Method and apparatus for predicting discoloration of artificial leather

Abstract

A method for generating a post-exposure color change estimation model according to an embodiment of this specification may include the following steps: obtaining color information of a dyed substrate and dye combination information corresponding to the color information; obtaining process information corresponding to the dye combination; obtaining post-exposure color change information of artificial leather dyed using the process information; and generating a machine learning model by using the dye combination information, process information, and post-exposure color change information as a dataset, wherein the machine learning model estimates the post-exposure color change information based on the dye combination information and process information.

Description

Technical Field

[0001] This disclosure relates to a method for generating a post-exposure color change estimation model and a technique for dyeing artificial leather using this method. Specifically, this disclosure relates to a technique for estimating the post-exposure color change of dyed artificial leather by utilizing color information, dye combinations, dyeing conditions, etc., during the dyeing process. Background Technology

[0002] The dyeing industry has undergone various cultural and historical developments. In the early days, hand-dyeing using natural dyes was dominant, but after the Industrial Revolution, dyeing techniques developed significantly with the invention of synthetic dyes and the introduction of mechanized processes.

[0003] However, despite this historical development, the modern dyeing industry still faces a variety of complex and unpredictable challenges. Traditional dyeing methods rely heavily on the user's hand and experience, which greatly limits the predictability and consistency of the dyeing process. For example, in manual dyeing, the mixing ratio of dyes, dyeing time, temperature, etc., depend on human judgment, making it difficult to reproduce the same results.

[0004] This traditional approach has two main problems. First, the lack of reproducibility and consistency in the dyeing process poses a significant challenge in modern industry, which requires large-scale production and standardization. Second, the complexity of the dyeing process hinders efficiency and sustainability. Many manual processes require time and labor, and frequent trial and error lead to wasted resources.

[0005] The aforementioned background technology is technical information owned by the inventor for deriving this disclosure or obtained in the process of deriving this disclosure, and is not publicly known technology disclosed to the public before this disclosure was submitted. Summary of the Invention

[0006] Technical issues

[0007] The embodiments described herein are proposed to solve the above-mentioned problems, and the embodiments described herein can determine the staining process more efficiently.

[0008] Solution to the problem

[0009] According to embodiments of this disclosure, a method for generating a post-exposure color change estimation model includes: obtaining color information of a substrate to be dyed and dye combination information corresponding to the color information; obtaining process information corresponding to the dye combination information; obtaining post-exposure color change information of artificial leather dyed based on the process information; and generating a machine learning model by using the dye combination information, process information, and post-exposure color change information as a dataset, wherein the machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and process information.

[0010] Process information may include information on the use of dyes and dyeing auxiliaries, composition information of the product to be dyed, proportion of dyeing liquid, dyeing temperature, dyeing time, and pretreatment information.

[0011] The method may also include augmenting the process information based on at least one of numerical transformation, interpolation, and noise addition.

[0012] Machine learning models can be implemented using algorithms based on multiple regression analysis.

[0013] According to embodiments of this disclosure, a method for dyeing artificial leather includes: identifying a first color and first post-exposure color change information of a substrate to be dyed; obtaining first dye combination information and first process information corresponding to the first color and first post-exposure color change information of the substrate to be dyed based on a machine learning model; and dyeing the substrate to be dyed based on the first dye combination information and the first process information.

[0014] The machine learning model can be generated by the following method: obtaining a first color of the substrate to be dyed and dye combination information corresponding to the first color; obtaining process information corresponding to the dye combination information; obtaining post-exposure color change information of the substrate that has been dyed based on the process information; and generating a machine learning model by using the dye combination information, process information and post-exposure color change information as a dataset, the machine learning model being configured to estimate the post-exposure color change information based on the dye combination information and process information.

[0015] According to an embodiment of the present disclosure, a computer device includes a processor configured to execute instructions including: obtaining color information of a substrate to be dyed and dye combination information corresponding to the color information; obtaining process information corresponding to the dye combination information; obtaining post-exposure color change information of a substrate dyed based on the process information; and generating a machine learning model by using the dye combination information, process information, and post-exposure color change information as a dataset, the machine learning model being configured to estimate the post-exposure color change information based on the dye combination information and process information.

