot air leaf moistening compensation steam opening as an influence factor through a premixing cabinet;
step four, predicting the moisture
According to the calibration model of each section of the moisture meter in the step three, real-time segmented prediction is carried out on the moisture of the material by combining historical batch parameters;
step five, abnormity early warning
And comparing and analyzing the predicted value and the measured value of each section of the moisture meter based on the fourth step, and early warning and displaying the moisture meter with the predicted value exceeding the material moisture deviation requirement.
The invention has the following beneficial effects:
compared with the prior art, the method has the advantages that:
(1) the on-line moisture meter calibration system and the method can predict the moisture of the material in each stage in real time according to the historical batch parameters (process parameters, production parameters and environmental parameters) of the silk production line, carry out on-line real-time calibration on the accuracy of each moisture meter and know the running state of each moisture meter in time;
(2) the method carries out real-time and sectional prediction on the moisture of the material on the basis of each prediction model through the moisture prediction module, and can improve the prediction accuracy by means of a feedback loop real-time optimization model, so that the prediction model has self-learning optimization capability;
(3) according to the invention, the early warning module is used for carrying out data analysis, online comparison analysis is carried out on the predicted value and the measured value, early warning and display are carried out on the moisture meter with the predicted value exceeding the material moisture deviation requirement, potential process quality accidents are preprocessed in time, and the quality and the production efficiency of the silk making process can be effectively improved.
Drawings
The invention will be further described with reference to the accompanying drawings and specific embodiments,
FIG. 1 is a schematic view of the modular construction of the present invention;
FIG. 2 is a schematic structural view of a moisture meter arranged on a wire manufacturing production line by a moisture meter setting module according to the invention;
FIG. 3 is a schematic diagram of the prediction result of the moisture at the outlet of loose moist leaves of a loose moisture regaining instrument calibration model;
FIG. 4 is a schematic diagram of the prediction error of the loose moist leaf outlet moisture of the loose moisture regain instrument calibration model;
FIG. 5 is a schematic diagram of the predicted result of the moisture at the leaf wetting feed outlet of the leaf wetting feed moisture meter calibration model;
FIG. 6 is a schematic diagram of the predicted error of the leaf moistening feed outlet moisture for a leaf moistening feed moisture meter calibration model;
FIG. 7 is a schematic diagram showing the predicted result of moisture at the leaf-moistening feed outlet of the hot air leaf-moistening moisture meter calibration model;
FIG. 8 is a schematic diagram showing the prediction error of the moisture at the leaf-moistening feed outlet of the verification model of the hot air leaf-moistening moisture meter.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the present invention, unless otherwise expressly specified or limited, the terms "disposed," "mounted," "connected," and "fixed" are to be construed broadly and may, for example, be fixedly connected or detachably connected; may be a mechanical connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Example 1
Referring to fig. 1, an on-line moisture meter calibration system for tobacco shred production links comprises an information management system, wherein historical production data are stored in the information management system, the historical production data comprise historical batch parameters, the historical batch parameters specifically refer to process parameters, production parameters, environmental parameters and the like of each process link of a shred production line, and a sheet shred dryer of a shred drying procedure is taken as an example:
the technological parameters comprise the moisture at the outlet of the sheet cut tobacco dryer, the moisture at the inlet of the sheet cut tobacco dryer and the temperature of the roller of the sheet cut tobacco dryer; wherein outlet/inlet moisture is a key indicator of the system;
the production parameters comprise the opening degree of a steam film valve of the sheet cut tobacco dryer, the hot air temperature of the sheet cut tobacco dryer, the moisture discharge opening degree of the sheet cut tobacco dryer, the frequency of an underground fan of the sheet cut tobacco dryer, HT steam and the temperature of a sheet platform;
the environmental parameter includes ambient humidity.
The historical batch parameters of other process links are similar to the cut tobacco drying process.
The system also includes a communication interface with the information management system
The moisture meter setting module is used for setting a moisture meter at the front end of each process of the silk production line and carrying out sectional self-definition on each moisture meter;
the modeling module is used for establishing a moisture meter calibration model in a segmented manner according to the definition result;
the moisture prediction module is used for performing real-time dynamic sectional prediction on the moisture of the material by combining historical batch parameters of corresponding processes according to the calibration models of the moisture meters;
and the early warning module is used for comparing and analyzing the predicted value and the measured value and carrying out early warning and display on a moisture meter with the predicted value exceeding the material moisture deviation requirement.
