Method for predicting changes in coating film, system for predicting changes in coating film, and application software

Abstract

To provide a method for predicting changes in a coating film from information on the coating film and / or information on the paint that constitutes the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint that constitutes the coating film and the results of weather resistance tests on the coating film. [Solution] A method for predicting changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, using an artificial intelligence model that has been machine-learned to determine the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests on the coating film.

Description

[Technical field]

[0001] The present invention relates to a method for predicting a change in a coating film, a coating change prediction system for predicting a change in a coating film, and application software. [Background technology]

[0002] In the development of paints, one of the most important technical issues is to understand how the coating film formed by applying the paint changes in the usage environment, especially how it deteriorates. Until now, exposure tests were conducted by placing painted panels in the usage environment or harsh environments, and paints were developed taking the results into consideration. However, it takes years to obtain the results of exposure tests, which was one of the obstacles to rapid development of paints. For this reason, accelerated weathering tests are performed using accelerated weathering testers to change the coating film in a short period of time, but there is often a discrepancy between the results of actual exposure tests and tests using accelerated weathering testers, and improvements were needed.

[0003] Furthermore, in exposure tests, a large number of painted panels must be prepared for each of the many different types of paint, and work must be done to transport the painted panels to the exposure test site and place them there. Similarly, in accelerated weathering tests using an accelerated weathering tester, a large number of painted panels must be prepared for each of the many different types of paint, which is a significant burden in terms of cost and workload, and improvements were desired.

[0004] There have been studies conducted on predicting deterioration of coating films. For example, Patent Documents 1 to 7 disclose methods or systems for predicting deterioration of coating films. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2005-17132 A [Patent Document 2] JP 2008-196887 A [Patent Document 3] JP 2005-156309 A [Patent Document 4] JP 2022-124933 A [Patent Document 5] JP 2015-206603 A [Patent Document 6] Japanese Patent Application Publication No. 57-197447 [Patent Document 7] China Patent Application Publication No. 116976196 Summary of the Invention [Problem to be solved by the invention]

[0006] None of the methods or systems for predicting deterioration of a coating film disclosed in Patent Documents 1 to 7 are methods or systems that use an artificial intelligence model that has been machine-learned to determine the relationship between information on the coating film and / or information on the paint that constitutes the coating film and the results of weather resistance tests of the coating film to predict changes in the coating film from information on the coating film and / or information on the paint used to form the coating film, and therefore the accuracy of predicting changes in the coating film is satisfactory.

[0007] One of the problems that the present invention aims to solve is to provide a method for predicting changes in a coating film from information on the coating film and / or information on the paint that constitutes the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint that constitutes the coating film, and the results of weather resistance tests on the coating film. One of the problems that the present invention aims to solve is to provide a coating change prediction system that predicts changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, and that is equipped with an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint that constitutes the coating film and the results of weather resistance tests on the coating film. One of the problems that the present invention aims to solve is to provide a method for predicting changes in a coating film, and a coating change prediction system for predicting changes in a coating film, which are capable of predicting the degree of change in a coating film over time with high accuracy. One of the problems that the present invention aims to solve is to provide application software for causing an information processing device to execute the method for predicting changes in a coating film, or application software for controlling and operating the coating change prediction system. [Means for solving the problem]

[0008] As a result of intensive research into solving the above-mentioned problems, the inventors discovered that the above-mentioned problems can be solved by (i) a method for predicting changes in a coating film using a specific artificial intelligence model, (ii) a coating change prediction system for predicting changes in a coating film that is equipped with a specific artificial intelligence, (iii) application software for causing an information processing device to execute the method for predicting changes in a coating film, and (iv) application software for controlling and operating the system for predicting changes in a coating film, and thus completed the present invention. That is, the present invention is as shown in the following items 1 to 13.

