Method and system for predicting durability of actual exposure of coating film

Abstract

To provide a method for quickly and accurately predicting a secular change in properties of a coating film of an object at an arbitrary point by predicting durability of actual exposure of the coating film by using a machine learning method.SOLUTION: A predetermined artificial intelligence model includes, as an input, (a) data of coating material information of a coating material composition and property information data before actual exposure of a coating film obtained by applying the coating material composition, and (b) data of at least one of an exposure time of the coating film, environmental information of exposure of the coating film, an installation angle and an installation orientation of a coated object on which the coating film is formed, and an evaluation result of an accelerated test of the coating film, and outputs a result of durability of the actual exposure of the coating film. In the artificial intelligence model, the durability of the coating film in actual exposure is calculated and predicted by inputting the data of (a) and the data of (b) by a computer.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a method and a system for predicting the durability of the actual exposure of a coating film obtained by applying a coating composition.

Background Art

[0002] On the walls and roofs of buildings such as houses and buildings, various coating compositions are applied for the purpose of maintaining the quality and appearance of the walls and roofs under conditions of being exposed to wind, rain, and direct sunlight. Such coating compositions are required to have durability against wind, rain, and sunlight.

[0003] Therefore, various methods for predicting the degree of secular change in the properties of a coating film have been proposed. For example, in Patent Document 1, it is proposed to predict the results of an accelerated test as one of the evaluations of an article by using an artificial intelligence model in which coating information is an explanatory variable and the evaluation of the article is an objective variable by a machine learning method. According to such a machine learning method, it is said that rapid prediction is possible.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the accelerated test is a test in which a test body sample having a coating film on its surface is exposed to conditions in which the intensities of ultraviolet rays, heat, water, etc., which are factors of the secular change in the properties of the coating film, are artificially amplified, and the state change is evaluated. There are often large deviations from the results of actual exposure, and there has been a problem that it may not be sufficient as an index of aging deterioration.

[0006] Therefore, an object of the present invention is to provide a method for quickly and accurately predicting the aging change of the properties of a coating film possessed by an object at an arbitrary location by predicting the durability of the actual exposure of the coating film using a machine learning method.

Means for Solving the Problems

[0007] The gist configuration of the present invention is as follows. (1) A method for predicting the durability of actual exposure of a coating film obtained by applying a coating composition using a machine learning method, in a predetermined artificial intelligence model that includes, as inputs, (a) data on the coating information of the coating composition and data on the properties of the coating film before actual exposure obtained by applying the coating composition, and (b) at least any one of the data on the exposure time of the coating film, the environmental information of the exposure of the coating film, the installation angle and installation orientation of the coated object on which the coating film is formed, and the evaluation result of the accelerated test of the coating film, and outputs the result of the durability of the actual exposure of the coating film, a computer calculates and predicts the durability of the actual exposure of the coating film by inputting (a) data on the coating information of the coating composition and data on the properties of the coating film before actual exposure obtained by applying the coating composition, and (b) at least any one of the data on the exposure time, the environmental information of the exposure, the installation angle and installation orientation of the coated object, and the evaluation result of the accelerated test, and includes a step for predicting the durability of the actual exposure of the coating film.

[0008] (2) The input of the artificial intelligence model includes (a) data on the coating information of the coating composition and data on the properties of the coating film before actual exposure obtained by applying the coating composition, and (b) at least the exposure time of the coating film. In the step for predicting the durability of the actual exposure, (a) data on the coating information of the coating composition and data on the properties of the coating film before actual exposure obtained by applying the coating composition, and (b) at least the exposure time are input. The method for predicting the durability of the actual exposure of the coating film according to (1) above.

[0009] (3) The input of the artificial intelligence model includes (a) data on the paint information of the paint composition and data on the properties of the paint film before actual exposure obtained by applying the paint composition, and (b) at least data on the exposure time of the paint film and data on the environmental information of the exposure of the paint film. In the step of predicting the durability of the actual exposure, the method for predicting the durability of the actual exposure of the paint film according to (1) or (2) above, which inputs (a) data on the paint information of the paint composition and data on the properties of the paint film before actual exposure obtained by applying the paint composition, and (b) at least data on the exposure time and data on the environmental information of the exposure.

[0010] (4) The method for predicting the durability of the actual exposure of the paint film according to any one of (1) to (3) above, wherein the data on the paint information includes at least information on the formulation of the paint composition.

[0011] (5) The method for predicting the durability of the actual exposure of the paint film according to any one of (1) to (4) above, wherein the environmental information of the exposure of the paint film includes at least any one of information on latitude, solar radiation, ultraviolet radiation, temperature, precipitation, relative humidity, wind speed, sea salt particle adhesion amount, and sulfur oxide adhesion amount.