[0016] Process information may include dye usage and liquid ratio information, composition information of the substrate to be dyed, dyeing temperature and time information, and post-dyeing process conditions.

[0017] The instructions may also include process information based on at least one of numerical transformation, interpolation, and noise addition.

[0018] Machine learning models can be post-exposure color change estimation models implemented using algorithms based on multiple regression analysis.

[0019] According to embodiments of this disclosure, a fabric dyeing machine includes: a dye supplier configured to supply dye based on first dye combination information and first process information; a temperature controller configured to control the temperature and time of the fabric; and a controller configured to identify a first color and first post-exposure color change information of a substrate to be dyed, obtain first dye combination information and first process information corresponding to the first color and first post-exposure color change information of the substrate to be dyed based on a machine learning model, and control the dyeing of the substrate to be dyed based on the first dye combination information and the first process information.

[0020] The machine learning model can be generated by the following method: obtaining a first color of the substrate to be dyed and dye combination information corresponding to the first color; obtaining process information corresponding to the dye combination information; obtaining post-exposure color change information of artificial leather that has been dyed based on the process information; and generating the machine learning model by using the dye combination information, process information and post-exposure color change information as a dataset, wherein the machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and process information.

[0021] Beneficial effects of the present invention

[0022] According to embodiments of this disclosure, the post-exposure color change of artificial leather can be estimated using a machine learning model based on dye combination information and process information.

[0023] According to embodiments of this disclosure, the dyeing process can be performed based on dyeing conditions and post-exposure color change requirements.

[0024] The effects of the implementation are not limited to those described above, and other effects not mentioned will be clearly understood by those skilled in the art as described in the claims. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the operation of generating a machine learning model according to an embodiment of the present disclosure.

[0026] Figure 2 This is a flowchart illustrating the operation of dyeing a substrate according to an embodiment of the present disclosure.

[0027] Figure 3 This is a diagram used to explain the machine learning model according to embodiments of this disclosure.

[0028] Figure 4 This is a schematic block diagram illustrating the block configuration of a computer device according to an embodiment of the present disclosure.

[0029] Figure 5 This is a schematic block diagram illustrating the block configuration of a fabric dyeing machine according to an embodiment of the present disclosure. Detailed Implementation

[0030] Because this disclosure allows for various modifications and numerous implementations, the embodiments will be illustrated in the accompanying drawings and described in detail in the written description. The effects and features of this disclosure, as well as methods for implementing them, will be illustrated with reference to the embodiments described in detail below with reference to the accompanying drawings. However, this disclosure is not limited to the following embodiments and can be implemented in various forms.

[0031] In the following, embodiments of this disclosure will be described in detail with reference to the accompanying drawings. The same reference numerals denote the same elements in the drawings.

[0032] It should be understood that although this document may use terms such as “first” and “second” to describe various elements, these elements should not be limited by these terms, and these terms are only used to distinguish one element from another.

[0033] In the following implementations, unless the context clearly indicates otherwise, the singular form includes the plural form.

[0034] Furthermore, it should be understood that the terms “comprising,” “including,” and “having” as used herein specify the presence of the stated features or elements, but do not exclude the presence or addition of one or more other features or elements.

[0035] For ease of description, the dimensions of the elements in the accompanying drawings may be enlarged or reduced. For example, because the dimensions and thicknesses of the elements in the drawings are arbitrarily shown for ease of description, this disclosure is not limited thereto.

[0036] When an implementation can be carried out differently, a particular process sequence can be executed in an order different from the order described. For example, two processes described consecutively can be executed substantially simultaneously or in the reverse order of their description. In this embodiment, the term "...part / device" refers to a software or hardware component, and "...part / device" performs certain roles. However, the term "...part / device" is not limited to software or hardware. "...part / device" can be configured in addressable storage media or can be configured to operate one or more processors.

