CN113017132A - Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction - Google Patents
Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction Download PDFInfo
- Publication number
- CN113017132A CN113017132A CN202110382903.0A CN202110382903A CN113017132A CN 113017132 A CN113017132 A CN 113017132A CN 202110382903 A CN202110382903 A CN 202110382903A CN 113017132 A CN113017132 A CN 113017132A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- moisture
- data
- parameters
- cut tobacco
- 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 108
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000008569 process Effects 0.000 title claims abstract description 44
- 238000005457 optimization Methods 0.000 title claims abstract description 29
- 238000001035 drying Methods 0.000 claims abstract description 29
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 28
- 238000004886 process control Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 239000000463 material Substances 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000033228 biological regulation Effects 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000013499 data model Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 230000018044 dehydration Effects 0.000 abstract 1
- 238000006297 dehydration reaction Methods 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 9
- 238000005070 sampling Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000003908 quality control method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000013072 incoming material Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 210000000349 chromosome Anatomy 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011143 downstream manufacturing Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 239000011265 semifinished product Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003339 best practice Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003860 storage 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
- A24B3/00—Preparing tobacco in the factory
- A24B3/04—Humidifying or drying tobacco bunches or cut tobacco
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B9/00—Control of the moisture content of tobacco products, e.g. cigars, cigarettes, pipe tobacco
Landscapes
- Drying Of Solid Materials (AREA)
Abstract
The invention discloses a method for optimizing tobacco shred quality based on tobacco dryer process parameter prediction, which belongs to the field of tobacco processing and comprises the following steps of 1, data acquisition: (1) acquiring process control data of the tobacco dryer, wherein the process control data comprises historical data and real-time data, and comprises fixed parameters including formula parameters and equipment parameters, and adjustable process parameters having great correlation with tobacco shred moisture; (2) the external sensor comprises an environment temperature sensor and an environment humidity sensor; step 2, establishing an outlet water prediction model, and step 3, establishing a process control optimization model; and 4, evaluating the cut tobacco drying capacity. The method has the advantages that the tobacco drying process data are acquired in real time on line, and the mechanism analysis of the moisture balance of the tobacco drying cylinder and the dehydration process of the tobacco shreds is combined, so that the stability of the moisture at the outlet is improved, the fluctuation is reduced, and the dependence on human experience can be reduced.
Description
Technical Field
The invention belongs to the field of tobacco, and particularly relates to a tobacco shred quality optimization method based on tobacco dryer process parameter prediction.
Background
Cut tobacco drying is an important procedure in the cut tobacco production process, and outlet moisture is an important quality control index in the cut tobacco production process. The common drum-type cut tobacco drier equipment at home and abroad adjusts the moisture content of the dried cut tobacco by adjusting the technological parameters such as the temperature, the humidity, the opening degree of a valve and the like of a drum wall. However, the cut tobacco drying process is affected by many factors, such as the batch, the moisture content, the water absorption of raw materials, the flow rate, etc., of the cut tobacco, and meanwhile, the process parameters of the cut tobacco drying machine are strongly coupled to each other, and the adjustment of any parameter may cause a great error in the moisture content of the cut tobacco. With the development of the cigarette industry, tobacco varieties increase, and the quality control requirement is higher and higher, but the defects of the traditional PID control mode in dealing with a tobacco drying system with large hysteresis, strong coupling and nonlinearity are particularly obvious, the traditional PID control mode is difficult to solve the contradiction between stability and accuracy, and particularly when a controlled object dynamically changes, the traditional control method is difficult to realize timely tracking and effective control. The problems encountered in the actual production process are as follows:
1. the size of the water content of the outlet is related to a plurality of interference factors, including the characteristics, batch, water content, water absorption, tobacco shred flow, environment temperature and humidity and the like of the incoming material; meanwhile, the method is also related to the process parameters of different cut-tobacco dryers and the experience of different workers;
2. the technological parameters of the silk drying cylinder and the water content have a strong nonlinear relation, and the moisture variation caused by the same temperature rise or fall is different at different temperature levels;
3. uncertainty and large hysteresis characteristics exist in the cut tobacco drying process, and the control effect may not be completely the same under the same control conditions and environments; moreover, the effect of the adjustment of the control variable exhibits a hysteresis characteristic;
4. the cut tobacco drying process is generally divided into three sections, namely a stub bar, a middle material and a tail material, because the stub bar has no outlet moisture content measurement quantity, the feed back control cannot be carried out, the control is completely carried out according to experience, and because the quantity of cut tobacco is suddenly reduced, the temperature reduction rate of the cylinder wall is slow, the phenomenon that the stub bar is dry and the tail is serious occurs;
5. the service life of common cut-tobacco drier equipment is longer, but due to continuous use, the operation habits of operators are different, the ageing of equipment parts and the cut-tobacco drying performance are also reduced to different degrees, and the effective cut-tobacco drying effect cannot be achieved by the original control strategy or internal control index.