Referring to fig. 2, the moisture meter setting module sets the moisture meters at the front end of the procedures of loosening and dampening, temporary storage cabinet, moistening and feeding leaves, premixing cabinet, moistening leaves with hot air, shredding and drying shreds on the shred production line, and the moisture meters are defined as follows:
a first stage: comprises a moisture meter for the stage of the tobacco leaf coming material to the loosening and moisture regaining outlet;
and (2) second stage: a moisture meter comprising a stage from a leaf moistening feed inlet to a leaf moistening feed outlet;
and (3) three stages: a moisture meter which is arranged from a leaf moistening feeding outlet to a hot air leaf moistening outlet;
and a fourth stage: comprises a moisture meter from a loosening and conditioning inlet to a cut tobacco drying inlet.
The modeling module is based on massive historical data collected in the information management system, by using the data model concept for reference, mining and analyzing historical production data, integrating operation methods such as a multiple regression analysis algorithm, a neural network algorithm and the like, and establishing a loose moisture regain moisture meter calibration model, a leaf moistening and charging moisture meter calibration model and a hot air leaf moistening moisture meter calibration model in sections.
Wherein:
the loose moisture regaining tester calibration model is a multiple regression model established by taking the loose moisture regaining inlet moisture (X1), the total water pumping amount (X3), the compensation steam opening (X4), the time (X5) from vacuum moisture regaining to loose moisture regaining as influence factors and the loose moisture regaining outlet moisture (X2) as dependent variables.
The coefficients of the various influencing factors are shown in table 1:
table 1: influence factor coefficient of loose moisture regaining moisture meter calibration model
Establishing a regression equation according to each influence factor coefficient:
y (loose moisture regain outlet moisture X2) ═ 2.802X1+0.351X3-0.024X4+0.003X5-0.922
The equation goodness of fit is 0.903.
The water content of the corresponding process is predicted by using the formula, and the results are shown in fig. 3 and 4.
As can be seen from the above figure, the prediction curve and the production curve have high goodness of fit, and the average value of the absolute values of the prediction errors is only 0.24 percent according to the calculation of the prediction errors, so that the tolerance requirement of the water content of the loose moist leaves outlet (the set value is +/-0.5 percent) can be met, and the judgment requirement of the water content of less than +/-0.3 percent on excellent prediction values is met.
Wherein:
the leaf moistening feeding moisture meter calibration model is a neural network model established by taking leaf moistening feeding inlet moisture as input, leaf moistening feeding outlet moisture as output, temporary storage cabinet storage time, compensation steam opening and leaf moistening feeding and moisture discharging opening as influence factors.
The coefficients of the various influencing factors are shown in Table 2:
table 2: neural network structure information of leaf moistening and feeding moisture meter calibration model
| PointType | X | | V4 |
| scale | |||
| 0 | 3.3333 | Deviation of | |
| |
0 | 2.6667 | |
| scale | |||
| 0 | 2 | | |
| scale | |||
| 0 | 1.3333 | | |
| scale | |||
| 0 | 0.6667 | V17 | |
| scale | 1 | 2.6667 | Deviation of |
| scale | 1 | 1.3333 | Hidden layer activation: activating a hyperbolic tangent output layer: identity equation |
| scale | 2 | 2 | V22 |
In table 2: v17-temporary storage cabinet storage time; v20-wetting leaf feed inlet moisture; v22-moisture at the leaf moistening feed outlet; v24-wetting the leaves and adding materials to compensate the steam opening; v26-wetting leaf feeding and moisture discharging opening degree.
The importance of each of the above influencing factors is shown in Table 3:
table 3: importance of various influence factors of moistening leaf feeding moisture meter calibration model
| Nodes | Importance | Importance | V22 |
| V26 | 0.104 | 0.104 | 0.104 |
| V17 | 0.1651 | 0.1651 | 0.1651 |
| V24 | 0.2469 | 0.2469 | 0.2469 |
| V20 | 0.484 | 0.484 | 0.484 |
And (3) constructing a verification model of the leaf moistening and charging moisture meter by using a neural network model, and predicting moisture of corresponding procedures, wherein the results are shown in fig. 5 and 6.