[0009] [Section 1] A method for predicting changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests on the coating film. [Section 2] Item 2. The method according to item 1, wherein the change in the coating film includes one or more changes selected from the group consisting of color tone, water resistance, acid resistance, chemical resistance, surface roughness, gloss, luster, smoothness, adhesion, water contact angle, oil contact angle, scratch resistance, and coating film appearance. [Section 3] Item 3. The method according to item 1 or 2, wherein the information on the coating film includes one or more selected from the group consisting of a coating film configuration, information on a substrate to which the coating film is applied, coating film formation conditions, coating film measurement conditions, and coating film test conditions. [Section 4] 4. The method according to any one of items 1 to 3, wherein the information about the coating film includes a configuration of the coating film, and the configuration of the coating film includes a layer configuration of the coating film and a thickness of each layer. [Section 5] The method according to any one of items 1 to 4, wherein the information on the coating film includes measurement conditions for the coating film, and the measurement conditions for the coating film include whether or not the coating film surface has been polished and / or whether or not the coating film surface has been washed with water when the coating film is measured. [Section 6] The method according to any one of items 1 to 5, wherein the information on the paint includes one or more selected from the group consisting of the type and amount of a coating film-forming resin, the type and amount of a pigment, the type and color tone of a luster material, the type and amount of an additive, the type and amount of a pigment paste, and the type and amount of a solvent. [Section 7] 7. The method according to any one of items 1 to 6, wherein the information on the paint includes the type and amount of pigment paste. [Section 8] 8. The method according to any one of items 1 to 7, wherein the coating film is a multilayer coating film including a color base coating film and a clear coating film. [Section 9] The method according to any one of items 1 to 8, wherein the machine learning uses one or more of a decision tree, a linear regression, a partial least squares regression, a Lasso regression, a ridge regression, a polynomial regression, a Gaussian process regression, a support vector machine, a random forest, a gradient boosting decision tree, a K nearest neighbor method, a neural network, a graph neural network, a Bayesian estimation, or a prediction algorithm by ensemble learning thereof. [Section 10] The method according to any one of items 1 to 9, comprising predicting weather resistance of an automobile coating. [Section 11] A coating change prediction system that predicts changes in a coating from information on the coating and / or information on the paint used to form the coating, the system being equipped with an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating and / or information on the paint used to form the coating, and the results of weather resistance tests on the coating. [Section 12] Application software for causing an information processing device to execute the method according to any one of items 1 to 10. [Section 13] Item 12. Application software for controlling and operating the coating change prediction system according to item 11. Effect of the Invention

[0010] The present invention provides a method for predicting changes in a coating film from information on the coating film and / or information on the paint that constitutes the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint that constitutes the coating film and the results of weather resistance tests on the coating film. The present invention provides a coating change prediction system that predicts changes in a coating film from information on the coating film and / or information on the paint that constitutes the coating film, and that is equipped with an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint that constitutes the coating film and the results of weather resistance tests of the coating film. The present invention provides a method for predicting changes in a coating film and a system for predicting changes in a coating film, which are capable of predicting the degree of changes in a coating film over time with high accuracy. The present invention provides application software for causing an information processing device to execute the method for predicting changes in a coating film, or application software for controlling and operating the coating change prediction system. [Brief description of the drawings]

[0011] [Figure 1] FIG. 2 is a flow diagram of a method for predicting changes in a coating according to one embodiment of the present invention. [Diagram 2] FIG. 1 is a diagram showing an example of the configuration of a coating change prediction system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. It should be understood that the present invention is not limited to the following embodiments, but includes various modified examples that are implemented within the scope that does not deviate from the gist of the present invention.

[0013] [Method to predict changes in coating film] The method for predicting changes in a coating film of the present invention is a method for predicting changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, using an artificial intelligence model in which the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests of the coating film has been machine-learned. By predicting changes in the coating film, it is possible to provide information on deterioration and changes over time of the coating film, changes over time and evaluation of the appearance of the coated article and physical properties caused by the coating. The method of predicting changes in a coating film according to the present invention is preferably carried out using a coating change prediction system described below.

[0014] <Coating film> In the method of predicting changes in a coating film of the present invention, the "coating film" is not particularly limited as long as it is a coating film formed by applying a paint to a substrate. The coating film may be either a single-layer coating film composed of only one layer, or a multi-layer coating film formed by applying two or more types of paint. Examples of multi-layer coating films include multi-layer coating films having two or more coating films, such as an electrodeposition coating film, an intermediate coating film, a color base coating film (color base coat layer), a glitter coating film, a colored coating film, and a clear coating film (clear coat layer). The coating film in the method of predicting changes in a coating film of the present invention is preferably a multilayer coating film (for example, (a) a multilayer coating film including a color base coating film and a clear coating film, (b) a multilayer coating film including an electrodeposition coating film, a color base coating film and a clear coating film, (c) a multilayer coating film including an intermediate coating film, a color base coating film and a clear coating film, (d) a multilayer coating film including an electrodeposition coating film, an intermediate coating film, a color base coating film and a clear coating film, etc.). When forming a coating film on top of a coating film, the coating film may be formed on a coating film in a wet state, or the coating film may be formed on a coating film that has been set and / or preheated and / or cured. When forming the coating film, each coating film may be heated and cured as it is formed, or any two or more uncured coating films may be heated simultaneously to form a plurality of cured coating films simultaneously. In the present invention, a plurality of uncured coating films can be formed to form an uncured multi-layer coating film, which can then be heat-cured to form a coating film in which a plurality of uncured coating films are simultaneously heat-cured.

