Coating film characteristic estimation method and coating film characteristic estimation model generation method

Abstract

The present invention provides a coating film characteristic estimation method in which a machine learning model trained using information about painting conditions, paint properties, paint formulations, coating film measurement conditions, and coating film measurement results as variables is used, and information about painting conditions, paint properties, paint formulation, and coating film characteristic measurement conditions is input to the machine learning model to output estimated values of coating film measurement results.

Description

Coating film characteristic estimation method and coating film characteristic estimation model generation method

[0001] This application claims priority to Japanese Patent Application No. 2024-008766, filed on January 24, 2024, the contents of which are incorporated herein by reference.

[0002] When painting automobiles and their parts, multi-layer coatings are typically formed by sequentially applying electrodeposition coating, primer coating, base coating, and clear coating to the substrate. As a result of the coating process, the coated object develops coating characteristics such as smoothness and gloss. Understanding coating characteristics is extremely important because they are closely related to the appearance and functionality of the coating. However, coating characteristics vary in complex ways depending on factors such as the combination of paints used, the type of substrate, and the coating conditions, making it difficult to estimate coating characteristics before painting. Therefore, in order to understand coating characteristics, the paint must actually be prepared and applied, which poses a significant challenge in terms of work time.

[0003] Japanese Patent Application Laid-Open No. 2021-140420

[0004] An object of the present invention is to provide a coating film characteristic estimation method and a coating film characteristic estimation model generation method that can estimate coating film characteristics before coating is performed.

[0005] One aspect of the present invention is a coating film property estimation method that uses a machine learning model in which information regarding coating conditions, paint properties, paint formulation, coating film property measurement conditions, and coating film property measurement results is learned as variables, and outputs an estimated value of the coating film property measurement results by inputting information regarding the coating conditions, paint properties, paint formulation, and coating film property measurement conditions into the machine learning model.

[0006] According to the present invention, it is possible to estimate the coating film characteristics before coating is performed.

[0007] FIG. 1 is a diagram showing an example of the configuration of a paint film property estimation model generation device 10 according to a first embodiment. FIG. 2 is a flowchart showing the operation of the paint film property estimation model generation device 10 according to the first embodiment. FIG. 3 is a diagram showing an example of the configuration of a paint film property estimation device 20 according to the first embodiment. FIG. 4 is a flowchart showing the operation of the paint film property estimation device 20 according to the first embodiment. FIG. 5 is a diagram showing data sets in second to fourth embodiments.

[0008]

[0023] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. (First Embodiment) Fig. 1 is a diagram showing an example of the configuration of a paint film property estimation model generation device 10 according to a first embodiment. The paint film property estimation model generation device 10 includes a dataset acquisition unit 110, a machine learning model generation unit 120, and a machine learning model output unit 130.

[0009] The dataset acquisition unit 110 acquires a dataset. The dataset includes, as variables, information on painting conditions, paint properties, paint formulation, coating film property measurement conditions, and coating film property measurement results. Hereinafter, the painting conditions and paint properties may be collectively referred to as test conditions.

[0010] The coating film characteristics to be estimated preferably include at least one of smoothness, gloss, and color. Smoothness can be measured using a Wave-scan, Wave-scan dual (both manufactured by BYK Gardner), or the like. Smoothness is expressed as the amplitude of a specific wavelength range, and when measured using a Wave-scan, it is expressed in six levels: dullness / Wa / Wb / Wc / Wd / We, or in two levels: SW / LW. Gloss, also known as sheen or gloss, can be measured using a micro-tri-gloss (manufactured by BYK Gardner), or the like. When measured using a micro-tri-gloss, gloss can be measured at three angles: 20°, 60°, and 85°. In this embodiment, it is preferable to include information on 20° and 60°. Color is measured using a multi-angle spectrophotometer, such as a BYK-Mac i (manufactured by BYK) or an MA-68II (manufactured by X-Rite). Color-related data includes data representing lightness, saturation, and hue, or data that can specify color through calculation. For example, data based on a color system such as the XYZ color system (X, Y, Z values), the RGB color system, the L*a*b* color system (L*, a*, b* values), the Hunter Lab color system (L, a, b values), the L*C*h color system (L*, C*, h values) specified by CIE (1994), or the Munsell color system (H, V, C values) is preferred. Among these, data based on the L*a*b* color system or the L*C*h color system is preferred. When measuring using a BYK-Mac i, color can be measured at six angles: -15°, 15°, 25°, 45°, 75°, and 110°, and when measuring using an MA-68II, color can be measured at five angles: 15°, 25°, 45°, 75°, and 110°. In this embodiment, it is preferable to include color information from three angles: 25°, 45°, and 75°. The coating film characteristics to be estimated are preferably the characteristics of a multi-layer coating film formed by sequentially applying an undercoat coat, a base coat, and a clear coat.