[0012] (6) A prediction system for the durability of the actual exposure of a paint film obtained by applying a paint composition by means of a machine learning method, (a) Data on the paint information of the paint composition and data on the properties of the paint film obtained by applying the paint composition before actual exposure, and (b) at least any one of the data on the exposure time of the paint film, the environmental information of the exposure of the paint film, the installation angle of the coated object on which the paint film is formed, the installation orientation, and the evaluation results of the accelerated test of the paint film, are included as inputs, and in a predetermined artificial intelligence model that outputs the results of the durability of the actual exposure of the paint film, by a computer, (a) the data on the paint information of the paint composition and the data on the properties of the paint film obtained by applying the paint composition before actual exposure, and (b) at least any one of the data on the exposure time, the environmental information of the exposure, the installation angle of the coated object, the installation orientation, and the evaluation results of the accelerated test, are input to calculate and predict the durability of the actual exposure of the paint film. A prediction system for the durability of the actual exposure of a paint film, characterized by comprising a durability prediction unit for actual exposure that predicts the durability of the actual exposure of the paint film.

Effect of the Invention

[0013] According to the present invention, by using a machine learning method to predict the durability of the actual exposure of a paint film, it is possible to provide a method for quickly and accurately predicting the aging change of the properties of the paint film of an object at any location.

Brief Description of the Drawings

[0014]

Figure 1

Mode for Carrying Out the Invention

[0015] Hereinafter, embodiments of the present invention will be illustrated and described in detail with reference to the drawings.

[0016] <Method for Predicting the Durability of the Actual Exposure of a Paint Film> FIG. 1 is a flowchart of a method for predicting the actual exposure durability of a coating film according to an embodiment of the present invention. Hereinafter, with reference to FIG. 1, an embodiment of a method for predicting the actual exposure durability of a coating film obtained by applying a paint composition by a machine learning method will be exemplarily described. Note that the method for predicting the actual exposure durability of the coating film in the present embodiment can be executed, for example, using a system for predicting the actual exposure durability of a coating film according to an embodiment of the present invention described below.

[0017] As shown in FIG. 1, in the present embodiment, first, (a) data on paint information of the paint composition and data on the properties information of the coating film obtained before actual exposure of the coating film obtained by applying the paint composition, and (b) at least any one of the data on the exposure time of the coating film, the environmental information of the exposure of the coating film, the installation angle, the installation orientation of the coated object on which the coating film is formed, and the evaluation result of the accelerated test of the coating film, and the relationship data showing the relationship with the result of the actual exposure durability of the coating film are prepared (step S101).

[0018] The “data on paint information of the paint composition” in (a) is data on the paint information in the initial state of the paint composition. Here, the “data on paint information of the paint composition” in (a) preferably includes at least information on the formulation of the paint composition. Specifically, the information can be the raw material names (also referred to as compound names) of the paint composition and their blending amounts. Instead of or in addition to the raw material names, data on the product names (product numbers) can also be used. Also, the color (L * value, a * value, b * value, spectral reflectance spectrum), and the coating amount of the obtained coating film can also be included in the data. Examples of the shape include the shape of color materials (spherical, flaky, fibrous, etc.), average primary particle diameter, average secondary particle diameter, average dispersed particle diameter, particle size distribution, aspect ratio, thickness, etc. Examples of the chemical properties include molecular weight, molecular weight distribution, discoloration temperature, reactivity, etc.

[0019] Also, the “properties information data before actual exposure” in (a) can be data on one or more of the color and gloss of the obtained coating film before actual exposure.

[0020] The color, for example, is L * a * b * The L in the color space * value, a * value, b * value (JIS Z_8781-4 (2013)), X-Y-Z color system, R-G-B color system, Yxy color system, Hunter L-a-b color system, L * -C * -h * color systems such as those based on color systems can be used. The color can be measured using known color measurement methods. As an example, when using the CM-512m3 commercially available from Konica Minolta, Inc., with the light-receiving part perpendicular to the coating film set to 0°, the L * value, a * value, b * values can be measured. Alternatively, it can be measured using the X-Rite MA68II (manufactured by X-Rite). The measurement angle can be appropriately adjusted according to the purpose or the equipment used. Any other arbitrary index can be used. Further, for example, reflection spectrum data, such as an index using the reflection spectrum intensity every 5 nm from 380 nm to 780 nm as the color, any arbitrary index can also be used.

[0021] The gloss is not particularly limited, but gloss can be used as an index. The gloss can be measured using known gloss measurement methods. As an example, the 60° gloss of the coating film formed on the test plate can be measured in accordance with JIS K 5600-4-7 (specular gloss) using a specular gloss meter (gloss meter VG-7000 (manufactured by Nippon Denshoku Industries Co., Ltd.)).

[0022] The "data on the properties of the coating film before actual exposure" may include data on the smoothness of the coating film before actual exposure. It is preferable to use the wave scan value as an index for smoothness. The wave scan value is preferably any one or more of du (wavelength 0.1 mm or less), Wa (wavelength 0.1 - 0.3 mm), Wb (wavelength 0.3 - 1.0 mm), Wc (wavelength 1.0 - 3.0 mm), Wd (wavelength 3.0 - 10.0 mm), We (wavelength 10.0 - 30.0 mm), Lw (wavelength 1.2 - 12 mm), and Sw (wavelength 0.3 - 1.2 mm). Note that the smaller the wave scan value, the fewer the irregularities of the corresponding wavelength on the surface, which means better appearance quality of the coating film. Also, these indices may be calculated by digital analysis using 3D scanning. The flip-flop property can be measured using a goniometer or the like. Coating film abnormalities specifically include unevenness, swelling, cracking, sagging, pinholes, and frames. These can also be measured by known methods respectively. The "data on the properties of the coating film before actual exposure" may also include, among other things, the hiding power, flip-flop property, micro-glitter feeling, visual appearance, electrical resistance, contact angle, contaminability, solar reflectance, ultraviolet transmittance, viscoelasticity, etc.