Disclosure of Invention
The invention comprehensively collects the processing parameters and process quality data of finished products and semi-finished products through online real-time monitoring, including an online detection system (equipment), associates environment and upstream and downstream process data, performs correlation analysis based on big data, constructs an analysis and control model, is tightly integrated with a centralized control system, automatically adjusts core key parameters, automatically pre-warns and automatically corrects deviation, so that the 'management' and 'control' work reduces human factors to the maximum extent, and the intelligent quality control is realized by producing on a preset track and track; operation standardization and process parameterization are realized through a mechanism analysis and data driving mode, quality fluctuation is reduced, and accurate control and optimal control are realized.
In order to realize the purpose, the invention is realized by adopting the following technical scheme: the method for optimizing the tobacco shred quality based on the tobacco shred dryer process parameter prediction comprises the following steps of 1, data acquisition: (1) acquiring process control data of the tobacco dryer, wherein the process control data comprises historical data and real-time data, and comprises fixed parameters including formula parameters and equipment parameters, and adjustable process parameters having great correlation with tobacco shred moisture; (2) the external sensor comprises an environment temperature sensor and an environment humidity sensor; step 2, establishing an outlet water prediction model, and step 3, establishing a process control optimization model; and 4, evaluating the cut tobacco drying capacity.
Preferably, the step 2 establishes an outlet moisture prediction model, and is realized by adopting the following two steps: (1) screening variable parameters with high correlation with outlet moisture through correlation analysis to serve as input, wherein the variable parameters include but are not limited to tobacco shred inlet moisture, inlet flow, inlet temperature, cylinder wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, roller rotating speed and environment temperature and humidity; (2) establishing a regression model with time delay, wherein input parameters comprise tobacco shred inlet moisture, inlet flow, inlet temperature, barrel wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, roller rotating speed, environment temperature and humidity, a three-stage prediction mode, a stub bar, a material center and a material tail.
Preferably, the prediction of the moisture of the head material, the middle material and the tail material comprises the following steps: the initial stage of the stub bar has no measurement quantity of the water content of the outlet, the feedback control cannot be carried out according to the water content of the outlet, and in addition, the regulation and the control are not easy to stabilize due to the fluctuation of the inlet flow, so that the modeling method mainly takes a mechanism model as a main part and takes data support as an auxiliary part; continuous cut tobacco output exists in the material, cut tobacco quality parameters can be obtained in real time, a self-adaptive data driving model is constructed, the cut tobacco drying performance can be comprehensively evaluated, the water holding rate is predicted, the error between the water holding rate and the actually monitored water content is calculated, the data model is fed back and corrected through the analysis of the error, and a parameter regulation and control suggestion instruction is formed; in the tail control stage, similar to the situation of the material head, the control parameters are predicted under the condition that the quantity of the cut tobacco is gradually reduced through moisture balance mechanism analysis, so that the moisture content of the discharged material is predicted.
Preferably, the process control optimization module in step 3 selects n continuous values of outlet moisture, forms a time sequence by using m historical measured real values and n-m future predicted values before the current time, and divides the control map into 6 regions according to 8 different criteria specified by the conventional control map of the national standard GB/T4091-2001, wherein the width of each region is 1 sigma.
Preferably, the evaluation of the cut-tobacco drying capability in the step 4 is mainly embodied in process capability indexes including outlet moisture and outlet temperature, standard deviation, variation coefficient, process control precision Cp value, process capability index Cpk and head and tail dryness rate.
The invention has the beneficial effects that:
the invention comprehensively collects the processing parameters and process quality data of finished products and semi-finished products through online real-time monitoring, including an online detection system (equipment), associates environment and upstream and downstream process data, performs correlation analysis based on big data, constructs an analysis and control model, is tightly integrated with a centralized control system, automatically adjusts core key parameters, automatically pre-warns and automatically corrects deviation, so that the 'management' and 'control' work reduces human factors to the maximum extent, and the intelligent quality control is realized by producing on a preset track and track; operation standardization and process parameterization are realized through a mechanism analysis and data driving mode, quality fluctuation is reduced, and accurate control and optimal control are realized.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a cut tobacco outlet moisture control chart;
FIG. 3 is a diagram of an optimization control model;
FIG. 4 shows the system of the present invention.
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those skilled in the art, the technical solutions of the present invention will be further described with reference to the accompanying drawings and specific embodiments.
With the development of the process technology and the requirements of the characteristic process technology, the process control is changed from result control to process prediction and control, aiming at the process standard, an optimal control parameter combination needs to be searched according to algorithms such as analysis of historical data, curve fitting and the like, corresponding data basis support is provided, the formulation of the process internal control standard is assisted and verified, the process technical parameters are adjusted in time, the performance of equipment is ensured to meet the process index requirements, meanwhile, the process index formulation meets the current situation of the equipment, and the production homogenization management is realized.
