CN117441924A - Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line - Google Patents
Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line Download PDFInfo
- Publication number
- CN117441924A CN117441924A CN202311552409.XA CN202311552409A CN117441924A CN 117441924 A CN117441924 A CN 117441924A CN 202311552409 A CN202311552409 A CN 202311552409A CN 117441924 A CN117441924 A CN 117441924A
- Authority
- CN
- China
- Prior art keywords
- data
- cut tobacco
- value
- moisture
- outlet
- 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
- 241000208125 Nicotiana Species 0.000 title claims abstract description 152
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 152
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000001105 regulatory effect Effects 0.000 title claims abstract description 9
- 230000001276 controlling effect Effects 0.000 title description 3
- 239000012467 final product Substances 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000010606 normalization Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000010923 batch production Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000007664 blowing Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000000047 product Substances 0.000 claims description 3
- 238000011958 production data acquisition Methods 0.000 claims description 3
- 238000001035 drying Methods 0.000 abstract description 5
- 206010063385 Intellectualisation Diseases 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- A24B3/10—Roasting or cooling 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
- 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
- A24B3/00—Preparing tobacco in the factory
- A24B3/16—Classifying or aligning leaves
-
- 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
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses a method for setting and regulating a target value of outlet moisture of a cut tobacco drying machine of a cut tobacco production line, which comprises the following steps of: acquiring a plurality of groups of production data of the current batch in real time, wherein the production data comprise cut tobacco moisture at the outlet of a cut tobacco dryer, cut tobacco moisture at the outlet of a winnowing machine, moisture of final finished cut tobacco, environmental temperature/humidity of the cut tobacco dryer and environmental temperature/humidity after winnowing; preprocessing data, eliminating useless data and extracting effective data; extracting data characteristic values from the effective data, wherein the data characteristic values comprise; inputting the cut tobacco machine data characteristic value and the final product data characteristic value of the data characteristic value into a first prediction model by the cut tobacco machine data characteristic value and the cut tobacco moisture average value of an outlet of the air separator, and comparing the output data of the first prediction model with a preset cut tobacco machine outlet cut tobacco moisture prediction value until reaching a target value; the method can realize the intellectualization of the outlet moisture target value setting of the cut tobacco dryer to a certain extent, and improve the rationality of the cut tobacco drying moisture target value setting.
Description
Technical Field
The invention relates to a method for setting and regulating a target value of outlet moisture of a cut tobacco production line cut tobacco dryer, which is based on an extreme learning machine.
Background
The tobacco shred drying is the last and most important process in the tobacco shred making process, and the water content of the tobacco shreds at the outlet can reach the specified quality index, so that the quality of the tobacco shreds is directly affected. In the tobacco shred production process, the change of the moisture content of the tobacco shreds from the tobacco shred drying outlet to the finished tobacco shred outlet has uncertainty and uncontrollability, so that the target value setting of the moisture content of the tobacco shreds at the tobacco shred drying outlet directly influences whether the moisture content of the finished tobacco shreds reaches the standard. The target value of the current cut tobacco moisture content at the cut tobacco baking outlet is mainly set by depending on experience of operators, is difficult to quantitatively adjust according to various factors such as weather change, and has low automation and intelligent degree. Therefore, it is necessary to design a method for setting and adjusting the target value of the moisture content of cut tobacco at the cut tobacco outlet according to environmental changes and other factors.
Disclosure of Invention
The invention aims to provide a cut tobacco machine outlet moisture target value setting and regulating method for a cut tobacco production line, which is a cut tobacco machine outlet moisture target value setting and regulating method based on an extreme learning machine, and the cut tobacco machine outlet moisture target value is set through the Extreme Learning Machine (ELM), so that the method has the advantages of high accuracy and high calculation speed, meets the requirement of strong real-time in the cut tobacco production process, and can effectively realize intelligent setting of the cut tobacco machine outlet moisture target value.
In order to achieve the above object, the technical scheme of the present invention is as follows:
a method for setting and regulating an outlet moisture target value of a cut tobacco production line cut tobacco dryer comprises the steps that the cut tobacco production line cut tobacco dryer is followed by a winnowing machine, a control server is arranged on the production line, and historical production data of the production line are stored in the control server; the method comprises the following steps:
step 1: acquiring a plurality of groups of production data of the current batch in real time, wherein the production data comprise cut tobacco moisture at the outlet of a cut tobacco dryer, cut tobacco moisture at the outlet of a winnowing machine, moisture of final finished cut tobacco, environmental temperature/humidity of the cut tobacco dryer and environmental temperature/humidity after winnowing;
step 2: preprocessing data, eliminating useless data and extracting effective data;
step 3: extracting data characteristic values from the effective data, wherein the data characteristic values comprise; cut-tobacco dryer data characteristic value and final product data characteristic value, wherein:
cut-tobacco dryer data characteristic value: is the average value of effective data of the temperature/humidity of the tobacco shred at the outlet of the cut tobacco dryer;
final product data characteristic value: is the average value of the effective data of the moisture of the tobacco shreds of the final finished product;
step 4: inputting a cut tobacco machine data characteristic value of the data characteristic value and a cut tobacco moisture average value of an outlet of the air separator into a first prediction model, and comparing output data of the first prediction model with a preset cut tobacco machine outlet cut tobacco moisture prediction value;
step 5: adjusting the temperature control parameter of the cut tobacco dryer according to the comparison result of the step 4, and returning to the step 1 until the comparison result is smaller than the set threshold value;
step 6: whether the current batch production is finished or not is: storing the current value of the tobacco shred moisture at the outlet of the final cut tobacco dryer into a control server, and ending the production data acquisition; otherwise, returning to the step 1;
wherein:
the first predictive model is a neural network model;
the tobacco shred moisture predicted value at the outlet of the tobacco dryer is obtained by obtaining a tobacco shred data characteristic value of a plurality of batches of qualified production data and a tobacco shred moisture average value at the outlet of the air separator, inputting the tobacco shred data characteristic value and the tobacco shred moisture average value into a first prediction model for training, and taking an output value obtained by training as the tobacco shred moisture predicted value at the outlet of the tobacco dryer.
The scheme is further as follows: extracting data characteristic values from the effective data, wherein the data characteristic values of the winnowing machine are average values of tobacco shred moisture at an outlet of the winnowing machine and effective data of environmental temperature/humidity after winnowing;
the method further performs after the end of step 5:
step 5.1: inputting the winnowing machine data characteristic value and the final product data characteristic value of the data characteristic value into a second prediction model, and comparing the output data of the second prediction model with a preset winnowing machine outlet tobacco shred moisture prediction value;
step 5.2: adjusting the blowing control parameters of the winnowing machine according to the comparison result in the step 5.1, and returning to the step 1 until the comparison result is smaller than a set threshold value;
in step 6, whether the current batch production is finished is: simultaneously storing the current value of the tobacco shred moisture at the outlet of the winnowing machine into a control server;
wherein:
the second predictive model is a neural network model;
the predicted value of the tobacco shred moisture at the outlet of the winnowing machine is obtained by acquiring a winnowing machine data characteristic value and a final product data characteristic value of a plurality of batches of qualified production data, inputting the winnowing machine data characteristic value and the final product data characteristic value into a second prediction model for training, and taking an output value obtained by training as the predicted value of the tobacco shred moisture at the outlet of the winnowing machine.
The scheme is further as follows: the data preprocessing comprises missing value processing, abnormal value processing, repeated value processing, data filtering and data normalization processing.
The scheme is further as follows: the normalization processing is to perform normalization processing on the effective data by adopting a normalization formula to eliminate the data dimension,
the normalization formula is:
wherein:
x is the effective data of the data;
x max is the maximum value of effective data;
x min is the minimum value of the valid data;
the results were normalized for the valid data.
The scheme is further as follows: the neural network model is an ELM machine learning algorithm model.
The beneficial effects of the invention are as follows: the outlet moisture target value of the cut tobacco drier is set through an Extreme Learning Machine (ELM), the method has the advantages of being high in accuracy and high in calculation speed, meets the requirement of strong instantaneity in the cut tobacco production process, can effectively achieve intelligent setting of the outlet moisture target value of the cut tobacco drier, can achieve intelligent setting of the outlet moisture target value of the cut tobacco to a certain extent, and improves rationality of setting of the outlet moisture target value of the cut tobacco drier.
The invention is described in detail below with reference to the drawings and examples.
Drawings
Fig. 1 is a schematic diagram of a tobacco shred production line.
Detailed Description
As shown in FIG. 1, the method for setting and controlling the target value of the outlet moisture of the cut tobacco dryer of the cut tobacco production line comprises the following steps of: the tobacco shred processing machine comprises a raw material storage leaf cabinet 1, a raw material feeding bin 2, a shredding machine 3, a feeding bin 4, an HT damping machine 5, a cut tobacco drier 6, a winnowing machine 7 and a tobacco shred storage cabinet 8, wherein each working procedure is provided with a sensor, the sensors provide working states of each working procedure, the cut tobacco drier 7 is followed by the cut tobacco drier 6 of the tobacco shred production line, a control server is arranged on the production line, and historical production data of each batch of the production line are stored in the control server; the method comprises the following steps:
step 1: acquiring a plurality of groups of production data of the current batch in real time, wherein the production data comprise cut tobacco moisture at the outlet of a cut tobacco dryer, cut tobacco moisture at the outlet of a winnowing machine, moisture of final finished cut tobacco, environmental temperature/humidity of the cut tobacco dryer and environmental temperature/humidity after winnowing;
step 2: preprocessing data, eliminating useless data and extracting effective data;
step 3: extracting data characteristic values from the effective data, wherein the data characteristic values comprise; cut-tobacco dryer data characteristic value and final product data characteristic value, wherein:
cut-tobacco dryer data characteristic value: is the average value of effective data of the temperature/humidity of the tobacco shred at the outlet of the cut tobacco dryer;
final product data characteristic value: is the average value of the effective data of the moisture of the tobacco shreds of the final finished product;
step 4: inputting a cut tobacco machine data characteristic value of the data characteristic value and a cut tobacco moisture average value of an outlet of the air separator into a first prediction model, and comparing output data of the first prediction model with a preset cut tobacco machine outlet cut tobacco moisture predicted value (target value);
step 5: adjusting the temperature control parameter of the cut tobacco dryer according to the comparison result of the step 4, and returning to the step 1 until the comparison result is smaller than the set threshold value;
step 6: whether the current batch production is finished or not is: storing the current value of the tobacco shred moisture at the outlet of the final cut tobacco dryer into a control server, and ending the production data acquisition; otherwise, returning to the step 1;
wherein:
the first predictive model is a neural network model;
the cut tobacco dryer outlet cut tobacco moisture predicted value (target value) is obtained by obtaining cut tobacco dryer data characteristic values of a plurality of batches of qualified production data and the average value of the cut tobacco moisture at the outlet of the air separator, inputting the cut tobacco data characteristic values and the average value of the cut tobacco moisture at the outlet of the air separator into a first prediction model for training, and taking an output value obtained by training as the cut tobacco dryer outlet cut tobacco moisture predicted value (target value).
In the embodiment, the data characteristic value extracted from the effective data also comprises a winnowing machine data characteristic value, wherein the winnowing machine data characteristic value is the average value of tobacco shred moisture at an outlet of the winnowing machine and effective data of environmental temperature/humidity after winnowing;
the method further performs after the end of step 5:
step 5.1: inputting the winnowing machine data characteristic value and the final product data characteristic value of the data characteristic value into a second prediction model, and comparing the output data of the second prediction model with a preset winnowing machine outlet tobacco shred moisture prediction value;
step 5.2: adjusting the blowing control parameters of the winnowing machine according to the comparison result in the step 5.1, and returning to the step 1 until the comparison result is smaller than a set threshold value;
in step 6, whether the current batch production is finished is: simultaneously storing the current value of the tobacco shred moisture at the outlet of the winnowing machine into a control server;
wherein:
the second predictive model is a neural network model;
the predicted value (target value) of the tobacco shred moisture at the outlet of the winnowing machine is obtained by acquiring a winnowing machine data characteristic value and a final product data characteristic value of a plurality of batches of qualified production data, inputting the winnowing machine data characteristic value and the final product data characteristic value into a second prediction model for training, and taking an output value obtained by training as the predicted value (target value) of the tobacco shred moisture at the outlet of the winnowing machine.
Wherein: the data preprocessing comprises missing value processing, abnormal value processing, repeated value processing, data filtering and data normalization processing.
The normalization processing is to perform normalization processing on the effective data by adopting a normalization formula to eliminate data dimension, wherein the normalization formula is as follows:
wherein:
is valid data of the data;
is the maximum value of effective data;
is the minimum value of the valid data;
the results were normalized for the valid data.
In an embodiment, the neural network model uses ELM as a machine learning algorithm model. The extreme learning machine ELM is a currently known machine learning algorithm used to train the single hidden layer feedforward neural network SLFN.
According to the method, the predicted value of the outlet moisture target of the cut tobacco dryer is set through the Extreme Learning Machine (ELM), the method has the advantages of being high in accuracy and high in calculation speed, meeting the requirement of strong instantaneity in the cut tobacco production process, effectively realizing intelligent setting of the outlet moisture target of the cut tobacco dryer, realizing intelligent setting of the outlet moisture target of the cut tobacco dryer to a certain extent, and improving rationality of setting of the outlet moisture target of the cut tobacco dryer.
Claims (5)
1. A method for setting and regulating an outlet moisture target value of a cut tobacco production line cut tobacco dryer comprises the steps that the cut tobacco production line cut tobacco dryer is followed by a winnowing machine, a control server is arranged on the production line, and historical production data of the production line are stored in the control server; characterized in that the method comprises:
step 1: acquiring a plurality of groups of production data of the current batch in real time, wherein the production data comprise cut tobacco moisture at the outlet of a cut tobacco dryer, cut tobacco moisture at the outlet of a winnowing machine, moisture of final finished cut tobacco, environmental temperature/humidity of the cut tobacco dryer and environmental temperature/humidity after winnowing;
step 2: preprocessing data, eliminating useless data and extracting effective data;
step 3: extracting data characteristic values from the effective data, wherein the data characteristic values comprise; cut-tobacco dryer data characteristic value and final product data characteristic value, wherein:
cut-tobacco dryer data characteristic value: is the average value of effective data of the temperature/humidity of the tobacco shred at the outlet of the cut tobacco dryer;
final product data characteristic value: is the average value of the effective data of the moisture of the tobacco shreds of the final finished product;
step 4: inputting a cut tobacco machine data characteristic value of the data characteristic value and a cut tobacco moisture average value of an outlet of the air separator into a first prediction model, and comparing output data of the first prediction model with a preset cut tobacco machine outlet cut tobacco moisture prediction value;
step 5: adjusting the temperature control parameter of the cut tobacco dryer according to the comparison result of the step 4, and returning to the step 1 until the comparison result is smaller than the set threshold value;
step 6: whether the current batch production is finished or not is: storing the current value of the tobacco shred moisture at the outlet of the final cut tobacco dryer into a control server, and ending the production data acquisition; otherwise, returning to the step 1;
wherein:
the first predictive model is a neural network model;
the tobacco shred moisture predicted value at the outlet of the tobacco dryer is obtained by obtaining a tobacco shred data characteristic value of a plurality of batches of qualified production data and a tobacco shred moisture average value at the outlet of the air separator, inputting the tobacco shred data characteristic value and the tobacco shred moisture average value into a first prediction model for training, and taking an output value obtained by training as the tobacco shred moisture predicted value at the outlet of the tobacco dryer.
2. The method according to claim 1, wherein the extracting data characteristic value of the effective data further comprises a winnowing machine data characteristic value, wherein the winnowing machine data characteristic value is an average value of tobacco shred moisture at an outlet of the winnowing machine and effective data of environmental temperature/humidity after winnowing;
the method further performs after the end of step 5:
step 5.1: inputting the winnowing machine data characteristic value and the final product data characteristic value of the data characteristic value into a second prediction model, and comparing the output data of the second prediction model with a preset winnowing machine outlet tobacco shred moisture prediction value;
step 5.2: adjusting the blowing control parameters of the winnowing machine according to the comparison result in the step 5.1, and returning to the step 1 until the comparison result is smaller than a set threshold value;
in step 6, whether the current batch production is finished is: simultaneously storing the current value of the tobacco shred moisture at the outlet of the winnowing machine into a control server;
wherein:
the second predictive model is a neural network model;
the predicted value of the tobacco shred moisture at the outlet of the winnowing machine is obtained by acquiring a winnowing machine data characteristic value and a final product data characteristic value of a plurality of batches of qualified production data, inputting the winnowing machine data characteristic value and the final product data characteristic value into a second prediction model for training, and taking an output value obtained by training as the predicted value of the tobacco shred moisture at the outlet of the winnowing machine.
3. The method of claim 1, wherein the preprocessing of the data comprises missing value processing, outlier processing, duplicate value processing, data filtering, and data normalization processing.
4. The method of claim 3, wherein the normalization process is to normalize the effective data using a normalization formula to eliminate data dimension,
the normalization formula is:
wherein:
x is the effective data of the data;
x max is the maximum value of effective data;
x min is the minimum value of the valid data;
the results were normalized for the valid data.
5. A method of regulating according to claim 1 or 2, wherein the neural network model is an ELM machine learning algorithm model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311552409.XA CN117441924A (en) | 2023-11-21 | 2023-11-21 | Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311552409.XA CN117441924A (en) | 2023-11-21 | 2023-11-21 | Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117441924A true CN117441924A (en) | 2024-01-26 |
Family
ID=89596706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311552409.XA Pending CN117441924A (en) | 2023-11-21 | 2023-11-21 | Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117441924A (en) |
-
2023
- 2023-11-21 CN CN202311552409.XA patent/CN117441924A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110893001B (en) | Method and system for controlling water content of outlet of loosening and dampening process | |
CN113017132A (en) | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction | |
CN111887460A (en) | Tobacco cut-tobacco drying moisture and temperature control prediction system and method | |
CN111109643B (en) | Method and system for controlling water content of cut tobacco of sheet cut tobacco drying | |
CN110946314B (en) | Method and system for controlling water content of cut tobacco through air flow cut tobacco drying | |
CN108308691A (en) | A method of promoting tobacco scrap prodn quality stability | |
CN114027539B (en) | Model prediction control-based loosening and conditioning quantitative water adding control method | |
CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
CN110946313B (en) | Method and system for controlling water content of outlet of cut tobacco drying process | |
CN112790418B (en) | Water adding control method and system for super moisture regain of cut tobacco | |
CN102147613A (en) | Model predictive control method and system for moisture and temperature of tobacco redryer | |
CN110879581A (en) | Feed liquid control method and system for blade charging | |
CN112931913A (en) | Control method for air-flow type cut stem drying outlet water content | |
CN117441924A (en) | Method for setting, regulating and controlling outlet moisture target value of cut tobacco dryer of cut tobacco production line | |
CN113303489B (en) | Method for accurately controlling moisture of tobacco leaves in tobacco shred making process | |
CN112263012B (en) | Moisture content control method of redrying machine based on formula parameter library | |
CN116268521B (en) | Self-adaptive intelligent control system of charging machine | |
CN111248485A (en) | Method for online adjusting perfuming moisture of mixed silk | |
CN111728252A (en) | Control method and system for drying strength of tobacco roller | |
CN112790421B (en) | Cut stem charging outlet water content control method based on sliding window prediction | |
CN112434867A (en) | Intelligent prediction model for water content of blade section and application | |
CN113040412A (en) | Intelligent control method and device for roller airflow cut-tobacco drier | |
CN112434868A (en) | Sheet drying process accurate control intelligent prediction model and application | |
CN113876008A (en) | Method for controlling stability of moisture content of loose moisture regaining tobacco flakes | |
CN112471572A (en) | Method and system for controlling consistency of processing strength of tobacco tunnel type temperature increasing equipment |
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 |