[0023] Also, the "data on the properties of the coating film before actual exposure" in (a) above may include information on the film thickness of the coating film. When the coating film consists of multiple layers, it may also include the formulation information and film thickness information of each layer. It may also include information on the object to be coated (substrate) on which the coating film is applied.

[0024] The "exposure time of the coating film" in (b) above is information on the time (period) during which the coating film is exposed to the environment. For example, it may be information on the start date (year, month, day) of exposure and the date (year, month, day) at a certain point in time thereafter, or the difference time (period) calculated from them.

[0025] The "environmental information of the coating film exposure" in (b) above preferably includes information on at least any one of latitude, solar radiation amount, ultraviolet ray amount, air temperature, precipitation amount, relative humidity, wind speed, sea salt particle adhesion amount, and sulfur oxide adhesion amount.

[0026] "Latitude" can be in any unit system. As an example, units such as "°" can be used. "Solar radiation amount" can use, for example, SRAD (J / cm 2 )(period average or period cumulative), etc. "Ultraviolet radiation amount" can use, for example, UVA / UVB / UV (J / cm 2 )(period average or period cumulative), etc. "Air temperature" can be in any unit system. As an example, "℃" (period average or period cumulative) can be used. "Precipitation amount" can be in any unit system. As an example, "mm" (period average or period cumulative) can be used. "Relative humidity" can be in any unit system. As an example, "%" (period average or period cumulative) can be used. "Wind speed" can be in any unit system. As an example, "m / s" (period average or period cumulative) can be used. "Amount of sea salt particles attached (chloride)" can be in any unit system. As an example, "mgNaCl / (m 2 ·day)" (period average or period cumulative) can be used. "Amount of sulfur oxides attached (SO2, etc.)" can be in any unit system. As an example, "mgSO2 / (m 2 ·day)" (period average or period cumulative) can be used.

[0027] Regarding the "installation angle and installation orientation of the coated object on which the coating film is formed" in (b) above, the "installation angle" can be an angle based on any direction. As an example, the unit can use "°". The "installation orientation" can be an orientation based on any direction. As an example, the unit can use "°". The "installation angle and installation orientation of the coated object on which the coating film is formed" can be the installation angle and / or installation orientation of the coated object on which the coating film is formed.

[0028] In the above (b), the "evaluation results of the coating film acceleration test" can use SWOM, QUV-A, QUV-B, SUV, Xe, SST, CCT, SDT, hot water resistance test, etc. as the evaluation (test) methods for the acceleration test. Here, "SWOM" is a sunshine carbon arc lamp type weather resistance test, "QUV" is a test using an ultraviolet fluorescent lamp weather tester QUV (ASTM G154, JIS K 7350-3), "SUV" is an abbreviation for super UV, meaning a weather resistance test with a metal halide lamp, "Xe" is a test using a xenon arc. Also, "SST" is an abbreviation for a salt spray test, meaning a durability test in a state where the sprayed salt water always adheres to the test piece, "CCT" is an abbreviation for a salt water composite cycle test, meaning a durability test that repeats cycle tests such as salt spray, drying, and wetting, "SDT" is an abbreviation for a warm salt water test, meaning a durability test in which the test piece is immersed in warm salt water, and the "hot water resistance test" means a durability test in which the test piece is immersed in warm water maintained at a certain temperature. The "evaluation results of the coating film acceleration test" can be the deterioration information (any one or more fluctuation values such as color difference, glossiness, rust width, bulge width, and chalking level, peeling area, and film thickness) at an arbitrary test time.

[0029] Also, the "durability of the actual exposure of the coating film" can be evaluated using any one or more of color difference, glossiness, rust width, bulge width, chalking level, peeling area, and film thickness.

[0030] Note that the relationship data is preferably updated always or timely or periodically in order to enable more accurate prediction.

[0031] As shown in FIG. 1, in the present embodiment, next, (a) data on paint information of the paint composition and data on the properties of the paint film obtained before actual exposure of the paint composition applied, and (b) at least any one of the data on the exposure time of the paint film, environmental information on the exposure of the paint film, the installation angle, installation orientation of the coated object on which the paint film is formed, and the evaluation results of the accelerated test of the paint film, and the results of the durability of the actual exposure of the paint film, the relationship data showing the relationship (that is, the relationship data prepared in step S101) is input to the computer (step S102).