The method is realized by four functional modules: step 1, data acquisition is realized by (1) an intelligent sensing module, and the intelligent sensing module comprises two parts, namely configuration management and data acquisition.
Configuration management, which mainly comprises equipment configuration, measuring point configuration, parameter configuration and user authority management; each of the attached cut-tobacco drier devices is given a unique identification code, such as a factory-line-device number (FFF-LLL-TT001), and device attribute information, such as model and age, is manually entered into the system. The configuration of the measuring points and the parameters is mainly combined with the data acquisition way to set different interface protocols to ensure the data acquisition.
Data acquisition, which mainly aims at the acquisition of two types of data, namely acquiring process control data of a tobacco dryer, wherein the process control data comprises historical data and real-time data, fixed parameters including formula parameters and equipment parameters, and adjustable process parameters having great correlation with tobacco moisture; and the external sensor comprises an environment temperature sensor, an environment humidity sensor and the like.
Firstly, controlling data of a cut tobacco dryer process:
the formula parameters mainly comprise 6 items of process brand, cylinder wall temperature during rated work, discharge flow rate during TT rated work, TT drying coefficient, TT hot air set temperature, moisture set at an outlet of a cut tobacco dryer and HT moisture increase.
The equipment parameters mainly comprise tobacco shred inlet time, tobacco shred outlet time, a pressure building stage value, the opening degree of a steam valve in the pressure building stage, the set preheating temperature, a tobacco shred drying linear coefficient, idling speed, starting speed, production speed, tailing speed, a feed-forward control state, the temperature of the cylinder wall in the preloading process, the opening degree of a moisture exhaust air door in the starting state, the opening degree of a moisture exhaust air door in the production state, the opening degree of a moisture exhaust air door in the tailing state, the rotating speed of a hot air motor, the maximum speed of a TT roller, the maximum pressure of TT steam and the like.
The controllable parameters are: cylinder wall temperature (DEG C), moisture exhaust air door opening degree (%), hot air temperature (DEG C), and hot air valve opening degree (%); hot air motor frequency (HZ), drum speed (rpm), bottom air temperature (deg.c), air door opening (%), steam valve opening (%);
among the uncontrollable (but obtainable) parameters are: incoming material moisture (%), incoming material temperature (deg.C), discharge flow (kg/h), process flow, main steam temperature (deg.C), and discharge water content (%).
Secondly, the external sensor is used for supporting a process control optimization module, mainly assisting in supporting process control optimization, monitoring signals in the tobacco drying process can be obtained through a centralized control system, but influences of environment temperature and humidity on tobacco shreds are ignored, and therefore the installation of the environment temperature and humidity sensor is recommended to obtain two main environment variables of environment temperature (DEG C) and environment humidity (%).
In combination with the data sampling protocol of the existing control system, the above data sampling frequencies refer to the sampling frequency of the centralized control system in use, for example, the data sampling interval of the centralized control of a common cut-tobacco drier is 6 s; the selection of the environmental temperature and humidity is consistent with the centralized control acquisition frequency, and the sampling can be performed once every 6 s. While the vibration signal suggests a high sampling frequency, e.g. 25600 Hz.
More importantly, the intelligent sensing module has the function of intelligent analysis on the edge side, and the functions of high-order analysis and pretreatment such as data sorting, alignment, data quality detection and the like are performed on the collected multi-source data. And in the edge data acquisition stage, correlation analysis of sensor and controller data, data screening, data quality inspection of each measuring point, including basic inspection, inspection of distribution characteristics, inspection of randomness and autocorrelation, inspection of trend and stationarity, inspection of predictability and multi-dimensional sequence evaluation. The intelligent sensing module realizes the acquisition and the preprocessing of data and provides normalized data with guaranteed quality for subsequent functional modules, thereby ensuring the realization of the whole function.
The step 2 of establishing an outlet moisture prediction model comprises the following steps: and the outlet moisture prediction module and the process optimization module are realized.
In order to solve the problems of hysteresis of traditional control, fluctuation of a control process of a material head and a material tail, unstable outlet moisture caused by factors such as environmental influence and the like, the influence of the factors such as environment, raw materials, equipment, manpower and the like on a result variable is fully considered by combining with the setting requirement of process parameters, and two module functions, namely an outlet moisture prediction module and a process optimization module, are designed in the module.
Submodule one: outlet moisture prediction model
Firstly, variable parameters with high correlation with outlet moisture are screened out through correlation analysis to serve as input, wherein the variable parameters include but are not limited to tobacco shred inlet moisture, inlet flow, inlet temperature, barrel wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, roller rotating speed and environment temperature and humidity.
Secondly, establishing a regression model with time delay, inputting parameters including tobacco shred inlet moisture, inlet flow, inlet temperature, cylinder wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, drum rotating speed, environment temperature and humidity, a three-stage prediction mode, and a stub bar, a material center and a material tail. And in the stub bar stage, 4 cut tobacco drying performance evaluation indexes in each stub bar stage are calculated according to historical batch data, and a regression model is trained by adopting historical best practice, so that the result predicted by the feed starting stage in the stub bar stage based on an empirical model is controlled according to the trained model. Similarly, the modeling mode of the material tail stage is similar to that of the material head stage. In the middle stage of material, because the flow of the tobacco shreds is stable, the time length of the tobacco shreds passing through the roller is calculated according to the measured flow speed, the measured quantity of the inlet/outlet is aligned according to the time length, a nonlinear model such as a Kalman filtering method is established, because data has fluctuation and measurement errors, all parameters are subjected to down-sampling, all parameters are respectively averaged every minute, and the discharged water per minute is predicted in real time. Meanwhile, the error between the predicted value and the real value measured in real time is fed back to the model for optimization iteration. The specific analysis is described in detail below.
Stub bar moisture prediction
The initial stage of the stub bar has no measurement quantity of the water content of the outlet, so that the feedback control can not be carried out according to the water content of the outlet, and in addition, the regulation and the control are not easy to stabilize due to the fluctuation of the inlet flow. Therefore, the modeling method mainly takes a mechanism model as a main part and takes data support as an auxiliary part. On one hand, sample data of all batches of stub bar stages are screened out from historical data, the quality index, the standard deviation of discharged water content, the CPK value of the discharged water content and the CPK value of the discharged temperature of the stub bar are calculated for the outlet moisture of the stub bar, and historical optimal practices are found out to be used as input and output of model training and super parameters of a training mechanism model; on the other hand, a production simulation data environment is formed through a prediction model obtained through training, a single parameter or a parameter combination of equipment control is adjusted in a simulation environment, the value of outlet moisture is predicted, and tracking comparison is carried out in an actual environment.
Moisture prediction in feed
Continuous cut tobacco output exists in the material, and cut tobacco quality parameters such as cut tobacco outlet moisture and temperature can be obtained in real time; the input information of the model comprises sensor data, controller data and fault alarm and maintenance information, meanwhile, considering delay caused by tobacco shreds passing through a tobacco drying cylinder, calculating delay time of the tobacco shreds passing through the model according to the measured flow rate, considering quality performance parameters (mainly the moisture content of the outlet tobacco shreds) corresponding to the delay as output of the model, constructing a self-adaptive data driving model, comprehensively evaluating the tobacco drying performance, predicting the water holding rate, calculating errors with the actually monitored moisture content, feeding back a correction data model for analysis of the errors, and forming parameter regulation and control suggestion instructions. Aiming at the selection of a prediction model, a large amount of historical data of related parameters of the cut tobacco drying is required to be obtained, different data reconstruction methods of selectable prediction models (PSO, Kalman Filter, Particle Filter and the like) are respectively tested on a large data platform, comparison and evaluation are carried out from the aspects of error range, residual sequence stability and the like, and an optimal control algorithm model is selected.
Prediction of tailing moisture
The amount of the cut tobacco is obviously reduced due to the fact that the material tail is close to the tail of the batch, and the flowing speed of the cut tobacco in the cylinder depends on the speed of wind; the temperature of the cylinder wall is quickly reduced, the flow rate of the cut tobacco is accelerated, and the retention time of the cut tobacco in the cylinder is shortened, so that the quantity of the dry cut tobacco is reduced. In the tail control stage, similar to the situation of the material head, the control parameters are predicted under the condition that the quantity of the cut tobacco is gradually reduced through moisture balance mechanism analysis, so that the moisture content of the discharged material is predicted.