[0011] The painting conditions are conditions related to the painting work. In this embodiment, the information on the painting conditions preferably includes at least one of the following groups, which differ depending on the painting process: paint type, paint film structure, paint booth temperature and humidity, discharge rate, gun speed, film thickness, and baking conditions. The painting processes include, for example, at least one of an undercoat paint application process, a base paint application process, and a clear paint application process. The paint type includes information regarding the number of paint types used in each painting process. The paint film structure includes information regarding the number of times each paint is applied (number of layers) in each painting process. The paint booth temperature and humidity refer to the temperature and humidity within the booth used for painting in each painting process, and may include the amount of water vapor within the booth calculated from the temperature and humidity as a variable. The discharge rate is the amount of paint discharged per unit time from the paint sprayer used for painting in each painting process. The gun speed is the speed at which the paint sprayer used for painting in each painting process moves during painting. The film thickness is the thickness of the paint film after the paint is applied and dried in each painting process. Baking conditions refer to whether or not baking is performed after the paint is applied in each coating process, and / or the heating conditions when baking and drying to form a coating film. Baking conditions typically include variables such as the setting time after coating before placing the coating in a heating and drying oven, the temperature during setting, the time the coating is placed in the heating and drying oven, the temperature of the heating and drying oven, and the orientation of the coating film surface (horizontal or vertical) during setting and heating and drying. It is preferable to include at least one of the orientations of the coating film surface (horizontal or vertical) during coating, setting, and heating and drying as variables, more preferably to include at least one of the orientations of the coating film surface during setting and heating and drying as variables, and it is particularly preferable to include both the orientations of the coating film surface during setting and heating and drying as variables. The above-mentioned coating conditions often differ for each coating film to be applied and must be set for each coating process. Specifically, for example, the coating conditions for the primer coating process, the base coating process, and the clear coating process are each input as variables.

[0012] The paint properties are specific values ​​related to the paint, and preferably include at least one of viscosity and solids concentration. Viscosity can be measured using any conventionally known method without limitation. However, for primer paints and base paints, it is preferable to use viscosity measured with a Brookfield rotational viscometer, and for clear paints, it is preferable to use viscosity measured with a Ford cup. The viscosity measured using a Brookfield rotational viscometer is defined as the viscosity measured one minute after the start of measurement under certain conditions. Specifically, it is defined as the viscosity measured one minute after the start of measurement using a Brookfield viscometer at 6 rpm at a temperature of 20°C (also referred to as the "B6 value" in this specification). It may also be defined as the viscosity measured one minute after the start of measurement using a Brookfield viscometer at 6 rpm at a temperature of 20°C (also referred to as the "B60 value" in this specification). The viscometer used in this case is the LVDV-I (trade name, Brookfield, Brookfield, Brookfield). The viscosity may also include the "thixotropic index (Ti value)" as a variable. The "Ti value (thixotropic index)" is described in JIS K 5101-6-2 (2004), Pigment Testing Method, Section 2, Rotational Viscosity Method. It can be determined by measuring the viscosity (mPa·s) at 20°C and rotational speeds of 6 and 60 rpm using a Brookfield viscometer, and calculating the viscosity measurement value of "viscosity measurement at 6 rpm / viscosity measurement at 60 rpm." The solids concentration refers to the concentration of the residue after removing volatile components. The residue may be solid or liquid at room temperature. For example, it can be calculated by measuring the amount of remaining components after heating a sample at 105°C for 3 hours to remove volatile components. Since the above-mentioned paint properties often differ for each paint, they must be set for each coating process in the case of a multi-layer process. Specifically, for example, the paint properties of the primer paint, base paint, and clear paint are input as variables.

[0013] The paint formulation refers to the components and their amounts that make up the paint. Examples of paint components include resins, pigments, solvents, and additives. In particular, the paint formulation information preferably includes information on the pigment type and its amount, and particularly information on at least one of the size of the luster pigment, the color of the luster pigment, the color of the color pigment, and the chemical structure of the color pigment. Because the paint formulation differs for each paint, it must be set for each painting process in the case of a multi-layer process. Specifically, for example, the paint formulation information includes information on the formulation of the primer paint, information on the formulation of the base paint, and information on the formulation of the clear paint. The primer paint process, base paint process, and clear paint process may involve applying two or more layers of paint in a single process, in which case it is preferable to input information for each paint. In this embodiment, from the perspective of improving prediction accuracy, the paint formulation information preferably includes information on the formulation of the base paint.

[0014] The information on coating film property measurement conditions is information on the conditions for measuring the coating film properties. If the coating film property to be estimated is smoothness, information such as the equipment used and the wavelength to be measured is input; if it is gloss or color, information such as the equipment used and the measurement angle is input. The coating film property measurement results are the results of measuring the coating film properties of a coating film applied under the above-mentioned coating conditions, paint properties, and paint blend, and measurement results corresponding to the above-mentioned coating film property measurement conditions are input.

[0015] The information contained in the data set may be processed by a computer or the like.

[0016] The machine learning model generation unit 120 generates a machine learning model based on the dataset. The machine learning model is a model that outputs an estimated value of the coating film property measurement results when information on the coating conditions, paint properties, paint formulation, and coating film property measurement conditions is input. The machine learning model generation unit 120 generates a machine learning model using information on the coating conditions, paint properties, paint formulation, and coating film property measurement conditions as explanatory variables and the coating film property measurement results as the objective variable. Examples of algorithms for the machine learning model include decision trees, decision trees using gradient boosting, linear regression, logistic regression, simple perceptron, MLP, neural networks, support vector machines, random forests, Gaussian processes, Bayesian networks, k-nearest neighbor methods, Ridge regression, Lasso regression, graph neural networks, K-means algorithms, naive Bayes, CNN, and other algorithms used in machine learning. These algorithms may be used alone or in combination. In the present invention, it is preferable to use a decision tree using gradient boosting.

[0017] The machine learning model output unit 130 outputs the generated machine learning model.

[0018] 2 is a flowchart showing the operation of the coating film property estimation model generating device 10 according to the first embodiment. The dataset acquisition unit 110 acquires a dataset (step S101). The machine learning model generation unit 120 generates a machine learning model based on the dataset (step S102). The machine learning model output unit 130 outputs the generated machine learning model (step S103).

[0019] 3 is a diagram showing an example of the configuration of the paint film property estimation device 20 according to the first embodiment. The paint film property estimation device 20 includes a paint data acquisition unit 210, a paint film property measurement result estimation unit 220, a paint film property measurement result output unit 230, and a memory unit 290. The memory unit 290 stores the machine learning model output by the paint film property estimation model generation device 10.

[0020] The painting data acquisition unit 210 acquires painting data, which are explanatory variables of the machine learning model, including painting conditions, paint properties, paint formulations, and coating film characteristic measurement conditions.

[0021] The coating film characteristic measurement result estimation unit 220 estimates the coating film characteristic measurement result by inputting the painting data into a machine learning model and outputting an estimated value of the coating film characteristic measurement result.

[0022] The coating film property measurement result output unit 230 outputs estimated values ​​of the coating film property measurement results output by the machine learning model. The estimated values ​​of the coating film property measurement results output from the coating film property measurement result output unit 230 are recorded in the memory unit 290 together with the corresponding painting data, for example. The estimated values ​​of the coating film property measurement results output from the coating film property measurement result output unit 230 are input to and displayed on, for example, an external display device.

[0023] 4 is a flowchart showing the operation of the paint film property estimation device 20 according to the first embodiment. The paint data acquisition unit 210 acquires paint data (step S201). The paint film property measurement result estimation unit 220 estimates paint film property measurement results using a machine learning model based on the paint data (step S202). The paint film property measurement result output unit 230 outputs estimated values ​​of the paint film property measurement results (step S203).

[0024] As described above, the paint film characteristic estimation device 20 can estimate the paint film characteristic measurement conditions before painting by using a machine learning model to estimate the paint film characteristic measurement conditions from the painting conditions, paint properties, and paint formulation.

[0025] Second Embodiment A coating film property estimation model generating device 10 according to a second embodiment will now be described. In the second embodiment, the dataset acquired by the dataset acquisition unit 110 includes, in addition to the dataset in the first embodiment, differences in test conditions and differences in coating film property measurement results corresponding to the differences in test conditions when the paint formulation and coating film property measurement conditions are the same. Figure 5 is a diagram showing the dataset in the second embodiment.

[0026] The data set is for paint formulation C １ , coating film property measurement conditions are E １Test condition B when １ and coating film property measurement results F １ and test condition B ２ and coating film property measurement results F ２ The data set includes the difference ΔB in the test conditions and the difference ΔF in the coating property measurement results. Here, ΔB and ΔF are B １ and B ２ The difference and F １ and F ２ This is the difference between

[0027] The machine learning model generation unit 120 according to the second embodiment generates a machine learning model so as to output a second coating film characteristic measurement result corresponding to the second test condition when a paint formulation, a coating film characteristic measurement condition, a first test condition, a difference between the first test condition and the second test condition, and a first coating film characteristic measurement result corresponding to the first test condition are input. The first test condition and the second test condition are different test conditions. Explained using the dataset shown in FIG. 5 , the machine learning model generation unit 120 according to the second embodiment generates a machine learning model so as to output a second coating film characteristic measurement result corresponding to the second test condition. １ , E １ , B １ , ΔB, F １ When you enter ２ Generate a machine learning model that outputs

[0028] The machine learning model generation unit 120 according to the second embodiment may generate a machine learning model so as to output a difference between the second coating film characteristic measurement result and the first coating film characteristic measurement result when a paint formulation, coating film characteristic measurement conditions, first test conditions, a difference between the first test conditions and the second test conditions, and a first coating film characteristic measurement result corresponding to the first test conditions are input. Explained using the dataset shown in FIG. 5 , the machine learning model generation unit 120 according to the second embodiment generates a machine learning model so as to output a difference between the second coating film characteristic measurement result and the first coating film characteristic measurement result. １ , E １ , B １ , ΔB, F １ A machine learning model may be generated that outputs ΔF when

[0029] The following describes a paint film property estimation device 20 according to a second embodiment. The paint data acquisition unit 210 according to the second embodiment acquires paint formulations, paint film property measurement conditions, known paint film property measurement results, known test conditions, and differences between the known test conditions and unknown test conditions. Here, the known paint film property measurement results are paint film property measurement results acquired by the paint data acquisition unit 210 under the paint formulations, paint film property measurement conditions, and known test conditions. The known paint film property measurement results are acquired in advance, similar to the data set. The unknown test conditions are test conditions under which the paint film property measurement results are unknown, including the unknown test conditions and the paint formulations and paint film property measurement conditions acquired by the paint data acquisition unit 210. Hereinafter, the paint film property measurement results acquired by the paint data acquisition unit 210 under the paint formulations, paint film property measurement conditions, and unknown test conditions are referred to as unknown paint film property measurement results.

[0030] The coating film characteristic measurement result estimation unit 220 of the second embodiment inputs the paint formulation, coating film characteristic measurement conditions, known test conditions, the difference between the known test conditions and the unknown test conditions, and the known coating film characteristic measurement results into the machine learning model generated by the machine learning model generation unit of the second embodiment, and outputs an estimated value of the unknown coating film characteristic measurement results.

[0031] The coating film characteristic measurement result estimation unit 220 of the second embodiment may input the paint formulation, coating film characteristic measurement conditions, known test conditions, the difference between the known test conditions and the unknown test conditions, and the known coating film characteristic measurement results into the machine learning model generated by the machine learning model generation unit of the second embodiment, and output an estimated value of the difference between the known coating film characteristic measurement results and the estimated value of the unknown coating film characteristic measurement results.

[0032] Third Embodiment A coating film property estimation model generating device 10 according to a third embodiment will now be described. In the third embodiment, the dataset acquired by the dataset acquisition unit 110 includes, in addition to the dataset in the first embodiment, differences in test conditions and differences in coating film property measurement results corresponding to the differences in test conditions when the paint formulation and coating film property measurement conditions are the same. Figure 5 is a diagram showing a dataset in the third embodiment. Explanation of symbols in Figure 5 will be omitted as they are the same as those in the second embodiment.

