Filter stick pressure drop determination method, device and equipment and medium

Abstract

The invention discloses a filter stick pressure drop determination method and device, equipment and a medium, and relates to the technical field of cigarettes, and the method comprises the following steps: carrying out data statistical analysis and data processing operation on production data to obtain processed production data, and carrying out cross validation on the processed production data to obtain training group data; establishing a multiple linear regression model based on the training group data, and predicting the pressure drop design parameters by using the multiple linear regression model to obtain a pressure drop result; establishing a three-dimensional computational domain according to the production data and the pressure drop design parameters, and executing pressure drop simulation calculation based on the three-dimensional computational domain, the porous medium model and the pressure drop result to obtain a simulation result; comparing the pressure drop result with the simulation result, judging whether the comparison result meets a preset comparison condition or not, and if yes, determining the pressure drop of the filter stick based on the comparison result. The filter stick pressure drop determination accuracy can be improved, the filter stick pressure drop is highly matched with the expected pressure drop, the filter stick design and production circulation efficiency is improved, and the production difficulty and raw material consumption are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarettes, and particularly relates to a method, device, equipment and medium for determining the pressure drop of a filter rod. Background Art

[0002] A cigarette filter rod is composed of various raw materials such as forming paper, tow, and plasticizer. In actual production, to meet the design standard of pressure drop, the characteristics of various raw materials need to be considered. In the design stage, sufficiently accurate design parameters need to be determined, resulting in material waste and extended working hours for staff during the continuous debugging of production and design values. Currently, the industry lacks an understanding of the internal pressure drop change mechanism of various types of filter rods, which restricts the design and quality control of filter rods. Moreover, currently, there are various types of cigarette filter rods, but the design of filter rods is mostly based on production experience. For example, the design of a composite filter rod performs algebraic addition based on the experience of each round rod, resulting in a large deviation between actual production data and design values, increasing production difficulty and raw material consumption.

[0003] As can be seen from the above, how to improve the accuracy of determining the pressure drop of a filter rod, achieve a high degree of matching between the pressure drop of the filter rod and the expected pressure drop, thereby improving the design and production transfer efficiency of the filter rod, and reducing production difficulty and raw material consumption is a problem to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for determining the pressure drop of a filter rod, which can improve the accuracy of determining the pressure drop of a filter rod, achieve a high degree of matching between the pressure drop of the filter rod and the expected pressure drop, thereby improving the design and production transfer efficiency of the filter rod, and reducing production difficulty and raw material consumption. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses a method for determining the pressure drop of a filter rod, including:

[0006] Performing data statistical analysis and data processing operations on production data to obtain the processed production data, and performing cross-validation on the processed production data to obtain training set data;

[0007] Based on the training set data, establishing a multiple linear regression model, obtaining pressure drop design parameters, and using the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result;

[0008] According to the production data and the pressure drop design parameters, establishing a three-dimensional computational domain, and performing pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result;

[0009] Compare the pressure drop result with the simulation result to obtain a comparison result, and determine whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, determine the pressure drop of the filter rod based on the comparison result.

[0010] Optionally, perform statistical analysis on production data, including:

[0011] Perform statistical analysis on the production data and draw a data distribution map of each parameter in the production data to obtain production values; the parameters include the distribution rules of circumference, length, weight, and pressure drop.

[0012] Compare the production values with the filter rod process standard values to obtain the deviation degree.

[0013] Optionally, perform data processing operations on production data, including:

[0014] Perform data preprocessing on the production data based on the deviation degree to obtain preprocessed data.

[0015] Screen and reorganize the preprocessed data according to the filter rod type to obtain the processed production data.

[0016] Optionally, establishing a multiple linear regression model based on the training set data, obtaining pressure drop design parameters, and predicting the pressure drop design parameters using the multiple linear regression model includes:

[0017] Determine the variable coefficients from the training set data and establish the multiple linear regression model based on the variable coefficients.

[0018] Obtain the pressure drop design parameters, and use the multiple linear regression model with the length, circumference, forming paper, and tow parameters in the pressure drop design parameters as independent variables and the pressure drop as the dependent variable for prediction.

[0019] Optionally, performing pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result includes:

[0020] Perform mesh division on the three-dimensional computational domain to obtain a mesh file.

[0021] Import the mesh file into fluid simulation software, and perform pressure drop simulation calculations based on the fluid simulation software, the preset porous medium model, and the pressure drop result to obtain the simulation result.

[0022] Optionally, after importing the mesh file into the fluid simulation software, it further includes:

[0023] Determine the setting conditions for the circumference region.

[0024] Set the circumferential region of the mesh file in the fluid simulation software according to the conditions set for the circumferential region.

[0025] Optionally, after determining whether the comparison result meets the preset comparison conditions, it further includes:

[0026] If the comparison result does not meet the preset comparison conditions, adjust the pressure drop design parameters based on the comparison result to obtain the adjusted pressure drop design parameters, and then jump to the step of establishing a three-dimensional calculation domain until the comparison result meets the preset comparison conditions.

[0027] In a second aspect, the present application discloses a filter rod pressure drop determination device, including:

[0028] A data processing and verification module, configured to perform data statistical analysis and data processing operations on production data to obtain the processed production data, and perform cross-verification on the processed production data to obtain training set data;

[0029] A pressure drop prediction module, configured to establish a multiple linear regression model based on the training set data, obtain pressure drop design parameters, and use the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result;

[0030] A pressure drop simulation calculation module, configured to establish a three-dimensional calculation domain according to the production data and the pressure drop design parameters, and perform pressure drop simulation calculations based on the three-dimensional calculation domain, a preset porous medium model, and the pressure drop result to obtain a simulation result;

[0031] A pressure drop determination module, configured to compare the pressure drop result and the simulation result to obtain a comparison result, determine whether the comparison result meets the preset comparison conditions, and if the comparison result meets the preset comparison conditions, determine the filter rod pressure drop based on the comparison result.

[0032] In a third aspect, the present application discloses an electronic device, including:

[0033] A memory, configured to store a computer program;

[0034] A processor, configured to execute the computer program to implement the foregoing filter rod pressure drop determination method.

[0035] In a fourth aspect, the present application discloses a computer storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the steps of the foregoing disclosed filter rod pressure drop determination method are implemented.

[0036] It can be seen that the present application provides a method for determining the pressure drop of a filter rod, which includes performing data statistical analysis and data processing operations on production data to obtain the processed production data, performing cross-validation on the processed production data to obtain training set data; establishing a multiple linear regression model based on the training set data, obtaining pressure drop design parameters, using the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result; establishing a three-dimensional computational domain according to the production data and the pressure drop design parameters, performing pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result; comparing the pressure drop result and the simulation result to obtain a comparison result, and determining whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the pressure drop of the filter rod is determined based on the comparison result. The present application adopts the idea of integrating theoretical analysis with production data, which can reduce the production difficulty. On the one hand, the production data is processed and cross-validated to establish a multiple linear regression model for predicting the pressure drop design parameters to obtain a pressure drop result, and the pressure drop mechanism inside the filter rod is analyzed based on computational fluid dynamics, fully considering the mutual influence of the tow filling and the forming paper; on the other hand, a three-dimensional computational domain is established based on the production data, and pressure drop simulation calculations are performed on the pressure drop result based on the three-dimensional computational domain to obtain a simulation result; finally, the pressure drop result and the simulation result are compared to analyze the differences between the production process and the design process, providing digital support for the design and production optimization of the filter rod, thereby improving the accuracy of determining the pressure drop of the filter rod, and being able to achieve a high degree of matching between the pressure drop of the filter rod and the expected pressure drop, effectively improving the design and production turnover efficiency of the filter rod and reducing raw material consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0038] Figure 1 It is a flowchart of a method for determining the pressure drop of a filter rod disclosed in the present application;

[0039] Figure 2 It is a flowchart of another method for determining the pressure drop of a filter rod disclosed in the present application;

[0040] Figure 3 It is a structural diagram of a three-dimensional computational domain disclosed in the present application;

[0041] Figure 4 It is a specific flowchart of a method for determining the pressure drop of a filter rod disclosed in the present application;

[0042] Figure 5 Schematic structural diagram of a filter rod pressure drop determination device disclosed in the present application;

[0043] Figure 6 Structural diagram of an electronic device provided by the present application. Specific embodiments

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0045] The cigarette filter rod is composed of various raw materials such as forming paper, tow, and plasticizer. In actual production, to meet the design standard of pressure drop, the characteristics of various raw materials need to be considered. In the design stage, sufficiently accurate design parameters need to be determined, resulting in material waste and extended working hours of staff during the continuous debugging of production and design values. At present, the industry lacks an understanding of the internal pressure drop change mechanism of various types of filter rods, which restricts the design and quality control of filter rods. And currently, there are various types of cigarette filter rods, but the design of filter rods is mostly based on production experience. For example, the design of composite filter rods uses algebraic addition based on the experience of each round rod, resulting in a large deviation between actual production data and design values, increasing production difficulty and raw material consumption. As can be seen from the above, how to improve the accuracy of filter rod pressure drop determination, achieve a high degree of matching between the filter rod pressure drop and the expected pressure drop, thereby improving the design and production turnover efficiency of filter rods, and reducing production difficulty and raw material consumption is a problem to be solved in this field.

[0046] See Figure 1 As shown, the embodiments of the present invention disclose a method for determining the pressure drop of a filter rod, which specifically may include:

[0047] Step S11: Perform data statistical analysis and data processing operations on production data to obtain the processed production data, and perform cross-validation on the processed production data to obtain training set data.

[0048] In this embodiment, performing data statistical analysis on production data includes: performing data statistical analysis on the production data and plotting the data distribution diagrams of each parameter in the production data to obtain production values; the parameters include the distribution laws of circumference, length, weight, and pressure drop; comparing the production values with the filter rod process standard values to obtain the deviation degree.

[0049] In this embodiment, data processing operations are performed on production data, including: performing data preprocessing on the production data based on the deviation degree to obtain preprocessed data; screening and reorganizing the preprocessed data according to the filter rod type to obtain the processed production data.

[0050] Specifically, data statistical analysis is performed on the production data of the current main types of filter rods, data distribution diagrams of various parameters are drawn, and the distribution laws of the main characteristic parameters including circumference, length, weight, and pressure drop are obtained. By comparing with the process standard values of the corresponding filter rods, the deviation degree between the production value and the design value is obtained. Taking the ordinary rod as an example, data preprocessing is performed on the production data of filter rods including regular, medium, and thin branches, including cleaning data with excessive deviation from the standard production range and incomplete target parameters, etc. Selecting the 2σ confidence interval range, data outside the range of two standard deviations above and below the average value in each batch of production data is regarded as abnormal data and excluded, while preserving as much data as possible and improving the accuracy and generality of the model as much as possible. Considering the difference in the production data volume of filter rods with different circumferences, the preprocessed data is screened and reorganized according to the filter rod type to ensure that the filter rods are included according to the tow specifications and different brands, and the processed production data is obtained. Then, k-fold cross-validation is performed on the processed production data. By comparing when k values are 5 and 10, it is found that the validation score is higher when k = 5. Therefore, k = 5 is used as the standard for cross-validation, and finally the training group data and the control group data are obtained.

[0051] Step S12: Establish a multiple linear regression model based on the training group data, obtain the pressure drop design parameters, and use the multiple linear regression model to predict the pressure drop design parameters to obtain the pressure drop result.

[0052] In this embodiment, the variable coefficients are determined from the training group data, and the multiple linear regression model is established based on the variable coefficients; the pressure drop design parameters are obtained, and the length, circumference, forming paper, and tow parameters in the pressure drop design parameters are used as independent variables, and the pressure drop is used as the dependent variable for prediction using the multiple linear regression model to obtain the pressure drop result.

[0053] Specifically, based on the multiple linear regression model, regression analysis is performed with length, circumference, forming paper, and tow parameters as independent variables and pressure drop as the dependent variable (that is, prediction is performed using the following formula to obtain the pressure drop result):

[0054] ΔP = β 0 + β 1 X1 + β 2 X2 + β 3 X3 + β 4 X4 + β 5 X5 + ε;

[0055] Among them, X1, X2, X3, X4, and X5 are the circumference, length, denier per filament of the tow, total denier of the tow, and tow filling amount respectively, ΔP is the pressure drop result, and β 5 X5 is the consumption of the filter rod calculated based on the tow characteristic curve.

[0056] Step S13: Establish a three-dimensional computational domain based on the production data and the pressure drop design parameters, and perform a pressure drop simulation calculation based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result.

[0057] In this embodiment, based on the three-dimensional computational domain, the porous medium model, and the tow parameters and weight consumption in the corresponding pressure drop results obtained from the corresponding multiple regression analysis model, by setting different flow resistance coefficients for the tow and the forming paper, representing the ability of the gas to penetrate the two, and performing a pressure drop simulation calculation, simulation results of different filter rod pressure drops and velocity distributions are obtained.

[0058] Step S14: Compare the pressure drop result and the simulation result to obtain a comparison result, and determine whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, determine the filter rod pressure drop based on the comparison result.

[0059] In this embodiment, after determining whether the comparison result meets the preset comparison condition, it further includes: if the comparison result does not meet the preset comparison condition, adjust the pressure drop design parameters based on the comparison result to obtain the adjusted pressure drop design parameters, and then jump to the step of establishing a three-dimensional computational domain until the comparison result meets the preset comparison condition.

[0060] In this embodiment, compare the pressure drop result and the simulation result to obtain a comparison result. If the comparison result has a large difference (i.e., does not meet the preset comparison condition), adjust the pressure drop design parameters and re-perform the operations in steps 13 - 14 until the comparison result meets the preset comparison condition. For example, the error of the comparison result is less than 5%.

[0061] In this embodiment, statistical analysis and data processing operations are performed on production data to obtain the processed production data, and cross-validation is performed on the processed production data to obtain training set data; a multiple linear regression model is established based on the training set data to obtain pressure drop design parameters, and the multiple linear regression model is used to predict the pressure drop design parameters to obtain a pressure drop result; a three-dimensional computational domain is established according to the production data and the pressure drop design parameters, and pressure drop simulation calculations are performed based on the three-dimensional computational domain, a preset porous media model, and the pressure drop result to obtain a simulation result; the pressure drop result and the simulation result are compared to obtain a comparison result, and it is determined whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the filter rod pressure drop is determined based on the comparison result. This application adopts the idea of integrating theoretical analysis with production data, which can reduce production difficulty. On the one hand, production data is processed and cross-validated to establish a multiple linear regression model for predicting pressure drop design parameters to obtain a pressure drop result, and the pressure drop mechanism inside the filter rod is analyzed based on computational fluid dynamics, fully considering the mutual influence of the tow filling and the forming paper; on the other hand, a three-dimensional computational domain is established based on production data, and pressure drop simulation calculations are performed on the pressure drop result based on the three-dimensional computational domain to obtain a simulation result; finally, the pressure drop result and the simulation result are compared to analyze the differences between the production process and the design process, providing digital support for the design and production optimization of the filter rod, thereby improving the accuracy of determining the filter rod pressure drop, and enabling a high degree of matching between the filter rod pressure drop and the expected pressure drop, effectively improving the design and production turnover efficiency of the filter rod and reducing raw material consumption.

[0062] See Figure 2 As shown, an embodiment of the present invention discloses a method for determining the filter rod pressure drop, which may specifically include:

[0063] Step S21: Perform statistical analysis and data processing operations on production data to obtain the processed production data, and perform cross-validation on the processed production data to obtain training set data.

[0064] Step S22: Establish a multiple linear regression model based on the training set data to obtain pressure drop design parameters, and use the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result.

[0065] Step S23: Establish a three-dimensional computational domain according to the production data and the pressure drop design parameters, perform mesh division on the three-dimensional computational domain to obtain a mesh file, import the mesh file into a fluid simulation software, and perform pressure drop simulation calculations based on the fluid simulation software, the preset porous media model, and the pressure drop result to obtain the simulation result.

[0066] In this embodiment, after importing the grid file into the fluid simulation software, the following steps are further included: determining the circumferential region setting conditions; and setting the circumferential region of the grid file in the fluid simulation software according to the circumferential region setting conditions.

[0067] In this embodiment, the three-dimensional calculation domain of the filter rod established based on the production data and the pressure drop design parameters is as Figure 3 shown. Considering that the air permeability of the forming paper will cause gas to pass through the forming paper and affect the pressure drop, a multi-layer concentric circle structure is adopted for the three-dimensional calculation domain. D1 represents the circumferential diameter of the filter rod technical index or the actual production circumferential diameter, D2 represents the circumferential diameter of the forming paper, and D3 represents the computational fluid domain. Since it is necessary to place the filter rod including the forming paper in a free air interval to study the situation of fluid flowing through the forming paper with different air permeabilities, the size of D3 is specified as 10 times the circumferential diameter of the conventional rod. At the same time, based on the ICEM (Integrated Computer Engineering and Manufacturing) software, the three-dimensional calculation domain is meshed to generate a grid file, which is then imported into the Fluent (fluid simulation) software. Then, the circumferential region setting conditions are determined, and the three different circumferential regions represented by D1 to D3 are respectively set as three different fluid domains Z1 (tow), Z2 (forming paper), and Z3 (free domain). Specifically, the reference values of the parameters of the three-dimensional calculation domain are shown in Table 1, and the internal surfaces between them ensure the intercommunication of the fluid.

[0068] Table 1

[0069] Type D1 (mm) D2 (mm) D3 (mm) Regular 7.639 8.435 76.39 Medium gauge 6.334 7 76.39 Fine gauge 5.427 6.048

[0070] Step S24: Comparing the pressure drop result and the simulation result to obtain a comparison result, and determining whether the comparison result meets the preset comparison conditions. If the comparison result meets the preset comparison conditions, the filter rod pressure drop is determined based on the comparison result.

[0071] The specific process of this application is as Figure 4As shown in the figure, (1) perform data statistical analysis and data processing operations on the production data to obtain the processed production data, and perform cross-validation on the processed production data to obtain the training set data; (2) establish a multiple linear regression model based on the training set data; (3) obtain the pressure drop design parameters; (4) use the multiple linear regression model to predict the pressure drop design parameters to obtain the pressure drop result; (5) establish a three-dimensional computational domain according to the production data and the pressure drop design parameters; (6) perform pressure drop simulation calculations based on the three-dimensional computational domain, the preset porous media model, and the pressure drop result to obtain the simulation result; (6) compare the pressure drop result and the simulation result to obtain a comparison result, and determine whether the comparison result meets the preset comparison conditions. If the comparison result meets the preset comparison conditions, determine the filter rod pressure drop based on the comparison result.

[0072] The key points of this application are: (1) establishing a multiple regression model based on production data, which combines pressure drop prediction and tow consumption prediction; (2) proposing a multi-region collaborative simulation method that establishes computational domains for both the filter rod tow and the forming paper thickness. This application combines numerical simulation methods and multiple regression analysis methods. Starting from both theoretical analysis and production statistics, it proposes a new idea for filter rod design and optimization: without adjusting production equipment and setting parameters, through the analysis of production data, a multiple linear regression model that can quickly predict pressure drop and tow consumption is established based on multiple regression analysis, taking into account the influence of the forming paper, breaking through the conventional method of only relying on the tow characteristic curve to judge pressure drop and tow consumption; introducing a numerical simulation method of multi-region collaborative simulation, which can intuitively analyze the pressure drop formation mechanism inside the filter rod. In the filter rod design and optimization stage, it provides a detailed digital characterization scheme to help employees quickly identify the reasonable range of each design parameter, establishing a rapid comparison channel between design and production by combining numerical simulation and regression analysis, effectively improving the efficiency of filter rod optimization and reducing material losses caused by production attempts.

[0073] In this embodiment, statistical analysis and data processing operations are performed on production data to obtain the processed production data, and cross-validation is performed on the processed production data to obtain training set data; a multiple linear regression model is established based on the training set data to obtain pressure drop design parameters, and the multiple linear regression model is used to predict the pressure drop design parameters to obtain a pressure drop result; a three-dimensional computational domain is established according to the production data and the pressure drop design parameters, and pressure drop simulation calculations are performed based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result; the pressure drop result and the simulation result are compared to obtain a comparison result, and it is determined whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the filter rod pressure drop is determined based on the comparison result. This application adopts the idea of integrating theoretical analysis with production data, which can reduce the production difficulty. On the one hand, the production data is processed and cross-validated to establish a multiple linear regression model for predicting the pressure drop design parameters to obtain a pressure drop result, and the pressure drop mechanism inside the filter rod is analyzed based on computational fluid dynamics, fully considering the mutual influence of the tow filling and the forming paper; on the other hand, a three-dimensional computational domain is established based on the production data, and pressure drop simulation calculations are performed on the pressure drop result based on the three-dimensional computational domain to obtain a simulation result; finally, the pressure drop result and the simulation result are compared to analyze the differences between the production process and the design process, providing digital support for the design and production optimization of the filter rod, thereby improving the accuracy of determining the filter rod pressure drop, and enabling a high degree of matching between the filter rod pressure drop and the expected pressure drop, effectively improving the design and production transfer efficiency of the filter rod and reducing raw material consumption.

[0074] See Figure 5 As shown, an embodiment of the present invention discloses a device for determining the pressure drop of a filter rod, which specifically may include:

[0075] A data processing and verification module 11, configured to perform statistical analysis and data processing operations on production data to obtain the processed production data, and perform cross-validation on the processed production data to obtain training set data;

[0076] A pressure drop prediction module 12, configured to establish a multiple linear regression model based on the training set data to obtain pressure drop design parameters, and use the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result;

[0077] A pressure drop simulation calculation module 13, configured to establish a three-dimensional computational domain according to the production data and the pressure drop design parameters, and perform pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result;

[0078] The pressure drop determination module 14 is configured to compare the pressure drop result with the simulation result to obtain a comparison result, and determine whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the filter rod pressure drop is determined based on the comparison result.

[0079] In this embodiment, data statistical analysis and data processing operations are performed on the production data to obtain the processed production data, and the processed production data is cross-validated to obtain training set data; a multiple linear regression model is established based on the training set data to obtain pressure drop design parameters, and the multiple linear regression model is used to predict the pressure drop design parameters to obtain a pressure drop result; a three-dimensional computational domain is established according to the production data and the pressure drop design parameters, and pressure drop simulation calculations are performed based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result; the pressure drop result and the simulation result are compared to obtain a comparison result, and it is determined whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the filter rod pressure drop is determined based on the comparison result. This application adopts the idea of integrating theoretical analysis with production data, which can reduce the production difficulty. On the one hand, the production data is processed and cross-validated to establish a multiple linear regression model for predicting the pressure drop design parameters to obtain a pressure drop result, and the pressure drop mechanism inside the filter rod is analyzed based on computational fluid dynamics, fully considering the mutual influence of the tow filling and the forming paper; on the other hand, a three-dimensional computational domain is established based on the production data, and pressure drop simulation calculations are performed on the pressure drop result based on the three-dimensional computational domain to obtain a simulation result; finally, the pressure drop result and the simulation result are compared to analyze the differences between the production process and the design process, providing digital support for the design and production optimization of the filter rod, thereby improving the accuracy of determining the filter rod pressure drop, and being able to achieve a high degree of matching between the filter rod pressure drop and the expected pressure drop, effectively improving the design and production turnover efficiency of the filter rod and reducing raw material consumption.

[0080] In some specific embodiments, the data processing and verification module 11 may specifically include:

[0081] The data statistical analysis module is configured to perform data statistical analysis on the production data and draw a data distribution diagram of each parameter in the production data to obtain production values; the parameters include the distribution rules of circumference, length, weight, and pressure drop;

[0082] The deviation degree determination module is configured to compare the production values with the filter rod process standard values to obtain the deviation degree.

[0083] In some specific embodiments, the data processing and verification module 11 may specifically include:

[0084] A data preprocessing module, configured to perform data preprocessing on the production data based on the degree of deviation to obtain preprocessed data;

[0085] A screening and recombination module, configured to screen and recombine the preprocessed data according to the filter rod type to obtain the processed production data.

[0086] In some specific embodiments, the pressure drop prediction module 12 may specifically include:

[0087] A model establishment module, configured to determine variable coefficients from the training set data and establish the multiple linear regression model based on the variable coefficients;

[0088] A prediction module, configured to obtain the pressure drop design parameters, use the multiple linear regression model, and take the length, circumference, forming paper, and tow parameters in the pressure drop design parameters as independent variables and the pressure drop as the dependent variable for prediction.

[0089] In some specific embodiments, the pressure drop simulation calculation module 13 may specifically include:

[0090] A mesh generation module, configured to perform mesh generation on the three-dimensional computational domain to obtain a mesh file;

[0091] A pressure drop simulation calculation module, configured to import the mesh file into fluid simulation software, and perform pressure drop simulation calculation based on the fluid simulation software, the preset porous medium model, and the pressure drop result to obtain the simulation result.

[0092] In some specific embodiments, the pressure drop simulation calculation module 13 may specifically include:

[0093] A condition determination module, configured to determine the setting conditions for the circumferential region;

[0094] A circumferential region setting module, configured to set the circumferential region of the mesh file in the fluid simulation software according to the circumferential region setting conditions.

[0095] In some specific embodiments, the pressure drop determination module 14 may specifically include:

[0096] An adjustment module, configured to, if the comparison result does not meet the preset comparison conditions, adjust the pressure drop design parameters based on the comparison result to obtain the adjusted pressure drop design parameters, and then jump to the step of establishing a three-dimensional computational domain until the comparison result meets the preset comparison conditions.

[0097] Figure 6A schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the filter rod pressure drop determination method executed by the electronic device disclosed in any of the foregoing embodiments.

[0098] In this embodiment, the power supply 23 is used to provide a working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and specific limitations are not imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitations are made here.

[0099] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0100] Among them, the operating system 221 is used to manage and control each hardware device on the electronic device 20 and the computer program 222 to implement the operation and processing of the data 223 in the memory 22 by the processor 21, and it can be Windows, Unix, Linux, etc. In addition to the computer program that can be used to complete the filter rod pressure drop determination method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. The data 223 can include not only the data transmitted by external devices received by the filter rod pressure drop determination device, but also the data collected by its own input / output interface 25, etc.

[0101] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well known in the technical field.

[0102] Further, an embodiment of the present application also discloses a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the steps of the filter rod pressure drop determination method disclosed in any of the foregoing embodiments.

[0103] Finally, it should also be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0104] The above has introduced in detail a filter rod pressure drop determination method, apparatus, device and storage medium provided by the present invention. Specific examples are used herein to illustrate the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for determining the pressure drop of a filter rod, characterized in that, Including: Performing data statistical analysis and data processing operations on production data to obtain the processed production data, and performing cross-validation on the processed production data to obtain training set data; Establishing a multiple linear regression model based on the training set data, obtaining pressure drop design parameters, and using the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result; Establishing a three-dimensional computational domain according to the production data and the pressure drop design parameters, and performing pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result; Comparing the pressure drop result and the simulation result to obtain a comparison result, and determining whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, determining the filter rod pressure drop based on the comparison result.

2. The method for determining the pressure drop of the filter rod according to claim 1, wherein Performing data statistical analysis on production data, including: Performing data statistical analysis on the production data and plotting data distribution diagrams of each parameter in the production data to obtain production values; the parameters include the distribution laws of circumference, length, weight, and pressure drop; Comparing the production values with the filter rod process standard values to obtain the deviation degree.

3. The method for determining the pressure drop of the filter rod according to claim 2, wherein Performing data processing operations on production data, including: Performing data preprocessing on the production data based on the deviation degree to obtain preprocessed data; Screening and reorganizing the preprocessed data according to the filter rod type to obtain the processed production data.

4. The method for determining the pressure drop of the filter rod according to claim 1, wherein The establishing a multiple linear regression model based on the training set data, obtaining pressure drop design parameters, and using the multiple linear regression model to predict the pressure drop design parameters includes: determining variable coefficients from the training set data, and establishing the multiple linear regression model based on the variable coefficients; Obtaining the pressure drop design parameters, and using the multiple linear regression model and taking the length, circumference, forming paper, and tow parameters in the pressure drop design parameters as independent variables and the pressure drop as the dependent variable for prediction.

5. The method for determining the pressure drop of the filter rod according to claim 1, characterized in that The performing pressure drop simulation calculations based on the three-dimensional computational domain, a preset porous medium model, and the pressure drop result to obtain a simulation result includes: Performing mesh division on the three-dimensional computational domain to obtain a mesh file; importing the mesh file into fluid simulation software, and performing pressure drop simulation calculations based on the fluid simulation software, the preset porous medium model, and the pressure drop result to obtain the simulation result.

6. The method for determining the pressure drop of the filter rod according to claim 5, characterized in that, After importing the mesh file into the fluid simulation software, it further includes: Determining the circumferential region setting conditions; Performing circumferential region setting on the mesh file in the fluid simulation software according to the circumferential region setting conditions.

7. The method for determining the pressure drop of a filter rod according to any one of claims 1 to 6, characterized in that, After determining whether the comparison result meets the preset comparison condition, it further includes: if the comparison result does not meet the preset comparison condition, adjusting the pressure drop design parameters based on the comparison result to obtain the adjusted pressure drop design parameters, and then jumping to the step of establishing a three-dimensional computational domain until the comparison result meets the preset comparison condition.

8. A filter rod pressure drop determination device, characterized in that, Including: A data processing and verification module, which is used to perform data statistical analysis and data processing operations on production data to obtain the processed production data, and perform cross-verification on the processed production data to obtain training set data; A pressure drop prediction module, which is used to establish a multiple linear regression model based on the training set data, obtain pressure drop design parameters, and use the multiple linear regression model to predict the pressure drop design parameters to obtain a pressure drop result; A pressure drop simulation calculation module, which is used to establish a three-dimensional calculation domain according to the production data and the pressure drop design parameters, and perform pressure drop simulation calculations based on the three-dimensional calculation domain, a preset porous medium model, and the pressure drop result to obtain a simulation result; A pressure drop determination module, which is used to compare the pressure drop result with the simulation result to obtain a comparison result, and judge whether the comparison result meets a preset comparison condition. If the comparison result meets the preset comparison condition, the filter rod pressure drop is determined based on the comparison result.

9. An electronic device, characterized in that, Including: A memory, which is used to store a computer program; A processor, which is used to execute the computer program to implement the filter rod pressure drop determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by the processor, the filter rod pressure drop determination method according to any one of claims 1 to 7 is implemented.

Images