[0032] Next, as shown in FIG. 1, by machine learning by a computer, (a) data on paint information of the paint composition and data on the properties of the paint film obtained before actual exposure of the paint composition applied, and (b) at least any one of the data on the exposure time of the paint film, environmental information on the exposure of the paint film, the installation angle, installation orientation of the coated object on which the paint film is formed, and the evaluation results of the accelerated test of the paint film are used as inputs, and a predetermined artificial intelligence model that outputs the results of the durability of the actual exposure of the paint film is created (step S103). In the present embodiment, an artificial intelligence model is created in this step, but it is not necessarily required to create an artificial intelligence model, and the created artificial intelligence model can also be obtained from the outside. For example, the artificial intelligence model can also be obtained by the communication unit of the computer, or can be obtained by transfer or the like by a person.

[0033] The machine learning algorithm can use any known algorithm, for example, decision tree, linear regression, partial least squares regression, lasso regression, ridge regression, polynomial regression, Gaussian process regression, support vector machine, random forest, gradient boosting, K-nearest neighbor method, neural network, Bayesian estimation, or a prediction algorithm by these ensemble learning methods. It is particularly preferable that the machine learning uses a prediction algorithm by a neural network. For the neural network, convolutional neural network and deep learning that forms 3 to several hundred layers while performing dropout may be used. Also, when creating artificial intelligence, machine learning frameworks such as TensorFlow, Keras, Caffe, PyTorch, Chainer, and Scikit-learn may be used.

[0034] Here, the machine learning can be supervised learning (including reinforcement learning). In this embodiment, step S103 is performed by a computer by machine learning (supervised learning) using the relationship data input in step S102 as learning data (in this example, supervised data).

[0035] Here, the algorithm is preferably determined by the following method. That is, a plurality of artificial intelligence models are created using various machine learning algorithms, and the accuracy of each artificial intelligence model is confirmed by comparing the predicted value of the output with the said answer using data whose answer is already known in advance. Then, among the plurality of algorithms, for the algorithm with high accuracy, for example, a model is created by cross-validation, or Bayesian optimization or the like is used to determine the optimal hyperparameters. By re-training all the data with the determined hyperparameters, (a) data on the paint information of the paint composition and data on the properties of the paint film obtained before actual exposure of the paint composition, and (b) at least any one of the exposure time of the paint film, environmental information of the exposure of the paint film, installation angle of the coated object on which the paint film is formed, installation orientation, and evaluation results of the accelerated test of the paint film are used as inputs, and an artificial intelligence model that outputs the result of the durability of the actual exposure of the paint film can be created.

[0036] Here, in this embodiment, preprocessing is performed on the prepared relationship data. Here, for example, predetermined operations such as normalization / standardization of data, taking logarithms, multiplying by powers (power processing), etc., are added to the prepared relationship data, or processing such as generation of new data or data filtering processing for removing inappropriate data is performed. For example, data with a large difference between the measured value and the predicted value of the paint properties can be examined, and data suspected of input errors or description errors can be deleted. As described above, in this embodiment, various machine learning algorithms can be used, but the above preprocessing can be applied commonly to a plurality or all of the algorithms (for example, removing data such as outliers that are considered inappropriate for any machine learning algorithm), or can be applied exclusively to the machine learning algorithm actually used (for example, removing data that is likely to cause errors in a specific algorithm).

[0037] In the pretreatment, when the exposure time of the coating film is 0, it is preferable to add zero-point relationship data indicating the relationship that the durability result of the actual exposure of the coating film remains as it was before the actual exposure (change amount is 0) (zero-point addition). Thereby, the prediction accuracy can be further improved. Here, instead of zero, a numerical value close to zero may be used.

[0038] As a pretreatment, interpolation data can also be added between the data. For example, an approximate straight line or an approximate curve can be obtained from the data, and the points on the approximate straight line or the approximate curve can be used as the interpolation data. Thereby, the number of data can be increased and the prediction accuracy can be further improved. Also, the past data and the data can be connected by a straight line or a curve, and an arbitrary number of data can be amplified on the line.

[0039] By such pretreatment and normalization, in the machine learning described later, it becomes possible to predict the durability result of the actual exposure with higher accuracy. However, in the present disclosure, it is not essential to perform the pretreatment, and this step can also be omitted. A predetermined artificial intelligence model can be created using the data after the pretreatment in the same manner as described above.

[0040] Next, in the present embodiment, by a computer, in the artificial intelligence model, (a) data on the paint information of the paint composition and data on the properties of the coating film before the actual exposure obtained by applying the paint composition, and (b) at least any one of the data of the exposure time, the exposure environmental information, the installation angle of the coated object, the installation orientation, and the evaluation result of the accelerated test are input, and the durability result of the actual exposure of the coating film is calculated and predicted (step S104 (actual exposure durability prediction step)).

[0041] Note that the predicted value of the durability result of the actual exposure of the coating film may be a single value, or may be composed of a plurality of candidate groups. When the calculated predicted value is composed of a plurality of candidate groups, it is preferable to further include a step of appropriately selecting a single value from them using a predetermined criterion.