[0015] <Changes in coating film> In the method of predicting a change in a coating film of the present invention, the "change in the coating film" to be predicted is a change in the coating film after an arbitrary time has elapsed since the preparation of the coating film, and includes at least a change in the appearance of the coating film and / or a change in the physical properties of the coating film.

[0016] The change in the coating film includes, for example, one or more changes selected from the group consisting of color tone, water resistance, acid resistance, chemical resistance, surface roughness, gloss, luster, smoothness, adhesion, contact angle, scratch resistance, electrical resistance, film thickness, stain resistance, solar reflectance, ultraviolet transmittance, haze, light transmittance, light reflectance, weather resistance, flip-flop properties, micro-brilliance, and coating film appearance. Among these, it is preferable to include one or more changes selected from the group consisting of color tone, water resistance, acid resistance, chemical resistance, surface roughness, gloss, luster, smoothness, adhesion, water contact angle, oil contact angle, scratch resistance, and coating film appearance.

[0017] The changes in color tone include, for example, fading and whitening. * a * b * Color system, XYZ color system, Munsell color system, L * u * v * Color system, RGB color system, Yxy color system, Hunter Lab color system, L * C * It can be expressed as the change in each value in various color systems such as the h color system between the value immediately after the coating film is made and the value of the coating film after a certain period of time has passed. It may also be a change based on the results of spectral reflectance measurements or the visual perception of an evaluator.

[0018] The changes in water resistance, acid resistance, chemical resistance, surface roughness, gloss, luster, smoothness, adhesion, contact angle, scratch resistance, electrical resistance, film thickness, stain resistance, solar reflectance, ultraviolet transmittance, light reflectance, weather resistance, flip-flop property and micro-brilliance can be expressed as the change in the value of each property between immediately after the coating film is produced and the value of the coating film after an arbitrary period of time has passed, using a property measuring device. Also, the changes may be based on the visual sense, tactile sense, etc. of the evaluator.

[0019] Changes in the appearance of the coating film include, for example, changes due to the occurrence of coating film cracks (cracks), blistering, peeling, scratches, contamination, shrinkage, blisters, etc., changes in the gloss and luster of the coating film, etc. The degree of these changes in the appearance of the coating film can be confirmed by visual inspection by the evaluator, and can also be quantified by means of instrumental measurement, image diagnosis, etc.

[0020] <Painting information> In the method of predicting changes in a coating film of the present invention, "information about the coating film" includes one or more of the composition of the coating film, information about the substrate to which the coating film is applied, conditions for forming the coating film, conditions for measuring the coating film, and conditions for testing the coating film.

[0021] The coating film configuration includes information on the coating film itself, such as the layer configuration of the coating film (single layer, multiple layers, number of layers, stacking order, function of each layer, etc.), coating film thickness (color base coating film thickness, clear coating film thickness), coating film color tone, coating film physical properties (reflectance, light transmittance, water absorption rate, contact angle, gloss, surface roughness, micro-glossiness, flip-flop property, water repellency, water slippage, smoothness, haze, hiding rate, etc.), coating film shape, coating film use, coating product number (product number, coating code, etc.), etc. Among these, from the viewpoint of improving prediction accuracy, it is preferable that the coating film configuration includes the layer configuration and coating film thickness of the coating film.

[0022] The information on the substrate to which the coating film is applied may include, for example, one or more of the material of the substrate, the physical properties of the substrate, the surface condition of the substrate, the surface treatment of the substrate, the shape of the substrate, and the use of the substrate (use of the coated object (part name, location, etc.)).

[0023] The conditions for forming the coating film may include, for example, one or more of the coating method, coating work conditions (the orientation of the coating surface on the substrate (vertical surface, inclined surface, flat surface, etc.), temperature during coating, humidity during coating, coating location, coating film former, etc.), coating equipment used, coating equipment operating conditions, drying conditions (baking temperature, maximum temperature reached, heating time, heating rate, cooling rate, cooling time), etc.

[0024] As measurement conditions for the coating film, for example, one or more of the following can be mentioned: measuring equipment, measuring method, measurement conditions, measurer, pretreatment during measurement (when measuring the exposed plate after exposure, such as the presence or absence of polishing on the coating film surface, the presence or absence of water washing on the coating film surface, etc.). Among them, from the viewpoint of improving prediction accuracy, it is preferable to include information on the pretreatment of the coating film during measurement, particularly information regarding the presence or absence of polishing on the coating film surface and / or the presence or absence of water washing on the coating film surface.

[0025] As test conditions for the coating film, for example, one or more of the following can be mentioned: test conditions in the exposure test (exposure location, exposure period, exposure time, etc.), test conditions in the acceleration test (type of acceleration test, acceleration test apparatus, acceleration test conditions, etc.).

[0026] <Information on the paint used for forming the coating film> In the method for predicting changes in the coating film of the present invention, "information on the paint used for forming the coating film" includes, for example, one or more of the following: information on the paint itself, information related to the manufacturing conditions of the paint, information on each component constituting the paint / each component used in the manufacture of the paint.

[0027] As information on the paint itself, for example, one or more of the following can be mentioned: the formulation composition of the paint, the color of the paint, the physical properties of the paint (gloss, viscosity, storage modulus, loss tangent, electrical resistance, contact angle, solar reflectance, ultraviolet transmittance, weather resistance, viscoelasticity, drawability, haze, light transmittance, foaming property, surface tension, solid content concentration, pH, storage stability, repellency, circulation property, etc.), the product number / trade name of the paint, the supplier of the paint.

[0028] As information related to the manufacturing conditions of the paint, one or more of the following can be mentioned: the manufacturer of the paint, the manufacturing time of the paint, the manufacturing location of the paint, the manufacturing conditions of the paint (dispersion conditions, temperature conditions, equipment used, etc.).

[0029] Examples of information on each component constituting the paint / each component used in the manufacture of the paint include information on each component contained in the paint and each component used in the manufacture of the paint. For example, the type, shape (e.g., form, aspect ratio, thickness, primary particle size, secondary particle size, particle size distribution, etc.), properties (e.g., curability, thermoplasticity, solubility, dispersibility, dispersed particle size, molecular weight, molecular weight distribution, heat resistance temperature, glass transition point, softening point, reactivity, etc.) and their blending amount of the coating film-forming resin, the type, shape, properties (e.g., hardness, surface properties, presence or absence of surface modification, wettability, dispersibility, pH, zeta potential, etc.), color tone and its blending amount, the type, shape, properties, color tone and its blending amount of the lustrous material, the type, shape, properties and its blending amount of the dispersant, the type, properties and its blending amount of the solvent, the type, shape, properties and its blending amount of the additive, etc., the type, properties, composition and its blending amount of the premix such as pigment paste, the manufacturing method thereof, manufacturing time, manufacturer, distributor, product number, lot number, etc. may be one or more of these. Among these, from the viewpoint of improving prediction accuracy, it is preferable to include information on the premix, in particular information on the type of pigment paste and / or the blending amount thereof.

[0030] <Weatherability test results of coating film> In the method of predicting changes in a coating film of the present invention, the "results of weather resistance tests of the coating film" are data obtained as a result of conducting weather resistance tests of the coating film, such as the results of weather resistance tests performed using outdoor exposure, indoor exposure, and accelerated weather resistance testers (e.g., a xenon weather meter, a sunshine weather meter, an ultraviolet fluorescent lamp weather meter, and an ultraviolet fade meter). The data may include measurements taken with measuring instruments, evaluation results from evaluators such as panelists, and the like. The types of data obtained as a result of weathering tests on a coating film include one or more of the data related to the items listed in the change in the coating film, and may further include data related to the duration of the weathering test.

[0031] <Machine learning artificial intelligence model> In the method of predicting changes in a coating film of the present invention, the algorithm used in the machine learning to create the "machine-learned artificial intelligence model" is not particularly limited as long as it is a machine learning algorithm capable of creating an artificial intelligence model. For example, one or more of the following prediction algorithms may be used: decision tree, linear regression, partial least squares regression, lasso regression, ridge regression, polynomial regression, Gaussian process regression, support vector machine, random forest, gradient boosting decision tree, K-nearest neighbor method, neural network, graph neural network, Bayesian estimation, or ensemble learning of these. In the present invention, it is preferable to use one or more of a random forest and a neural network as the machine learning algorithm, and it is more preferable to use an algorithm based on a random forest.

[0032] In machine learning of an artificial intelligence model, an appropriate machine learning framework / library can be used depending on the data scale, execution environment, etc. The machine learning framework / library may be one that has been developed, or one or more available ones can be used. As the machine learning framework / library, for example, one or more of TensorFlow, PyTorch, Keras, Caffe, Microsoft Cognitive Toolkit, MXNet, Chainer, Scikit-learn, OpenCV, spaCy, etc. can be used.

[0033] The machine learning may be either supervised learning or unsupervised learning. In the present invention, supervised learning is preferable, in which information on the coating film and / or information on the paint used to form the coating film is associated with the results of weather resistance tests of the coating film and machine learning is performed.

[0034] In machine learning, the input of information on the coating film and / or information on the paint used to form the coating film, as well as the results of weather resistance tests on the coating film, can be performed by transmitting data via a wired, wireless, or combination of these communication means, or via a recording medium. Examples of input using a communication means include one or more combinations of various communication networks such as a LAN (local area network), a WAN (wide area network), the Internet, and a telephone network. Input via a recording medium can be performed by reading data from a recording medium such as a magnetic recording medium, an optical recording medium, or a paper recording medium using an appropriate reading means.

[0035] In machine learning, the reliability of information on coatings and / or information on the paints used to form the coatings, as well as the results of weather resistance tests on coatings, can be increased by improving consistency (consistency in labeling standards), reproducibility (highly reproducible labeling for the same data), and transparency (clarity of the data creation process and the basis for labeling).

[0036] In machine learning, it is preferable to preprocess raw data related to information on the coating film and / or information on the paint used to form the coating film, and the results of weather resistance tests on the coating film, to create teacher data. Examples of preprocessing include processing such as complementing missing data, filtering such as removing outliers, normalizing / standardizing data, and arithmetic processing (logarithmic processing, exponentiation, etc.). This makes it possible to make the data commonly applicable to various machine learning algorithms, and also makes it possible to make the data specialized for a specific machine learning algorithm.

[0037] <Prediction of changes in coating> FIG. 1 is a flow diagram of a method for predicting changes in a coating film according to one embodiment of the present invention. A method for predicting a change in a coating film according to one embodiment of the present invention includes at least the following steps S01 to S05: Step S01: Obtaining information on the coating film and / or the paint used to form the coating film, as well as the results of weather resistance tests on the coating film Step S02: Machine learning is used to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests on the coating film. Step S03: Creating an artificial intelligence model Step S04: Input of information on the coating film and / or the paint used to form the coating film Step S05: Using artificial intelligence model to predict changes in coating It includes.

[0038] (Step S01) Step S01 is a step of acquiring information on the coating film and / or information on the paint used to form the coating film, and the results of the weather resistance test of the coating film. Details of the information on the coating film, information on the paint used to form the coating film, and the results of the weather resistance test of the coating film are as described above in <Information on the coating film>, <Information on the paint used to form the coating film>, and <Results of the weather resistance test of the coating film>, respectively. In step S01, the information on the coating film and / or information on the paint used to form the coating film and the corresponding results of the weather resistance test of the coating film are acquired in a mutually associated form.

[0039] Information on the coating film and / or information on the paint used to form the coating film, as well as the results of weather resistance tests on the coating film, may be obtained by inputting the information into a database within the system that predicts changes in the coating film, or may be obtained by accessing an external database via a communication line.

[0040] By forming a coating film, conducting a weather resistance test on the coating film, recording the results of the weather resistance test, and accumulating this as data in a database, information on the coating film and / or information on the paint used to form the coating film and the corresponding weather resistance test results for the coating film can be easily obtained in a mutually associated manner.

[0041] (Step S02) Step S02 is a step of machine learning the relationship between the information on the coating film and / or the information on the paint used to form the coating film and the results of the weather resistance test of the coating film. The algorithm in the machine learning is as described above in the <Machine Learning Artificial Intelligence Model>. By performing machine learning by associating the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests on the coating film, supervised machine learning can be achieved.

[0042] Machine learning can be started by inputting information on the coating film and / or information on the paint used to form the coating film, and the results of weather resistance tests on the coating film. When inputting, the information on the coating film and / or information on the paint used to form the coating film, and the results of weather resistance tests on the coating film are inputted by an appropriate data input means. These inputs may be performed by data transfer and data import (download) from a database.

[0043] (Step S03) Step S03 is a step for creating an artificial intelligence model. In step S02, the relationship between the information on the coating film and / or the information on the paint used to form the coating film and the results of the weather resistance test of the coating film is machine-learned, whereby an artificial intelligence model can be created that inputs the information on the coating film and / or the information on the paint used to form the coating film and outputs a prediction of the change in the coating film.

[0044] (Step S04) Step S04 is a step of inputting information on the coating film and / or information on the paint used to form the coating film into the artificial intelligence model. The input information on the coating film and / or information on the paint used to form the coating film may be different from or the same as the information used in the machine learning.

[0045] By inputting information on a coating film different from that used in machine learning and / or information on the paint used to form the coating film, it is possible to predict the changes in the coating film at any time for a desired coating film or a coating film obtained from a desired paint. This makes it possible to provide information on the deterioration and aging of the coating film, and the aging and evaluation of the appearance of the coated object and the physical properties caused by the coating.

[0046] By inputting the same coating information and / or paint information used in coating formation as used in machine learning, the performance and versatility of the artificial intelligence model created by machine learning can be verified and evaluated. In addition, it is possible to predict future changes in coatings and to predict changes in coatings at a point in time when no specific measurements have been taken.

[0047] There is no particular limitation on the method of inputting information on the coating film and / or information on the paint used to form the coating film into the artificial intelligence model. Information can be input by an appropriate data input means, similar to the input of information for machine learning in step S02. Information can be input by extracting, transferring, or importing (downloading) information from a database. Information can also be input using a program.

[0048] (Step S05) Step S05 is a step of predicting changes in the coating film by using an artificial intelligence model to calculate predicted data of changes in the coating film at any point in time based on the information on the coating film and / or information on the paint used to form the coating film input in step S04. When calculating predicted data of the change in the coating film at any time, only one predicted data can be calculated, or multiple predicted data can be calculated as a candidate group. When multiple predicted data are calculated as a candidate group, the most suitable predicted data can be selected from the candidate group based on a predetermined criterion. The predetermined criterion can be, for example, a selection that focuses on a specific physical property and ensures that the characteristic value falls within a predetermined range, or a numerical value calculated from a predetermined formula or the like.

[0049] When predicting changes in a coating film, it is possible to make highly accurate predictions that take into account their mutual influences by simultaneously predicting various physical properties that are involved in the changes in the coating film. For example, by simultaneously predicting not only the changes in the appearance of the coating film but also the changes in the coating film physical properties, it is possible to make highly accurate predictions that take into account their mutual influences. In the present invention, it is possible to simultaneously predict two or more of the changes in the appearance of the coating film, and it is possible to simultaneously predict two or more of the physical properties of the coating film. For example, ΔE and L * a * b * It is possible to predict the values ​​of each of these simultaneously, or it is also possible to predict any of them independently. When predicting changes in a coating, the prediction data output from the artificial intelligence model can be used as a variable to offset factors such as variation and measurement error, thereby improving the accuracy of the prediction.

[0050] In predicting changes in a coating film, by programming steps S01 to S05, especially steps S04 to S05, it is possible to predict changes in the coating film as a group even for coating films in which various compositions and conditions, etc., contained in the coating film information and various compositions and conditions, etc., contained in the coating film forming paint information are changed within a certain range. It is also possible to check whether the input is appropriate, and further to check the suitability of updates to the system.

[0051] (Other steps) The method for predicting a change in a coating film according to one embodiment of the present invention may include one or more other steps in addition to the above steps S01 to S05. Other steps include, for example, one or more of a data preprocessing step prior to step S01, in which raw data relating to information on the coating film and / or information on the paint used to form the coating film and results of weather resistance tests on the coating film is preprocessed; an artificial intelligence model verification and evaluation step following step S03, in which the created artificial intelligence model is verified and evaluated; and a prediction data selection step following step S05, in which optimal prediction data is selected when multiple candidate data are calculated in step S05.

[0052] <Applications of the method for predicting changes in coatings> The method of predicting changes in a coating film of the present invention is capable of predicting the state of the coating film at a specific time in the future, and therefore can be suitably used in paint application, particularly in applications where it is necessary to predict changes in the coating film on a painted object. For example, it can be used to predict the durability of product coatings, predict changes in coatings on buildings and structures in the civil engineering and construction industries (predicting maintenance such as repainting times), promote the commercial value of paints, etc. In particular, it can predict the weather resistance of coatings on products such as automobiles, which is useful when developing and proposing paints.

[0053] [Paint film change prediction system that predicts changes in paint films] The coating change prediction system of the present invention is a system for predicting changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, which is equipped with an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests of the coating film. The coating change prediction system of the present invention is preferably used in the method of predicting changes in a coating film of the present invention.

[0054] FIG. 2 is a diagram showing an example of the configuration of a coating change prediction system 1 according to an embodiment of the present invention. The coating change prediction system 1 shown in FIG. 2 includes a computer 10, and the coating change prediction system 1 shown in FIG. The coating change prediction system 1 comprises an artificial intelligence model 101, a coating change prediction unit 102, an (internal) database 103a, a reception unit 104, a display unit 105, and a recording unit 106. The coating change prediction system 1 is connectable to user terminals 20a to 20c of users 2a to 2c via a communication line N, and is also connectable to an (external) database 103b via the communication line N. Furthermore, the display unit 105 is connectable to a virtual space M, and is configured to be able to display an image of the change in the coating in the virtual space M.

[0055] The computer 10 is under the control of the operator or provider of the coating change prediction system 1. The operator or provider of the coating change prediction system 1 is a provider of the method for predicting changes in a coating of the present invention or a person requested or commissioned by the provider. The users 2a to 2c are not particularly limited as long as they use the coating film change prediction system 1. For example, they may be one or more of a paint user, a paint manufacturer, a coating contractor, a coating product manufacturer, etc. The user terminals 2a to 2c are not particularly limited as long as they are terminals that can be connected to the coating film change prediction system 1 via a communication line N. For example, they may be one or more of a notebook computer, a mobile phone (smartphone), a mobile information terminal, etc. Note that, although only users 2a to 2c are shown in FIG. 2, the number of users is not particularly limited. The operator or provider of the coating film change prediction system 1 may also charge at least some of the users for use of the system or for some operations when using the system.

[0056] The coating film change prediction system 1 obtains information on the coating film and / or information on the paint used for forming the coating film, as well as the results of the weather resistance test of the coating film, from information sources and data sources such as an (internal) database 103a, an (external) database 103b, and external measuring instruments (not shown), and in some cases via a communication line N, and machine-learns an artificial intelligence model 101. When obtaining information on the coating film and / or information on the paint used for forming the coating film, as well as the results of the weather resistance test of the coating film, from sources other than the (internal) database 103a, such as the (external) database 103b and external measuring instruments, and performing machine learning of the artificial intelligence model 101, it can be done via a reception unit 104. In that case, data confirmation and preprocessing can be performed in the reception unit 104.

[0057] After the machine learning of the artificial intelligence model 101 is completed, information on the coating film for predicting changes in the coating film and / or information on the paint used for forming the coating film is input by an input means (not shown) in the computer 10 and also by any one or more input means of the user terminals 20a to 20c via the communication line N. The coating film change prediction system 1 predicts changes in the coating film using the artificial intelligence model 101 based on the input information, and calculates the results in a coating film change prediction unit 102.

[0058] The predicted change in the coating film that has been calculated can be displayed on a display unit 105 and / or in a virtual space M connected to the display unit 105. Also, the predicted change in the coating film that has been calculated can be displayed on the user terminals 20a to 20c via the communication line N, and users can also participate in the virtual space M via the user terminals 20a to 20c. The predicted change in the coating film that has been calculated can be stored in a recording unit 106, and if necessary, the prediction accuracy of the coating film change prediction system 1 can be improved by comparing it with the actual measured value of the change in the coating film.

[0059] [Application software] The application software of the present invention is application software for causing an information processing device to execute the method for predicting a change in a coating film, and functions to execute the method for predicting a change in a coating film of the present invention. The application software of the present invention is application software for controlling and operating the coating change prediction system, and functions to control and operate the coating change prediction system of the present invention.

[0060] The application software of the present invention may be stored in advance in a recording device such as an HDD (Hard Disk Drive) or flash memory that is included in an information processing terminal that executes the method for predicting changes in a coating film of the present invention, the coating change prediction system of the present invention, or an apparatus that executes each means constituting the information processing terminal or system. Also, the application software may be installed in the apparatus, etc., by using a wireless or wired communication means, a removable recording medium such as a DVD, a CD-ROM, or a USB memory. [Explanation of symbols]

[0061] 1. Paint film change prediction system 10. Computers 101 Artificial Intelligence Model 102 Paint Film Change Prediction Department 103a (internal) database 103b (External) Database 104 Reception 105 Display section 106 Recording Section N Communication Line M Virtual Space 2a~2c users 20a~20c User terminal

Claims

1. A method for predicting changes in a coating film from information on the coating film and / or information on a paint used in forming the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on a paint used in forming the coating film and the results of a weather resistance test of the coating film, comprising: The information on the coating film includes one or more selected from the group consisting of a composition of the coating film, information on a substrate to which the coating film is applied, conditions for forming the coating film, conditions for measuring the coating film, and conditions for testing the coating film; A method for predicting changes in said coating.

2. A method for predicting changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, using an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests of the coating film, comprising: The information on the paint includes one or more selected from the group consisting of the type and amount of a coating film-forming resin, the type and amount of a pigment, the type and color tone of a luster material, the type and amount of an additive, the type and amount of a pigment paste, and the type and amount of a solvent. A method for predicting changes in said coating.

3. 3. The method according to claim 1 or 2, wherein the change in the coating film includes one or more changes selected from the group consisting of color tone, water resistance, acid resistance, chemical resistance, surface roughness, gloss, luster, smoothness, adhesion, water contact angle, oil contact angle, scratch resistance, and coating film appearance.

4. The method according to claim 2, wherein the information on the coating film includes one or more selected from the group consisting of a coating film configuration, information on a substrate to which the coating film is applied, coating film formation conditions, coating film measurement conditions, and coating film test conditions.

5. The method according to claim 1 or 2, wherein the information about the coating film includes a composition of the coating film, the composition of the coating film including a layer composition of the coating film and a thickness of each layer.

6. The method according to claim 1 or 2, wherein the information about the coating film includes measurement conditions for the coating film, the measurement conditions for the coating film including whether or not the coating film surface has been polished and / or whether or not the coating film surface has been washed with water when the coating film is measured.

7. 2. The method according to claim 1, wherein the information on the paint includes one or more selected from the group consisting of the type and amount of a coating film-forming resin, the type and amount of a pigment, the type, color tone and amount of a luster material, the type and amount of an additive, the type and amount of a pigment paste, and the type and amount of a solvent.

8. The method according to claim 1 or 2, wherein the paint information includes the type and amount of pigment paste.

9. 3. The method according to claim 1, wherein the coating film is a multi-layer coating film including a color base coating film and a clear coating film.

10. The method according to claim 1 or 2, wherein the machine learning uses one or more of a prediction algorithm using a decision tree, a linear regression, a partial least squares regression, a Lasso regression, a ridge regression, a polynomial regression, a Gaussian process regression, a support vector machine, a random forest, a gradient boosting decision tree, a K nearest neighbor method, a neural network, a graph neural network, a Bayesian estimation, or an ensemble learning thereof.

11. 3. The method of claim 1 or 2, comprising predicting the weatherability of automotive paintwork.

12. A coating change prediction system that predicts changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, the system comprising an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests of the coating film, The information on the coating film includes one or more selected from the group consisting of a composition of the coating film, information on a substrate to which the coating film is applied, conditions for forming the coating film, conditions for measuring the coating film, and conditions for testing the coating film; The coating change prediction system.

13. A coating change prediction system that predicts changes in a coating film from information on the coating film and / or information on the paint used to form the coating film, the system comprising an artificial intelligence model that has been machine-learned to learn the relationship between information on the coating film and / or information on the paint used to form the coating film and the results of weather resistance tests of the coating film, the system comprising: The information on the paint includes one or more selected from the group consisting of the type and amount of a coating film-forming resin, the type and amount of a pigment, the type and color tone of a luster material, the type and amount of an additive, the type and amount of a pigment paste, and the type and amount of a solvent. The coating change prediction system.

14. 3. Application software for causing an information processing device to execute the method according to claim 1 or 2.

15. Application software for controlling and operating the coating change prediction system according to claim 12 or 13.

Images