Submodule II: process control optimization model
The process control optimization module selects continuous n numerical values of the outlet moisture, forms a time sequence by using m historical measured real values and n-m future predicted numerical values before the current moment, and divides a control chart into 6 areas according to 8 different criteria specified by a national standard GB/T4091-2001 conventional control chart, wherein the width of each area is 1sigma, and the reference is shown in the figure 2. The 8 criteria for differentiation are:
one point falls outside zone A
The continuous 9 points fall on the same side of the central line
Successive 6-point increments or decrements
Adjacent two points in the continuous 14 points alternate up and down
2 of the continuous 3 points fall outside the B area on the same side of the central line
4 of the 5 points are outside the C area on the same side of the central line
15 points are above and below the center line of the C zone
6 points are on both sides of the center line, but no 1 point is in the C region
And judging control chart judgment criteria of the outlet moisture sequence, and starting an online optimization module when any one criterion is met. The optimization module adopts a genetic algorithm to solve, the cylinder wall temperature, the opening degree of the moisture exhaust air door, the hot air temperature and the opening degree of the hot air door are used as optimization variables and are expressed by six-bit binary codes, and the encoding process is explained by taking the cylinder wall temperature as an example: the upper and lower limits of the temperature of the cylinder wall are 110 to 180 degrees, if the code is '010011', the six-digit binary code can represent an integer interval of 0 to 63, so that the value represented by '010011' is 19/63-0.30158, and then the six-digit binary code is converted into the range of the upper and lower limits of the temperature of the cylinder wall, namely 110+0.30158 (180-110) ═ 131.11 degrees, and so on. The binary codes of the four variables are combined into a chromosome with the length of 24 bits, namely the coding process. The fitness function is the relative deviation of the outlet moisture content predicted by using the current variable combination and the actual moisture content. The population number is set to be 40, two chromosomes are crossed by adopting a multi-point crossing strategy, and the crossing probability is 0.9. Random variation is adopted, and the variation probability is set to be 0.05. And when the optimal fitness of the population does not change any more in a plurality of continuous iterations or reaches the upper limit of the iteration times, stopping the algorithm and outputting the result to obtain the optimal parameter combination of the cylinder wall temperature, the moisture exhaust air door opening degree, the hot air temperature and the hot air door opening degree. Thus, the adjustment amount of the parameter to be adjusted is calculated and fed back to the interface or directly to the controller.
The model prediction results are all set with a confidence interval and are not directly used for parameter adjustment, but the control chart abnormality judgment criterion is set through short-term trend prediction, when the future outlet water abnormality judgment is predicted, namely the standard of 'needing to be optimized' is reached, the constraint condition of the optimization model is configured, if the current value is increased, the current value is used as a lower bound, if the current value is decreased, the current value is used as an upper bound, the optimization model enters the parameter optimization model, and corresponding parameter adjustment instructions are given.
Calculating the delay time of a tobacco drying roller to be n according to the speed of a belt, wherein the average value or the median value of outlet moisture per minute represents the tobacco moisture due to measurement errors and fluctuation of actual tobacco outlet moisture, predicting the outlet moisture value of n minutes in the future from an outlet moisture prediction module, starting an optimization algorithm when the predicted value of more than half of the outlet moisture exceeds a first upper and lower limit threshold, wherein the optimization algorithm comprises configuration of constraint conditions of an optimization model, decision variables and objective functions, recommending methods such as a genetic algorithm, a particle swarm optimization algorithm and an annealing algorithm, calculating on line, and giving out the adjustment quantity of parameters to be adjusted.
Therefore, the hybrid model can simulate the physical reaction process of the hybrid model through a mechanism, and can dynamically identify the change of working conditions, so that dynamic control instructions are given under different working conditions, the optimal control parameter combination is given in a self-adaptive manner, and the optimal patch operation is achieved.
Step 3, the cut tobacco drying capability evaluation is realized by a cut tobacco drying capability evaluation module: for the quality of the export cut tobacco, a set of comprehensive performance evaluation method for evaluating the quality of the process control is summarized. The method for evaluating the comprehensive performance of the cut tobacco dryer is mainly embodied in the process capability index comprising outlet moisture and outlet temperature, standard deviation, variation coefficient, process control precision Cp value, process capability index Cpk and dry head and tail rate, and the specific indexes are shown in the following table 1
TABLE 1 cut tobacco dryer Performance control index
(4) System device module
Based on the description of the three functional modules, the invention designs a set of automatic online system device, as shown in fig. 4.
In order to ensure the real-time performance of data, a workshop is taken as a unit, technological parameters, equipment parameters and process control parameters of the cut tobacco dryer equipment are accessed through an industrial control ring network, meanwhile, sensor signals are obtained from an edge intelligent terminal, temperature and humidity signals of the environment and the like are accessed into an edge MySQL database, and worksheet data accessed from an MES or ERP system are obtained. Then, the multi-source signals are subjected to data management, alignment, arrangement, storage, extraction and the like on an edge server to form an intelligent sensing module; meanwhile, an intelligent algorithm module and an outlet moisture prediction and process optimization module are executed. The cloud server is deployed in a cloud service center of a group or a factory, cluster management, model training, optimization and management are carried out on the cut tobacco dryers in all workshops on the cloud server, and full life cycle management of all the cut tobacco dryers is achieved.
Finally, in a webpage or mobile phone APP terminal display mode, on one hand, control operation suggestions are provided for operators on an operation table, and equipment maintenance suggestions are provided for maintainers; on the other hand, a control instruction is directly formed, set values of the cylinder wall temperature, the hot air fan frequency, the hot air temperature and the moisture removal fan frequency are given, the cut tobacco dryer is directly fed back and controlled through an OPC/DA (optical proximity correction/data acquisition) protocol, and automatic closed-loop control is achieved.