As can be seen from the above figure, the mean value of the moisture at the feeding outlet of the moistening leaves is predicted to be 22.84, the maximum predicted value is 23.15, the minimum predicted value is 22.50 and the mean value of the prediction error is 0.20% through a neural network model.
Wherein:
the hot air leaf moistening moisture meter calibration model is a neural network model established by taking hot air leaf moistening inlet moisture as input and hot air leaf moistening outlet moisture as output, and taking hot air leaf moistening compensating steam opening as an influence factor through a premixing cabinet.
The various impact factor coefficients are shown in table 4:
table 4: neural network structure information of hot air leaf moistening moisture meter calibration model
| PointType | X | | V4 |
| scale | |||
| 0 | 2.4 | Deviation of | |
| |
0 | 1.8 | |
| scale | |||
| 0 | 1.2 | | |
| scale | |||
| 0 | 0.6 | V32 | |
| scale | 1 | 2.4 | Deviation of |
| scale | 1 | 1.8 | Hidden layer activation: activating a hyperbolic tangent output layer: identity equation |
| scale | 1 | 1.2 | Hidden layer activation: activating a hyperbolic tangent output layer: identity equation |
| scale | 1 | 0.6 | Hidden layer activation: activating a hyperbolic tangent output layer: identity equation |
| scale | 2 | 1.5 | V36 |
In table 4: v32-premix cabinet storage duration; v34-moistening leaf with hot air; v36-moisture at the outlet of hot air leaf moistening; v38-hot air wetting leaf to compensate the steam opening.
The importance of each of the above influencing factors is shown in Table 5:
table 5: importance of various influence factors of hot air leaf moistening moisture meter calibration model
| Nodes | Importance | Importance | V36 |
| V38 | 0.2442 | 0.2442 | 0.2442 |
| V32 | 0.3365 | 0.3365 | 0.3365 |
| V34 | 0.4193 | 0.4193 | 0.4193 |
A hot air leaf moistening moisture meter calibration model is constructed by utilizing a neural network model, moisture prediction of corresponding procedures is carried out, and the results are shown in figures 7 and 8.
From the above figure, the mean value of the water at the outlet of the hot air leaf moistening is predicted to be 22.35, the maximum predicted value is 22.46, the minimum predicted value is 22.22 and the mean value of the prediction error is 0.10% through the neural network model.
The early warning module is provided with the predicted moisture deviation requirement of each section of moisture meter, namely an early warning threshold value, wherein
A first stage: the moisture deviation requirement of the loosening and moisture regaining instrument is +/-1%;
and (2) second stage: the moisture deviation requirement of the leaf moistening and feeding moisture meter is +/-1 percent;
and (3) three stages: the moisture deviation requirement of the hot air leaf moistening moisture meter is +/-0.5%.
The early warning module compares and analyzes the predicted value with the measured value of each section of the moisture meter (and the historical production data of the same section, such as the average value of the inlet moisture and the standard value of the inlet moisture), and performs early warning and display on the moisture meter of which the predicted value exceeds the requirement of the deviation of the material moisture (deviation is equal to (measured value-predicted value)/predicted value) by combining the early warning threshold value so as to remind a worker to perform timely preprocessing, such as adjusting process parameters, overhauling the corresponding moisture meter and the like.
The online moisture meter calibration system can predict the material moisture of each procedure outlet in real time according to the historical production data of the silk making production line, perform online and real-time calibration on the accuracy of each moisture meter, know the running state of each moisture meter in time, and further preprocess potential process quality accidents in time, and can effectively improve the silk making process quality and the production efficiency.
In addition, a feedback loop is arranged between the modeling module and the early warning module.
The method carries out real-time and sectional prediction on the moisture of the material on the basis of each prediction model through the moisture prediction module, and can also optimize the prediction model in real time by means of a feedback loop so as to improve the prediction accuracy and enable the prediction model to have self-learning optimization capability.
