CN116172231A - Method and device for controlling outlet water content of sheet cut-tobacco dryer - Google Patents
Method and device for controlling outlet water content of sheet cut-tobacco dryer Download PDFInfo
- Publication number
- CN116172231A CN116172231A CN202310274896.1A CN202310274896A CN116172231A CN 116172231 A CN116172231 A CN 116172231A CN 202310274896 A CN202310274896 A CN 202310274896A CN 116172231 A CN116172231 A CN 116172231A
- Authority
- CN
- China
- Prior art keywords
- cut
- tobacco
- control model
- tobacco dryer
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004519 manufacturing process Methods 0.000 claims abstract description 58
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 238000012417 linear regression Methods 0.000 claims description 18
- 239000000463 material Substances 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000001035 drying Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 7
- 230000007246 mechanism Effects 0.000 abstract description 5
- 241000208125 Nicotiana Species 0.000 description 19
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 19
- 238000004140 cleaning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001704 evaporation Methods 0.000 description 3
- 230000008020 evaporation Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- 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
- A24B3/10—Roasting or cooling 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
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working
Landscapes
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention provides a method and a device for controlling outlet water content of a sheet cut-tobacco dryer, wherein the method comprises the following steps: acquiring a set value of outlet moisture of the cut-tobacco drier and a current outlet moisture value of the cut-tobacco drier, and starting an optimized control model of the cut-tobacco drier when the deviation is greater than a first threshold value; according to different stages of the current production state of the cut-tobacco drier, different optimization control models are matched, specific parameter values of control variables are output, and the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air valve of the sheet cut-tobacco drier; when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model; when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model; and when the current production state of the cut-tobacco drier is the tail feeding stage, matching the tail feeding control model. According to the method and the device for controlling the outlet water content of the sheet cut-tobacco dryer, provided by the invention, the control model is optimized in real time by stages, so that abnormal production states are identified according to real-time production conditions, and an early warning mechanism is constructed.
Description
Technical Field
The embodiment of the invention relates to the technical field of cut-tobacco dryers, in particular to a method and a device for controlling the water content of an outlet of a sheet cut-tobacco dryer.
Background
The cut tobacco sheet dryer is used as one of key equipment in a tobacco cut tobacco manufacturing line, and has the main technical task of drying cut tobacco leaves after shredding to the water content meeting the technical requirements, wherein the control precision of the cut tobacco sheet dryer is directly related to the water content, the temperature and the like of finished cut tobacco. PID control is one of the earliest developed control strategies, and is widely applied to process control and motion control due to simple algorithm and high reliability, but the control mode has certain hysteresis, so that the fluctuation of the water content of tobacco shreds at the outlet of the cut tobacco dryer is larger, and the control effect is not ideal.
Therefore, it is necessary to provide a method and a device for controlling the outlet water content of a sheet cut-tobacco dryer, so as to effectively solve the above problems.
Disclosure of Invention
The invention provides a method and a device for controlling the outlet water content of a sheet cut-tobacco dryer, which are used for optimizing a control model in real time by stages, so that abnormal production states are identified according to real-time production conditions, and an early warning mechanism is constructed.
The embodiment of the invention provides a method for controlling the water content of an outlet of a sheet cut-tobacco dryer, which comprises the following steps:
acquiring a set value of outlet moisture of the cut-tobacco drier and a current outlet moisture value of the cut-tobacco drier;
when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value, starting an optimized control model of the cut-tobacco dryer;
according to different stages of the current production state of the cut-tobacco drier, different optimized control models are matched, and specific parameter values of control variables are output, wherein the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air door of the sheet cut-tobacco drier;
when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model, wherein the stub bar control model is based on multiple linear regression and Xgboost;
when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model, wherein the steady-state control model is based on deep learning and machine learning;
and when the current production state of the cut-tobacco drier is a tail stage, matching a tail control model, wherein the tail control model is based on multiple linear regression and Xgboost. Preferably, the specific parameter value of the hot air fan frequency of the sheet cut-tobacco dryer is calculated by the following formula:
476.4+30.89*x+1.184*x-0.01232*x*x*x
wherein x represents the actual value of the hot air quantity.