The operation panel has included basic information display function, ejection of compact moisture content quality index, operation aid decision suggestion function.
The state information shows the running state of the equipment, the cut tobacco batch/brand and the sampling time;
the state monitoring information comprises inlet temperature, inlet flow and cut tobacco drying capacity evaluation indexes (5 indexes);
the adjusting parameters comprise the cylinder wall temperature, the hot air fan frequency, the hot air temperature and the moisture removal fan frequency;
the prediction analysis result displays the real-time monitoring value and the future prediction value of the outlet moisture, an inlet moisture trend graph and an outlet moisture trend graph;
an operation recommendation, a recommendation value for the adjustment parameter.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction is characterized in that: the method for optimizing the tobacco shred quality based on the tobacco shred dryer process parameter prediction comprises the following steps of 1, data acquisition: (1) acquiring process control data of the tobacco dryer, wherein the process control data comprises historical data and real-time data, and comprises fixed parameters including formula parameters and equipment parameters, and adjustable process parameters having great correlation with tobacco shred moisture; (2) the external sensor comprises an environment temperature sensor and an environment humidity sensor; step 2, establishing an outlet water prediction model, and step 3, establishing a process control optimization model; and 4, evaluating the cut tobacco drying capacity.
2. The method for optimizing the tobacco shred quality based on the tobacco shred dryer process parameter prediction according to claim 1, wherein the method comprises the following steps: the step 2 of establishing an outlet water prediction model is realized by adopting the following two steps: (1) screening variable parameters with high correlation with outlet moisture through correlation analysis to serve as input, wherein the variable parameters include but are not limited to tobacco shred inlet moisture, inlet flow, inlet temperature, cylinder wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, roller rotating speed and environment temperature and humidity; (2) establishing a regression model with time delay, wherein input parameters comprise tobacco shred inlet moisture, inlet flow, inlet temperature, barrel wall temperature, moisture exhaust air door opening degree, hot air temperature, hot air door opening degree, steam temperature, steam valve opening degree, roller rotating speed, environment temperature and humidity, a three-stage prediction mode, a stub bar, a material center and a material tail.
3. The method for optimizing the tobacco shred quality based on the tobacco shred dryer process parameter prediction according to claim 2, wherein the method comprises the following steps: the prediction of the moisture of the head material, the middle material and the tail material comprises the following steps: the initial stage of the stub bar has no measurement quantity of the water content of the outlet, the feedback control cannot be carried out according to the water content of the outlet, and in addition, the regulation and the control are not easy to stabilize due to the fluctuation of the inlet flow, so that the modeling method mainly takes a mechanism model as a main part and takes data support as an auxiliary part; continuous cut tobacco output exists in the material, cut tobacco quality parameters can be obtained in real time, a self-adaptive data driving model is constructed, the cut tobacco drying performance can be comprehensively evaluated, the water holding rate is predicted, the error between the water holding rate and the actually monitored water content is calculated, the data model is fed back and corrected through the analysis of the error, and a parameter regulation and control suggestion instruction is formed; in the tail control stage, similar to the situation of the material head, the control parameters are predicted under the condition that the quantity of the cut tobacco is gradually reduced through moisture balance mechanism analysis, so that the moisture content of the discharged material is predicted.
4. The method for optimizing the cut tobacco quality based on the process parameter prediction of the cut tobacco dryer according to any one of claims 1, 2 and 3, is characterized in that: and 3, selecting continuous n numerical values of the outlet water by the process control optimization module, forming a time sequence by using m historical measured real values and n-m future predicted numerical values before the current moment, and dividing the control chart into 6 regions according to 8 different criteria specified by the national standard GB/T4091-2001 conventional control chart, wherein the width of each region is 1 sigma.