Example 2
The method for verifying the on-line moisture meter in the tobacco shred making link is applied to the system for verifying the on-line moisture meter in the tobacco shred making link in the embodiment 1, and comprises the following steps of:
step one, data acquisition
The data source is as follows: corresponding historical production data in the silk-making line information management system;
step two, setting a production line moisture meter
Setting a moisture meter setting module at the front end of the loosening and dampening, temporary storage cabinet, leaf moistening and feeding, premixing cabinet, hot air leaf moistening, shredding and shred drying processes of a shred production line, and defining each moisture meter;
step three, establishing a model
Establishing a loose moisture regaining instrument calibration model, a leaf moistening and feeding moisture instrument calibration model and a hot air leaf moistening moisture instrument calibration model in sections through a modeling module;
wherein:
the loose conditioning moisture meter calibration model is a multiple regression model established by taking the water content at a loose conditioning inlet, the total water pumping amount, the compensated steam opening degree and the time from vacuum conditioning to loose conditioning as influence factors and taking the water at a loose conditioning outlet as a dependent variable;
the verification model of the leaf moistening feeding moisture meter is a neural network model established by taking leaf moistening feeding inlet moisture as input, leaf moistening feeding outlet moisture as output, and taking temporary storage cabinet storage time, compensation steam opening and leaf moistening feeding and moisture removing opening as influence factors;
the hot air leaf moistening moisture meter calibration model is a neural network model established by taking hot air leaf moistening inlet moisture as input and hot air leaf moistening outlet moisture as output, and taking hot air leaf moistening compensation steam opening as an influence factor through a premixing cabinet;
step four, establishing a moisture prediction module
According to the calibration model of each section of the moisture meter in the step three, real-time segmented prediction is carried out on the moisture of the material by combining historical batch parameters;
step five, establishing an early warning module
And comparing and analyzing the predicted value and the measured value of each section of the moisture meter based on the fourth step, and early warning and displaying the moisture meter with the predicted value exceeding the material moisture deviation requirement.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (6)
1. The on-line moisture meter calibration method for the tobacco shred production link is characterized by comprising the following steps of: comprises the following steps
Step one, data acquisition
The data source is as follows: corresponding historical production data in the production line information management system, wherein the historical production data comprises historical batch parameters;
step two, setting a production line moisture meter
Setting a moisture meter setting module at the front end of the loosening and dampening, temporary storage cabinet, leaf moistening and feeding, premixing cabinet, hot air leaf moistening, shredding and shred drying processes of a shred production line, and defining each moisture meter;
step three, establishing a model
Establishing a loose moisture regaining instrument calibration model, a leaf moistening and feeding moisture instrument calibration model and a hot air leaf moistening moisture instrument calibration model in sections through a modeling module;
step four, predicting the moisture
According to the calibration model of each section of the moisture meter in the step three, real-time segmented prediction is carried out on the moisture of the material by combining historical batch parameters;
step five, abnormity early warning
And comparing and analyzing the predicted value and the measured value of each section of the moisture meter based on the fourth step, and early warning and displaying the moisture meter with the predicted value exceeding the material moisture deviation requirement.
2. The on-line moisture meter calibration method for the cigarette tobacco shred making link according to claim 1, characterized by comprising the following steps: defining each moisture meter in the second step:
a first stage: comprises a moisture meter for the stage of the tobacco leaf coming material to the loosening and moisture regaining outlet;
and (2) second stage: a moisture meter comprising a stage from a leaf moistening feed inlet to a leaf moistening feed outlet;
and (3) three stages: a moisture meter which is arranged from a leaf moistening feeding outlet to a hot air leaf moistening outlet;
and a fourth stage: comprises a moisture meter from a loosening and conditioning inlet to a cut tobacco drying inlet.
3. The on-line moisture meter calibration method for the cigarette tobacco shred making link according to claim 1, characterized by comprising the following steps: the loose moisture regaining instrument calibration model is a multiple regression model established by taking the water content at the loose moisture regaining inlet, the total water pumping amount, the compensated steam opening degree and the time from vacuum moisture regaining to loose moisture regaining as influence factors and taking the water content at the loose moisture regaining outlet as a dependent variable.
4. The on-line moisture meter calibration method for the cigarette tobacco shred making link according to claim 1, characterized by comprising the following steps: the moistening leaf feeding moisture meter calibration model is a neural network model established by taking moistening leaf feeding inlet moisture as input, moistening leaf feeding outlet moisture as output, and temporary storage cabinet storage time, compensation steam opening and moistening leaf feeding and moisture discharging opening as influence factors.
5. The on-line moisture meter calibration method for the cigarette tobacco shred making link according to claim 1, characterized by comprising the following steps: the hot air leaf moistening moisture meter calibration model is a neural network model established by taking hot air leaf moistening inlet moisture as input and hot air leaf moistening outlet moisture as output, and taking hot air leaf moistening compensating steam opening as an influence factor through a premixing cabinet.
6. The on-line moisture meter calibration method for the cigarette tobacco shred making link according to claim 1, characterized by comprising the following steps: and fifthly, meeting the moisture deviation requirement of each section of moisture meter, namely setting an early warning threshold value as follows:
a first stage: the moisture deviation requirement of the loosening and moisture regaining instrument is +/-1%;
and (2) second stage: the moisture deviation requirement of a leaf moistening and feeding moisture meter is +/-1 percent;
and (3) three stages: the moisture deviation requirement of the hot air leaf moistening moisture meter is +/-0.5%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210276230.5A CN114794521B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration method for tobacco shred making link |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210276230.5A CN114794521B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration method for tobacco shred making link |
| CN202010662317.7A CN112021641B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration system for tobacco shred making link |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010662317.7A Division CN112021641B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration system for tobacco shred making link |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114794521A true CN114794521A (en) | 2022-07-29 |
| CN114794521B CN114794521B (en) | 2023-02-03 |
Family
ID=73579032
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210276230.5A Active CN114794521B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration method for tobacco shred making link |
| CN202010662317.7A Active CN112021641B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration system for tobacco shred making link |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010662317.7A Active CN112021641B (en) | 2020-07-10 | 2020-07-10 | On-line moisture meter calibration system for tobacco shred making link |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114794521B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115517392A (en) * | 2022-08-29 | 2022-12-27 | 杭州安脉盛智能技术有限公司 | Method for predicting outlet moisture of leaf segments of cigarette cut tobacco making line |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673144A (en) * | 2021-07-13 | 2021-11-19 | 上海烟草集团有限责任公司 | Prediction system and method for data of tobacco stem drying equipment |
| CN114271523A (en) * | 2021-12-30 | 2022-04-05 | 贵州中烟工业有限责任公司 | Silk making system |
| CN114601190B (en) * | 2022-03-21 | 2023-04-11 | 红塔烟草(集团)有限责任公司 | Method for regulating and controlling drying moisture of slice threads |
| CN114642268B (en) * | 2022-03-31 | 2023-05-16 | 张家口卷烟厂有限责任公司 | Intelligent control system and method for drying silk based on volatile moisture content |
| CN114766709A (en) * | 2022-04-22 | 2022-07-22 | 红云红河烟草(集团)有限责任公司 | Error-preventing control method suitable for moisture meter in wire making workshop and moisture meter |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3929155A1 (en) * | 1989-09-02 | 1991-03-14 | Reemtsma H F & Ph | METHOD AND DEVICE FOR DETERMINING THE FILLABILITY OF TOBACCO AND THE HARDNESS OF CIGARETTES |
| CN105341985A (en) * | 2015-12-10 | 2016-02-24 | 龙岩烟草工业有限责任公司 | Moisture content control method and system of inlet cut tobaccos of cut-tobacco drier |
| CN106370554A (en) * | 2016-12-09 | 2017-02-01 | 重庆中烟工业有限责任公司 | Tobacco-moisture-content detecting and online-moisture-meter monitoring method |
| CN108652066A (en) * | 2018-05-31 | 2018-10-16 | 福建中烟工业有限责任公司 | The water feeding method of loosening and gaining moisture process and the device for predicting the process amount of water |
| CN108720069A (en) * | 2018-06-20 | 2018-11-02 | 福建中烟工业有限责任公司 | The method of dry pipe tobacco and the device of prediction outlet moisture content of cut tobaccos |
| CN108871542A (en) * | 2018-09-21 | 2018-11-23 | 龙岩烟草工业有限责任公司 | For monitoring the methods, devices and systems of weighing belt accuracy |
| 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 |