[0033] The machine learning model generation unit 120 according to the third embodiment generates a machine learning model so as to output a second coating film characteristic measurement result corresponding to the second test condition when a paint formulation, a coating film characteristic measurement condition, a second test condition, a difference between the second test condition and the first test condition, and a first coating film characteristic measurement result corresponding to the first test condition are input. The first test condition and the second test condition are different test conditions. Explained using the dataset shown in FIG. 5 , the machine learning model generation unit 120 according to the second embodiment generates a machine learning model so as to output a second coating film characteristic measurement result corresponding to the second test condition. １ , E １ , B ２ , ΔB, F １ When you enter ２ Generate a machine learning model that outputs

[0034] The machine learning model generation unit 120 according to the third embodiment may generate a machine learning model so as to output a difference between the second coating film characteristic measurement result and the first coating film characteristic measurement result when the paint formulation, the coating film characteristic measurement conditions, the second test conditions, the difference between the second test conditions and the first test conditions, and the first coating film characteristic measurement result are input. Explained using the dataset shown in FIG. 5 , the machine learning model generation unit 120 according to the third embodiment generates a machine learning model so as to output a difference between the second coating film characteristic measurement result and the first coating film characteristic measurement result. １ , E １ , B ２ , ΔB, F １ A machine learning model may be generated that outputs ΔF when

[0035] The coating film property estimation device 20 according to the third embodiment will be described below. The coating data acquisition unit 210 according to the third embodiment acquires paint formulations, coating film property measurement conditions, unknown test conditions, differences between the unknown test conditions and known test conditions, and known coating film property measurement results.

[0036] The coating film characteristic measurement result estimation unit 220 according to the third embodiment inputs the paint formulation, coating film characteristic measurement conditions, unknown test conditions, the difference between the unknown test conditions and the known test conditions, and the known coating film characteristic measurement results into the machine learning model generated by the machine learning model generation unit according to the third embodiment, and outputs an estimated value of the unknown coating film characteristic measurement results.

[0037] The coating film characteristic measurement result estimation unit 220 of the third embodiment may input the paint formulation, coating film characteristic measurement conditions, unknown test conditions, the difference between the unknown test conditions and the known test conditions, and the known coating film characteristic measurement results into the machine learning model generated by the machine learning model generation unit of the third embodiment, and output the difference between the known coating film characteristic measurement results and the estimated value of the unknown coating film characteristic measurement results.

[0038] Fourth Embodiment A coating film property estimation device 20 according to a fourth embodiment will be described below. The coating film property estimation device 20 according to the fourth embodiment calculates an estimated value of a second coating film property measurement result using both the machine learning model according to the second embodiment and the machine learning model according to the third embodiment.

[0039] The coating film characteristic measurement result estimation unit 220 of the fourth embodiment inputs the paint formulation, coating film characteristic measurement conditions, known test conditions, the difference between the known test conditions and the unknown test conditions, and the known coating film characteristic measurement results into the machine learning model of the second embodiment, and outputs an estimated value of the unknown coating film characteristic measurement results (hereinafter referred to as the second estimated value).

[0040] In addition, the coating film characteristic measurement result estimation unit 220 of the fourth embodiment inputs the paint formulation, coating film characteristic measurement conditions, unknown test conditions, the difference between the unknown test conditions and the known test conditions, and the known coating film characteristic measurement results into the machine learning model of the third embodiment, and outputs an estimated value of the unknown coating film characteristic measurement results (hereinafter referred to as the third estimated value).

[0041] The coating film property measurement result estimating unit 220 according to the fourth embodiment calculates an estimate of the unknown coating film property measurement result based on the second and third estimates. For example, the coating film property measurement result estimating unit 220 according to the fourth embodiment calculates the average value of the second and third estimates as the estimate of the unknown coating film property measurement result.

[0042] The coating film characteristic measurement result estimation unit 220 of the fourth embodiment may input the paint formulation, coating film characteristic measurement conditions, known test conditions, the difference between the known test conditions and the unknown test conditions, and the known coating film characteristic measurement results into the machine learning model of the second embodiment, and output the difference between the known coating film characteristic measurement results and the estimated value of the unknown coating film characteristic measurement results (hereinafter referred to as the second difference estimated value).

[0043] In addition, the coating film characteristic measurement result estimation unit 220 according to the fourth embodiment may input the paint formulation, coating film characteristic measurement conditions, unknown test conditions, the difference between the unknown test conditions and the known test conditions, and the known coating film characteristic measurement results into the machine learning model according to the third embodiment, thereby outputting the difference between the known coating film characteristic measurement results and the estimated value of the unknown coating film characteristic measurement results (hereinafter referred to as the third difference estimated value).

[0044] The coating film property measurement result estimating unit 220 according to the fourth embodiment calculates an estimate of the difference between the known coating film property measurement result and the unknown coating film property measurement result based on the second difference estimate value and the third difference estimate value. For example, the coating film property measurement result estimating unit 220 according to the fourth embodiment may calculate the average value of the second difference estimate value and the third difference estimate value as the estimate of the difference between the known coating film property measurement result and the unknown coating film property measurement result.

[0045] In the second to fourth embodiments, the coating film characteristic measurement result estimation unit 220 may calculate a correction value for the estimated value of the unknown coating film characteristic measurement result or a correction value for the difference between the known coating film characteristic measurement result and the estimated value of the unknown coating film characteristic measurement result, and correct the difference between the known coating film characteristic measurement result and the estimated value of the unknown coating film characteristic measurement result or the estimated value of the unknown coating film characteristic measurement result.

[0046] In the second to fourth embodiments, the coating film property measurement result estimating unit 220 inputs the paint formulation, the coating film property measurement conditions, the known test conditions, and the known coating film property measurement results into a machine learning model, thereby outputting an estimated value of the known coating film property measurement results. At this time, the coating film property measurement result estimating unit 220 inputs 0 as the difference in the test conditions.

[0047] In the second to fourth embodiments, the coating film property measurement result estimating unit 220 calculates a correction value based on the known coating film property measurement result and the estimated value of the known coating film property measurement result. For example, the coating film property measurement result estimating unit 220 calculates the correction value as the difference between the known coating film property measurement result and the estimated value of the known coating film property measurement result.

[0048] Other Embodiments One embodiment of the present invention has been described in detail above with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes and the like can be made within the scope that does not deviate from the gist of the present invention.

[0049] All or part of the functions of the coating film property estimation model generating apparatus 10 and the coating film property estimation apparatus 20 in the above-described embodiments may be implemented by a computer. In this case, a program for implementing the functions may be recorded on a computer-readable recording medium, and the program may be loaded into a computer system and executed. Note that the term "computer system" as used herein includes an operating system (OS) and peripheral hardware. Furthermore, the term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into a computer system. Furthermore, the term "computer-readable recording medium" may also include media that dynamically store programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or telephone lines, or media that store programs for a fixed period of time, such as volatile memory within a computer system that serves as a server or client. Furthermore, the program may be a program that implements part of the above-described functions, or may be a program that can implement the above-described functions in combination with a program already stored in the computer system. In addition, all or part of the functions of the coating film property estimation model generating device 10 and the coating film property estimation device 20 may be realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0050] According to the present invention, it is possible to estimate the coating film characteristics before coating is performed.

[0051] 10 Coating film property estimation model generation device, 110 Data set acquisition unit, 120 Machine learning model generation unit, 130 Machine learning model output unit, 20 Coating film property estimation device, 210 Painting data acquisition unit, 220 Coating film property measurement result estimation unit, 230 Coating film property measurement result output unit, 290 Memory unit

Claims

1. A method for estimating coating film properties, which uses a machine learning model learned by variables including information on coating conditions, paint properties, paint formulation, coating film property measurement conditions, and coating film property measurement results, and inputs information on coating conditions, paint properties, paint formulation, and coating film property measurement conditions into the machine learning model to output an estimated value of the coating film property measurement result.

2. The variable includes information on the difference in test conditions including coating conditions and paint properties and the difference in coating film property measurement results corresponding to the difference in the test conditions when the paint formulation and the coating film property measurement conditions are the same. By inputting information on the first test condition, the difference between the first test condition and the second test condition (where the second test condition is a test condition different from the first test condition), the paint formulation, the coating film property measurement conditions, and the first coating film property measurement result corresponding to the first test condition into the machine learning model, an estimated value of the second coating film property measurement result corresponding to the second test condition and / or the difference between the estimated value of the first coating film property measurement result and the estimated value of the second coating film property measurement result is output. The method for estimating coating film properties according to claim 1.

3. The variable includes information on the difference in test conditions including coating conditions and paint properties and the difference in coating film property measurement results corresponding to the difference in the test conditions when the paint formulation and the coating film property measurement conditions are the same. By inputting information on the second test condition, the difference between the second test condition and the first test condition (where the first test condition is a test condition different from the second test condition), the paint formulation, the coating film property measurement conditions, and the first coating film property measurement result corresponding to the first test condition into the machine learning model, an estimated value of the second coating film property measurement result corresponding to the second test condition and / or the difference between the estimated value of the second coating film property measurement result and the first coating film property measurement result is output. The method for estimating coating film properties according to claim 1.

4. By inputting information regarding the second test conditions, the difference between the first test conditions and the second test conditions, the paint formulation, the coating film property measurement conditions, and the first coating film property measurement results into the machine learning model, an estimated value of the second coating film property measurement results and / or a difference between the first coating film property measurement results and the estimated value of the second coating film property measurement results is output. Based on the estimated value of the second coating film property measurement results and / or the difference between the first coating film property measurement results and the estimated value of the second coating film property measurement results output from the machine learning model by inputting the first test conditions, and the estimated value of the second coating film property measurement results and / or the difference between the first coating film property measurement results and the estimated value of the second coating film property measurement results output from the machine learning model by inputting the second test conditions, an estimated value of the second coating film property measurement results and / or a difference between the first coating film property measurement results and the estimated value of the second coating film property measurement results is calculated. The coating film property estimation method according to claim 2.

5. By inputting information regarding the first test conditions, the paint formulation, the coating film property measurement conditions, and the first coating film property measurement results into the machine learning model, an estimated value of the first coating film property measurement results corresponding to the first test conditions is output. A correction value is calculated based on the first coating film property measurement results and the estimated value of the first coating film property measurement results. The estimated value of the second coating film property measurement results and / or the difference between the first coating film property measurement results and the estimated value of the second coating film property measurement results is corrected by the correction value. The coating film property estimation method according to any one of claims 2 to 4.

6. The coating film properties include at least one of smoothness, gloss, and color. The coating film property estimation method according to any one of claims 1 to 4.

7. The painting conditions include at least one of different groups composed of painting booth temperature and humidity, discharge amount, gun speed, film thickness, and baking conditions in the painting process. The coating film property estimation method according to any one of claims 1 to 4.

8. The paint properties include at least one of viscosity and solid content concentration. The coating film property estimation method according to any one of claims 1 to 4.

9. The paint formulation includes at least one of the size of the brightening material, the color of the brightening material, the color of the coloring pigment, and the chemical structure of the coloring pigment. The coating film property estimation method according to any one of claims 1 to 4.

10. A method for generating a coating film property estimation model, which acquires information on coating conditions, paint properties, paint formulation, coating film property measurement conditions, and coating film property measurement results as variables, and generates a machine learning model that outputs an estimated value of the coating film property measurement result when information on coating conditions, paint properties, paint formulation, and coating film property measurement conditions is input using the variables.

11. The variables include information on the difference in test conditions including coating conditions and paint properties and the difference in coating film property measurement results corresponding to the difference in the test conditions when the paint formulation and the coating film property measurement conditions are the same. By inputting information on the first test conditions, the difference between the first test conditions and the second test conditions (where the second test conditions are different from the first test conditions), the paint formulation, the coating film property measurement conditions, and the first coating film property measurement result corresponding to the first test conditions, a machine learning model is generated that outputs an estimated value of the second coating film property measurement result corresponding to the second test conditions and / or the difference between the estimated value of the first coating film property measurement result and the estimated value of the second coating film property measurement result. The method for generating a coating film property estimation model according to claim 10.

12. The variables include information on the difference in test conditions including coating conditions and paint properties and the difference in coating film property measurement results corresponding to the difference in the test conditions when the paint formulation and the coating film property measurement conditions are the same. By inputting information on the second test conditions, the difference between the second test conditions and the first test conditions (where the first test conditions are different from the second test conditions), the paint formulation, the coating film property measurement conditions, and the first coating film property measurement result corresponding to the first test conditions, a machine learning model is generated that outputs an estimated value of the second coating film property measurement result corresponding to the second test conditions and / or the difference between the estimated value of the second coating film property measurement result and the first coating film property measurement result. The method for generating a coating film property estimation model according to claim 10.

Images