5. The method for optimizing the tobacco shred quality based on the tobacco shred dryer process parameter prediction according to claim 4, wherein the method comprises the following steps: and 4, the evaluation of the cut tobacco drying capacity is mainly embodied in process capacity indexes including outlet moisture and outlet temperature, standard deviation, variation coefficient, process control precision Cp value, process capacity index Cpk and head-to-tail ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110382903.0A CN113017132A (en) | 2021-04-09 | 2021-04-09 | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110382903.0A CN113017132A (en) | 2021-04-09 | 2021-04-09 | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113017132A true CN113017132A (en) | 2021-06-25 |
Family
ID=76456304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110382903.0A Pending CN113017132A (en) | 2021-04-09 | 2021-04-09 | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113017132A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537635A (en) * | 2021-08-10 | 2021-10-22 | 昆明理工大学 | Tobacco shredding process parameter optimization method based on edge calculation |
| CN113576017A (en) * | 2021-07-15 | 2021-11-02 | 河南中烟工业有限责任公司 | Cut tobacco drying water control method |
| CN113656456A (en) * | 2021-08-13 | 2021-11-16 | 上海铸世自动化科技有限公司 | Real-time acquisition control method for process parameter big data in die-casting production |
| CN114027539A (en) * | 2021-11-04 | 2022-02-11 | 湖北中烟工业有限责任公司 | Model prediction control-based loosening and conditioning quantitative water adding control method |
| CN114115393A (en) * | 2021-11-04 | 2022-03-01 | 湖北中烟工业有限责任公司 | Method for controlling moisture and temperature at outlet of cut tobacco dryer for sheet cut tobacco making line |
| CN114304709A (en) * | 2021-12-30 | 2022-04-12 | 云南烟叶复烤有限责任公司 | Automatic control method, storage medium and system for operating parameters of threshing and redrying equipment |
| CN114324764A (en) * | 2021-12-30 | 2022-04-12 | 红云红河烟草(集团)有限责任公司 | Multi-dimensional evaluation method for product quality in cigarette shredding process based on material characteristic value |
| 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 |
| CN115226925A (en) * | 2022-07-18 | 2022-10-25 | 红云红河烟草(集团)有限责任公司 | Monitoring method for steam quality stability of sheet cut-tobacco drier, storage medium and application |
| 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 |
| CN115978977A (en) * | 2023-02-10 | 2023-04-18 | 上海益实智能科技有限公司 | Method and device for controlling moisture content of outlet of thin plate cut tobacco dryer in stages |
| CN116076765A (en) * | 2023-01-18 | 2023-05-09 | 红塔烟草(集团)有限责任公司 | Cut-tobacco dryer outlet moisture prediction method based on transfer function |
| CN116172231A (en) * | 2023-03-21 | 2023-05-30 | 上海益实智能科技有限公司 | Method and device for controlling outlet water content of sheet cut-tobacco dryer |
| CN116258080A (en) * | 2023-03-21 | 2023-06-13 | 上海益实智能科技有限公司 | Method and device for predicting outlet water content of sheet cut-tobacco dryer |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE1632157A1 (en) * | 1967-12-23 | 1972-01-05 | Quester Fa Wilh | Method and device for drying tobacco and the like. |
| CN101488024A (en) * | 2009-01-23 | 2009-07-22 | 秦皇岛烟草机械有限责任公司 | On-line quality evaluation and real-time intelligent control method for tobacco process parameter |
| CN102488308A (en) * | 2011-12-14 | 2012-06-13 | 东华大学 | Advanced coordinated control system for moisture in cut tobacco dryer |
| CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method for predicting control index by using processing parameter in tobacco processing procedure |
| 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 |
| CN105996107A (en) * | 2016-06-17 | 2016-10-12 | 河南中烟工业有限责任公司 | Cut tobacco quality control method and system based on sheet cut tobacco drying |
| CN107966976A (en) * | 2017-12-06 | 2018-04-27 | 中南大学 | A kind of baking silk moisture control loop performance evaluation of data-driven and adjustment system |
| CN110826229A (en) * | 2019-11-07 | 2020-02-21 | 长沙学院 | Cut tobacco drying head process modeling and optimal setting control method based on long-term prediction |
| CN111045326A (en) * | 2019-10-22 | 2020-04-21 | 杭州安脉盛智能技术有限公司 | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network |
-
2021
- 2021-04-09 CN CN202110382903.0A patent/CN113017132A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE1632157A1 (en) * | 1967-12-23 | 1972-01-05 | Quester Fa Wilh | Method and device for drying tobacco and the like. |
| CN101488024A (en) * | 2009-01-23 | 2009-07-22 | 秦皇岛烟草机械有限责任公司 | On-line quality evaluation and real-time intelligent control method for tobacco process parameter |
| CN102488308A (en) * | 2011-12-14 | 2012-06-13 | 东华大学 | Advanced coordinated control system for moisture in cut tobacco dryer |
| CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method for predicting control index by using processing parameter in tobacco processing procedure |
| 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 |
| CN105996107A (en) * | 2016-06-17 | 2016-10-12 | 河南中烟工业有限责任公司 | Cut tobacco quality control method and system based on sheet cut tobacco drying |
| CN107966976A (en) * | 2017-12-06 | 2018-04-27 | 中南大学 | A kind of baking silk moisture control loop performance evaluation of data-driven and adjustment system |
| CN111045326A (en) * | 2019-10-22 | 2020-04-21 | 杭州安脉盛智能技术有限公司 | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network |
| CN110826229A (en) * | 2019-11-07 | 2020-02-21 | 长沙学院 | Cut tobacco drying head process modeling and optimal setting control method based on long-term prediction |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113576017B (en) * | 2021-07-15 | 2022-09-23 | 河南中烟工业有限责任公司 | Cut tobacco drying water control method |
| CN113576017A (en) * | 2021-07-15 | 2021-11-02 | 河南中烟工业有限责任公司 | Cut tobacco drying water control method |
| CN113537635A (en) * | 2021-08-10 | 2021-10-22 | 昆明理工大学 | Tobacco shredding process parameter optimization method based on edge calculation |
| CN113656456A (en) * | 2021-08-13 | 2021-11-16 | 上海铸世自动化科技有限公司 | Real-time acquisition control method for process parameter big data in die-casting production |
| CN113656456B (en) * | 2021-08-13 | 2024-10-01 | 上海铸世自动化科技有限公司 | Real-time acquisition control method for big data of technological parameters in die casting production |
| CN114115393A (en) * | 2021-11-04 | 2022-03-01 | 湖北中烟工业有限责任公司 | Method for controlling moisture and temperature at outlet of cut tobacco dryer for sheet cut tobacco making line |
| CN114027539A (en) * | 2021-11-04 | 2022-02-11 | 湖北中烟工业有限责任公司 | Model prediction control-based loosening and conditioning quantitative water adding control method |
| CN114324764A (en) * | 2021-12-30 | 2022-04-12 | 红云红河烟草(集团)有限责任公司 | Multi-dimensional evaluation method for product quality in cigarette shredding process based on material characteristic value |
| CN114304709A (en) * | 2021-12-30 | 2022-04-12 | 云南烟叶复烤有限责任公司 | Automatic control method, storage medium and system for operating parameters of threshing and redrying equipment |
| 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 |
| CN115226925A (en) * | 2022-07-18 | 2022-10-25 | 红云红河烟草(集团)有限责任公司 | Monitoring method for steam quality stability of sheet cut-tobacco drier, storage medium and application |
| 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 |
| CN116076765A (en) * | 2023-01-18 | 2023-05-09 | 红塔烟草(集团)有限责任公司 | Cut-tobacco dryer outlet moisture prediction method based on transfer function |
| CN115978977A (en) * | 2023-02-10 | 2023-04-18 | 上海益实智能科技有限公司 | Method and device for controlling moisture content of outlet of thin plate cut tobacco dryer in stages |
| CN116172231A (en) * | 2023-03-21 | 2023-05-30 | 上海益实智能科技有限公司 | Method and device for controlling outlet water content of sheet cut-tobacco dryer |
| CN116258080A (en) * | 2023-03-21 | 2023-06-13 | 上海益实智能科技有限公司 | Method and device for predicting outlet water content of sheet cut-tobacco dryer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113017132A (en) | Cut tobacco quality optimization method based on cut tobacco dryer process parameter prediction | |
| AU2021102749A4 (en) | Intelligent control system and method of thin plate drier for cut tobacco | |
| CN112021626B (en) | Intelligent control system and method for tobacco shred making link | |
| CN111045326B (en) | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network | |
| CN102147613B (en) | Model predictive control method and system for moisture and temperature of tobacco redryer | |
| CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
| CN111887460A (en) | Tobacco cut-tobacco drying moisture and temperature control prediction system and method | |
| CN111103854A (en) | System and method for improving production stability of tobacco cut-tobacco drier | |
| CN105996106B (en) | A kind of tobacco quality control method and system based on pneumatic conveying drying | |
| CN105996107A (en) | Cut tobacco quality control method and system based on sheet cut tobacco drying | |
| CN112327960B (en) | Intelligent control system for loosening and dampening equipment | |
| CN114115393A (en) | Method for controlling moisture and temperature at outlet of cut tobacco dryer for sheet cut tobacco making line | |
| CN114510098B (en) | Production environment regulation and control method and system | |
| CN115251445B (en) | Control method for moisture content of tobacco leaves at outlet of loosening and conditioning machine | |
| CN109032117B (en) | ARMA model-based single-loop control system performance evaluation method | |
| CN111165866A (en) | Quality control method and system based on airflow type cut stem drying | |
| CN115328062A (en) | Intelligent control system for spunlace production line | |
| CN108376263B (en) | Method and device for predicting environment temperature and humidity of workplace | |
| CN113303489A (en) | Method for accurately controlling moisture of tobacco leaves in tobacco shred making process | |
| CN111950166B (en) | Cost optimization method for household paper making machine based on data mining | |
| CN116757354A (en) | Tobacco redrying section key parameter screening method based on multilayer perceptron | |
| CN116611349A (en) | Neural network-based roller wire drying process parameter optimization method and system | |
| CN109001989B (en) | Machine control method based on intelligent learning algorithm | |
| CN106072743A (en) | A kind of stem method of quality control being dried based on stem and system | |
| CN115356995A (en) | Tobacco drying process heat energy analysis system based on industrial big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |