CN114493311A - Automatic regulation and control method and device for cigarette loose-end rejection rate - Google Patents
Automatic regulation and control method and device for cigarette loose-end rejection rate Download PDFInfo
- Publication number
- CN114493311A CN114493311A CN202210125329.5A CN202210125329A CN114493311A CN 114493311 A CN114493311 A CN 114493311A CN 202210125329 A CN202210125329 A CN 202210125329A CN 114493311 A CN114493311 A CN 114493311A
- Authority
- CN
- China
- Prior art keywords
- cigarette
- rejection rate
- target
- equipment process
- correlation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24C—MACHINES FOR MAKING CIGARS OR CIGARETTES
- A24C5/00—Making cigarettes; Making tipping materials for, or attaching filters or mouthpieces to, cigars or cigarettes
- A24C5/32—Separating, ordering, counting or examining cigarettes; Regulating the feeding of tobacco according to rod or cigarette condition
- A24C5/34—Examining cigarettes or the rod, e.g. for regulating the feeding of tobacco; Removing defective cigarettes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Genetics & Genomics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an automatic regulation and control method and device for the cigarette loose-end rejection rate, which comprises the following steps: determining a plurality of target equipment process parameters which have a correlation with the cigarette loose-end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients; based on multiple groups of historical data, obtaining a target prediction model with multiple target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables through a regression algorithm; acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm, and forming an optimal value group corresponding to a plurality of equipment process parameters; and inputting the optimal value set into a cigarette making machine management platform so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value set. The control on the cigarette loose end rejection rate is realized by acquiring the optimal values of all the influence factors for reducing the cigarette loose end rejection rate to the lowest, and the quality of cigarette products is improved.
Description
Technical Field
The application relates to the technical field of control of cigarette loose-end rejection rate, in particular to an automatic regulation and control method and device of cigarette loose-end rejection rate.
Background
In the production process of cigarettes, the rejection rate of cigarette loose ends is an important index influencing the production cost and the appearance quality of the cigarettes, and the existence of the cigarette loose ends not only directly relates to the quantity of cigarette waste in the production process, but also restricts the improvement of the production cost; but also has obvious influence on the stable control of the physical and chemical indexes and the internal quality of the cigarettes.
In the prior art, the reduction of the cigarette loose end rejection rate is generally adjusted by adopting a single-factor optimization mode, the mode has limitation, a plurality of equipment process parameters in the cigarette production process can influence the cigarette loose end rejection rate, the cigarette loose end rejection rate is controlled from a single-factor direction, and various equipment process parameters in the cigarette production process are changed in real time, so that the cigarette loose end rejection rate is suddenly high and suddenly low, the control on the cigarette loose end rejection rate cannot be realized, and the quality of cigarette products cannot be ensured.
Disclosure of Invention
In view of this, an object of the present application is to provide at least an automatic control method and device for cigarette loose-end rejection rate, which control the cigarette production process by obtaining optimal values of various influencing factors that reduce the cigarette loose-end rejection rate to the lowest and by using a plurality of optimal values, thereby realizing control of the cigarette loose-end rejection rate and improving the quality of cigarette products.
The application mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides an automatic control method for a cigarette loose-end rejection rate, where the method includes: acquiring multiple groups of historical data, wherein each group of historical data comprises equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the defective cigarette rejection rate in the final cigarette rolling and packing process; according to multiple groups of historical data, performing correlation analysis between the cigarette loose end rejection rate and each equipment process parameter to obtain multiple correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter; determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients; based on multiple groups of historical data, obtaining a target prediction model with multiple target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables through a regression algorithm; acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm, and forming an optimal value group corresponding to a plurality of equipment process parameters; and inputting the optimal value set into a cigarette making machine management platform so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value set.
