EP-4737880-A1 - APPARATUS AND METHOD FOR DESIGNING MULTILAYER FILM

EP4737880A1EP 4737880 A1EP4737880 A1EP 4737880A1EP-4737880-A1

Abstract

Disclosed are a design apparatus and method for a multilayer film. The design apparatus for a multilayer film may model the laminated structure of the multilayer film to be designed, collect dart impact strength data for the single layer film forming the laminated structure as stress-strain data, read a value stored in advance in a storage space accessible to the design apparatus for the multilayer film, acquire a feature setting mode for designating different feature setting methods according to the read value, set a plurality of physical indicators selected from the dart impact strength data and the thickness of the single layer film as the features according to the feature setting mode, predict the dart impact strength of the multilayer film by using a machine learning model trained from a plurality of supervised learning models using features as an independent variable and the dart impact strength of the multilayer film as a target variable, and generate design data for the multilayer film by combining the predicted values for other characteristics and the predicted values of the dart impact strength.

Inventors

IM, Damhyeok
JO, Seongin
JUNG, Jinmi
MOON, SUNG NAM
HWANG, Seokyung
SEO, MINJI
JEON, Yeojin

Assignees

LG Chem, Ltd.

Dates

Publication Date: 20260506
Application Date: 20240902

Claims (20)