[0042] According to the method for predicting the durability of the actual exposure of the coating film of the present embodiment, since a predicted value of the durability of the actual exposure of the coating film can be obtained by inputting data using an artificial intelligence model, efficiency can be achieved. Further, since the relationship between the data of the coating material information and the property information data of the coating film before actual exposure, and the results of the exposure conditions and the accelerated test in (b) and the durability results of "actual exposure" is learned, the problem that a deviation may occur between the accelerated test and the actual exposure, which is the above-mentioned problem, can also be avoided. As a result, as shown in the examples described later, highly accurate prediction of the durability of the actual exposure of the coating film becomes possible. Thereby, it is possible to predict in advance whether there is a risk of coating film deterioration or the degree of the risk, and to take measures such as being able to avoid the risk by, for example, formulation adjustment. As described above, according to the method for predicting the durability of the actual exposure of the coating film of the present embodiment, by predicting the durability of the actual exposure of the coating film using a machine learning method, it is possible to quickly and accurately predict the secular change in the properties of the coating film of an object at an arbitrary location.

[0043] Further, according to the method for predicting the durability of the actual exposure of the coating film of the present embodiment, it is also possible to predict the durability of the actual exposure for a coating film produced using a paint composition with a formulation for which there is no record of exposure experiments.

[0044] The input to the artificial intelligence model includes (a) data on the coating material information of the coating composition and property information data of the coating film obtained by applying the coating composition before actual exposure, and (b) at least the exposure time of the coating film. In the durability prediction step of actual exposure (step S104), it is preferable to input (a) data on the coating material information of the coating composition and property information data of the coating film obtained by applying the coating composition before actual exposure, and (b) at least the exposure time. This is because by including at least the exposure time of the coating film in the input, it becomes possible to obtain a prediction of the deterioration behavior of the coating film in a time series and its prediction error.

[0045] In addition, in the above (b), it is also preferable to include the installation angle and / or installation orientation of the coated object on which the coating film is formed. This is because it becomes possible to predict the deterioration behavior of the coating film at various installation angles and / or installation orientations and obtain the prediction error thereof.

[0046] The input of the artificial intelligence model includes (a) data on the paint information of the paint composition and data on the properties of the coating film obtained before actual exposure after applying the paint composition, and (b) at least data on the exposure time of the coating film and data on the environmental information of the exposure of the coating film. In the actual exposure durability prediction step (step S104), it is preferable to input (a) data on the paint information of the paint composition and data on the properties of the coating film obtained before actual exposure after applying the paint composition, and (b) at least data on the exposure time and data on the environmental information of the exposure. This is because by including the exposure time of the coating film and the environmental information of the exposure of the coating film in the above (b), it becomes possible to predict the deterioration behavior of the coating film in a time series considering the environmental information and obtain the prediction error thereof.

[0047] <Prediction System for Durability of Actual Exposure of Coating Film> The prediction system for the durability of the actual exposure of a coating film according to an embodiment of the present invention is a prediction system for the durability of the actual exposure of a coating film obtained by applying a coating composition by means of machine learning. The system of this embodiment includes, as inputs, (a) data on the coating information of the coating composition and data on the properties information of the coating film before actual exposure obtained by applying the coating composition, and (b) data on at least any one of the exposure time of the coating film, the environmental information of the exposure of the coating film, the installation angle of the coated object on which the coating film is formed, the installation orientation, and the evaluation result of the accelerated test of the coating film, and outputs the result of the durability of the actual exposure of the coating film. In a predetermined artificial intelligence model, a computer calculates and predicts the durability of the actual exposure of the coating film by inputting (a) data on the coating information of the coating composition and data on the properties information of the coating film before actual exposure obtained by applying the coating composition, and (b) data on at least any one of the exposure time, the environmental information of the exposure, the installation angle of the coated object, the installation orientation, and the evaluation result of the accelerated test. The durability prediction unit can be any known processor. Regarding the above (a) and (b) of the system, since they are the same as those described for the above (a) and (b) of the embodiment of the previous method, the repeated description is omitted.

[0048] Also, with the prediction system for the durability of the actual exposure of the coating film of this embodiment, by inputting data using an artificial intelligence model, a predicted value of the durability of the actual exposure of the coating film can be obtained, so that efficiency can be achieved. Further, since the relationship between (a) the data on the coating information and the data on the properties information of the coating film before actual exposure, and (b) the exposure conditions and the results of the accelerated test and the result of the durability of "actual exposure" is learned, the problem that a deviation may occur between the accelerated test and the actual exposure can also be avoided. As a result, as shown in the examples described later, highly accurate prediction of the result of the durability of the actual exposure of the coating film becomes possible. Thereby, it is possible to predict in advance whether there is a risk of coating film deterioration or the degree of the risk, and for example, take measures such as avoiding the risk by adjusting the formulation. As described above, according to the prediction system for the durability of the actual exposure of the coating film of the present embodiment, by predicting the durability of the actual exposure of the coating film using a machine learning method, it is possible to quickly and accurately predict the secular change in the properties of the coating film of an object at any location. Hereinafter, examples of the present invention will be described, but the present invention is not limited to the following examples at all.

Examples

[0049] (Method for preparing coating composition) Method for preparing polyester resin (A) In a reaction vessel equipped with a thermometer, a condenser, and a stirrer, 155 parts by mass of neopentyl glycol, 222 parts by mass of 1,6 - hexanediol, 50 parts by mass of trimethylolpropane, 441 parts by mass of isophthalic acid, 132 parts by mass of adipic acid, and 26 parts by mass of xylene were mixed, and the temperature was gradually raised to 230 °C in a nitrogen stream. While distilling off the generated water, an esterification reaction was carried out until the amount of water removed reached 126 parts by mass and the reactant reached a predetermined viscosity. Then, after lowering the temperature of the reaction vessel to 50 °C, 90 parts by mass of xylene, 379 parts by mass of T - SOL 150, and 87 parts by mass of propylene glycol monomethyl ether acetate were mixed to prepare a coating - film - forming resin (A) (solid - content concentration: 60% by mass, number - average molecular weight: 3,000, hydroxyl value: 55 mgKOH / g).

[0050] Method for preparing colorant Method for preparing yellow colorant 1 59 parts by mass of polyester resin (A), 16 parts by mass of cross - linker 1, 6 parts by mass of organic solvent 1, and 1 part by mass of organic solvent 2 were uniformly mixed using a disperser and dispersed using a sand mill (dispersion medium: glass beads) until the maximum particle diameter of the pigment coarse particles became 10 μm or less to prepare a yellow colorant 1.

[0051] Colorants were prepared in the same manner as the yellow colorant Y1, except that the type and / or amount of each component was changed as shown in Table 1.

[0052]

Table 1

[0053] Method for preparing coating composition A 73 parts by mass of white colorant 1, 1 part by mass of blue colorant 1, 11 parts by mass of black colorant 1, 4 parts by mass of yellow colorant 1, 8 parts by mass of aggregate 1, and 3 parts by mass of surface conditioner were added, and they were uniformly mixed using a disperser to prepare paint composition A.

[0054] Details of the materials used in the preparation of paint composition A are as follows. · Acrylic resin (A): Paraloid B44 (manufactured by Rohm & Haas), solid content concentration: 100% by mass · Fluororesin (A): KYNAR500 (manufactured by ARKEMA), solid content concentration: 100% by mass · Crosslinking agent 1: Super Beckamine L-155-70 (manufactured by DIC), butylated melamine resin; solid content concentration: 70% by mass · Aggregate 1: Nipsil E-200A (manufactured by Tosoh Silica Corporation), silica fine particles; average particle diameter: 3 μm · Aggregate 2: Gasil HP395 (manufactured by INEOS SILICAS), synthetic silica; average particle diameter: 15 μm · Aggregate 3: Silicia 435 (manufactured by Fuji Silysia Chemical Ltd.), silicon dioxide; average particle diameter: 4 μm · Surface conditioner: Disparon OX-70 (manufactured by Kusumoto Chemicals, Ltd.), acrylic-based surface conditioner; solid content concentration: 30% by mass · White pigment 1: Taypeak CR-97 (manufactured by Ishihara Sangyo Kaisha, Ltd.), titanium dioxide · White pigment 2: TI-PURE R-706 (manufactured by DuPont), titanium dioxide · Black pigment 1: Black 6350 (manufactured by Asahi Kasei Chemicals Corporation), chromium iron oxide · Black pigment 2: Mitsubishi Carbon Black MA-100 (manufactured by Mitsubishi Chemical Corporation), carbon black · Yellow pigment 1: TAROX Synthetic Iron Oxide HY-100 (manufactured by Titanium Industry Co., Ltd.), yellow iron oxide · Yellow pigment 2: TAROX Synthetic Iron Oxide LL-XLO (manufactured by Titanium Industry Co., Ltd.), yellow iron oxide · Red pigment 1: TODA COLOR KN-V (manufactured by Toda Pigment Co., Ltd.), iron oxide · Red pigment 2: TODA COLOR 140ED (manufactured by Toda Industries Co., Ltd.), iron oxide · Organic solvent 1: T-SOL 150 (manufactured by JXTG Energy Corporation), aromatic solvent · Organic solvent 2: Cyclohexanone (manufactured by Shoei Chemical Industry Co., Ltd.), ketone solvent · Organic solvent 3: Isophorone (manufactured by ARKEMA), ketone solvent

[0055] Except for changing the type and / or amount of each component as shown in Table 2, paint compositions B to F were prepared in the same manner as paint composition A.

[0056]

Table 2

[0057] (Method for preparing the coating film of paint composition A) After subjecting a hot-dip galvanized steel sheet with a thickness of 0.4 mm to alkaline degreasing, chemical conversion treatment was performed by applying a phosphating treatment agent Surfcoat EC2310 (manufactured by Nippon Paint Surf Chemicals Co., Ltd.) to the front and back surfaces of the steel sheet, and then drying. On the surface of the obtained steel sheet, as an undercoat paint, Flexcoat 612WW Youprimer (manufactured by Nippon Paint Industrial Coatings Co., Ltd., polyester resin-based primer) was applied using a bar coater so that the dry film thickness would be 5 μm, and baking was performed for 25 seconds under the condition that the maximum temperature reached by the material was 215 °C to form an undercoat coating film. Then, the paint composition A obtained above was applied using a bar coater so that the dry coating film would be 15 μm, and baking was performed for 25 seconds under the condition that the maximum temperature reached by the material was 220 °C to form a surface topcoat coating film, thereby obtaining a coating film of the paint composition.

[0058] (Method for preparing the coating films of paint compositions B, C, and D) In the same manner as in the case of the coating composition A, coating films of coating compositions B, C, and D were obtained.

[0059] (Method for preparing a coating film of coating composition E) After subjecting a hot-dip galvanized steel sheet with a thickness of 0.4 mm to alkaline degreasing, chemical conversion treatment was performed by applying a phosphating agent Surfcoat EC2310 (manufactured by Nippon Paint Surf Chemicals Co., Ltd.) to the front and back surfaces of the steel sheet, followed by drying. Next, as an undercoat paint, Fine Tough G Primer (an epoxy resin-based primer: manufactured by Nippon Paint Industrial Coatings Co., Ltd.) was applied using a bar coater so that the dry film thickness became 5 μm, and baking was performed for 60 seconds under the condition that the maximum temperature reaching the material was 210 °C to form an undercoat film. Thereafter, the coating composition E obtained above was applied using a bar coater so that the dry coating film became 18 μm, and baking was performed for 60 seconds under the condition that the maximum temperature reaching the material was 250 °C to form a surface topcoat film, and a coating film of coating composition E was obtained.

[0060] (Method for preparing a coating film of coating composition F) In the same manner as in the case of the coating composition E, a coating film of coating composition F was obtained.

[0061] (Method for measuring color difference) For each of the various coating films obtained above, using a spectrophotometer colorimeter SM-T45 (manufactured by Suga Test Instruments Co., Ltd.), color (L * , a * , b * values, and the color difference (ΔE) before and after the test were measured.

[0062] (Method for measuring gloss) For each of the various coating films obtained above, using a gloss meter VG7000 (manufactured by Nippon Denshoku Industries Co., Ltd.), in accordance with JIS K 5600-4-7 (specular glossiness), the 60° glossiness was measured, and the gloss retention rate before and after the test was calculated by the formula shown below. Gloss retention rate (%) = 60° glossiness after the test / 60° glossiness before the test × 100

[0063] (Accelerated weather resistance test: SWOM) Each of the various test panels obtained above was subjected to an accelerated weather resistance test for a maximum of 5,000 hours using a Sunshine Weather Meter S80 (manufactured by Suga Test Instruments Co., Ltd.), which is a sunshine carbon arc lamp type accelerated weather resistance tester specified in JIS B 7753. The operating conditions are as follows Irradiance: 255 W / m 2 Black panel temperature: 63 °C Water spray time: 18 minutes out of 120 minutes

[0064] (Exposure test) The test panels were installed for 10 years at various latitudes such as Miyakojima and Iwafune, in accordance with JIS K 5600-7-6, at an angle of 20° with respect to the horizontal plane facing south (equatorial plane). Exposure location 1: Nippon Paint Miyakojima Weathering Center: 3742, Karumata, Hirara, Miyakojima City, Okinawa Prefecture (latitude 24°51'N) Exposure location 2: Nippon Paint Iwafune Weathering Center: 3-1351, Nagai, Asahi City, Chiba Prefecture (latitude 35°69'N)

[0065] For 854 paint types (property information data before actual exposure; film thickness: 6 - 28 μm, L * value: 7 - 91, a * value: -30 - 48, b * value: -49 - 41, 60° gloss: 1 - 93) prepared in the same manner as in the production example of the paint composition before adjustment, exposure tests were carried out at 6 locations including the exposure locations, and a total of 20,381 data for exposure times of 0 - 240 months were prepared.

[0066] Examples 1 to 4, Comparative Example 1 (a) Paint information and property information data before exposure, (b) exposure time, exposure environment information, installation angle of the coated object, installation orientation, and the combination of variables used as explanatory variables among the evaluation results of the accelerated weather resistance test (SWOM) are shown in Table 3. As paint information, the formulation of the paint composition, and as property information data before exposure, the film thickness, initial L * , initial a * , initial b *For the initial gloss and exposure environment information, latitude, ultraviolet radiation amount, and precipitation were used. For the target variables, color difference (ΔE) and gloss after the exposure test were used. Gaussian process regression was used for learning. By inputting the input information shown in Table 3 into the program obtained by the learning, prediction of unlearned data was performed, and the prediction results were compared with the exposure results of the unlearned data. When confirming the prediction accuracy, verification was performed using the Leave-Group-out method so that the unlearned data was not included in the learned data, and the root mean squared error (RMSE) was calculated to compare the accuracy (the degree of difference between the predicted value and the exposure result). The results are shown in Table 3. Here, the degree of difference between the predicted value and the measured value was evaluated by the root mean squared error (RMSE: Root Mean Squared Error). The root mean squared error is an index for measuring how much the predicted value and the measured value deviate, and the closer the value is to zero, the smaller the difference. In Table 3, "○" indicates that it was used as an explanatory variable or a target variable, and "×" indicates that it was not used as an explanatory variable or a target variable.

[0067] Comparative Example 2 From the results of the accelerated weathering test (SWOM), the RMSE was calculated when the test time of 250 hours was estimated to be equivalent to one year of actual exposure, and the prediction accuracies were compared. The evaluation results are shown in Table 3 below.

[0068]

Table 3

[0069] Example 1 is an example in which all of the above-mentioned explanatory variables are used. Example 2 is an example in which the accelerated weathering evaluation results are not included in the explanatory variables. Example 3 is an example in which the exposure environment information is not included in the explanatory variables. Example 4 is an example in which only the exposure time is included in the explanatory variables. It can be seen that in any of the examples, the numerical values of the RMSE of the color difference and gloss are small, and the aging change of the coating film properties can be predicted with high accuracy. On the other hand, Comparative Example 1 is an example that does not include any explanatory variables (b), and the numerical values of RMSE for color difference and glossiness are large, and the prediction accuracy of the aging change of the coating film properties was not sufficiently satisfactory. Further, Comparative Example 2 is an example of predicting the exposure test results from the accelerated weathering (SWOM) evaluation results, and the numerical values of RMSE for color difference and glossiness are large, and the prediction accuracy of the aging change of the coating film properties was not sufficiently satisfactory.

Industrial Applicability

[0070] According to the present invention, by predicting the durability of the actual exposure of the coating film using a machine learning method, it is possible to provide a method for quickly and accurately predicting the aging change of the coating film properties of an object at an arbitrary location. For example, it is also applicable to the prediction of plastic deterioration.

Claims

1. A method for predicting the durability of actual exposure of a coating film obtained by applying a coating composition by a machine learning method, comprising: (a) data of coating information of the coating composition and data of property information before actual exposure of the coating film obtained by applying the coating composition, and (b) at least any one of data of the exposure time of the coating film, environmental information of the exposure of the coating film, the installation angle and installation orientation of the coated object on which the coating film is formed, and the evaluation result of the accelerated test of the coating film. In a predetermined artificial intelligence model that takes the above as input and outputs the result of the durability of the actual exposure of the coating film, by a computer, (a) data of coating information of the coating composition and data of property information before actual exposure of the coating film obtained by applying the coating composition, and (b) at least any one of the exposure time, environmental information of the exposure, the installation angle and installation orientation of the coated object, and the evaluation result of the accelerated test. By inputting the data, a durability prediction step for calculating and predicting the durability of the actual exposure of the coating film is included. A method for predicting the durability of actual exposure of a coating film, characterized in that it includes this.

2. The input of the artificial intelligence model includes (a) data of coating information of the coating composition and data of property information before actual exposure of the coating film obtained by applying the coating composition, and (b) at least the exposure time of the coating film. In the durability prediction step of the actual exposure, (a) data of coating information of the coating composition and data of property information before actual exposure of the coating film obtained by applying the coating composition, and (b) at least the exposure time are input. The method for predicting the durability of actual exposure of a coating film according to claim 1.

3. The input of the artificial intelligence model includes (a) data of coating information of the coating composition and data of property information before actual exposure of the coating film obtained by applying the coating composition, and (b) at least data of the exposure time of the coating film and environmental information of the exposure of the coating film. In the durability prediction step of the actual exposure, data on the paint information of the paint composition and data on the properties of the paint film obtained by applying the paint composition before actual exposure, and (b) at least data on the exposure time and the environmental information of the exposure are input. The method for predicting the durability of the actual exposure of the paint film according to claim 1 or 2.

4. The data on the paint information includes at least information on the formulation of the paint composition. The method for predicting the durability of the actual exposure of the paint film according to claim 1 or 2.

5. The environmental information of the exposure of the paint film includes at least any one of information on latitude, solar radiation amount, ultraviolet ray amount, air temperature, precipitation amount, relative humidity, wind speed, sea salt particle adhesion amount, and sulfur oxide adhesion amount. The method for predicting the durability of the actual exposure of the paint film according to claim 1 or 2.

6. A prediction system for the durability of the actual exposure of a paint film obtained by applying a paint composition by a machine learning method, (a) Data on the paint information of the paint composition and data on the properties of the paint film obtained by applying the paint composition before actual exposure, and (b) at least any one of the exposure time of the paint film, the environmental information of the exposure of the paint film, the installation angle and installation orientation of the coated object on which the paint film is formed, and the evaluation result of the accelerated test of the paint film are included as inputs. In a predetermined artificial intelligence model that outputs the result of the durability of the actual exposure of the paint film, a computer calculates and predicts the durability of the actual exposure of the paint film by inputting (a) data on the paint information of the paint composition and data on the properties of the paint film obtained by applying the paint composition before actual exposure, and (b) at least any one of the exposure time, the environmental information of the exposure, the installation angle and installation orientation of the coated object, and the evaluation result of the accelerated test. A prediction system for the durability of the actual exposure of a paint film, characterized by comprising a durability prediction unit for actual exposure.

Images