Nonwoven breathable film production line operating parameter optimization control system and method

By optimizing and controlling the surface data and simulation of the nonwoven breathable membrane production line, the problem of insufficient control in the nonwoven breathable membrane production process was solved, and the hot pressing effect and production quality were improved.

CN118821568BActive Publication Date: 2024-11-22JIANGSU HANYAO MEDICAL DEVICES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411303282.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-22
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

In existing technologies, there is limited control over the production process of nonwoven breathable membranes, resulting in poor manufacturing outcomes.

Method used

By acquiring surface data and simulation data of nonwoven fabrics and breathable membranes, finite element mesh and regression network models are constructed to optimize tensile parameters and humidification amount, thereby achieving parameter optimization control of the nonwoven fabric breathable membrane production line.

Benefits of technology

The heat-pressing effect of the nonwoven breathable membrane was improved, ensuring that the air permeability and roughness met the requirements, thus improving the production quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118821568B_ABST
    Figure CN118821568B_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of non-woven breathable film processing control, and discloses a non-woven breathable film production line operation parameter optimization control system and method, comprising: performing simulation based on first surface data and simulation data to obtain target surface data, obtaining corresponding stretching parameters according to basic data, stretching the breathable film to be processed according to the stretching parameters, obtaining second surface data of the breathable film after stretching, determining an air permeability score according to the second surface data, calculating a roughness score according to the target surface data, inputting the roughness score and the air permeability score into a pre-constructed humidification prediction model to obtain a target humidification amount, and finally humidifying the non-woven fabric and the breathable film based on the target humidification amount. The invention can control parameters in the production process of the non-woven breathable film, and can obtain a suitable humidification amount according to the actual conditions of the non-woven fabric and the breathable film, thereby improving the subsequent hot pressing effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of non-woven breathable film processing control, and more specifically, to a non-woven breathable film production line operating parameter optimization control system and method. Background Art

[0002] Non-woven fabric is a kind of fabric that does not require weaving. Special functions such as waterproof, breathable, antistatic, etc. can be added according to needs. Correspondingly, non-woven breathable membrane is a composite material made by adding breathable function on the basis of ordinary non-woven fabric. For example, non-woven breathable membrane is formed by hot pressing non-woven fabric and breathable membrane. Non-woven breathable membrane is widely used in medical care, personal care, industrial protection and other fields due to its unique physical properties, such as high air permeability, good isolation and filtering effect. In the prior art, there are usually related contents about the production process control of non-woven fabrics, but there are rarely related contents about the production process control of non-woven breathable membranes.

[0003] For example, the Chinese patent with publication number CN117873001A provides an intelligent control system for a spunbond nonwoven fabric production line. The patent uses a convolutional neural network model in deep learning to extract and analyze the input data to obtain classification results indicating whether the temperature value of the spunbond nonwoven fabric to be controlled should be increased or decreased; the Chinese patent with publication number CN114089705A provides a nonwoven fabric processing technology control method and system, which uses the first fiber ratio information as the first control parameter, and the needle punching strength information as the second control parameter, and inputs the first control parameter and the second control parameter into the nonwoven fabric processing technology control system, compares the actual working parameters, and performs intelligent control on the nonwoven fabric processing technology.

[0004] The above patents all disclose the content about parameter control in the production process of non-woven fabrics, but the production process of non-woven breathable membranes is different from that of non-woven fabrics. For example, in the production process of non-woven breathable membranes, the non-woven fabrics and the breathable membranes are usually required to be hot pressed, and before hot pressing, the non-woven fabrics and the breathable membranes need to be humidified. Therefore, in the prior art, there is little control over the production process of non-woven breathable membranes, resulting in poor manufacturing effect of non-woven breathable membranes.

[0005] In view of this, the present invention proposes a non-woven breathable membrane production line operating parameter optimization control system and method to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control system and method for optimizing the operating parameters of a non-woven breathable membrane production line.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The method for optimizing and controlling the operating parameters of the non-woven breathable film production line includes:

[0009] Acquire first surface data and simulation data of the nonwoven fabric to be processed, perform simulation based on the first surface data and the simulation data, and obtain target surface data;

[0010] Obtain basic data of the breathable film to be processed, obtain corresponding stretching parameters according to the basic data, perform stretching on the breathable film to be processed according to the stretching parameters, obtain N groups of real-time stretching data during the stretching process, and determine whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1;

[0011] Acquire the second surface data of the breathable membrane after stretching, determine the air permeability score according to the second surface data, calculate the roughness score according to the target surface data, input the roughness score and the air permeability score into a pre-built humidification prediction model, and obtain the target humidification amount;

[0012] The nonwoven fabric and the breathable membrane are humidified based on the target humidification amount.

