Method and apparatus for predicting discoloration of artificial leather

Abstract

A method for generating a post-exposure discoloration estimation model, according to an embodiment of the present specification, may comprise the steps of: acquiring color information of a dyeing substrate and dye combination information corresponding to the color information; acquiring process information corresponding to the dye combination information; acquiring post-exposure discoloration information of artificial leather dyed by using the process information; and generating a machine learning model, which estimates the post-exposure discoloration information from the dye combination information and the process information, by using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

Description

Method and device for predicting discoloration of artificial leather

[0001] The present invention relates to a method for generating a model for estimating post-exposure discoloration and to a technique for dyeing artificial leather using the same. In particular, the technique utilizes color information, dye combinations, dyeing conditions, etc. from the dyeing process to estimate the post-exposure discoloration of dyed artificial leather.

[0002] The dyeing industry has evolved across diverse cultures and eras. Initially, hand-dyeing using natural dyes predominated. However, following the Industrial Revolution, the invention of synthetic dyes and the introduction of mechanized processes led to significant advancements in dyeing technology.

[0003] Despite these historical advancements, the modern dyeing industry still faces numerous complex and unpredictable challenges. Traditional dyeing methods rely primarily on the operator's hands and experience, which significantly limits the predictability and consistency of the dyeing process. For example, in manual dyeing processes, factors such as dye mixing ratios, dyeing time, and temperature depend on human judgment, making it difficult to reproduce identical results.

[0004] These traditional methods suffer from two major problems. First, the lack of reproducibility and consistency in the dyeing process poses significant challenges in modern industries that demand mass production and standardization. Second, the complexity of the dyeing process hinders efficiency and sustainability. Many manual processes are time-consuming and labor-intensive, and frequent trial and error leads to a waste of resources.

[0005] The background technology described above is technical information that the inventor possessed for the purpose of deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be considered as publicly known technology disclosed to the general public prior to the application for the present invention.

[0006] The embodiments of the present specification are proposed to solve the above-described problems and can determine the dyeing process more effectively.

[0007] A method for generating a post-exposure discoloration characteristic prediction model according to one embodiment of the present specification for achieving the above-described task may include: obtaining color information of a dyeing substrate and dye combination information corresponding to the color information; obtaining process information corresponding to the dye combination information; obtaining information on the post-exposure discoloration of artificial leather dyed by the process information; and generating a machine learning model for estimating the post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

[0008] The above process information may include information on the amount of dye and dyeing agent used, information on the composition of the dyeing material, information on the dyeing liquid ratio, information on the dyeing temperature, information on the dyeing time, and information on pretreatment.

[0009] The method may further include a step of augmenting the process information based on at least one of numerical transformation, interpolation, and noise addition.

[0010] The above machine learning model can be implemented using a multiple regression analysis-based algorithm.

[0011] A method for dyeing artificial leather according to one embodiment of the present specification for achieving the above-described task may include: a step of identifying a first color of a dyeing base material and discoloration information after a first exposure; a step of obtaining first dye combination information and first process information corresponding to the first color of the dyeing base material and the discoloration information after the first exposure based on a machine learning model; and a step of dyeing the dyeing base material based on the first dye combination information and the first process information.

[0012] The machine learning model can be generated by a method including: obtaining a first color of the dyeing material and dye combination information corresponding to the first color; obtaining process information corresponding to the dye combination information; obtaining post-exposure discoloration information of the material dyed by the process information; and generating a machine learning model that estimates post-exposure discoloration information from the dye combination information and the process information using the dye combination information, the process information, and the pre- and post-exposure colorimetric value information as a data set.

[0013] According to one embodiment of the present specification for achieving the above-described task, a computer device includes a processor, and the processor can execute instructions including: obtaining color information of a dyed substrate and dye combination information corresponding to the color information; obtaining process information corresponding to the dye combination information; obtaining post-exposure discoloration information of a substrate dyed by the process information; and generating a machine learning model that estimates the post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

[0014] The above process information may include dye usage amount and liquid ratio information, dyeing material composition information, dyeing temperature and time information, and post-dyeing process conditions.

[0015] The above command may further include a step of augmenting the process information based on at least one of numerical transformation, interpolation, and noise addition.

[0016] The above machine learning model may be a post-exposure discoloration prediction model implemented using a multiple regression analysis-based algorithm.

[0017] According to one embodiment of the present specification for achieving the above-described task, a fabric dyeing machine may include: a dye supply unit for supplying a dye based on first dye combination information and first process information; a temperature control unit for controlling the temperature and time of the fabric; and a control unit for identifying a first color of a dyeing base material and discoloration information after a first exposure, and obtaining the first dye combination information and the first process information corresponding to the first color of the dyeing base material and the discoloration information after the first exposure based on a machine learning model, and controlling to dye the dyeing base material based on the first dye combination information and the first process information.

[0018] The machine learning model can be generated by a method including: obtaining a first color of the dyeing material and dye combination information corresponding to the first color; obtaining process information corresponding to the dye combination information; obtaining post-exposure discoloration information of artificial leather dyed with the process information; and generating a machine learning model that estimates post-exposure discoloration information from the dye combination information and the process information using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

[0019] According to one embodiment of the present invention, the post-exposure discoloration of artificial leather can be estimated from dye combination information and process information using a machine learning model.

[0020] According to one embodiment of the present invention, a dyeing process can be performed according to dyeing conditions and post-exposure discoloration requirements.

[0021] The effects of the embodiment are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by a person skilled in the art from the description of the claims.

[0022] FIG. 1 is a flowchart illustrating an operation for generating a machine learning model according to one embodiment of the present invention.

[0023] Figure 2 is a flowchart illustrating an operation of dyeing a substrate according to one embodiment of the present invention.

[0024] FIG. 3 is a diagram illustrating a machine learning model according to one embodiment of the present invention.

[0025] FIG. 4 is a block diagram schematically illustrating the block configuration of a computer device according to one embodiment of the present invention.

[0026] Fig. 5 is a block diagram schematically illustrating the block configuration of a fabric dyeing machine according to one embodiment of the present invention.

[0027] The present invention is capable of various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, as well as the methods for achieving them, will become clearer with reference to the embodiments described in detail below, along with the drawings. However, the present invention is not limited to the embodiments disclosed below and can be implemented in various forms.

[0028] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals and redundant descriptions thereof will be omitted.

[0029] In the examples below, the terms first, second, etc. are not used in a limiting sense, but are used for the purpose of distinguishing one component from another.

[0030] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0031] In the examples below, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that one or more other features or components may be added.

[0032] For convenience of explanation, the sizes of components in the drawings may be exaggerated or reduced. For example, the sizes and thicknesses of each component shown in the drawings are arbitrarily indicated for convenience of explanation, and thus the present invention is not necessarily limited to what is shown.

[0033] In some embodiments, where implementations are otherwise feasible, a specific process sequence may be performed in a different order than the described order. For example, two processes described in succession may be performed substantially simultaneously, or may be performed in a reverse order from the described order. In this case, the term "~unit" used in the present embodiment refers to a software or hardware component, and the "~unit" performs certain roles. However, the "~unit" is not limited to software or hardware. The "~unit" may be configured to be on an addressable storage medium, or may be configured to reproduce one or more processors.

[0034] In describing the present disclosure below, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present disclosure, the detailed description will be omitted.

[0035] "Machine learning" according to the present disclosure may encompass any form of technology or methodology used by a computer system to acquire knowledge from data and utilize it to perform specific tasks or solve problems. This includes, but is not limited to, traditional data analysis methods, supervised learning, unsupervised learning, and machine learning methodologies such as reinforcement learning.

[0036] That is, machine learning may include traditional machine learning algorithms such as linear regression, logistic regression, decision trees, random forests, and support vector machines. This "machine learning" refers to algorithms and models used to learn from data and predict or classify meaningful results for specific inputs, and these can be learned through methods such as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Furthermore, this may include various learning methods and structures, such as ensemble learning, multi-modal learning, and models using transfer learning, in addition to a single algorithm. These machine learning methodologies are applied in various fields such as data analysis, pattern recognition, and natural language processing, and these models can be learned on one computer system and utilized on another computer system. Learning according to the present disclosure may instruct a computer system to improve the performance of a model by reflecting patterns or rules within a data set to the model's weights or parameters based on an algorithm.

[0037] The present invention relates to a technology utilizing machine learning technology for estimating discoloration after exposure of a dyed dyeing material.

[0038] FIG. 1 is a flowchart illustrating an operation for generating a machine learning model according to one embodiment of the present invention.

[0039] Referring to FIG. 1, the computer device can obtain color information of a dyeing base material and dye combination information corresponding to the color information at step S110. Such color information can be quantitatively expressed using CIE Lab* color space, RGB, CMYK, wavelength-specific K / S spectrum (Kubelka-Munk function), and other color systems. The dye combination information can indicate a combination of specific dyes used to create a dyeing base material having a color according to the color information. Such dye combination information may vary depending on the dyeing base material, and may include dyes that have different colors, such as direct dyes, reactive dyes, sulfur dyes, disperse dyes, vat dyes, and acid dyes, which are used in single or composite applications of various fiber compositions such as cotton, polyester, nylon, PE, and PP, or in artificial leather in the form of PU-impregnated fibers, or in fabrics in the form of PU-based artificial leather. In addition, the dye combination information may include information between dyes and auxiliary agents.

[0040] A computer device according to one embodiment of the present invention can acquire process information corresponding to dye combination information at step S120. This process information includes various parameters used in the dyeing process, and may include at least one of dye usage information, dyeing temperature information, dyeing time information, and preprocessing information for the dyeing material.

[0041] The dye usage information, as described above, is an indicator of the quantitative amount of a specific dye used in the dyeing process and can be expressed as a percentage of dye usage (%owf) relative to the weight of the fiber. Dyeing temperature information can indicate the temperature used in the dyeing process. Dyeing time information can indicate the total time the dye is in contact with the substrate. Pretreatment information for the dyed material can include information on processes performed before dyeing, such as washing, bleaching, mercerizing, fiber fineness, and the composition and content of the impregnating PU.

[0042] A computer device according to one embodiment of the present invention can obtain post-exposure discoloration information of a dyed substrate using process information in step S130. This post-exposure discoloration information can be quantified as color difference information before and after exposure. For example, the computer device can obtain color difference information in the CIE Lab* color space, where L* can represent lightness, and a* and b* can represent red / green and yellow / blue color components, respectively. The computer device can evaluate the post-exposure discoloration of a dyed substrate by exposing it under a light source for a certain period of time, and comparing the colors before and after exposure, and specifically measuring changes in the L*, a*, and b* values. This color difference before and after exposure can be expressed as a Delta E value, which is the distance between two colors within the color space.

[0043] According to one embodiment of the present invention, a computer device can augment process information at step S140 based on at least one of numerical transformation, interpolation, and noise addition. The computer device can expand existing data points to encompass a wider range of values.

[0044] For each dye usage, a variation in the range of ±x% can be applied. For example, if 10% owf was previously used, the data can be augmented to a value between 9.7% and 10.3% owf, or a variation of the temperature value transformed within the range of -x to +x degrees can be applied for the dyeing temperature. For example, if the dyeing temperature is 125 degrees, the data can be augmented to a value between 123 and 127 degrees. In addition, for the post-exposure discoloration, a transformed color difference value within the range of -x to +x can be generated for a given color difference value. For example, if the color difference is 5.0, the data can be augmented to a value between 4.4 and 5.5.

[0045] According to an embodiment of the present invention, a computer device can generate a machine learning model for estimating the post-exposure discoloration information from the dye combination information and the process information using the dye combination information, the process information, and the post-exposure discoloration information as data sets in step S150. The computer device can learn a model for estimating the post-exposure discoloration information from the dye combination information and the process information using the dye combination information, the process information, and the post-exposure discoloration information as data sets. For example, the computer device can gradually determine weights in a manner of performing statistical analysis using the dye combination information and the process information as independent variables and the post-exposure discoloration information as a dependent variable based on at least one algorithm among multiple regression analysis, a decision tree, a random forest, and a neural network algorithm.

[0046] FIG. 2 is a flowchart illustrating an operation for dyeing artificial leather according to one embodiment of the present invention. The machine learning model in FIG. 2 may correspond to the machine learning model in FIG. 1.

[0047] Referring to Figure 2, the fabric dyeing machine can identify the first color of the dyeing material and the discoloration information after the first exposure at step S210. This first color can indicate the final color to be achieved during the dyeing process, and the discoloration information after the first exposure can indicate the color difference before and after the final discoloration to be achieved during the dyeing process.

[0048] In one embodiment of the present invention, a fabric dyeing machine can, at step S220, acquire first dye combination information and first process information corresponding to the first color of the dyeing material and the discoloration information after the first exposure based on a machine learning model. This first dye combination information and first process information can indicate dye combination information and process information that satisfy both the final color to be achieved during the dyeing process and the color difference conditions before and after exposure.

[0049] According to one embodiment of the present invention, a fabric dyeing machine can dye a dyeing material based on first dye combination information and first process information at step S230. A computer device can dye the fabric using dye information corresponding to the first dye combination, dye and auxiliary agent relationship information, and dye usage amount information, dyeing temperature information, dyeing time information, and pretreatment information corresponding to the first process information.

[0050] FIG. 3 is a diagram illustrating a machine learning model according to one embodiment of the present invention. As illustrated in FIG. 3, the machine learning model can generate a machine learning model that estimates post-exposure discoloration information from each process information for each color information of a dyeing material and dye combination information corresponding to the color information.

[0051] Referring to FIG. 3, the computer device can generate a model for estimating color difference (Delta E) information (330) before and after exposure based on process information dye usage information (320) and dyeing condition information (310) such as dyeing temperature information, dyeing time information, and pretreatment information. The computer device can learn a machine learning model based on at least one algorithm among multiple regression analysis, decision tree, random forest, and neural network algorithms, with usage information (320) and dyeing condition information (310) as independent variables and color difference (Delta E) information (330) as a dependent variable.

[0052] FIG. 4 is a block diagram schematically illustrating the block configuration of a computer device according to one embodiment of the present invention.

[0053] The computer device may include a memory (410) and a processor (420). The computer device may execute one or more sets of instructions that cause any one or more of the methodologies described herein to be performed.

[0054] The memory (410) may store a set of instructions including instructions related to a system that performs any one or more of the methodologies described herein. For example, the memory (410) may store data such as molecular structure data, geometric and chemical descriptor data, learning model data, and molecular dynamics simulation results. The memory (410) temporarily or permanently stores data such as basic programs, application programs, and setting information for the operation of the device. The memory (410) may include, but is not limited to, a non-volatile mass storage device such as a random access memory (RAM), a read only memory (ROM), and a disk drive. These software components may be loaded from a computer-readable storage medium separate from the memory (410) using a drive mechanism. Such a separate computer-readable storage medium may include a computer-readable storage medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. Depending on the embodiment, the software components may be loaded into memory (410) via a communication unit rather than a computer-readable storage medium. This memory (410) may store dye combinations, dyeing process information, post-exposure discoloration information, and machine learning models trained based on algorithms. These machine learning models may be transferred to other devices and utilized in other computer systems.

[0055] The processor (420) controls the overall operations of the device. Furthermore, the processor (420) may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (420) by the memory (410). For example, the processor (420) may be configured to execute instructions received according to program code stored in a storage device such as the memory (410). For example, the processor (420) performs various operations necessary to execute the methodology described in the present invention.

[0056] The processor (420) can process and calculate all data, including dye combinations, dyeing process information, and post-exposure discoloration information. This data can be used to calculate various variables and algorithms required to build and execute a machine learning model.

[0057] A processor (420) according to one embodiment of the present invention may obtain color information of a dyeing material and dye combination information corresponding to the color information, obtain process information corresponding to the dye combination information, obtain post-exposure discoloration information of artificial leather dyed by the process information, and generate a machine learning model that estimates post-exposure discoloration information from the dye combination information and the process information using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

[0058] This processor (420) can be implemented as a single CPU or multiple CPUs (or DSPs, SoCs). The processor (420) can be implemented as a digital signal processor (DSP) that processes digital signals, a microprocessor, a time controller (TCON). However, the processor (420) is not limited thereto, and may include one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), an ARM processor, or may be defined by the terms thereof.

[0059] Meanwhile, the computer program may be specifically designed and constructed for the present invention, or may be one known and available to those skilled in the computer software field. Examples of computer programs may include not only machine language code, such as that generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

[0060] FIG. 5 is a block diagram schematically illustrating a block configuration (500) of a fabric dyeing machine according to one embodiment of the present invention.

[0061] The fabric dyeing machine may include a dye supply unit (510), a temperature control unit (520), and a control unit (530). The fabric dyeing machine may execute one or more sets of instructions that cause any one or more of the methodologies described herein to be performed.

[0062] The dye supply unit (510) can supply dyes required for a specific dyeing process in precise quantities and ratios. The dye supply unit (510) can store various types of dyes and supply them by mixing them according to the required dye combination. The dye combination is based on dye combination information determined by the control unit (530). The dye supply unit (510) can be controlled by the control unit (530) to suit the characteristics of each dyeing process.

[0063] The temperature control unit (520) can control the temperature of the fabric during the dyeing process. This is controlled according to process information provided by the control unit (530). The temperature control unit (520) is controlled by the control unit (530) to maintain or change the temperature required during the dyeing process of the fabric.

[0064] The control unit (530) is a component that performs overall control of the dyeing machine and can control and manage the dyeing process. The control unit (530) uses a machine learning model generated by the processor (420) to process various data, including dye combination information, process information, and post-exposure discoloration information. Based on this information, the control unit (530) can adjust the dye supply unit (510) and temperature control unit (520) to dye the fabric.

[0065] A control unit (530) according to one embodiment of the present invention can identify a first color of a dyeing substrate and discoloration information after a first exposure, obtain first dye combination information and first process information corresponding to the first color of the dyeing substrate and the discoloration information after a first exposure based on a machine learning model, and control to dye the dyeing substrate based on the first dye combination information and the first process information.

[0066] This control unit (530) can be implemented with a single CPU or multiple CPUs (or DSP, SoC). The control unit (530) can be implemented with a digital signal processor (DSP), a microprocessor, or a time controller (TCON) that processes digital signals. However, the control unit (530) is not limited thereto, and may include one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, or may be defined by the corresponding term.

[0067] The specific implementations described in the present invention are exemplary embodiments and do not limit the scope of the present invention in any way. For the sake of brevity, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the lines connecting or connecting members between components depicted in the drawings are merely representative of functional connections and / or physical or circuit connections, and may be replaced or represented as various additional functional connections, physical connections, or circuit connections in an actual device. In addition, unless specifically mentioned as "essential," "important," etc., a component may not be absolutely necessary for the application of the present invention.

[0068] Although the present invention has been described with reference to the preferred embodiments mentioned above, various modifications and variations are possible without departing from the spirit and scope of the invention. Therefore, the scope of the appended claims shall encompass such modifications and variations as long as they fall within the spirit of the present invention.

Claims

1. A method for generating a model for estimating discoloration after exposure, A step of obtaining color information of a dyeing material and dye combination information corresponding to the color information; A step of obtaining process information corresponding to the above dye combination information; A step of obtaining discoloration information after exposure of artificial leather dyed by the above process information; and A step of generating a machine learning model that estimates the post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set, A method for generating a model for estimating post-exposure discoloration.

2. In paragraph 1, The above process information includes dye usage information, dyeing temperature information, dyeing time information, and pretreatment information. A method for generating a model for estimating post-exposure discoloration.

3. In paragraph 2, Further comprising a step of augmenting the above process information based on at least one of numerical transformation, interpolation and noise addition. A method for generating a model for estimating post-exposure discoloration.

4. In paragraph 1, The above machine learning model is a method for generating a post-exposure discoloration estimation model implemented using a multiple regression analysis-based algorithm.

5. In the method of dyeing artificial leather, A step of identifying the first color of the dyeing material and the discoloration information after the first exposure; A step of obtaining first dye combination information and first process information corresponding to the first color of the dyeing material and the first post-exposure discoloration information based on the machine learning model; and A step of dyeing the dyeing material based on the first dye combination information and the first process information, The above machine learning model is, A step of obtaining a first color of the dyeing material and dye combination information corresponding to the first color; A step of obtaining process information corresponding to the above dye combination information; A step of obtaining discoloration information after exposure of artificial leather dyed by the above process information; and A method including a step of generating a machine learning model that estimates post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set, How to dye artificial leather.

6. In computer devices, Contains a processor, The above processor, A step of obtaining color information of a dyeing material and dye combination information corresponding to the color information; A step of obtaining process information corresponding to the above dye combination information; A step of obtaining discoloration information after exposure of artificial leather dyed by the above process information; and A computer device that executes a command including a step of generating a machine learning model that estimates the post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

7. In paragraph 6, The above process information includes dye usage information, dyeing temperature information, dyeing time information, and color difference information before and after bleaching. Computer devices.

8. In paragraph 7, The above command is, A computer device further comprising a step of augmenting the process information based on at least one of numerical transformation, interpolation, and noise addition.

9. In paragraph 6, The above machine learning model is a computer device that generates a post-exposure discoloration estimation model implemented with a multiple regression analysis-based algorithm.

10. In fabric dyeing machines, A dye supply unit for supplying dye based on first dye combination information and first process information; A temperature control unit capable of controlling the temperature and time of the fabric; and A control unit is included that identifies a first color and a first post-exposure discoloration information of a dyeing material, obtains the first dye combination information and the first process information corresponding to the first color and the first post-exposure discoloration information of the dyeing material based on a machine learning model, and controls to dye the dyeing material based on the first dye combination information and the first process information. The above machine learning model is, A step of obtaining a first color of the dyeing material and dye combination information corresponding to the first color; A step of obtaining process information corresponding to the above dye combination information; A step of obtaining discoloration information after exposure of artificial leather dyed by the above process information; and A fabric dyeing machine, comprising a method for producing a machine learning model that estimates post-exposure discoloration information from the dye combination information and the process information, using the dye combination information, the process information, and the post-exposure discoloration information as a data set.

Images