[0037] Although this disclosure has been described, detailed descriptions of relevant well-known functions or configurations may be omitted when it is thought that they may unnecessarily obscure the nature of this disclosure.

[0038] According to this disclosure, "machine learning" can include all forms of techniques or methods used by computer systems to acquire knowledge from data and use that knowledge to perform certain tasks or solve problems. This includes, but is not limited to, traditional data analysis methods and machine learning methods such as supervised learning, unsupervised learning, and reinforcement learning.

[0039] In other words, machine learning can 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 to predict or classify meaningful outcomes for certain inputs, and can be trained using methods such as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Furthermore, this can include not only single algorithms but also various learning methods and structures, such as models through ensemble learning, multimodal learning, and transfer learning. Such machine learning methods are applied to various fields such as data analysis, pattern recognition, and natural language processing, and such models can be trained on one computer system and used on another. According to this disclosure, "training" can refer to the process by which a computer system, based on an algorithm, reflects patterns or rules in a dataset as weights or parameters of a model to improve the model's performance.

[0040] This disclosure relates to a technique for estimating the color change of dyed articles after exposure using machine learning technology.

[0041] Figure 1 This is a flowchart illustrating the operation of generating a machine learning model according to an embodiment of the present disclosure.

[0042] Reference Figure 1 In operation S110, the computer equipment can obtain the color information of the substrate to be dyed and the corresponding dye combination information. The color information can be obtained using CIE Labs. Color spaces: red, green, and blue (RGB); cyan, magenta, yellow, and black (CMYK); wavelength-specific K / S spectra (…). Dye combination information can be quantitatively expressed using other color systems. It may refer to a combination of dyes used to produce a dyed substrate with a color according to the color information. Dye combination information can vary depending on the dyed substrate and may include dyes of different colors, such as direct dyes, reactive dyes, sulfur dyes, disperse dyes, vat dyes, and acid dyes, used in various fiber compositions (e.g., cotton, polyester, nylon, polyethylene (PE), and polypropylene (PP) applied alone or in combination), fabrics impregnated with polyurethane (PU), or in the form of PU-based synthetic leather. Furthermore, dye combination information may include information regarding the relationship between dyes and auxiliaries.

[0043] According to embodiments of this disclosure, in operation S120, the computer device can obtain process information corresponding to dye combination information. The 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 pretreatment information of the substrate to be dyed.

[0044] The dye usage information described above indicates the quantitative amount of a particular dye used in the dyeing process and can be expressed as a percentage of the fiber weight (%owf). Dyeing temperature information indicates the temperature used during the dyeing process. Dyeing time information indicates the total time the dye is in contact with the substrate. Pretreatment information for the article to be dyed may include information about processes performed prior to dyeing (such as washing, bleaching, and mercerizing), as well as the fineness of the fibers and the composition and content of the PU used for impregnation.

[0045] According to embodiments of this disclosure, in operation S130, the computer device can obtain post-exposure color change information of a substrate dyed based on process information. The post-exposure color change information can be quantified as color difference information before and after exposure. For example, the computer device can obtain CIE Lab... Color difference information in the color space. In this case, L It can indicate brightness, and a and b The red / green and yellow / blue components can be indicated separately. Computer equipment can measure the color by exposing the substrate to a light source for a certain period of time and then comparing the color before and after exposure, particularly by measuring the L... a and b The change in color value is used to evaluate the color change of the dyed substrate after exposure. This color difference before and after exposure can be expressed as the ΔE value, which is the distance between two colors in the color space.

[0046] According to embodiments of this disclosure, in operation S140, the computer device can augment the process information based on at least one of numerical transformation, interpolation, and noise addition. The computer device can extend existing data points to a wider range of values.

[0047] Variations within ±x% can be applied to each dye usage amount. For example, when previously using 10% owf, the data can be augmented to values ​​between 9.7% owf and 10.3% owf. Alternatively, modified temperature values ​​within the range of -x to +x degrees can be applied to the dyeing temperature. For example, when the dyeing temperature is 125 degrees, the data can be augmented to values ​​between 123 and 127 degrees. Furthermore, for post-exposure color changes, for a given color difference value, modified color difference values ​​within the range of -x to +x can be generated. For example, when the color difference is 5.0, the data can be augmented to values ​​between 4.4 and 5.5.

[0048] According to embodiments of this disclosure, in operation S150, the computer device can generate a machine learning model that estimates post-exposure color change information based on the dye combination information and process information by using dye combination information, process information, and post-exposure color change information as a dataset. The computer device can train the model to estimate post-exposure color change information based on the dye combination information and process information by using the dye combination information, process information, and post-exposure color change information as a dataset. For example, the computer device can gradually determine the weights by performing statistical analysis using at least one of multiple regression analysis, decision trees, random forests, and neural network algorithms, by using dye combination information and process information as independent variables and post-exposure color change information as a dependent variable.

[0049] Figure 2 This is a flowchart illustrating the dyeing process of artificial leather according to an embodiment of the present disclosure. Figure 2 The machine learning model in can correspond to Figure 1 Machine learning models in [the context of this].

[0050] refer to Figure 2 In operation S210, the fabric dyeing machine can identify the first color and the first post-exposure color change information of the substrate to be dyed. The first color indicates the final color to be achieved during the dyeing process, and the first post-exposure color change information indicates the color difference before and after the final color change to be achieved during the dyeing process.

[0051] According to embodiments of this disclosure, in operation S220, the fabric dyeing machine can obtain first dye combination information and first process information corresponding to the first color and first post-exposure color change information of the substrate to be dyed based on a machine learning model. The first dye combination information and first process information can indicate the dye combination information and process information that satisfy both the final color to be achieved in the dyeing process and the color difference conditions before and after exposure.

[0052] According to embodiments of this disclosure, in operation S230, the fabric dyeing machine can dye the substrate to be dyed based on first dye combination information and first process information. The computer device can dye the fabric using dye information corresponding to the first dye combination, information regarding the relationship between dyes and auxiliaries, and dye usage information, dyeing temperature information, dyeing time information, and pretreatment information corresponding to the first process information.

[0053] Figure 3 This is a diagram used to explain the machine learning model according to embodiments of this disclosure. For example... Figure 3 As shown, computer equipment can generate machine learning models that estimate color change information after exposure based on the color information of the substrate to be dyed, the dye combination information corresponding to the color information, and the corresponding process information.

[0054] refer to Figure 3 The computer device can generate a model that estimates the color difference (ΔE) 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 train the machine learning model based on at least one of the following algorithms: multiple regression analysis, decision tree, random forest, and neural network algorithm, using dye usage information 320 and dyeing condition information 310 as independent variables and color difference (ΔE) information 330 as the dependent variable.

[0055] Figure 4 This is a schematic block diagram illustrating the block configuration of a computer device according to an embodiment of the present disclosure.

[0056] The computer device may include memory 410 and processor 420. The computer device may execute one or more sets of instructions that cause the computer device to perform any or more of the methods described in this specification.

[0057] Memory 410 may store system-related instructions, including instruction sets, relating to enabling a computer device to perform any or more of the methods and functions described herein. For example, memory 410 may store data such as molecular structure data, geometric and chemical descriptor data, learning model data, and molecular dynamics simulation results. Memory 410 may temporarily or permanently store data such as basic programs, application programs, and setup information for device operation. Memory 410 may include random access memory (RAM), read-only memory (ROM), and permanent mass storage devices such as disk drives, but this disclosure is not limited thereto. Such software components may be loaded from a computer-readable recording medium separate from memory 410 using a drive mechanism. Such a separate computer-readable recording medium may include computer-readable recording media such as floppy disk drives, magnetic disks, magnetic tapes, digital versatile optical disc (DVD) / optical disc ROM (CD-ROM) drives, and memory cards. According to embodiments, software components may be loaded into memory 410 via a communicator instead of a computer-readable recording medium. Memory 410 may store machine learning models based on dye combinations, dyeing process information, post-exposure color change information, and algorithm training. Machine learning models can be sent to another device and used in another computer system.

[0058] Processor 420 controls the overall operation of the device. Furthermore, processor 420 can be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions can be provided to processor 420 by memory 410. For example, processor 420 can be configured to execute instructions received according to program code stored in a recording device such as memory 410. For example, processor 420 performs various operations required to perform the methods specified in this disclosure.

[0059] Processor 420 can process and compute all data, including dye combinations, dyeing treatment information, and post-exposure color change information. This data can be used to compute various variables and algorithms needed to build and execute machine learning models.

[0060] According to the embodiments of this disclosure, the processor 420 can obtain color information of the substrate to be dyed and dye combination information corresponding to the color information, obtain process information corresponding to the dye combination information, obtain post-exposure color change information of the artificial leather dyed based on the process information, and generate a machine learning model that estimates the post-exposure color change information based on the dye combination information and the process information by using the dye combination information, process information and post-exposure color change information as a dataset.

[0061] Processor 420 may be implemented as a single central processing unit (CPU) or multiple CPUs (or digital signal processors (DSPs) or system-on-a-chip (SoC)). Processor 420 may be implemented as a DSP, microprocessor, or time controller (TCON), each of which processes digital signals. However, this disclosure is not limited thereto, and processor 420 may include one or more of a CPU, microcontroller unit (MCU), microprocessor unit (MPU), controller, application processor (AP), communication processor (CP), and ARM processor, or may be defined by these terms.

[0062] Furthermore, the computer program may be specifically designed and configured for use in this disclosure, or may be known and available to those skilled in the art of computer software. Examples of computer programs may include high-level language code that can be executed by a computer using an interpreter, etc., and machine language code such as machine language code generated by a compiler.

[0063] Figure 5 This is a schematic block diagram showing a block configuration 500 of a fabric dyeing machine according to an embodiment of the present disclosure.

[0064] The fabric dyeing machine may include a dye supply 510, a temperature controller 520, and a controller 530. The fabric dyeing machine may execute one or more sets of instructions that cause the fabric dyeing machine to perform any one or more of the methods described in this specification.

[0065] The dye supplier 510 can supply the dye required for a specific dyeing process in accurate quantity and ratio. The dye supplier 510 can store various types of dyes and can mix and supply dyes according to the desired dye combination. The dye combination is based on dye combination information determined by the controller 530. The dye supplier 510 can be controlled by the controller 530 to be controlled according to the characteristics of each dyeing process.

[0066] Temperature controller 520 can control the temperature of the fabric during the dyeing process. Temperature controller 520 is controlled based on process information provided by controller 530. Temperature controller 520 can be controlled by controller 530 to maintain or change the required temperature during the dyeing process of the fabric.

[0067] Controller 530 is a component that performs overall control of the dyeing machine and can control and manage the dyeing process. Controller 530 processes various types of data, including dye combination information, processing information, and post-exposure color change information, using a machine learning model generated by processor 420. Controller 530 can dye the fabric by adjusting the dye supply 510 and temperature controller 520 based on such information.

[0068] According to embodiments of this disclosure, the controller 530 can identify the first color and the first post-exposure color change information of the substrate to be dyed, obtain the first dye combination information and the first process information corresponding to the first color and the first post-exposure color change information of the substrate to be dyed based on a machine learning model, and control the dyeing of the substrate to be dyed based on the first dye combination information and the first process information.

[0069] The controller 530 may be implemented as a single CPU or multiple CPUs (or DSPs or SoCs). The controller 530 may be implemented as a DSP, microprocessor, or TCON, each of which processes digital signals. However, this disclosure is not limited thereto, and the controller 530 may include one or more of a CPU, MCU, MPU, controller, AP, CP, and ARM processor, or may be defined by these terms.

[0070] The specific embodiments described in this disclosure are embodiments and do not limit the scope of this disclosure in any way. For the sake of brevity, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the system may be omitted. Furthermore, the connections or connecting members between components shown in the accompanying drawings are illustrations of functional connections and / or physical or electrical connections and may represent various alternative or additional functional, physical, or electrical connections in an actual device. Moreover, unless otherwise specifically stated as "necessary" or "important," a particular component may not necessarily be required for the application of this disclosure.

[0071] Although this disclosure has been described in conjunction with the foregoing embodiments, various modifications and variations may be made without departing from the spirit and scope of this disclosure. Therefore, the appended claims are intended to include such modifications and variations, provided they fall within the spirit of this disclosure.

Claims

1. A method for generating a post-exposure color change estimation model, the method comprising the following steps: Obtain the color information of the substrate to be dyed and the dye combination information corresponding to the color information; Obtain process information corresponding to the dye combination information; Obtain post-exposure color change information of artificial leather that has been dyed based on the process information; as well as A machine learning model is generated by using the dye combination information, the process information, and the post-exposure color change information as a dataset. The machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and the process information.

2. The method according to claim 1, wherein, The process information includes dye usage information, dyeing temperature information, dyeing time information, and pretreatment information.

3. The method according to claim 2, further comprising the following steps: The process information is augmented based on at least one of numerical transformation, interpolation, and noise addition.

4. The method according to claim 1, wherein, The machine learning model is implemented using an algorithm based on multiple regression analysis.

5. A method for dyeing artificial leather, the method comprising the following steps: Identify the first color and color change information after the first exposure of the substrate to be dyed; Based on a machine learning model, first dye combination information and first process information are obtained corresponding to the first color and the first color change information after the first exposure of the substrate to be dyed. as well as The substrate to be dyed is dyed based on the first dye combination information and the first process information. The machine learning model is generated using the following method, which includes the following steps: Obtain the first color of the substrate to be dyed and the dye combination information corresponding to the first color; Obtain process information corresponding to the dye combination information; Obtain post-exposure color change information of artificial leather that has been dyed based on the process information; and The machine learning model is generated by using the dye combination information, the process information, and the post-exposure color change information as a dataset. The machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and the process information.

6. A computer device, the computer device comprising a processor configured to execute instructions, the instructions including: Obtain the color information of the substrate to be dyed and the dye combination information corresponding to the color information; Obtain process information corresponding to the dye combination information; Obtain post-exposure color change information of artificial leather that has been dyed based on the process information; as well as A machine learning model is generated by using the dye combination information, the process information, and the post-exposure color change information as a dataset. The machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and the process information.

7. The computer device according to claim 6, wherein, The process information includes dye usage information, dyeing temperature information, dyeing time information, and color difference information before and after exposure.

8. The computer device according to claim 7, wherein, The instructions also include augmenting the process information based on at least one of numerical transformation, interpolation, and noise addition.

9. The computer device according to claim 6, wherein, The machine learning model is implemented using an algorithm based on multiple regression analysis.

10. A fabric dyeing machine, the fabric dyeing machine comprising: A dye supplier configured to supply dye based on first dye combination information and first process information; A temperature controller configured to control the temperature of the fabric and time; as well as A controller is configured to identify a first color and a first post-exposure color change information of a substrate to be dyed, obtain first dye combination information and first process information corresponding to the first color and the first post-exposure color change information of the substrate to be dyed based on a machine learning model, and control the dyeing of the substrate to be dyed based on the first dye combination information and the first process information. The machine learning model is generated using the following method, which includes the following steps: Obtain the first color of the substrate to be dyed and the dye combination information corresponding to the first color; Obtain process information corresponding to the dye combination information; Obtain post-exposure color change information of artificial leather that has been dyed based on the process information; and A machine learning model is generated by using the dye combination information, the process information, and the post-exposure color change information as a dataset. The machine learning model is configured to estimate the post-exposure color change information based on the dye combination information and the process information.

Images