[0013] Furthermore, a method for obtaining target surface data by simulating based on the first surface data and the simulation data includes:

[0014] A finite element mesh of the non-woven fabric to be processed is constructed based on the first surface data, the finite element mesh includes M nodes and multiple static edges for connecting the M nodes, the motion state of the non-woven fabric to be processed is simulated based on the finite element mesh and the simulation data, and an initial simulation result of the fabric is obtained, the initial simulation result at least includes the motion positions of the M nodes, for every two nodes among the M nodes, when the distance between the two nodes is less than a preset distance length, a dynamic edge between the two nodes is established, the motion positions of the M nodes in the finite element mesh and the connection relationship of the M nodes are input into a pre-constructed simulation correction model to obtain target surface data, and the connection relationship of the M nodes includes a static edge connection relationship and a dynamic edge connection relationship.

[0015] Furthermore, the method for constructing the simulation correction model includes:

[0016] A first sample data set is obtained, wherein the first sample data set includes historical node motion positions, historical node connection relationships, and historical target surface data. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical node motion positions and historical node connection relationships in the sample training set are used as input data of the regression network, and the historical target surface data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time target surface data. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a simulation correction model.

[0017] Furthermore, the method of obtaining corresponding stretching parameters according to basic data includes:

[0018] Determine the numerical range corresponding to each element in the basic data, and determine the corresponding stretching parameters according to the numerical range and the mapping relationship.

[0019] Furthermore, the real-time stretching data includes a maximum deformation amount and a stretching rate, and the method for determining whether to stop stretching according to N sets of real-time stretching data includes:

[0020] Determine whether there are H consecutive maximum deformation variables among the N maximum deformation variables greater than the preset deformation variable, and whether there are W consecutive stretching rates among the N stretching rates greater than the preset rate. If both exist, stop stretching, N>H, N>W, H and W are both integers greater than 0.

[0021] Furthermore, the second surface data includes porosity, average pore size value and pore distribution rate, and the porosity, average pore size value and pore distribution rate are comprehensively analyzed to obtain a permeability score.

[0022] Furthermore, the target surface data includes height difference, reflection intensity variance and time root mean square, and the height difference, reflection intensity variance and time root mean square are comprehensively analyzed to obtain a roughness score.

[0023] Furthermore, it also includes: determining a target hot pressing time according to a target humidification amount and a preset standard hot pressing time;

[0024] The method for determining the target heat pressing time according to the target humidification amount and the preset standard heat pressing time includes:

[0025] A first ratio between the target humidification amount and the preset standard humidification amount is calculated, and the product of the first ratio and the preset standard hot pressing time is used as the target hot pressing time.

[0026] The non-woven breathable film production line operation parameter optimization control system is used to implement the above-mentioned non-woven breathable film production line operation parameter optimization control method, including:

[0027] Simulation module: used for obtaining first surface data and simulation data of the non-woven fabric to be processed, and performing simulation based on the first surface data and the simulation data to obtain target surface data;

[0028] The first processing module is used to obtain basic data of the breathable film to be processed, obtain corresponding stretching parameters according to the basic data, perform stretching processing on the breathable film to be processed according to the stretching parameters, obtain N groups of real-time stretching data during the stretching process, and determine whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1;

[0029] The second processing module is used to obtain the second surface data of the breathable membrane after stretching, determine the air permeability score according to the second surface data, calculate the roughness score according to the target surface data, input the roughness score and the air permeability score into the pre-built humidification prediction model, and obtain the target humidification amount;

[0030] Humidification module: used to humidify the non-woven fabric and breathable membrane based on the target humidification amount.

[0031] An electronic device comprises a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the processor executes the computer program, the above-mentioned non-woven breathable membrane production line operating parameter optimization control method is implemented. The interface comprises a network interface and a data interface. The network interface comprises a wired or wireless interface, and the data interface comprises an input or output interface.

[0032] A computer-readable storage medium stores a computer program, and when the computer program is executed, the above-mentioned non-woven breathable membrane production line operating parameter optimization control method is implemented.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention performs simulation based on first surface data and simulation data to obtain target surface data, obtains corresponding stretching parameters according to basic data, performs stretching treatment on the breathable film to be treated according to the stretching parameters, obtains N groups of real-time stretching data during the stretching treatment, determines whether to stop stretching according to the N groups of real-time stretching data, obtains second surface data of the breathable film after stretching, determines an air permeability score according to the second surface data, calculates a roughness score according to the target surface data, inputs the roughness score and the air permeability score into a pre-constructed humidification prediction model to obtain a target humidification amount, and finally humidifies the non-woven fabric and the breathable film based on the target humidification amount. The present invention can control parameters in the production process of the non-woven fabric breathable film, and can obtain a suitable humidification amount according to the actual conditions of the non-woven fabric and the breathable film, thereby improving the subsequent hot pressing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of the method for optimizing the operating parameters of the non-woven breathable film production line of the present invention;

[0036] Figure 2 It is a structural schematic diagram of the operating parameter optimization control system of the non-woven breathable film production line in the present invention;

[0037] Figure 3 is a schematic diagram of a finite element mesh before simulation in the present invention;

[0038] Figure 4 A schematic diagram of a finite element mesh after simulation in the present invention;