In a possible implementation mode, the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and each equipment process parameter; the method comprises the following steps of determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients, wherein the step of determining the plurality of target equipment process parameters which have the correlation with the cigarette loose end rejection rate comprises the following steps: judging whether the correlation coefficient is in a weak correlation interval or not aiming at each correlation coefficient; if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation equipment process parameter; and if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
In a possible implementation mode, the step of obtaining the target prediction model with the process parameters of the target devices as independent variables and the cigarette loose-end rejection rate as dependent variables through a regression algorithm based on multiple sets of historical data comprises the following steps: screening weak relevant equipment process parameters from multiple groups of historical data to obtain multiple groups of target historical data; dividing a plurality of groups of target historical data into a training data set and a testing data set according to a preset proportion; establishing an initial prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables by using training set data; verifying the precision of the initial prediction model by using a test data set to obtain a precision verification result; and obtaining a target prediction model according to the precision verification result.
In one possible embodiment, the test set data includes a plurality of test samples, each test sample including a plurality of target equipment process parameters and a cigarette loose-end reject rate: verifying the precision of the initial prediction model by using the test data set, wherein the step of obtaining a precision verification result comprises the following steps: inputting a plurality of target equipment process parameters in each test sample into an initial prediction model to obtain a predicted value of the cigarette loose-end rejection rate corresponding to the test sample; acquiring a difference value between a predicted value of the cigarette loose end rejection rate corresponding to the test sample and an actual value of the cigarette loose end rejection rate in the test sample; and calculating the sum of squares of the obtained multiple difference values, and determining the sum of squares of the multiple difference values as a precision verification result.
In a possible implementation, the step of obtaining the target prediction model according to the precision verification result includes: judging whether the precision verification result is in a preset precision interval or not; and if the precision verification result is in a preset precision interval, determining the initial prediction model as a target prediction model.
In a possible implementation manner, the step of obtaining the optimal value of each target equipment process parameter, which enables the cigarette loose-end rejection rate to be reduced to the lowest, in the target prediction model through a genetic algorithm and forming the optimal value group corresponding to the plurality of equipment process parameters comprises the following steps: acquiring a preset value constraint range of each target device process parameter; and in the value restriction range of each target influence factor, acquiring the optimal value of each target equipment process parameter for reducing the cigarette loose-end rejection rate to the lowest value in the target prediction model by using a genetic algorithm.
In a second aspect, the embodiment of the present application further provides an automatic control device for a cigarette loose-end rejection rate, and the automatic control device includes: the first acquisition module is used for acquiring a plurality of groups of historical data, wherein each group of historical data comprises equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the defective cigarette rejection rate in the final cigarette rolling and packing process; the analysis module is used for carrying out correlation analysis between the cigarette loose end rejection rate and each equipment process parameter according to a plurality of groups of historical data to obtain a plurality of correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter; the first determination module is used for determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients; the second acquisition module is used for acquiring a target prediction model which takes a plurality of target equipment process parameters as independent variables and the cigarette loose-end rejection rate as dependent variables through a regression algorithm based on a plurality of groups of historical data; the third acquisition module is used for acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm and forming an optimal value group corresponding to a plurality of equipment process parameters; and the regulating and controlling module is used for determining that the optimal value group is input into the cigarette making machine management platform so that the cigarette making machine management platform can regulate the process parameters of each target device according to the received optimal value group.
In a possible embodiment, the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and the process parameters of each device; the first determining module is further configured to: judging whether the correlation coefficient is in a weak correlation interval or not aiming at each correlation coefficient; if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation equipment process parameter; and if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
In a possible implementation, the second obtaining module is further configured to: screening weak relevant equipment process parameters from multiple groups of historical data to obtain multiple groups of target historical data; dividing a plurality of groups of target historical data into a training data set and a testing data set according to a preset proportion; establishing an initial prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables by using training set data; verifying the precision of the initial prediction model by using a test data set to obtain a precision verification result; and obtaining a target prediction model according to the precision verification result.
In a possible implementation, the second obtaining module is further configured to: judging whether the precision verification result is in a preset precision interval or not; and if the precision verification result is in a preset precision interval, determining the initial prediction model as a target prediction model.
The embodiment of the application provides an automatic regulation and control method for the cigarette loose-end rejection rate, which comprises the following steps: acquiring multiple groups of historical data, wherein each group of historical data comprises equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the defective cigarette rejection rate in the final cigarette rolling and packing process; according to multiple groups of historical data, performing correlation analysis between the cigarette loose end rejection rate and each equipment process parameter to obtain multiple correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter; determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients; based on multiple groups of historical data, obtaining a target prediction model with multiple target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables through a regression algorithm; acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm, and forming an optimal value group corresponding to a plurality of equipment process parameters; and inputting the optimal value set into a cigarette making machine management platform so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value set. Through obtaining the optimal value of each influence factor which reduces the cigarette loose-end rejection rate to the lowest, the cigarette production process is regulated and controlled through a plurality of optimal values, so that the control on the cigarette loose-end rejection rate is realized, and the quality of cigarette products is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a flow chart illustrating an automatic control method for the rejection rate of cigarette loose ends according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating steps for determining process parameters for a plurality of target devices according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of the steps provided in an embodiment of the present application to obtain a target prediction model;
fig. 4 is a schematic structural diagram of an automatic control device according to an embodiment of the present application.
Detailed Description
To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In the prior art, the reduction of the cigarette loose end rejection rate is generally adjusted by adopting a single-factor optimization mode, the mode has limitation, the whole consideration of cigarette production procedures cannot be considered, a plurality of equipment process parameters in the cigarette production process can influence the cigarette loose end rejection rate, the cigarette loose end rejection rate is controlled from a single-factor direction, and various equipment process parameters in the cigarette production process change in real time, so that the cigarette loose end rejection rate is suddenly high and suddenly low, the control of the cigarette loose end rejection rate cannot be realized, and the quality of cigarette products cannot be ensured.
Based on this, this application embodiment provides an automatic regulation and control method of cigarette odd rejection rate, through obtaining the optimal value of each influence factor that drops cigarette odd rejection rate to minimum, through a plurality of optimal values, regulates and control cigarette production process to realize the control to cigarette odd rejection rate, promote cigarette product quality, specifically as follows:
referring to fig. 1, fig. 1 is a flowchart illustrating an automatic control method for a cigarette loose-end rejection rate according to an embodiment of the present disclosure. As shown in fig. 1, the method for automatically regulating and controlling the cigarette loose-end rejection rate provided by the embodiment of the application includes the following steps:
s100: and acquiring multiple sets of historical data.
Here, each set of historical data includes equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the cigarette loose-end rejection rate in the final cigarette rolling and packing process.
In specific implementation, the equipment technological parameters include, but are not limited to, humidity, temperature, cigarette weight deviation, cigarette moisture content, tobacco purity, cigarette weight and the like, the cigarette loose-end rejection rate refers to the ratio of the number of finally obtained loose-end cigarettes to the number of all produced cigarettes in a batch of cigarette production process, a sensor on the cigarette making machine equipment can detect and record various equipment technological parameter values in the cigarette production process in real time, and upload data to a data analysis platform according to the production batch, specifically, each cigarette making machine equipment can be integrated to the data analysis platform through a network interface to realize data interaction with the cigarette making machine equipment, and the data analysis platform is used for managing various equipment technological parameter data generated in the cigarette making machine equipment production process.
The method comprises the steps of obtaining multiple groups of historical data, wherein multiple batches of historical data of a large number of different cigarette making machine devices are stored in a data analysis platform, obtaining multiple batches of historical data of corresponding cigarette making machine devices from the data analysis platform, cleaning the multiple batches of historical data, namely processing the corresponding batches of historical data with equipment technological parameter loss and/or cigarette loose end rejection rate loss, and finally obtaining multiple groups of historical data.
S200: and according to multiple groups of historical data, performing correlation analysis between the cigarette loose end rejection rate and each equipment process parameter to obtain multiple correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter.
The method comprises the steps of obtaining a plurality of correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter through correlation analysis between the cigarette loose end rejection rate and each equipment process parameter, obtaining a plurality of actual values of the corresponding cigarette loose end rejection rate in a plurality of groups of historical data, obtaining a plurality of actual values of the corresponding equipment process parameter in a plurality of groups of historical data aiming at each equipment process parameter, and obtaining the correlation coefficients between the cigarette loose end rejection rate and the equipment process parameter according to a Pearson correlation coefficient method.
S300, determining a plurality of target equipment process parameters which have a correlation with the cigarette loose-end rejection rate from a plurality of equipment process parameters according to the plurality of correlation coefficients.
Here, the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and the technological parameters of each device, and the value of the correlation coefficient is generally (-1, 1).
Referring to fig. 2, fig. 2 is a flowchart illustrating a process for determining a plurality of target device process parameters according to an embodiment of the present disclosure. As shown in fig. 2, the step of determining a plurality of target equipment process parameters having a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients includes:
s310, for each correlation coefficient, determine whether the correlation coefficient is in a weak correlation interval.
In the specific implementation, the weak correlation interval is a certain interval which is preset and very close to 0, wherein the value of the correlation coefficient is greater than zero to indicate that the cigarette loose-end rejection rate is in positive correlation with the corresponding equipment process parameter, the value of the correlation coefficient is less than zero to indicate that the cigarette loose-end rejection rate is in negative correlation with the corresponding equipment process parameter, the value of the correlation coefficient is close to-1 or 1 to indicate that the stronger the correlation between the cigarette loose-end rejection rate and the corresponding equipment process parameter is, and the closer the value of the correlation coefficient is to 0 to indicate that the weaker the correlation between the cigarette loose-end rejection rate and the corresponding equipment process parameter is, so the weak correlation interval is the equipment process parameter which is used for eliminating the correlation with the cigarette loose-end rejection rate.
And S320, if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation process parameter.
In a specific embodiment, if the value of the correlation coefficient is in a weak correlation interval, that is, it indicates that there is no correlation between the cigarette loose-end rejection rate and the corresponding equipment process parameter, the equipment process parameter corresponding to the correlation coefficient is determined as the weak correlation equipment process parameter.
And S330, if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
In a specific embodiment, if the value of the correlation coefficient is not in the weak correlation interval, that is, the cigarette loose-end rejection rate and the corresponding equipment process parameter have correlation, the equipment process parameter corresponding to the correlation coefficient is determined as the target equipment process parameter.
Returning to the figure 1, and S400, obtaining a target prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables through a regression algorithm based on a plurality of groups of historical data.
Referring to fig. 3, fig. 3 is a flowchart illustrating steps of obtaining a target prediction model according to an embodiment of the present disclosure. As shown in fig. 3, the step of obtaining the target prediction model with the process parameters of the target devices as independent variables and the cigarette loose-end rejection rate as dependent variables through the regression algorithm includes:
and S410, screening weak related equipment process parameters from multiple sets of historical data to obtain multiple sets of target historical data.
In specific implementation, the weakly related equipment process parameters obtained in step S300 need to be screened from multiple sets of historical data, and multiple sets of target historical data are obtained, where each set of target historical data includes multiple target equipment process parameters and a cigarette loose-end rejection rate.
And S420, dividing the multiple groups of target historical data into a training data set and a testing data set according to a preset proportion.
In a preferred embodiment, the predetermined ratio is generally 7: 3 or 8: 2, the training data set and the test data set include different sets of target history data.
And S430, establishing an initial prediction model with the process parameters of the target devices as independent variables and the cigarette loose-end rejection rate as dependent variables by using the training set data.
The initial prediction model is used for predicting the cigarette loose end rejection rate through a plurality of target equipment process parameters, and the initial prediction model is a linear regression model with the plurality of target equipment process parameters as independent variables and the cigarette loose end rejection rate as dependent variables.
In a specific embodiment, a linear regression model with a plurality of target equipment process parameters as independent variables, a cigarette loose-end rejection rate as dependent variables and unknown model parameters may be established, where the model parameters are weights of each target equipment process parameter in the linear regression model, for example, the following formula:
y＝a1x1+a2x2+…+anxn (1)
as shown in formula (1), y represents the cigarette loose-end rejection rate, n represents the number of the target equipment process parameters, x represents each target equipment process parameter, and a represents the weight of each target equipment process parameter in the linear regression model, namely the model parameter, wherein a representsnxnRepresents a weight of anThe weight coefficient of each target equipment process parameter in the linear regression model is unknown, and the model parameters can be solved by using training set data and combining a least square method.
Specifically, the training data set comprises a plurality of training samples, each training sample is consistent with the content of each group of target historical data, namely comprises a plurality of target equipment process parameters and cigarette loose-end rejection rate, the plurality of training samples in the training data set can be input into the linear regression model with unknown model parameters, and specific model parameter values are obtained to obtain the initial prediction model.
And S440, verifying the precision of the initial prediction model by using the test data set to obtain a precision verification result.
In a preferred embodiment, specifically, the test set data includes a plurality of test samples, each test sample is consistent with the content in each set of target historical data, that is, includes a plurality of target equipment process parameters and a cigarette loose-end rejection rate, wherein the step of verifying the accuracy of the initial prediction model by using the test data set and obtaining the accuracy verification result includes:
and aiming at each test sample, inputting a plurality of target process parameters in the test sample into an initial prediction model, obtaining a predicted value of the cigarette loose-end rejection rate corresponding to the test sample, obtaining a difference value between the predicted value of the cigarette loose-end rejection rate corresponding to the test sample and an actual value of the cigarette loose-end rejection rate in the test sample, calculating the square sum of the obtained difference values, and determining the square sum of the difference values as a precision verification result.
In one embodiment, if the initial prediction model is y ═ 0.39x1+4.8, there are now 2 test samples (10, 9.5) and (11, 10), the first sample (10, 9.5) representing the target plant process parameter x1Is 10, the corresponding actual value of the cigarette loose end rejection rate is 9.5, and the second sample (11, 10) represents the target equipment process parameter x1The actual value of (1) is 11, the actual value of the corresponding cigarette loose end rejection rate is 10, and the target equipment process parameter x in the first sample and the second sample are respectively measured1The actual value of (a) is taken into y-0.39 x1+4.8, predicted values 8.5 and 9.09 of the cigarette loose-end rejection rate can be obtained, then the difference value between each predicted value and the actual value of the cigarette loose-end rejection rate in the corresponding test sample is calculated, and the square sum of 2 difference values is calculated, so that the precision verification result is 1.8281.
In another embodiment, the determination coefficient of the initial prediction model may also be obtained through a test sample, and the determination coefficient is determined as the precision verification result.
In other embodiments, the accuracy of the initial prediction model may also be determined by the difference between the predicted value of the cigarette loose-end rejection rate and the actual value of the cigarette loose-end rejection rate in the test sample, for example, it may be determined whether the absolute value of the difference is less than 0.1, and if the absolute value of the difference is less than 0.1, it is determined that the error fluctuation of the initial prediction model is good, that is, the accuracy of the initial prediction model is good.
And S450, acquiring a target prediction model according to the precision verification result.
In an embodiment, the step of obtaining the target prediction model according to the precision verification result includes:
and judging whether the precision verification result is in a preset precision interval or not, and if the precision verification result is in the preset precision interval, determining the initial prediction model as a target prediction model.
In a specific embodiment, the preset precision interval is used for measuring the fitting degree of the initial prediction model, generally, the higher the fitting degree is, the more accurate the initial prediction model is, but the too high fitting degree causes an overfitting phenomenon, and therefore, by setting the preset precision interval, whether the initial prediction model can be used as the final target prediction model is judged through the precision verification result.
Specifically, if the precision verification result is in the preset precision interval, the initial prediction model is considered to be the final target prediction model, and if the precision verification result is not in the preset precision interval, the fitting degree of the initial prediction model at this time is considered to be insufficient, or the initial prediction model is in an overfitting state, and at this time, new historical data needs to be introduced to obtain a new initial prediction model.
Returning to the figure 1 and S500, obtaining the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm, and forming an optimal value group corresponding to a plurality of equipment process parameters.
In the specific implementation, the steps of obtaining the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm and forming the optimal value group corresponding to the plurality of equipment process parameters comprise:
and acquiring a preset value constraint range of each target equipment process parameter, and acquiring the optimal value of each target equipment process parameter, which enables the cigarette loose-end rejection rate to be reduced to the lowest value in the target prediction model, by utilizing a genetic algorithm in the value constraint range of each target influence factor.
In a specific embodiment, the optimal value group includes optimal values of a plurality of target equipment process parameters corresponding to the plurality of target equipment process parameters one to one, before the optimal values of the target equipment process parameters are obtained by using a genetic algorithm, the preset value constraint range of each target equipment process parameter needs to be determined, the preset value constraint range of each target equipment process parameter is the upper and lower limit range of the corresponding target equipment process parameter at normal working time, that is, the finally obtained optimal value of each target equipment process parameter needs to be in the preset value constraint range.
S600, inputting the optimal value set into a cigarette making machine management platform, so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value set.
In a specific embodiment, the obtained optimal value set of the target device process parameters may be input to the cigarette making machine management platform, so that the cigarette making machine management platform regulates and controls the corresponding cigarette making machine devices.
In a preferred embodiment, the cigarette making machine management platform is used for butting the cigarette making machine equipment and other equipment involved in the cigarette production process, the cigarette making machine management platform can realize the regulation and control of each process parameter in the cigarette production process through the obtained optimal value group of the process parameters of the target equipment, for example, the temperature in the process parameters of the equipment is determined by an air conditioner in the environment where the cigarette making machine equipment is located, and after the optimal value of the temperature is obtained, the cigarette making machine management platform can control the temperature of the air conditioner to reach the optimal value corresponding to the temperature so as to realize the control of the temperature in the cigarette production process, thereby reducing the empty cigarette rejection rate.
Based on the same application concept, the embodiment of the application also provides an automatic regulation and control device for the defective cigarette rejection rate, which corresponds to the automatic regulation and control method provided by the embodiment.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an automatic control device according to an embodiment of the present disclosure. As shown in fig. 4, the automatic regulating device includes:
the first acquisition module 710 is used for acquiring multiple sets of historical data, wherein each set of historical data comprises equipment process parameters of the same batch of tobacco shreds in each procedure generated in the cigarette production process and the defective cigarette rejection rate in the final cigarette making and packing procedure;
the analysis module 720 is used for analyzing the correlation between the cigarette loose end rejection rate and each equipment process parameter according to a plurality of groups of historical data to obtain a plurality of correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter;
the first determining module 730 is used for determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients;
a second obtaining module 740, configured to obtain, based on multiple sets of historical data, a target prediction model using a regression algorithm and multiple target device process parameters as independent variables and a cigarette loose-end rejection rate as a dependent variable;
a third obtaining module 750, configured to obtain, through a genetic algorithm, optimal values of process parameters of each target device in the target prediction model, where the cigarette loose-end rejection rate is reduced to the minimum, and form an optimal value group corresponding to the plurality of device process parameters;
and the regulating and controlling module 760 is used for determining to input the optimal value group into the cigarette making machine management platform so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value group.
Optionally, the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and each equipment process parameter; the first determining module 730 is further configured to: judging whether the correlation coefficient is in a weak correlation interval or not aiming at each correlation coefficient; if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation equipment process parameter; and if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
Optionally, the second obtaining module 740 is further configured to: screening weak relevant process parameters from multiple sets of historical data to obtain multiple sets of target historical data; dividing a plurality of groups of target historical data into a training data set and a testing data set according to a preset proportion; establishing an initial prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables by using training set data; verifying the precision of the initial prediction model by using a test data set to obtain a precision verification result; and obtaining a target prediction model according to the precision verification result.
Optionally, the second obtaining module 740 is further configured to: judging whether the precision verification result is in a preset precision interval or not; and if the precision verification result is in a preset precision interval, determining the initial prediction model as the target prediction model.
Based on the same application concept, an electronic device provided in an embodiment of the present application includes: the system comprises a processor, a memory and a bus, wherein the memory stores machine readable instructions executable by the processor, when an electronic device runs, the processor and the memory are communicated through the bus, and the machine readable instructions are executed by the processor to execute the steps of the automatic regulation and control method in any one of the above embodiments.
Based on the same application concept, embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the automatic regulation and control method provided in the foregoing embodiments are executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units into only one type of logical function may be implemented in other ways, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some communication interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An automatic regulation and control method for the cigarette loose-end rejection rate is characterized by comprising the following steps:
acquiring multiple groups of historical data, wherein each group of historical data comprises equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the defective cigarette rejection rate in the final cigarette rolling and packing process;
according to the multiple groups of historical data, performing correlation analysis between the cigarette loose end rejection rate and each equipment process parameter to obtain multiple correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter;
determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients;
based on multiple groups of historical data, obtaining a target prediction model with multiple target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables through a regression algorithm;
acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm, and forming an optimal value group corresponding to a plurality of target equipment process parameters;
and inputting the optimal value set into a cigarette making machine management platform so that the cigarette making machine management platform adjusts the process parameters of each target device according to the received optimal value set.
2. The automatic regulating and controlling method according to claim 1, wherein the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and each equipment process parameter;
the method comprises the following steps of determining a plurality of target equipment process parameters which have a correlation with the cigarette loose-end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients, wherein the steps comprise:
judging whether the correlation coefficient is in a weak correlation interval or not aiming at each correlation coefficient;
if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation equipment process parameter;
and if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
3. The automatic regulating method according to claim 2, wherein the step of obtaining the target prediction model with the process parameters of the target devices as independent variables and the cigarette loose-end rejection rate as dependent variables through a regression algorithm based on a plurality of sets of historical data comprises:
screening weak relevant equipment process parameters from multiple groups of historical data to obtain multiple groups of target historical data;
dividing the multiple groups of target historical data into a training data set and a testing data set according to a preset proportion;
establishing an initial prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables by using the training data set;
verifying the precision of the initial prediction model by using the test data set to obtain a precision verification result;
and obtaining the target prediction model according to the precision verification result.
4. The automatic conditioning method according to claim 3, wherein the test data set comprises a plurality of test samples, each test sample comprising a plurality of target equipment process parameters and a cigarette loose-end rejection rate:
verifying the precision of the initial prediction model by using the test data set, wherein the step of obtaining a precision verification result comprises the following steps:
inputting a plurality of target equipment process parameters in each test sample into the initial prediction model to obtain a predicted value of the cigarette loose-end rejection rate corresponding to the test sample;
acquiring a difference value between a predicted value of the cigarette loose end rejection rate corresponding to the test sample and an actual value of the cigarette loose end rejection rate in the test sample;
and calculating the sum of squares of the obtained multiple difference values, and determining the sum of squares of the multiple difference values as a precision verification result.
5. The automatic regulation and control method of claim 4, wherein the step of obtaining the target prediction model according to the accuracy verification result comprises:
judging whether the precision verification result is in a preset precision interval or not;
and if the precision verification result is in a preset precision interval, determining the initial prediction model as the target prediction model.
6. The automatic control method according to claim 1, wherein the step of obtaining the optimal value of each target equipment process parameter in the target prediction model for minimizing the cigarette loose-end rejection rate through a genetic algorithm and forming the optimal value group corresponding to the plurality of equipment process parameters comprises:
acquiring a preset value constraint range of each target device process parameter;
and in the value restriction range of each target influence factor, acquiring the optimal value of each target equipment process parameter for reducing the cigarette loose-end rejection rate to the lowest value in the target prediction model by using a genetic algorithm.
7. The utility model provides an automatic regulation and control device of cigarette odd rejection rate which characterized in that, automatic regulation and control device includes:
the first acquisition module is used for acquiring a plurality of groups of historical data, wherein each group of historical data comprises equipment process parameters of the same batch of tobacco shreds in each process generated in the cigarette production process and the cigarette loose-end rejection rate in the final cigarette rolling and packing process;
the analysis module is used for analyzing the correlation between the cigarette loose end rejection rate and each equipment process parameter according to the plurality of groups of historical data to obtain a plurality of correlation coefficients between the cigarette loose end rejection rate and each equipment process parameter;
the first determination module is used for determining a plurality of target equipment process parameters which have a correlation with the cigarette loose end rejection rate from a plurality of equipment process parameters according to a plurality of correlation coefficients;
the second acquisition module is used for acquiring a target prediction model which takes a plurality of target equipment process parameters as independent variables and the cigarette loose-end rejection rate as dependent variables through a regression algorithm based on a plurality of groups of historical data;
the third acquisition module is used for acquiring the optimal value of each target equipment process parameter which enables the cigarette loose-end rejection rate to be reduced to the lowest in the target prediction model through a genetic algorithm and forming an optimal value group corresponding to a plurality of equipment process parameters;
and the regulating and controlling module is used for determining that the optimal value group is input into the cigarette making machine management platform so that the cigarette making machine management platform can adjust the process parameters of each target device according to the received optimal value group.
8. The automatic regulating and controlling device according to claim 7, wherein the correlation coefficient represents the correlation between the cigarette loose-end rejection rate and each equipment process parameter;
the first determining module is further configured to:
judging whether the correlation coefficient is in a weak correlation interval or not aiming at each correlation coefficient;
if the correlation coefficient is in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as a weak correlation equipment process parameter;
and if the correlation coefficient is not in the weak correlation interval, determining the equipment process parameter corresponding to the correlation coefficient as the target equipment process parameter.
9. The automatic tuning device of claim 8, wherein the second obtaining module is further configured to:
screening weak relevant equipment process parameters from multiple groups of historical data to obtain multiple groups of target historical data;
dividing the multiple groups of target historical data into a training data set and a testing data set according to a preset proportion;
establishing an initial prediction model with a plurality of target equipment process parameters as independent variables and a cigarette loose-end rejection rate as dependent variables by using the training data set;
verifying the precision of the initial prediction model by using the test data set to obtain a precision verification result;
and obtaining the target prediction model according to the precision verification result.
10. The automatic tuning device of claim 9, wherein the second obtaining module is further configured to:
judging whether the precision verification result is in a preset precision interval or not;
and if the precision verification result is in a preset precision interval, determining the initial prediction model as the target prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210125329.5A CN114493311A (en) | 2022-02-10 | 2022-02-10 | Automatic regulation and control method and device for cigarette loose-end rejection rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210125329.5A CN114493311A (en) | 2022-02-10 | 2022-02-10 | Automatic regulation and control method and device for cigarette loose-end rejection rate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114493311A true CN114493311A (en) | 2022-05-13 |
Family
ID=81478048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210125329.5A Pending CN114493311A (en) | 2022-02-10 | 2022-02-10 | Automatic regulation and control method and device for cigarette loose-end rejection rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114493311A (en) |
-
2022
- 2022-02-10 CN CN202210125329.5A patent/CN114493311A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111597729B (en) | Processing equipment technological parameter optimization method and system | |
| CN102090704B (en) | Method for improving batch procedure capability of tobacco shred making process | |
| CN102117731B (en) | Method and device for monitoring measurement data in process production flow of semiconductor | |
| JPH07507870A (en) | Improved systems and methods for flow data matching | |
| CN109343489B (en) | Self-healing control method and system for tobacco shred making process parameters | |
| CN110716500B (en) | Method and system for determining segmented modeling points of temperature sensitive interval | |
| CN102090705A (en) | Method for improving tobacco-drying process capability | |
| CN114398049A (en) | Self-adaptive dynamic updating method for digital twin model of discrete manufacturing workshop | |
| CN107111800B (en) | Part manufacturing method based on analysis of weighted statistical indicators | |
| CN113360983A (en) | Slope reliability analysis and risk assessment method | |
| JP2005519394A (en) | Automatic experiment planning method and system | |
| CN112650740B (en) | Method and system for reducing uncertainty of online monitoring carbon emission data | |
| CN114493311A (en) | Automatic regulation and control method and device for cigarette loose-end rejection rate | |
| CN117171896A (en) | Method and system for optimizing machining of input shaft of automobile steering gear | |
| CN112985556A (en) | Cigarette weight detection method, detection controller and detection system | |
| CN105628646A (en) | Online cigarette tar predicting and warning method | |
| CN113970502A (en) | Tobacco leaf water content prediction model construction method based on rapid oven method | |
| CN110928264A (en) | Data processing, data processing device, and computer-readable recording medium | |
| CN113836826A (en) | Key parameter determination method and device, electronic device and storage medium | |
| CN109858699B (en) | Water quality quantitative simulation method and device, electronic equipment and storage medium | |
| CN113778042A (en) | Industrial control equipment instruction simulation operation communication system based on informatization modeling | |
| WO2022034560A1 (en) | A system and method for evaluation of sand compactibility | |
| CN115034370B (en) | BP network model-based method for predicting hearth activity of blast furnace | |
| CN118266613A (en) | Method, device and storage medium for predicting water content and filling value of cut tobacco | |
| CN115952853B (en) | Method and device for constructing ore pulp density detection model and ore pulp density detection system |
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 |