Preferably, the specific parameter value of the opening degree of the tide gate is calculated by the following formula:
906.3-61.7*x+6.29*y*y-0.06179*y*y*y
wherein y represents the actual value of the tidal volume.
Preferably, the stub bar control model reduces the phenomenon of moisture overshoot according to the characteristics of short stub bar stage time and fast temperature rise.
Preferably, the steady-state control model predicts the advance control parameter when a large deviation of the outlet moisture occurs.
Preferably, the tail control model reduces the parameters in advance according to the characteristic of short tail stage time to shorten the tail drying rate.
Preferably, the optimized control model of the cut-tobacco dryer comprises the step of performing next optimization on the outlet moisture of the cut-tobacco dryer through an iterative algorithm according to the history information of the observed outlet moisture of the cut-tobacco dryer by using a Bayesian optimization algorithm.
Preferably, the optimized control model of the cut tobacco dryer comprises the steps of using a genetic algorithm, starting from a group, simultaneously comparing a plurality of individuals and searching an optimal solution.
Preferably, the optimized control model of the cut-tobacco dryer comprises the steps of selecting a series of specific search directions as heuristics from an initial feasible solution by using tabu search, and selecting to realize the movement with the most variation of specific objective function values.
The embodiment of the invention also provides a device for controlling the outlet water content of the sheet cut-tobacco dryer, which comprises:
the cut-tobacco dryer outlet moisture acquisition module is used for acquiring a set value of outlet moisture of the cut-tobacco dryer and a current outlet moisture value of the cut-tobacco dryer;
the cut-tobacco dryer optimizing control model starting module is used for starting the cut-tobacco dryer optimizing control model when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value;
the specific parameter value output module is used for matching different optimized control models according to different stages of the current production state of the cut-tobacco dryer and outputting specific parameter values of the control variables, wherein the control variables comprise the frequency of a hot air fan of the sheet cut-tobacco dryer and the opening degree of a tide-discharging air door;
the stub bar control model matching module is used for matching a stub bar control model when the current production state of the cut-tobacco drier is a stub bar stage, and the stub bar control model is based on multiple linear regression and Xgboost;
the steady-state control model matching module is used for matching a steady-state control model when the current production state of the cut-tobacco dryer is a steady production stage, and the steady-state control model is based on deep learning and machine learning;
and the material tail control model matching module is used for matching the material tail control model when the current production state of the cut-tobacco drier is a material tail stage, and is based on multiple linear regression and Xgboost.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
according to the method and the device for controlling the outlet water content of the sheet cut-tobacco dryer, provided by the embodiment of the invention, the set value of the outlet water content of the sheet cut-tobacco dryer and the current outlet water content value of the sheet cut-tobacco dryer are obtained; when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value, starting an optimized control model of the cut-tobacco dryer; according to different stages of the current production state of the cut-tobacco drier, different optimized control models are matched, and specific parameter values of control variables are output, wherein the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air door of the sheet cut-tobacco drier; when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model, wherein the stub bar control model is based on multiple linear regression and Xgboost; when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model, wherein the steady-state control model is based on deep learning and machine learning; when the current production state of the cut-tobacco drier is a tail stage, a tail control model is matched, and based on multiple linear regression and Xgboost, the tail control model is optimized in real time by stages, so that abnormal production state is identified according to real-time production conditions, and an early warning mechanism is constructed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the prior art, a brief description of the drawings is provided below, wherein it is apparent that the drawings in the following description are some, but not all, embodiments of the present invention. Other figures may be derived from these figures without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a schematic flow chart of a method for controlling outlet water content of a sheet cut-tobacco dryer according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a device for controlling outlet water content of a sheet cut-tobacco dryer according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Based on the problems existing in the prior art, the embodiment of the invention provides a method and a device for controlling the outlet water content of a sheet cut-tobacco dryer, which are used for optimizing a control model in real time by stages, so that abnormal production states are identified according to real-time production conditions, and an early warning mechanism is constructed.
Fig. 1 is a schematic flow chart of a method for controlling outlet water content of a sheet cut-tobacco dryer according to an embodiment of the present invention. Referring now to fig. 1, an embodiment of the present invention provides a method for controlling outlet water content of a sheet cut-tobacco dryer, the method comprising:
step S101: acquiring a set value of outlet moisture of the cut-tobacco drier and a current outlet moisture value of the cut-tobacco drier;
step S102: when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value, starting an optimized control model of the cut-tobacco dryer;
step S103: according to different stages of the current production state of the cut-tobacco drier, different optimized control models are matched, and specific parameter values of control variables are output, wherein the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air door of the sheet cut-tobacco drier;
step S104: when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model, wherein the stub bar control model is based on multiple linear regression and Xgboost;
step S105: when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model, wherein the steady-state control model is based on deep learning and machine learning;
step S106: and when the current production state of the cut-tobacco drier is a tail stage, matching a tail control model, wherein the tail control model is based on multiple linear regression and Xgboost.
Specifically, historical yarn-making batch data is imported, and the historical yarn-making batch production data is cleaned. And correcting and eliminating noise data, and carrying out data analysis and data modeling according to the special property of the data. The control model construction is to finish model output according to the formal sample data and the modeling tool. And finally outputting a control model for the moisture of the outlet of the baked yarn by using a Bayesian optimization algorithm, a genetic algorithm, tabu search, a matched modeling flow and training analysis of sample data.
In specific implementation, the specific parameter value of the hot air fan frequency of the sheet cut-tobacco dryer is calculated by the following formula:
476.4+30.89*x+1.184*x-0.01232*x*x*x
wherein x represents the actual value of the hot air quantity.
Specifically, the above formula is obtained by the following method: collecting experimental data, and collecting operation data of a certain amount of sheet cut-tobacco drier, wherein the operation data comprise the actual value of hot air quantity, the water content of an outlet and the like; data cleaning and processing, namely cleaning and processing the collected data, including operations of removing abnormal values, complementing missing values and the like, and smoothing the data to reduce interference of noise on a model; establishing a model, namely establishing a mathematical model between the outlet water content and the hot air volume according to collected experimental data, and adopting methods such as an LGBM algorithm, linear regression and the like in the modeling process; parameter optimization, after a model is established, parameter optimization is carried out, the accuracy and stability of the model are improved, and the combination optimization is carried out on parameters in the model by adopting methods such as grid search and the like, so that an optimal parameter combination is found; the model evaluation, through the cross verification method, the model is evaluated to determine the prediction capability and stability of the model, and in the evaluation process, the indexes such as the precision, recall rate and the like of the model are evaluated to determine the reliability of the model; and (3) model application, namely after model establishment and optimization are completed, applying the optimized control model to a control system of the sheet cut-tobacco dryer, so as to realize the optimal control of the hot air quantity. The specific parameter value of the frequency of the hot air blower is calculated through the formula, so that the actual value of the hot air quantity is controlled, and the aim of controlling the water content of the outlet is fulfilled.
In a specific implementation, the specific parameter value of the opening of the moisture removal air valve is calculated by the following formula:
906.3-61.7*x+6.29*y*y-0.06179*y*y*y
wherein y represents the actual value of the tidal volume.
Specifically, the above formula is obtained by the following method: collecting experimental data, and collecting operation data of a certain amount of sheet cut-tobacco drier, wherein the operation data comprise the actual value of hot air quantity, the water content of an outlet and the like; data cleaning and processing, namely cleaning and processing the collected data, including operations of removing abnormal values, complementing missing values and the like, and smoothing the data to reduce interference of noise on a model; establishing a model, namely establishing a mathematical model between the outlet water content and the hot air volume according to collected experimental data, and adopting methods such as an LGBM algorithm, linear regression and the like in the modeling process; parameter optimization, after a model is established, parameter optimization is carried out, the accuracy and stability of the model are improved, and the combination optimization is carried out on parameters in the model by adopting methods such as grid search and the like, so that an optimal parameter combination is found; the model evaluation, through the cross verification method, the model is evaluated to determine the prediction capability and stability of the model, and in the evaluation process, the indexes such as the precision, recall rate and the like of the model are evaluated to determine the reliability of the model; and (3) model application, namely after model establishment and optimization are completed, applying the optimized control model to a control system of the sheet cut-tobacco dryer, and realizing optimal control of the opening degree of the moisture removal air valve. The specific parameter value of the opening of the tide-discharging air door is calculated through the formula, so that the actual value of the opening of the air door is controlled, and the aim of controlling the water content of the outlet is fulfilled.
In specific implementation, the stub bar control model reduces the phenomenon of moisture overshoot according to the characteristics of short stub bar stage time and fast temperature rise. Firstly, the temperature rising rate of the heater is reduced, and in the stub bar stage, the temperature rising rate of the heater can be properly reduced, and the temperature change speed of cut tobacco is reduced, so that the amplitude of moisture overshoot is reduced. And secondly, the temperature of the hot air is properly reduced, and the moisture content of the tobacco shreds in the stub bar stage is high and is easily influenced by high temperature, so that the moisture evaporation is too fast, and therefore, the temperature of the hot air can be properly reduced, the moisture evaporation speed of the tobacco shreds is slowed down, and the phenomenon of moisture overshoot is relieved. Finally, adjusting the hot air volume: in the stub bar stage, the temperature change speed and the water evaporation speed of the cut tobacco can be controlled by adjusting the air quantity of hot air, so that the amplitude of water overshoot is reduced. Through the control strategy, the phenomenon of water overshoot can be weakened at the stub bar stage, and the stability and accuracy of the water content of the tobacco shred outlet are improved.
In a specific implementation, the steady-state control model predicts the advance control parameter when the outlet moisture is greatly deviated. According to the characteristics of a tail control model in the method for controlling the outlet water content of the sheet cut-tobacco dryer, the method mainly adjusts down parameters in advance in the tail stage so as to shorten the tail drying rate. The specific implementation method can be realized by the following steps: monitoring outlet water content data of a tail stage, and analyzing in real time; judging that the material is in a tail stage at present according to the analysis result, and reducing control parameters in advance according to the characteristic of short time of the stage; after adjusting the control parameters, re-monitoring and analyzing the outlet water content data, if the tail drying rate is obviously improved, maintaining the current parameters, otherwise, adjusting the control parameters again until the expected effect is achieved; and optimizing and adjusting parameters of the tail control model according to different production batches and material characteristics so as to obtain a better control effect. The realization of the tail control model requires real-time monitoring and analysis of outlet water content data, and adjustment of control parameters is carried out according to data analysis results so as to realize shortening of the tail drying rate. Meanwhile, in order to obtain a better control effect, parameter optimization and adjustment are required to be carried out for different production batches and material characteristics.
In a specific implementation, the tail control model reduces parameters in advance according to the characteristic of short tail stage time to shorten the tail drying rate. Judging whether the cut tobacco dryer enters a tail feeding stage according to the real-time monitored cut tobacco water content and outlet water content data; if the cut-tobacco drier enters a tail stage, determining tail control parameters which need to be adjusted down in advance according to experience or historical data; inputting the determined tail control parameters into a control model, and adjusting the operation parameters of the cut tobacco dryer through a control algorithm to enable the outlet water content to reach the target tail drying rate as soon as possible within a controllable range; before the end of the tail stage, gradually recovering the tail control parameters to normal values so as to avoid negative influence on the quality of the subsequent tobacco shreds.
In a specific implementation, the optimized control model of the cut-tobacco dryer comprises the step of using a Bayesian optimization algorithm to optimize the outlet moisture of the cut-tobacco dryer next time through an iterative algorithm according to the observed historical information of the outlet moisture of the cut-tobacco dryer. And carrying out result prediction feedback according to the point position value of the current equipment, and selecting the next group of parameter combinations from the parameter combination candidate set by using Bayesian probability information gain, wherein the group of parameter combinations can enable the target value to reach the optimal state under the constraint condition as much as possible.
In a specific implementation, the cut tobacco dryer optimization control model comprises the steps of starting from a group by using a genetic algorithm, and simultaneously comparing a plurality of individuals to search an optimal solution. Firstly, forming a group of cut-tobacco drier moisture control candidate solutions, and measuring and calculating the fitness of the candidate solutions according to the control model adaptability conditions; and reserving some candidate solutions according to the fitness, discarding other candidate solutions, and operating the reserved candidate solutions to generate new moisture control candidate solutions.
In a specific implementation, the optimized control model of the cut-tobacco dryer comprises the steps of using tabu search, selecting a series of specific search directions as heuristics from an initial feasible solution, and selecting to realize movement with the most variation of specific objective function values. Some objects corresponding to the searched local optimal solution are marked, and the objects are avoided in further iterative searching. The optimal solution of the occurrence of the privilege history is realized by setting a tabu table to tabu some experienced operations and setting the existing time or the length of the tabu table. The quality of the solution is improved over many successive movements.
Fig. 2 is a schematic block diagram of a device for controlling outlet water content of a sheet cut-tobacco dryer according to an embodiment of the present invention. Referring now to fig. 2, an embodiment of the present invention further provides a device for controlling the outlet water content of a sheet cut-tobacco dryer, the device comprising:
the cut-tobacco dryer outlet moisture obtaining module 21 is used for obtaining a set value of outlet moisture of the cut-tobacco dryer and a current outlet moisture value of the cut-tobacco dryer;
the cut-tobacco dryer optimization control model starting module 22 is configured to start the cut-tobacco dryer optimization control model when a deviation between a current outlet moisture value of the cut-tobacco dryer and an outlet moisture set value of the cut-tobacco dryer is greater than a first threshold;
a specific parameter value output module 23 of a control variable, which is used for matching different optimized control models according to different stages of the current production state of the cut-tobacco dryer, and outputting specific parameter values of the control variable, wherein the control variable comprises the frequency of a hot air fan and the opening degree of a moisture removal air gate of the sheet cut-tobacco dryer;
a stub bar control model matching module 24 for matching a stub bar control model based on multiple linear regression and Xgboost when the current production state of the cut-tobacco dryer is a stub bar stage;
a steady-state control model matching module 25 for matching a steady-state control model when the current production state of the cut-tobacco dryer is a steady production phase, the steady-state control model being based on deep learning and machine learning;
the tail control model matching module 26 is used for matching the tail control model when the current production state of the cut-tobacco dryer is the tail stage, and is based on multiple linear regression and Xgboost.
In summary, the embodiment of the invention obtains the set value of the outlet moisture of the cut-tobacco drier and the current outlet moisture value of the cut-tobacco drier; when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value, starting an optimized control model of the cut-tobacco dryer; according to different stages of the current production state of the cut-tobacco drier, different optimized control models are matched, and specific parameter values of control variables are output, wherein the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air door of the sheet cut-tobacco drier; when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model, wherein the stub bar control model is based on multiple linear regression and Xgboost; when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model, wherein the steady-state control model is based on deep learning and machine learning; when the current production state of the cut-tobacco drier is a tail stage, a tail control model is matched, and based on multiple linear regression and Xgboost, the tail control model is optimized in real time by stages, so that abnormal production state is identified according to real-time production conditions, and an early warning mechanism is constructed.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (10)
1. The method for controlling the water content of the outlet of the sheet cut-tobacco dryer is characterized by comprising the following steps of:
acquiring a set value of outlet moisture of the cut-tobacco drier and a current outlet moisture value of the cut-tobacco drier;
when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value, starting an optimized control model of the cut-tobacco dryer;
according to different stages of the current production state of the cut-tobacco drier, different optimized control models are matched, and specific parameter values of control variables are output, wherein the control variables comprise the frequency of a hot air fan and the opening degree of a moisture removal air door of the sheet cut-tobacco drier;
when the current production state of the cut-tobacco drier is a stub bar stage, matching a stub bar control model, wherein the stub bar control model is based on multiple linear regression and Xgboost;
when the current production state of the cut-tobacco drier is a stable production stage, matching a steady-state control model, wherein the steady-state control model is based on deep learning and machine learning;
and when the current production state of the cut-tobacco drier is a tail stage, matching a tail control model, wherein the tail control model is based on multiple linear regression and Xgboost.
2. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the specific parameter value of the hot air fan frequency of the sheet cut-tobacco dryer is calculated by the following formula:
476.4+30.89*x+1.184*x-0.01232*x*x*x
wherein x represents the actual value of the hot air quantity.
3. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the specific parameter value of the opening degree of the moisture removal air valve is calculated by the following formula:
906.3-61.7*x+6.29*y*y-0.06179*y*y*y
wherein y represents the actual value of the tidal volume.
4. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the stub bar control model reduces the phenomenon of water overshoot according to the characteristics of short stub bar stage time and quick temperature rise.
5. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the steady-state control model predicts the advance control parameter when the outlet water content deviates greatly.
6. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the tail control model reduces the parameters in advance to shorten the tail drying rate according to the characteristic of short tail stage time.
7. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the cut-tobacco dryer optimization control model comprises using a bayesian optimization algorithm to perform next optimization on the outlet water content of the cut-tobacco dryer through an iterative algorithm according to the observed historical information of the outlet water content of the cut-tobacco dryer.
8. The method for controlling the outlet water content of the sheet cut-tobacco dryer according to claim 1, wherein the optimized control model of the sheet cut-tobacco dryer comprises using a genetic algorithm to search for an optimal solution by comparing a plurality of individuals from a group at the same time.
9. The method according to claim 1, wherein the optimized control model of the cut-tobacco dryer includes using tabu search, selecting a series of specific search directions as heuristics from an initial feasible solution, and selecting to implement a movement that maximizes a change in a specific objective function value.
10. An outlet water content control device of a sheet cut-tobacco dryer, which is characterized by comprising:
the cut-tobacco dryer outlet moisture acquisition module is used for acquiring a set value of outlet moisture of the cut-tobacco dryer and a current outlet moisture value of the cut-tobacco dryer;
the cut-tobacco dryer optimizing control model starting module is used for starting the cut-tobacco dryer optimizing control model when the deviation between the current outlet moisture value of the cut-tobacco dryer and the outlet moisture set value of the cut-tobacco dryer is larger than a first threshold value;
the specific parameter value output module is used for matching different optimized control models according to different stages of the current production state of the cut-tobacco dryer and outputting specific parameter values of the control variables, wherein the control variables comprise the frequency of a hot air fan of the sheet cut-tobacco dryer and the opening degree of a tide-discharging air door;
the stub bar control model matching module is used for matching a stub bar control model when the current production state of the cut-tobacco drier is a stub bar stage, and the stub bar control model is based on multiple linear regression and Xgboost;
the steady-state control model matching module is used for matching a steady-state control model when the current production state of the cut-tobacco dryer is a steady production stage, and the steady-state control model is based on deep learning and machine learning;
and the material tail control model matching module is used for matching the material tail control model when the current production state of the cut-tobacco drier is a material tail stage, and is based on multiple linear regression and Xgboost.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310274896.1A CN116172231A (en) | 2023-03-21 | 2023-03-21 | Method and device for controlling outlet water content of sheet cut-tobacco dryer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310274896.1A CN116172231A (en) | 2023-03-21 | 2023-03-21 | Method and device for controlling outlet water content of sheet cut-tobacco dryer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116172231A true CN116172231A (en) | 2023-05-30 |
Family
ID=86448901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310274896.1A Pending CN116172231A (en) | 2023-03-21 | 2023-03-21 | Method and device for controlling outlet water content of sheet cut-tobacco dryer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116172231A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102871214A (en) * | 2012-10-08 | 2013-01-16 | 秦皇岛烟草机械有限责任公司 | Model prediction based cut tobacco dryer outlet moisture control method |
| CN111887460A (en) * | 2019-05-05 | 2020-11-06 | 贵州中烟工业有限责任公司 | Tobacco cut-tobacco drying moisture and temperature control prediction system and method |
| CN113017132A (en) * | 2021-04-09 | 2021-06-25 | 红云红河烟草(集团)有限责任公司 | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction |
| CN114403486A (en) * | 2022-02-17 | 2022-04-29 | 四川大学 | Intelligent control method of airflow type cut-tobacco drier based on local peak value coding circulation network |
-
2023
- 2023-03-21 CN CN202310274896.1A patent/CN116172231A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102871214A (en) * | 2012-10-08 | 2013-01-16 | 秦皇岛烟草机械有限责任公司 | Model prediction based cut tobacco dryer outlet moisture control method |
| CN111887460A (en) * | 2019-05-05 | 2020-11-06 | 贵州中烟工业有限责任公司 | Tobacco cut-tobacco drying moisture and temperature control prediction system and method |
| CN113017132A (en) * | 2021-04-09 | 2021-06-25 | 红云红河烟草(集团)有限责任公司 | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction |
| CN114403486A (en) * | 2022-02-17 | 2022-04-29 | 四川大学 | Intelligent control method of airflow type cut-tobacco drier based on local peak value coding circulation network |
Non-Patent Citations (7)
| Title |
|---|
| 任正云, 晏小平, 方维岚, 夏明东, 胡如高: "烘丝过程烟丝含水率的MFA控制", 烟草科技, no. 06, 20 June 2005 (2005-06-20) * |
| 何毅;李斌;普轶;李曾;周霄天;路瑶;金超;: "基于梯度提升树的烟草回潮机出料含水率预测", 软件, no. 06, 15 June 2020 (2020-06-15) * |
| 姚光明, 李晓, 尹献忠, 涂成金, 李明哲: "烟丝整丝率变化率对卷烟卷接质量的影响", 烟草科技, no. 11, 25 November 2004 (2004-11-25) * |
| 李军;刘旭强;钱启福;颜玉祥;邓瑞军;冯文超;: "烘丝机工艺参数对"干头干尾"烟丝含水率的影响研究", 云南农业大学学报(自然科学), vol. 30, no. 06, 3 November 2015 (2015-11-03), pages 873 - 879 * |
| 李秀芳;王永华;赵春元;李明伟;: "解决烘丝机干头干尾的方法与实现", 烟草科技, no. 09, 20 September 2013 (2013-09-20) * |
| 李雯琦;张超;李善莲;易斌;王晓辉;端凯;聂蓉;: "滚筒烘丝机干头干尾量的计算方法", 烟草科技, no. 07, 26 July 2018 (2018-07-26) * |
| 胡宇航;何毅;李凡;陈之辉;曲锋;杨进国;王哲;: "烘丝过程出口水分控制数据分析方法应用研究", 电脑与信息技术, no. 04, 15 August 2016 (2016-08-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111045326B (en) | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network | |
| CN108652066A (en) | The water feeding method of loosening and gaining moisture process and the device for predicting the process amount of water | |
| CN113017132A (en) | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction | |
| Iplikci | A comparative study on a novel model‐based PID tuning and control mechanism for nonlinear systems | |
| CN111109643B (en) | Method and system for controlling water content of cut tobacco of sheet cut tobacco drying | |
| CN114115393A (en) | Method for controlling moisture and temperature at outlet of cut tobacco dryer for sheet cut tobacco making line | |
| CN113128764A (en) | Generation of tobacco dryer outlet water content prediction model and regulation and control method based on same | |
| Hussain et al. | Comparison of PID controller tuning methods with genetic algorithm for FOPTD system | |
| CN105807607A (en) | Method for optimizing predictive fuzzy-PID coking furnace temperature control through genetic algorithm | |
| CN114027539B (en) | Model prediction control-based loosening and conditioning quantitative water adding control method | |
| CN109549241A (en) | A kind of steam computer heating control model, steam method for heating and controlling applied to throwing cartridge type smoke machine | |
| CN105334738B (en) | A kind of method of evaluating performance suitable for tobacco processing course pid control circuit | |
| CN109460890A (en) | A kind of intelligent self-healing method based on intensified learning and control performance monitoring | |
| CN113708389A (en) | Wind power plant primary frequency modulation model parameter identification method and system based on actual power response | |
| CN114403487B (en) | Water adding control method for loosening and dampening | |
| CN105595391A (en) | Advanced control method for comas tower dryer (CTD) | |
| CN116172231A (en) | Method and device for controlling outlet water content of sheet cut-tobacco dryer | |
| CN110826229B (en) | Modeling and optimizing setting control method for filament drying head drying process based on long-term prediction | |
| CN113759708A (en) | System optimization control method and device and electronic equipment | |
| CN116611349A (en) | Neural network-based roller wire drying process parameter optimization method and system | |
| Shah et al. | Nonlinear Modelling for Time-Varying Water Temperature PID Control | |
| Concha et al. | A novel implementation technique for genetic algorithm based auto-tuning PID controller | |
| Ahamed et al. | Reinforcement learning controllers for automatic generation control in power systems having reheat units with GRC and dead-band | |
| CN112800671B (en) | Data processing method and device and electronic equipment | |
| Zhu et al. | Control method of outlet moisture content of tobacco primary processing based on TVA-TCN-MPC |
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 |