[0039] Figure 5 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Example 1

[0042] See also Figure 1 As shown, this embodiment discloses a method for optimizing and controlling operating parameters of a non-woven breathable membrane production line, including:

[0043] S10: acquiring first surface data and simulation data of the non-woven fabric to be processed, and performing simulation based on the first surface data and the simulation data to obtain target surface data;

[0044] In this embodiment, the first surface data can be data obtained by directly detecting the surface of the non-woven fabric to be treated through sensors and other equipment. The first surface data includes but is not limited to height difference, reflection intensity variance and time root mean square. The height difference refers to the height difference between the highest peak and the lowest valley, and the highest peak is the maximum surface height of the non-woven fabric to be treated, and the corresponding lowest valley is the minimum surface height of the non-woven fabric to be treated. The non-woven fabric surface can be scanned by a laser sensor to obtain a high-resolution surface height; the reflection intensity refers to the reflection intensity of the surface of the non-woven fabric to be treated, and the time root mean square refers to the root mean square of the reflection time of the surface of the non-woven fabric to be treated. The above-mentioned reflection intensity and reflection time can be obtained by scanning the non-woven fabric surface with an ultrasonic sensor, and the calculation of the variance and the root mean square are both existing technologies, and this embodiment will not go into details.

[0045] It should be added that the first surface data represents the roughness of the non-woven fabric to be treated. Since the non-woven fabric to be treated needs to be hot pressed with the breathable membrane to be treated, the roughness during the hot pressing process will affect the quality of molding. Therefore, before hot pressing, the surface of the non-woven fabric to be treated needs to be humidified.

[0046] Specifically, the simulation data refers to the simulation data required for simulating the non-woven fabric to be treated. It should be noted that since the hot pressing work is usually performed by a hot pressing roller, the non-woven fabric to be treated needs to be transported when it reaches the position of the hot pressing roller on the production line, such as by a conveyor belt. In the process of transportation, the surface of the non-woven fabric to be treated will be worn or deformed, which will greatly increase the roughness of the non-woven fabric to be treated. However, after the non-woven fabric to be treated reaches the position of the hot pressing roller, hot pressing is required, which makes it difficult to detect the roughness of the non-woven fabric to be treated. Therefore, simulation and correction are required to obtain the accurate roughness of the non-woven fabric to be treated, so that it can be humidified according to the roughness to improve the effect of hot pressing.

[0047] In this embodiment, taking the transport equipment as a conveyor belt as an example, the simulation data at least includes the transport speed, transport length, conveyor belt material and conveyor belt tension, etc. Taking the conveyor belt tension as an example, the greater the conveyor belt tension, the greater the contact force between the non-woven fabric and the conveyor belt, resulting in an increase in friction force, which increases the roughness of the non-woven fabric surface accordingly.

[0048] A method for obtaining target surface data by simulating based on the first surface data and the simulation data includes:

[0049] A finite element mesh of the non-woven fabric to be processed is constructed based on the first surface data, the finite element mesh includes M nodes and multiple static edges for connecting the M nodes, the motion state of the non-woven fabric to be processed is simulated based on the finite element mesh and the simulation data, and an initial simulation result of the fabric is obtained, the initial simulation result at least includes the motion positions of the M nodes, for every two nodes among the M nodes, when the distance between the two nodes is less than a preset distance length, a dynamic edge between the two nodes is established, the motion positions of the M nodes in the finite element mesh and the connection relationship of the M nodes are input into a pre-constructed simulation correction model to obtain target surface data, and the connection relationship of the M nodes includes a static edge connection relationship and a dynamic edge connection relationship.

[0050] It should be noted that the target surface data also includes height difference, reflection intensity variance and time root mean square, but the first surface data represents the roughness of the non-woven fabric to be processed, and the target surface data represents the roughness of the non-woven fabric after simulation. In the above, both static edges and dynamic edges represent the distance between nodes. It can be understood that when the number of dynamic edges is large, it means that the distances between multiple nodes are less than the preset distance length, indicating that the roughness of the non-woven fabric surface is large.

[0051] It should be added that the above-mentioned simulation of the motion state of the non-woven fabric to be processed needs to be performed through existing simulation software, such as MSC Adams or ANSYS Mechanical and other simulation software. Before the above-mentioned simulation, it is necessary to construct a finite element mesh of the non-woven fabric to be processed based on the first surface data. For example, taking ANSYS Mechanical as an example, it is necessary to create a new project or open an existing project in ANSYS Mechanical, use the first surface data as input, import and create a new geometric body or surface model, and in the geometry module of ANSYS Mechanical, convert the imported surface model into a finite element mesh, use a meshing tool (such as automatic or manual division) to generate M nodes, and ensure that the node layout can reflect the roughness characteristics of the surface, and define the positions of the M nodes according to the height difference in the first surface data, where the highest peak and the lowest valley correspond to the maximum and minimum surface heights, and other data (such as fixed boundaries, elastic modulus, Poisson's ratio, etc.) can be set according to the default settings, or those skilled in the art can set them in advance according to actual conditions.

[0052] like Figure 3 and Figure 4 As shown, Figure 3 This is a schematic diagram of the finite element mesh before simulation. Figure 3 Nodes 10 and static edges 11 are shown. Figure 4 Schematic diagram of the finite element mesh after simulation. Figure 4 Nodes 10 and dynamic edges 12 are shown. It can be understood that in the finite element mesh before simulation, there will be static edges 11 whose length is less than the preset distance. However, after simulation, the length of the static edges 11 will change. Therefore, all edges in the finite element mesh before simulation are collectively referred to as static edges 11.

[0053] The construction method of the simulation correction model includes:

[0054] A first sample data set is obtained, wherein the first sample data set includes historical node motion positions, historical node connection relationships, and historical target surface data. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical node motion positions and historical node connection relationships in the sample training set are used as input data of the regression network, and the historical target surface data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time target surface data. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a simulation correction model. The initial regression network is preferably a deep neural network model.

[0055] It should be noted that the above-mentioned historical target surface data is obtained under an experimental environment. For example, under the experimental environment, the first surface data and simulation data corresponding to the experimental non-woven fabric are obtained in advance, and the corresponding historical node movement positions and historical node connection relationships are obtained after simulation. A transmission experiment is carried out on the non-woven fabric. For example, the non-woven fabric is transported to the position of the hot pressing roller by a conveyor belt, the non-woven fabric is taken out and its surface is inspected to obtain the corresponding historical target surface data. The historical node movement positions, historical node connection relationships and historical target surface data are used as sample data sets to train the deep neural network model, thereby generating a simulation correction model.

[0056] It can be understood that the deep neural network model includes an encoder, a feature processor and a decoder. The node motion position and the node connection relationship are input into the encoder to obtain node features and edge features. The feature processor can be a graph neural network, which performs convolution operations on the node features and edge features. The relationship between node features, edge features and target surface features is established by introducing a nonlinear function. The nonlinear function can be a ReLU (Rectified Linear Unit) function. The target surface feature refers to the feature converted from the target surface data. Finally, the decoder outputs the corresponding target surface data.

[0057] S20: acquiring basic data of the breathable film to be processed, acquiring corresponding stretching parameters according to the basic data, performing stretching processing on the breathable film to be processed according to the stretching parameters, acquiring N groups of real-time stretching data during the stretching processing, and determining whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1;

[0058] In this embodiment, the basic data includes but is not limited to membrane thickness and porosity. The porosity is the percentage of the pore area on the surface of the breathable membrane to be treated to the total area. The porosity acquisition method can be to first obtain a surface image of the breathable membrane to be treated, perform binarization on the surface image, and calculate the number of pixels in the white area (pore part) and the black area (solid part) by software such as MATLAB, so as to determine the porosity.

[0059] Specifically, the stretching parameters include at least the number of stretching times and the stretching force. The method for obtaining the corresponding stretching parameters according to the basic data includes:

[0060] Determine the numerical range corresponding to each element in the basic data, and determine the corresponding stretching parameters according to the numerical range and the mapping relationship.

[0061] It can be understood that, taking the porosity in the basic data as an example, the larger the porosity, the better the air permeability of the breathable membrane to be treated, so the corresponding stretching times and stretching forces can be set to smaller values. As for the establishment of the mapping relationship, it can be that a mapping relationship table is established, each row in the mapping relationship table represents a mapping relationship, and the mapping relationship table has a basic data column, a numerical interval column, and a stretching parameter column; the basic data, the numerical interval, and the stretching parameter are taken as a row of data, and are written into the basic data column, the numerical interval column, and the stretching parameter column respectively to achieve the establishment of the mapping relationship.

[0062] In this embodiment, the stretching treatment of the breathable film to be treated can be completed by existing equipment such as a unidirectional stretching film machine according to the stretching parameters, and the real-time stretching data includes at least the maximum deformation amount and the stretching rate. The maximum deformation amount refers to the maximum deformation length or maximum deformation thickness of the breathable film to be treated during a single stretching process, and the stretching rate refers to the extension speed of the breathable film to be treated per unit time during the stretching process.

[0063] The method for determining whether to stop stretching according to N sets of real-time stretching data includes:

[0064] Determine whether there are H consecutive maximum deformation variables among the N maximum deformation variables greater than the preset deformation variable, and whether there are W consecutive stretching rates among the N stretching rates greater than the preset rate. If both exist, stop stretching, N>H, N>W, H and W are both integers greater than 0.

[0065] It should be noted that the main purpose of stretching the breathable membrane is to improve the air permeability of the breathable membrane. When there are H consecutive maximum deformation variables greater than the preset deformation variable, and at the same time there are W consecutive stretching rates among N stretching rates greater than the preset rate, it indicates that the breathable membrane has reached or is close to the expected stretching effect. Therefore, the stretching can be stopped without completing the corresponding number of stretching times. When these two conditions do not exist at the same time, the stretching can be stopped only after reaching the corresponding number of stretching times. In this way, it is possible to flexibly choose whether to stop the stretching according to the actual stretching situation, which not only ensures the stretching effect but also avoids unexpected situations such as tearing of the breathable membrane.

[0066] S30: obtaining second surface data of the breathable membrane after stretching, determining an air permeability score according to the second surface data, calculating a roughness score according to the target surface data, inputting the roughness score and the air permeability score into a pre-built humidification prediction model, and obtaining a target humidification amount;

[0067] It should be noted that the second surface data at least includes porosity, average pore size value and pore distribution rate. The method for obtaining the above-mentioned average pore size value may be to first obtain a surface image of the breathable membrane after stretching, and then obtain a number of target pore size values ​​based on the surface image, and use the average of the target pore size values ​​as the average pore size value. The target pore size value may be an pore size value greater than a preset pore size threshold. The principle of obtaining porosity and pore size values ​​based on the surface image has been disclosed in the above content, and this embodiment will not go into details. The method for obtaining the pore distribution rate may be to generate a number of sub-images according to a preset grid division of the surface image, determine whether there are pores in the several sub-images, and if so, mark the sub-image, and use the ratio of the marked sub-image to the sum of the sub-images as the pore distribution rate.

[0068] Methods for determining an air permeability score based on the second surface data include:

[0069] ;

[0070] Where ROS is the air permeability score, is the porosity, is the pore distribution ratio, is the average pore size, is a logarithmic function with base 3, is an exponential function with base e, is the inverse cotangent function, , e are both constants greater than 0.

[0071] In this embodiment, porosity is used as an example. The greater the porosity, the better the air permeability of the breathable membrane after stretching. Therefore, it can be seen from the above content that the air permeability score is positively correlated with the air permeability of the breathable membrane.

[0072] The target surface data includes height difference, reflection intensity variance and time root mean square. The method for calculating the roughness score based on the target surface data includes:

[0073] ;

[0074] Where RHS is the roughness score, is the height difference, is the reflection intensity variance, is the time root mean square, is a logarithmic function with base e, is the hyperbolic cosine function, is the inverse tangent function.

[0075] In this embodiment, the reflection intensity variance is taken as an example. The larger the reflection intensity variance is, the more severe the roughness of the non-woven fabric after corresponding stretching is. Therefore, it can be seen from the above content that the roughness score is positively correlated with the roughness of the non-woven fabric.

[0076] The method for constructing the humidification prediction model includes:

[0077] A second sample data set is obtained, wherein the second sample data set includes a historical roughness score, a historical air permeability score, and a historical target humidification amount. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical roughness score and the historical air permeability score in the sample training set are used as input data of the regression network, and the historical target humidification amount in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time target humidification amount. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a humidification prediction model. The initial regression network is preferably a recurrent neural network model. The historical target humidification amount in the above-mentioned can be set by expert experience or obtained by experiments. For example, the humidification amount of different groups is set, and the effect of subsequent hot pressing is used as the judgment criterion, and the humidification amount of the optimal group is selected as the historical target humidification amount.

[0078] It should be added that, according to the above content, the air permeability score is positively correlated with the air permeability of the breathable film, and the roughness score is positively correlated with the roughness of the non-woven fabric. The more severe the roughness of the non-woven fabric, the greater the required humidification amount, and the better the air permeability of the breathable film, excessive moisture absorption will cause the material to become too moist. During the hot pressing process, excessive moisture of the material will affect the uniformity of heat conduction. Therefore, it is necessary to reduce the humidification amount to avoid the breathable film absorbing too much moisture, thereby avoiding affecting the subsequent hot pressing effect. By considering the actual conditions of the non-woven fabric and the breathable film, this embodiment can reasonably determine the humidification amount, thereby improving the effect of subsequent hot pressing.

[0079] S40: humidifying the nonwoven fabric and the breathable membrane based on the target humidification amount;

[0080] It should be noted that the non-woven fabric and the breathable membrane can be humidified together or separately. When humidified separately, the target humidification amount needs to be divided into a first humidification amount and a second humidification amount according to the predicted humidification ratio. The non-woven fabric is humidified according to the first humidification amount, and the breathable membrane is humidified according to the second humidification amount. After the humidification work is completed, subsequent hot pressing is carried out. The humidification work can be completed by existing steam humidification equipment or high-pressure spray humidification equipment.

[0081] In this embodiment, simulation is performed based on the first surface data and the simulation data to obtain target surface data, corresponding stretching parameters are obtained according to the basic data, the breathable film to be treated is stretched according to the stretching parameters, N groups of real-time stretching data are obtained during the stretching process, and it is determined whether to stop stretching according to the N groups of real-time stretching data, and the second surface data of the breathable film after stretching is obtained, and the air permeability score is determined according to the second surface data. The roughness score is calculated according to the target surface data, and the roughness score and the air permeability score are input into a pre-constructed humidification prediction model to obtain the target humidification amount. Finally, the non-woven fabric and the breathable film are humidified based on the target humidification amount. This embodiment can control the parameters in the production process of the non-woven fabric breathable film, and can obtain a suitable humidification amount according to the actual conditions of the non-woven fabric and the breathable film, thereby improving the subsequent hot pressing effect.

[0082] Example 2

[0083] In this embodiment, based on the embodiment 1, the non-woven breathable membrane production line operation parameter optimization control method further includes: S50: determining the target hot pressing time according to the target humidification amount and the preset standard hot pressing time;

[0084] The method for determining the target heat pressing time according to the target humidification amount and the preset standard heat pressing time includes:

[0085] A first ratio between the target humidification amount and the preset standard humidification amount is calculated, and the product of the first ratio and the preset standard hot pressing time is used as the target hot pressing time.

[0086] In this embodiment, the standard humidification amount corresponds to the standard hot pressing time, and the target humidification amount and the standard hot pressing time are both constants. Those skilled in the art store the target humidification amount and the standard hot pressing time in the system in advance. It can be understood that when the value of the humidification amount changes, the corresponding hot pressing time will naturally change as well, which can further improve the hot pressing effect between the non-woven fabric and the breathable membrane.

[0087] Example 3

[0088] like Figure 2As shown, this embodiment provides an optimization control system for operating parameters of a non-woven breathable film production line based on Embodiment 1, including:

[0089] Simulation module: used for obtaining first surface data and simulation data of the non-woven fabric to be processed, and performing simulation based on the first surface data and the simulation data to obtain target surface data;

[0090] In this embodiment, the first surface data can be data obtained by directly detecting the surface of the non-woven fabric to be treated through sensors and other equipment. The first surface data includes but is not limited to height difference, reflection intensity variance and time root mean square. The height difference refers to the height difference between the highest peak and the lowest valley, and the highest peak is the maximum surface height of the non-woven fabric to be treated, and the corresponding lowest valley is the minimum surface height of the non-woven fabric to be treated. The non-woven fabric surface can be scanned by a laser sensor to obtain a high-resolution surface height. The reflection intensity refers to the reflection intensity of the non-woven fabric surface to be treated, and the time root mean square refers to the root mean square of the reflection time of the non-woven fabric surface to be treated. The above-mentioned reflection intensity and reflection time can be obtained by scanning the non-woven fabric surface with an ultrasonic sensor, and the calculation of variance and root mean square are both existing technologies, which will not be elaborated in this embodiment.

[0091] A method for obtaining target surface data by simulating based on the first surface data and the simulation data includes:

[0092] A finite element mesh of the non-woven fabric to be processed is constructed based on the first surface data, the finite element mesh includes M nodes and multiple static edges for connecting the M nodes, the motion state of the non-woven fabric to be processed is simulated based on the finite element mesh and the simulation data, and an initial simulation result of the fabric is obtained, the initial simulation result at least includes the motion positions of the M nodes, for every two nodes among the M nodes, when the distance between the two nodes is less than a preset distance length, a dynamic edge between the two nodes is established, the motion positions of the M nodes in the finite element mesh and the connection relationship of the M nodes are input into a pre-constructed simulation correction model to obtain target surface data, and the connection relationship of the M nodes includes a static edge connection relationship and a dynamic edge connection relationship.

[0093] It should be noted that the target surface data also includes height difference, reflection intensity variance and time root mean square, but the first surface data represents the roughness of the non-woven fabric to be processed, and the target surface data represents the roughness of the non-woven fabric after simulation. In the above, both static edges and dynamic edges represent the distance between nodes. It can be understood that when the number of dynamic edges is large, it means that the distances between multiple nodes are less than the preset distance length, indicating that the roughness of the non-woven fabric surface is large.

[0094] The construction method of the simulation correction model includes:

[0095] A first sample data set is obtained, wherein the first sample data set includes historical node motion positions, historical node connection relationships, and historical target surface data. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical node motion positions and historical node connection relationships in the sample training set are used as input data of the regression network, and the historical target surface data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time target surface data. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a simulation correction model. The initial regression network is preferably a deep neural network model.

[0096] It should be noted that the above-mentioned historical target surface data is obtained under an experimental environment. For example, under the experimental environment, the first surface data and simulation data corresponding to the experimental non-woven fabric are obtained in advance, and the corresponding historical node movement positions and historical node connection relationships are obtained after simulation. A transmission experiment is carried out on the non-woven fabric. For example, the non-woven fabric is transported to the position of the hot pressing roller by a conveyor belt, the non-woven fabric is taken out and its surface is inspected to obtain the corresponding historical target surface data. The historical node movement positions, historical node connection relationships and historical target surface data are used as sample data sets to train the deep neural network model, thereby generating a simulation correction model.

[0097] The first processing module is used to obtain basic data of the breathable film to be processed, obtain corresponding stretching parameters according to the basic data, perform stretching processing on the breathable film to be processed according to the stretching parameters, obtain N groups of real-time stretching data during the stretching process, and determine whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1;

[0098] In this embodiment, the basic data includes but is not limited to membrane thickness and porosity. The porosity is the percentage of the pore area on the surface of the breathable membrane to be treated to the total area. The porosity acquisition method can be to first obtain a surface image of the breathable membrane to be treated, perform binarization on the surface image, and calculate the number of pixels in the white area (pore part) and the black area (solid part) by software such as MATLAB, so as to determine the porosity.

[0099] Specifically, the stretching parameters include at least the number of stretching times and the stretching force. The method for obtaining the corresponding stretching parameters according to the basic data includes:

[0100] Determine the numerical range corresponding to each element in the basic data, and determine the corresponding stretching parameters according to the numerical range and the mapping relationship.

[0101] The method for determining whether to stop stretching according to N sets of real-time stretching data includes:

[0102] Determine whether there are H consecutive maximum deformation variables among the N maximum deformation variables greater than the preset deformation variable, and whether there are W consecutive stretching rates among the N stretching rates greater than the preset rate. If both exist, stop stretching, N>H, N>W, H and W are both integers greater than 0.

[0103] It should be noted that the main purpose of stretching the breathable membrane is to improve the air permeability of the breathable membrane. When there are H consecutive maximum deformation variables greater than the preset deformation variable, and at the same time there are W consecutive stretching rates among N stretching rates greater than the preset rate, it indicates that the breathable membrane has reached or is close to the expected stretching effect. Therefore, the stretching can be stopped without completing the corresponding number of stretching times. When these two conditions do not exist at the same time, the stretching can be stopped only after reaching the corresponding number of stretching times. In this way, it is possible to flexibly choose whether to stop the stretching according to the actual stretching situation, which not only ensures the stretching effect but also avoids unexpected situations such as tearing of the breathable membrane.

[0104] The second processing module is used to obtain the second surface data of the breathable membrane after stretching, determine the air permeability score according to the second surface data, calculate the roughness score according to the target surface data, input the roughness score and the air permeability score into the pre-built humidification prediction model, and obtain the target humidification amount;

[0105] It should be noted that the second surface data at least includes porosity, average pore size value and pore distribution rate. The method for obtaining the above-mentioned average pore size value may be to first obtain a surface image of the breathable membrane after stretching, and then obtain a number of target pore size values ​​based on the surface image, and use the average of the target pore size values ​​as the average pore size value. The target pore size value may be an pore size value greater than a preset pore size threshold. The principle of obtaining porosity and pore size values ​​based on the surface image has been disclosed in the above content, and this embodiment will not go into details. The method for obtaining the pore distribution rate may be to generate a number of sub-images according to a preset grid division of the surface image, determine whether there are pores in the several sub-images, and if so, mark the sub-image, and use the ratio of the marked sub-image to the sum of the sub-images as the pore distribution rate.

[0106] Methods for determining an air permeability score based on the second surface data include:

[0107] ;

[0108] Where ROS is the air permeability score, is the porosity, is the pore distribution ratio, is the average pore size, is a logarithmic function with base 3, is an exponential function with base e, is the inverse cotangent function, , e are both constants greater than 0.

[0109] In this embodiment, porosity is used as an example. The greater the porosity, the better the air permeability of the breathable membrane after stretching. Therefore, it can be seen from the above content that the air permeability score is positively correlated with the air permeability of the breathable membrane.

[0110] The target surface data includes height difference, reflection intensity variance and time root mean square. The method for calculating the roughness score based on the target surface data includes:

[0111] ;

[0112] Where RHS is the roughness score, is the height difference, is the reflection intensity variance, is the time root mean square, is a logarithmic function with base e, is the hyperbolic cosine function, is the inverse tangent function.

[0113] In this embodiment, the reflection intensity variance is taken as an example. The larger the reflection intensity variance is, the more severe the roughness of the non-woven fabric after corresponding stretching is. Therefore, it can be seen from the above content that the roughness score is positively correlated with the roughness of the non-woven fabric.

[0114] Humidification module: used to humidify the non-woven fabric and breathable membrane based on the target humidification amount;

[0115] It should be noted that the non-woven fabric and the breathable membrane can be humidified together or separately. When humidified separately, the target humidification amount needs to be divided into a first humidification amount and a second humidification amount according to the predicted humidification ratio. The non-woven fabric is humidified according to the first humidification amount, and the breathable membrane is humidified according to the second humidification amount. After the humidification work is completed, subsequent hot pressing is carried out. The humidification work can be completed by existing steam humidification equipment or high-pressure spray humidification equipment.

[0116] Example 4

[0117] The present embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the non-woven breathable membrane production line operating parameter optimization control method provided by the above methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

[0118] Since the electronic device introduced in this embodiment is an electronic device used to implement the non-woven breathable membrane production line operating parameter optimization control method in the embodiment of this application, based on the non-woven breathable membrane production line operating parameter optimization control method introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used by the non-woven breathable membrane production line operating parameter optimization control method in the embodiment of this application, it belongs to the scope of protection of this application.

[0119] Example 5

[0120] like Figure 5 As shown, the present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned non-woven breathable membrane production line operation parameter optimization control method is implemented.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0122] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0123] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0125] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0129] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Optimization control method of operating parameters of non-woven breathable film production line, It is characterized in that include: Acquire first surface data and simulation data of the non-woven fabric to be processed, perform simulation based on the first surface data and the simulation data, and obtain target surface data, wherein the target surface data includes a height difference value, a reflection intensity variance, and a time root mean square; Obtain basic data of the breathable film to be processed, obtain corresponding stretching parameters according to the basic data, perform stretching on the breathable film to be processed according to the stretching parameters, obtain N groups of real-time stretching data during the stretching process, and determine whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1; Acquire second surface data of the breathable membrane after stretching, determine an air permeability score according to the second surface data, calculate a roughness score according to the target surface data, input the roughness score and the air permeability score into a pre-built humidification prediction model to obtain a target humidification amount, wherein the second surface data includes porosity, average pore size value, and pore distribution rate; humidifying the nonwoven fabric and the breathable membrane based on the target humidification amount; The method of performing simulation based on the first surface data and the simulation data to obtain the target surface data includes: A finite element mesh of the non-woven fabric to be processed is constructed based on the first surface data, the finite element mesh includes M nodes and multiple static edges for connecting the M nodes, the motion state of the non-woven fabric to be processed is simulated based on the finite element mesh and the simulation data, and an initial simulation result of the fabric is obtained, the initial simulation result at least includes the motion positions of the M nodes, for every two nodes among the M nodes, when the distance between the two nodes is less than a preset distance length, a dynamic edge between the two nodes is established, the motion positions of the M nodes in the finite element mesh and the connection relationship of the M nodes are input into a pre-constructed simulation correction model to obtain target surface data, and the connection relationship of the M nodes includes a static edge connection relationship and a dynamic edge connection relationship.

2. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that The method for constructing the simulation correction model comprises: A first sample data set is obtained, wherein the first sample data set includes historical node motion positions, historical node connection relationships, and historical target surface data. The first sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical node motion positions and historical node connection relationships in the sample training set are used as input data of the regression network, and the historical target surface data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time target surface data. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a simulation correction model.

3. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that The method for obtaining corresponding stretching parameters according to basic data includes: Determine the numerical range corresponding to each element in the basic data, and determine the corresponding stretching parameter according to the numerical range and the mapping relationship.

4. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that The real-time stretching data includes a maximum deformation amount and a stretching rate. The method for determining whether to stop stretching according to N sets of real-time stretching data includes: Determine whether there are H consecutive maximum deformation variables among the N maximum deformation variables greater than the preset deformation variable, and whether there are W consecutive stretching rates among the N stretching rates greater than the preset rate. If both exist, stop stretching, N>H, N>W, H and W are both integers greater than 0.

5. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that The porosity, average pore size and pore distribution are comprehensively analyzed to obtain the air permeability score.

6. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that The height difference, reflection intensity variance and time root mean square are comprehensively analyzed to obtain the roughness score.

7. The method for optimizing and controlling the operating parameters of a nonwoven breathable membrane production line according to claim 1, It is characterized in that Also includes: Determine the target heat pressing time according to the target humidification amount and the preset standard heat pressing time; The method for determining the target hot pressing time according to the target humidification amount and the preset standard hot pressing time includes: A first ratio between the target humidification amount and the preset standard humidification amount is calculated, and the product of the first ratio and the preset standard hot pressing time is used as the target hot pressing time.

8. A non-woven breathable film production line operating parameter optimization control system, which is used to implement the non-woven breathable film production line operating parameter optimization control method according to any one of claims 1 to 7, It is characterized in that include: Simulation module: used for obtaining first surface data and simulation data of the non-woven fabric to be processed, and performing simulation based on the first surface data and the simulation data to obtain target surface data; The first processing module is used to obtain basic data of the breathable film to be processed, obtain corresponding stretching parameters according to the basic data, perform stretching processing on the breathable film to be processed according to the stretching parameters, obtain N groups of real-time stretching data during the stretching process, and determine whether to stop stretching according to the N groups of real-time stretching data, where N is an integer greater than 1; The second processing module is used to obtain the second surface data of the breathable membrane after stretching, determine the air permeability score according to the second surface data, calculate the roughness score according to the target surface data, input the roughness score and the air permeability score into the pre-built humidification prediction model, and obtain the target humidification amount; Humidification module: used to humidify the non-woven fabric and breathable membrane based on the target humidification amount.

9. An electronic device comprising a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit, It is characterized in that When the central processing unit executes the computer program, it implements the non-woven breathable membrane production line operating parameter optimization control method described in any one of claims 1 to 7, and the interface includes a network interface and a data interface, the network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for optimizing and controlling the operating parameters of a non-woven breathable membrane production line according to any one of claims 1 to 7 is implemented.