A design apparatus for a multilayer film that designs the multilayer film based on properties of the multilayer film predicted only using information about a single layer film by executing a program code loaded into one or more memory devices through one or more processors, wherein the program code is executed to: model the laminated structure of the multilayer film to be designed; collect dart impact strength data for the single layer film forming the laminated structure as stress-strain data; read a value stored in advance in a storage space accessible to the design apparatus for the multilayer film, and acquire a feature setting mode for designating different feature setting methods according to the read value; set a plurality of physical indicators selected from the dart impact strength data and a thickness of the single layer film as a feature, according to the feature setting mode; select at least one of a plurality of supervised learning models capable of regression analysis as a machine learning model; predict the dart impact strength of the multilayer film using the machine learning model trained using the features as an independent variable and the dart impact strength of the multilayer film as a target variable; and generate design data for the multilayer film by combining predicted values for other characteristics and predicted values of the dart impact strength to satisfy design requirements of the multilayer film.
The design apparatus of claim 1, wherein: when the feature setting mode includes a first feature setting mode, the setting as the feature includes setting, as the feature, at least some of a yield point, yield stress, resilience, strain hardening, failure, strain hardening modulus, flow energy, strain hardening energy, toughness, 1% modulus, and 2% modulus, and a thickness of the single layer film.
The design apparatus of claim 2, wherein: the selecting as the machine learning model includes selecting one of a partial least squares (PLS) model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from at least some of the yield point, the yield stress, the resilience, the strain hardening, the failure, the strain hardening modulus, the flow energy, the strain hardening energy, the toughness, the 1% modulus, and the 2% modulus, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design apparatus of claim 1, wherein: when the feature setting mode includes a second feature setting mode, the setting as the feature includes setting, as the feature, at least some of yield stress, yield strain, necking stress, necking strain, breaking stress, and breaking strain, and the thickness of the single layer film.
The design apparatus of claim 4, wherein: the selecting as the machine learning model includes selecting one of a PLS model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from at least some of the yield stress, the yield strain, the necking stress, the necking strain, the breaking stress, and the breaking strain, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design apparatus of claim 1, wherein: when the feature setting mode includes a third feature setting mode, the setting as the feature includes setting, as the feature, indicators of yield stress, yield strain, and the yield stress being divided by the yield strain, and the thickness of the single layer film.
The design apparatus of claim 6, wherein: the selecting as the machine learning model includes selecting one of a PLS model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from the indicators of the yield stress, the yield strain, and the yield stress being divided by the yield strain, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design apparatus of claim 1, wherein: the generating of the design data for the multilayer film includes combining predicted values for at least one of stiffness, strength, strain, tear strength, high-speed dart impact strength, sealing initiation temperature (SIT), haze, moisture permeability, and air permeability of the multilayer film with the predicted values of the dart impact strength, when the multilayer film designed based on the combination of the predicted values satisfies the design requirements, generating the design data based on the combination, and when the multilayer film designed based on the combination of the predicted values does not satisfy the design requirements, changing the combination to another combination and redesigning the multilayer film.
The design apparatus of claim 1, wherein: the multilayer film is modeled as a multilayer film model, the multilayer film includes a first single layer film and a second single layer film that are laminated to each other, the multilayer film model includes n (n is a multiple of 6) model layers that are laminated to each other, and the first single layer film corresponds to two or more model layers among the model layers, and the second single layer film corresponds to two or more other model layers among the model layers.
The design apparatus of claim 9, wherein: the program code is executed to further: display the model layer on a display device, and provide a user interface that allows a user to set the model layer corresponding to the first single layer film and the model layer corresponding to the second single layer film.
A design method for a multilayer film that designs the multilayer film based on properties of the multilayer film predicted only using information about a single layer film performed by a computing device including one or more processors and one or more memory devices, the design method comprising: modeling the laminated structure of the multilayer film to be designed; collecting dart impact strength data for the single layer film forming the laminated structure as stress-strain data; reading a value stored in advance in a storage space accessible by the computing device and acquiring a feature setting mode for designating a different feature setting method according to the read value; setting a plurality of physical indicators selected from the dart impact strength data and a thickness of the single layer film as a feature, according to the feature setting mode; selecting at least one of a plurality of supervised learning models capable of regression analysis as a machine learning model; predicting the dart impact strength of the multilayer film using the machine learning model trained using the feature as an independent variable and the dart impact strength of the multilayer film as a target variable; and generating design data for the multilayer film by combining predicted values for other characteristics and predicted values of the dart impact strength to satisfy design requirements of the multilayer film.
The design method of claim 11, wherein: when the feature setting mode includes a first feature setting mode, the setting as the feature includes setting, as the feature, at least some of a yield point, yield stress, resilience, strain hardening, failure, strain hardening modulus, flow energy, strain hardening energy, toughness, 1% modulus, and 2% modulus, and a thickness of the single layer film.
The design method of claim 12, wherein: the selecting as the machine learning model includes selecting one of a PLS model, a Lasso regression model, and the random forest model as a machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from at least some of the yield point, the yield stress, the resilience, the strain hardening, the failure, the strain hardening modulus, the flow energy, the strain hardening energy, the toughness, the 1% modulus, and the 2% modulus, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design method of claim 11, wherein: when the feature setting mode includes a second feature setting mode, the setting as the feature includes setting, as the feature, at least some of yield stress, yield strain, necking stress, necking strain, breaking stress, and breaking strain, and the thickness of the single layer film.
The design method of claim 14, wherein: the selecting as the machine learning model includes selecting one of a PLS model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from at least some of the yield stress, the yield strain, the necking stress, the necking strain, the breaking stress, and the breaking strain, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design method of claim 11, wherein: when the feature setting mode includes a third feature setting mode, the setting as the feature includes setting, as the feature, indicators of yield stress, yield strain, and the yield stress being divided by the yield strain, and the thickness of the single layer film.
The design method of claim 16, wherein: the selecting as the machine learning model includes selecting one of a PLS model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model receives a vector generated from the indicators of the yield stress, the yield strain, and the yield stress being divided by the yield strain, and the thickness of the single layer film, and is trained to predict the dart impact strength of the multilayer film.
The design method of claim 11, wherein: the generating of the design data for the multilayer film includes: combining predicted values for at least one of stiffness, strength, strain, tear strength, high-speed dart impact strength, sealing initiation temperature (SIT), haze, moisture permeability, and air permeability of the multilayer film with the predicted values of the dart impact strength; when the multilayer film designed based on the combination of the predicted values satisfies the design requirements, generating the design data based on the combination; and when the multilayer film designed based on the combination of the predicted values does not satisfy the design requirements, changing the combination to another combination and redesigning the multilayer film.
The design method of claim 11, wherein: the multilayer film is modeled as a multilayer film model, the multilayer film includes a first single layer film and a second single layer film that are laminated to each other, the multilayer film model includes n (n is a multiple of 6) model layers that are laminated to each other, and the first single layer film corresponds to two or more model layers among the model layers, and the second single layer film corresponds to two or more other model layers among the model layers.
The design method of claim 19, further comprising: displaying the model layer on a display device, and providing a user interface that allows a user to set the model layer corresponding to the first single layer film and the model layer corresponding to the second single layer film.

Description

[Technical Field] CROSS-REFERENCE TO RELATED APPLICATION This application claims priority to and the benefit of Korean Patent Application Nos. 10-2023-0116487 and 10-2024-0117595 filed in the Korean Intellectual Property Office on September 01, 2023 and August 30, 2024, the entire contents of which are incorporated herein by reference. The present disclosure relates to a design apparatus and method for a multilayer film. [Background Art] Polymer films refer to a thin, flat structure manufactured from polymer materials. Here, polymer may have a molecular structure in the form of a long chain in which monomers, which are repeating units, are connected. A thickness of the polymer film may be set variously up to millimeters (mm). The polymer films may have various advantages, including flexibility, lightness, cost efficiency, and processability. Specifically, the polymer films may be manufactured in various shapes and sizes due to their excellent flexibility, so the polymer films may be applied to various product designs. In addition, due to the lightness of the polymer film, the polymer films may be suitable for products that require portability and reduce transportation and handling costs. In addition, the polymer films may be manufactured with relatively inexpensive raw materials and mass-produced, so the polymer film is cost-effective. In addition, the polymer films may be applied to various manufacturing and processing technologies, such as thermal processing, extrusion, and bonding, so the shape, size, and thickness of the product may be easily adjusted. In addition, the polymer films have high durability and strength, and some polymer films have excellent optical properties, excellent waterproofing, and may be breathable as needed. A multilayer film may be a film composed of two or more layers of polymers or other materials. This multilayer structure may improve the performance of the entire film by combining unique properties of each layer. For example, one layer may be used to increase durability and strength, another layer may provide waterproofing or moisture resistance, and another layer may provide resistance to a specific chemical. In this way, by combining layers with various characteristics, the multilayer film may adapt to a wider range of applications and specific requirements than a single layer film. [Disclosure] [Technical Problem] The present disclosure attempts to provide a design apparatus and method for a multilayer film capable of predicting properties of a multilayer film using only information on a single layer film that forms a multilayer film when designing the multilayer film. [Technical Solution] According to an example embodiment, there is provided a design apparatus for a multilayer film that designs the multilayer film based on properties of the multilayer film predicted only using information about a single layer film by executing a program code loaded into one or more memory devices through one or more processors, in which the program code may be executed to: model the laminated structure of the multilayer film to be designed, collect dart impact strength data for the single layer film forming the laminated structure as stress-strain data; read a value stored in advance in a storage space accessible to the design apparatus for the multilayer film, and acquire a feature setting mode for designating different feature setting methods according to the read value; set a plurality of physical indicators selected from the dart impact strength data and a thickness of the single layer film as a feature, according to the feature setting mode; select at least one of a plurality of supervised learning models capable of regression analysis as a machine learning model; predict the dart impact strength of the multilayer film using the machine learning model trained using the features as an independent variable and the dart impact strength of the multilayer film as a target variable; and generate design data for the multilayer film by combining predicted values for other characteristics and predicted values of the dart impact strength to satisfy design requirements of the multilayer film. In some example embodiments, when the feature setting mode includes a first feature setting mode, the setting as the feature may include setting, as the feature, at least some of a yield point, yield stress, resilience, strain hardening, failure, strain hardening modulus, flow energy, strain hardening energy, toughness, 1% modulus, and 2% modulus, and a thickness of the single layer film. In some example embodiments, the selecting as the machine learning model may include selecting one of a partial least squares (PLS) model, a Lasso regression model, and a random forest model as the machine learning model, and the machine learning model selected from among the PLS model, the Lasso regression model, and the random forest model may receive a vector generated from at least some of the yield point, the yield s