| CN110973680A (en) * | 2019-10-17 | 2020-04-10 | 红塔烟草(集团)有限责任公司 | Method and system for stabilizing processing strength of drum-type cut tobacco drying machine |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5215744B2 (en) * | 2008-06-13 | 2013-06-19 | 株式会社エー・アンド・デイ | Moisture meter |
| CN108294352B (en) * | 2017-01-11 | 2020-12-29 | 红塔烟草(集团)有限责任公司 | Material moisture overrun early warning control system of roller cut-tobacco drier |
-
2020
- 2020-07-10 CN CN202210276230.5A patent/CN114794521B/en active Active
- 2020-07-10 CN CN202010662317.7A patent/CN112021641B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3929155A1 (en) * | 1989-09-02 | 1991-03-14 | Reemtsma H F & Ph | METHOD AND DEVICE FOR DETERMINING THE FILLABILITY OF TOBACCO AND THE HARDNESS OF CIGARETTES |
| CN105341985A (en) * | 2015-12-10 | 2016-02-24 | 龙岩烟草工业有限责任公司 | Moisture content control method and system of inlet cut tobaccos of cut-tobacco drier |
| CN106370554A (en) * | 2016-12-09 | 2017-02-01 | 重庆中烟工业有限责任公司 | Tobacco-moisture-content detecting and online-moisture-meter monitoring method |
| CN108652066A (en) * | 2018-05-31 | 2018-10-16 | 福建中烟工业有限责任公司 | The water feeding method of loosening and gaining moisture process and the device for predicting the process amount of water |
| CN108720069A (en) * | 2018-06-20 | 2018-11-02 | 福建中烟工业有限责任公司 | The method of dry pipe tobacco and the device of prediction outlet moisture content of cut tobaccos |
| CN108871542A (en) * | 2018-09-21 | 2018-11-23 | 龙岩烟草工业有限责任公司 | For monitoring the methods, devices and systems of weighing belt accuracy |
| CN110973680A (en) * | 2019-10-17 | 2020-04-10 | 红塔烟草(集团)有限责任公司 | Method and system for stabilizing processing strength of drum-type cut tobacco drying machine |
| 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 (1)
| Title |
|---|
| 钟文焱等: "基于多因素分析的烘丝机入口含水率预测模型的建立与应用", 《烟草科技》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115517392A (en) * | 2022-08-29 | 2022-12-27 | 杭州安脉盛智能技术有限公司 | Method for predicting outlet moisture of leaf segments of cigarette cut tobacco making line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112021641A (en) | 2020-12-04 |
| CN112021641B (en) | 2022-04-29 |
| CN114794521B (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114794521B (en) | On-line moisture meter calibration method for tobacco shred making link | |
| CN112021626B (en) | Intelligent control system and method for tobacco shred making link | |
| CN112036701B (en) | Technological parameter optimization method for multi-process industrial production process | |
| CN112034095B (en) | System and method for analyzing structure of cut tobacco after online drying | |
| CN109222208B (en) | Cut tobacco making process analysis optimization method and system oriented to cigarette production index control | |
| US11576420B2 (en) | Intelligent control system and method of thin plate drier for cut tobacco | |
| CN113017132A (en) | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction | |
| CN112132316A (en) | System and method for monitoring abnormality of on-line equipment in silk making link | |
| CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
| CN114463954B (en) | Combustible gas monitoring and early warning system and method based on Internet of things | |
| CN114510098B (en) | Production environment regulation and control method and system | |
| CN112099393A (en) | System and method for monitoring operation and judging abnormality of cigarette machine equipment | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN115099457A (en) | On-line predicting and analyzing system for tobacco shred structure | |
| CN111275331A (en) | Monitoring method and device for production system | |
| CN115251445A (en) | Method for controlling moisture content of tobacco leaves at outlet of loosening and conditioning machine | |
| KR20000048928A (en) | A process and device for identification or pre-caculation of parameters of a time-variant industrial process | |
| CN115829335A (en) | Production line execution risk assessment system for aluminum profile machining | |
| CN115579876A (en) | Method and system for identifying fan power characteristic curve | |
| CN118076929A (en) | Monitoring production of material boards, in particular engineered wood boards, in particular using self-organizing maps | |
| CN113642251B (en) | Data analysis and prediction method and system for building ceramic spray powder preparation quality | |
| CN113379278B (en) | Method for evaluating quality of whole process of silk making batch | |
| Fonseca et al. | Fuzzy short-run control charts | |
| CN118052451A (en) | Method and device for predicting water content quality of cut tobacco at outlet of cut tobacco dryer | |
| CN116019248B (en) | Loose leaf-wetting outlet material temperature control method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |