Estimation method, estimation model generation method, and model determination model generation method

Abstract

To estimate paint performance without actually creating the paint. [Solution] An estimation method that uses a paint performance estimation model learned from variables including information on the paint formulation and / or properties of the paint and the measurement results of the paint performance, and outputs an estimated value of the measurement results of the paint performance by inputting information on the paint formulation and / or properties of the paint into the paint performance estimation model.

Description

Technical Field

[0001] The present invention relates to an estimation method, a method for generating an estimation model, and a method for generating a usage model determination model. This application claims priority based on Japanese Patent Application No. 2024-232646 filed in Japan on December 27, 2024, and incorporates its content herein.

Background Art

[0002] A coating film is formed by applying a paint to an object to be coated and drying it. The coating film has roles such as imparting aesthetics to the object to be coated and protecting it from the external environment, and it is very important to grasp various coating film performances according to the coating purpose. On the other hand, the influence of the performance of the paint before coating on the coating film is very large, and it is also important to grasp the performance of the paint. However, it is difficult to predict various performances of the paint from the formulation information. Therefore, it is common to grasp various performances of the paint by actually preparing the paint and conducting measurements and performance tests. However, since it takes a great deal of man-hours to prepare the paint, a technique for estimating the performance of the paint without preparing the paint is required.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide an estimation method, a method for generating an estimation model, and a method for generating a usage model determination model that can estimate paint performance without preparing the paint.

Means for Solving the Problems

[0005] One aspect of the present invention is an estimation method that uses a paint performance estimation model learned from variables including information on the paint formulation and / or properties of the paint and the measurement results of the paint performance, and outputs an estimated value of the measurement results of the paint performance by inputting information on the paint formulation and / or properties of the paint into the paint performance estimation model. [Effects of the Invention]

[0006] According to the present invention, paint performance can be estimated without manufacturing the paint itself. [Brief explanation of the drawing]

[0007] [Figure 1] This figure shows an example of the configuration of the estimation model generation device 10 according to the first embodiment. [Figure 2] This is a flowchart showing the operation of the estimation model generation device 10 according to the first embodiment. [Figure 3] This figure shows an example of the configuration of the estimation device 20 according to the first embodiment. [Figure 4] This is a flowchart showing the operation of the estimation device 20 according to the first embodiment. [Figure 5] This figure shows the configuration of the estimation model generation device 10 according to the second embodiment. [Figure 6] This figure shows the configuration of the estimation device 20 according to the second embodiment. [Figure 7] This is a flowchart showing the operation of the estimation model generation device 10 according to the second embodiment. [Figure 8] This is a flowchart showing the operation of the estimation device 20 according to the second embodiment. [Figure 9] This figure shows the experimental results. [Modes for carrying out the invention]

[0008] Embodiments of the present invention will be described in detail below with reference to the drawings. (First Embodiment) Figure 1 shows an example of the configuration of the estimation model generation device 10 according to the first embodiment. The estimation model generation device 10 includes a dataset acquisition unit 110, an estimation model generation unit 120, and an estimation model output unit 130.

[0009] The dataset acquisition unit 110 acquires a dataset. The dataset includes information as variables regarding the paint formulation and / or properties of the paint, as well as measurement results of the paint performance.

[0010] The paint performance is not limited to the performance of a single type of paint, and examples include circulation, storage stability, dispersion stability, repellency, adherence, flammability, combustibility, odor, non-combustibility, flame retardancy, foaming, and curing properties. The estimation model generated by the estimation model generation device 10 according to this embodiment is particularly effective in estimating circulation.

[0011] Typically, in the automotive body painting process, pumps and circulation piping are used to supply paint to the paint booth. Circulation performance is an indicator of the degree of paint degradation during the circulation process within the piping. Paints with high circulation performance will not have problems with paint film quality, such as appearance or performance, even after prolonged circulation before painting. However, paints with low circulation performance will cause deterioration of paint film quality, such as deterioration of the paint film's appearance. One method of testing circulation performance is to apply a load by agitating the paint or circulating it through the piping, and then observe the change in paint viscosity and color (color difference) before and after the load is applied.

[0012] Storage stability refers to the stability of paint quality when a paint is stored at a specified temperature for a certain period of time. Paints with low storage stability may exhibit large fluctuations in viscosity, pigment sedimentation, varnish separation, or skinning. Storage stability tests can be conducted by checking the appearance and viscosity changes of the paint before and after storage.

[0013] Dispersion stability is the stability of pigment dispersion in a paint containing pigments. Paints with low dispersion stability are prone to pigment aggregation, and sedimentation or paint splitting may occur. Paints with low dispersion stability tend to have low storage stability as described above.

[0014] Cissing is a type of coating film defect. It is a depression that occurs on the coating film, easily occurring when low-polarity substances such as oil or silicone adhere to the surface of the coating film. Paints with high cissing resistance are less likely to exhibit cissing.

[0015] The formulation of a paint is information regarding the usage amounts and ratios of each component constituting the paint. In the present embodiment, the formulation of the paint used as a variable and input information for the paint performance estimation model includes at least one selected from the group consisting of the type of brightening agent contained in the paint, the blending amount of the brightening agent contained in the paint, the color of the brightening agent contained in the paint, the particle size of the brightening agent contained in the paint, the thickness of the brightening agent contained in the paint, the type of surface treatment of the brightening agent contained in the paint, the type of coloring pigment contained in the paint, the blending amount of the coloring pigment contained in the paint, the color of the coloring pigment contained in the paint, the chemical structure of the coloring pigment contained in the paint, the particle size of the coloring pigment contained in the paint, the type of resin contained in the paint, the blending amount of the resin contained in the paint, the chemical structure of the resin contained in the paint, the type of dispersant contained in the paint, the blending amount of the dispersant contained in the paint, the chemical structure of the dispersant contained in the paint, the blending amount of the thickener contained in the paint, and the chemical structure of the thickener contained in the paint.

[0016] Incidentally, a brightening agent is a flaky pigment or plate-like pigment that imparts a glittery or optical interference effect to the coating film. Examples of the type of brightening agent include flaky aluminum (aluminum flake), vapor-deposited aluminum, aluminum oxide, oxybis(bismuth) chloride, mica, mica coated with titanium oxide, mica coated with iron oxide, iron oxide mica, silica coated with titanium oxide, alumina coated with titanium oxide, silica coated with iron oxide, alumina coated with iron oxide, glass flake, colored glass flake, vapor-deposited glass flake, hologram film, etc.

[0017] Examples of coloring pigments include, for example, white pigments. Examples of white pigments include titanium dioxide and the like. Examples of coloring pigments include, for example, black pigments. Examples of black pigments include carbon black, acetylene black, lamp black, bone black, graphite, iron black, aniline black and the like. Examples of coloring pigments include, for example, yellow pigments. Examples of yellow pigments include yellow iron oxide, titanium yellow, monoazo yellow, condensed azo yellow, azomethine yellow, bismuth vanadate, benzimidazolone, isoindolinone, isoindoline, quinophthalone, benzidine yellow, permanent yellow and the like. Examples of coloring pigments include, for example, orange pigments. Examples of orange pigments include permanent orange and the like. Examples of coloring pigments include, for example, red pigments. Examples of red pigments include red iron oxide, naphthol AS-based azo red, anthracene, anthraquinonyl red, perylene maroon, quinacridone-based red pigments, diketopyrrolopyrrole, watching red, permanent red and the like. Examples of coloring pigments include, for example, brown pigments. Examples of brown pigments include brown iron oxide and the like. Examples of coloring pigments include, for example, purple pigments. Examples of purple pigments include cobalt violet, quinacridone violet, dioxazine violet and other purple pigments. Examples of coloring pigments include, for example, blue pigments. Examples of blue pigments include cobalt blue, phthalocyanine blue, threne blue and the like. Examples of coloring pigments include, for example, green pigments. Examples of green pigments include phthalocyanine green and the like. The coloring pigment may be a combination of these pigments.

[0018] The resin is a binder that forms the coating film. The resin is not particularly limited as long as it is commonly used in paint applications, and may be in the form of a solvent-based or water-based liquid, or in the form of a powder for powder coatings. Examples of resin types include acrylic resins, phenolic resins, alkyd resins, polyester resins, urethane resins, polyether resins, polyolefin resins, epoxy resins, silicone resins, fluororesins, ethylene vinyl acetate copolymers, amino resins, polycarbonate resins, polyvinyl chloride resins, isocyanate compounds, and melamine resins.

[0019] Dispersants are additives used to uniformly disperse brightening agents or coloring pigments. Dispersants are not particularly limited as long as they are commonly used in paint applications; commercially available dispersants generally sold on the market can be used. Examples of dispersants include compounds containing nonionic, cationic, or anionic functional groups.

[0020] Thickening agents are additives used to adjust the viscosity of paints. The type of thickening agent is not particularly limited as long as it is commonly used in paint applications; commercially available thickening agents generally sold on the market can be used. Examples of thickening agents include alkaline thickening agents, nonionic association type, cellulose type, water-soluble polymer type, polyamide type, and clay type thickening agents.

[0021] The properties of the paint are information about the paint obtained through various measurements. In this embodiment, the properties of the paint used as variables and input information for the paint performance estimation model include at least one selected from the group consisting of paint viscosity, paint elasticity, paint solids content, paint pH, paint color, paint transmittance, paint surface tension, and paint drying conditions.

[0022] Formulation information for each paint can be obtained from, for example, product data for each paint or experimental level data during paint development. The properties of each paint are obtained by performing individual measurements. Subsequently, various paint performance tests are conducted, and the paint performance after the tests is measured. This allows for the creation of combinations of the formulation and / or properties of each paint and the measurement results of the paint performance. This allows for the creation of a dataset containing information on the formulation and / or properties of each paint and the measurement results of the paint performance as variables. Alternatively, the properties of each paint may be obtained by performing arbitrary paint performance tests on each paint and then performing individual measurements on each paint.

[0023] The dataset may include information regarding the paint formulation and / or properties and measurement results of the paint performance as variables, as well as information regarding the measurement test conditions for the paint. Preferably, the information regarding the measurement test conditions for the paint includes information on at least one selected from the group consisting of test temperature, test time, stirring speed, and painting conditions. Furthermore, if the paint performance is related to circulation, the information regarding the measurement test conditions for the paint may include information such as the number of circulation cycles (turns). If the dataset contains information about the measurement test conditions for paints, when obtaining information about each paint by performing individual measurements for each paint, the measurement test conditions for the paints should also be recorded.

[0024] The estimation model generation unit 120 generates an estimation model based on the dataset. The estimation model is a model that outputs an estimated value of the measurement result of paint performance when information on the paint formulation and / or properties of the paint is input. The estimation model generation unit 120 generates an estimation model using machine learning methods, with information on the paint formulation and / or properties of the paint as explanatory variables and the measurement result of paint performance as the dependent variable. Examples of machine learning techniques include decision trees, decision trees with gradient boosting, linear regression, logistic regression, simple perceptron, MLP, neural networks, support vector machines, random forests, Gaussian processes, Bayesian networks, k-nearest neighbors, Ridge regression, Lasso regression, graph neural networks, K-means algorithm, naive Bayes, CNN, and other algorithms used in machine learning. These algorithms may be used individually or in combination. In this embodiment, it is preferable to use a decision tree with gradient boosting. An example of a decision tree with gradient boosting is LightGBM.

[0025] The estimated model output unit 130 outputs the generated estimated model.

[0026] Figure 2 is a flowchart illustrating the operation of the estimation model generation device 10 according to the first embodiment. The dataset acquisition unit 110 acquires the dataset (step S101). The estimation model generation unit 120 generates an estimation model based on the dataset (step S102). The estimation model output unit 130 outputs the generated estimation model (step S103).

[0027] Figure 3 shows an example of the configuration of the estimation device 20 according to the first embodiment. The estimation device 20 comprises a paint data acquisition unit 210, a paint performance measurement result estimation unit 220, a paint performance measurement result output unit 230, and a storage unit 290. The storage unit 290 stores the estimation model output by the estimation model generation device 10.

[0028] The paint data acquisition unit 210 acquires paint data. The paint data consists of the paint formulation and / or paint properties, which are explanatory variables of the estimation model.

[0029] The paint performance measurement result estimation unit 220 estimates the paint performance measurement result by inputting paint data into the estimation model and outputting an estimated value of the paint performance measurement result.

[0030] The paint performance measurement result output unit 230 outputs estimated values ​​of the paint performance measurement results output by the estimation model. The estimated values ​​of the paint performance measurement results output from the paint performance measurement result output unit 230 are recorded in the storage unit 290, for example, along with the corresponding paint data. The estimated values ​​of the paint performance measurement results output from the paint performance measurement result output unit 230 are input to and displayed on an external display device, for example.

[0031] Figure 4 is a flowchart showing the operation of the estimation device 20 according to the first embodiment. The paint data acquisition unit 210 acquires paint data (step S201). The paint performance measurement result estimation unit 220 estimates the measurement result of paint performance using an estimation model based on the paint data (step S202). The paint performance measurement result output unit 230 outputs an estimated value of the measurement result of paint performance (step S203).

[0032] As described above, the estimation device 20 can estimate the measurement results of paint performance before painting by using an estimation model generated by machine learning to estimate the measurement results of paint performance from the paint formulation and / or paint properties. Furthermore, if the dataset includes not only information on the paint formulation and / or properties and measurement results of paint performance as variables, but also the paint measurement test conditions, the accuracy of the estimation can be improved by inputting the paint measurement test conditions in addition to the paint formulation and / or properties.

[0033] (Second embodiment) The estimation model generation device 10 according to the second embodiment will be described below. For the sake of clarity, the range of values ​​less than a predetermined value will be referred to as range D1, and the range of values ​​greater than or equal to the predetermined value will be referred to as range D2. In the second embodiment, the estimation model generation unit 120 generates multiple estimation models based on the dataset, depending on the range of values ​​indicating the measured paint performance. For example, the estimation model generation unit 120 generates an estimation model for when the values ​​indicating the measured paint performance are in range D1 and an estimation model for when they are in range D2, based on the dataset. The estimation model generation unit 120 generates an estimation model corresponding to range D1 based on the data included in the dataset where the values ​​indicating the measured paint performance are within range D1.

[0034] Furthermore, the estimation model generation unit 120 generates an estimation model corresponding to range D2 based on the data in the dataset whose values ​​indicating the measurement results of paint performance fall within range D2. However, if the dataset contains only a small number of data where the values ​​indicating the measurement results of paint performance fall within range D1 or D2, the estimation model generation unit 120 may generate an estimation model corresponding to range D1 or D2 based on all the data in the dataset.

[0035] For example, if the measurement result of circulation is viscosity, the estimation model generation unit 120 generates an estimation model used when the viscosity is less than a predetermined viscosity α, based on the data in the dataset where the viscosity is less than a predetermined viscosity α. Alternatively, the estimation model generation unit 120 generates an estimation model used when the viscosity is α or greater, based on all the data in the dataset, regardless of the viscosity range. The estimation model generation unit 120 may also generate an estimation model used when the viscosity is α or greater, based on the data in the dataset where the viscosity is α or greater. For example, if the measurement result of circulation performance is the color difference between the initial paint color and the paint color after the circulation test, the estimation model generation unit 120 generates an estimation model used when the color difference is less than a predetermined color difference, based on the data in the dataset where the color difference is less than a predetermined color difference. Alternatively, the estimation model generation unit 120 generates an estimation model used when the color difference is greater than or equal to a predetermined color difference, based on all the data in the dataset, regardless of the range of the color difference. The estimation model generation unit 120 may also generate an estimation model used when the color difference is greater than or equal to a predetermined color difference, based on the data in the dataset where the color difference is greater than or equal to a predetermined color difference.

[0036] Figure 5 shows the configuration of the estimation model generation device 10 according to the second embodiment. The estimation model generation device 10 according to the second embodiment includes, in addition to the estimation model generation device 10 according to the first embodiment, a model determination unit 140 and a model determination unit 150. The model determination model generation unit 140 generates a model determination model based on the dataset. The dataset used here includes information as variables about the range of values ​​that include the paint formulation and / or paint properties and the measured paint performance. This dataset may be generated by modifying a dataset acquired by the dataset acquisition unit 110, which includes information about the paint formulation and / or paint properties and the measured paint performance as variables, and determining the range of values ​​that include the measured results from the information about the measured results. Alternatively, this dataset may be newly acquired by the dataset acquisition unit 110.

[0037] The range in which the measured values ​​of the paint performance are included corresponds to the range corresponding to the generated estimation model. In this explanation, the information regarding the range in which the measured values ​​of the paint performance are included is whether the measured values ​​of the paint performance are included in range D1 or range D2. The model selection model determines the estimation model to be used when information regarding the paint formulation and / or properties of the paint is input. When information regarding the paint formulation and / or properties of the paint is input, the model selection model outputs estimation results for a range that includes the values ​​shown in the measurement results of the paint performance, and determines the estimation model corresponding to the range shown in the estimation results.

[0038] The model used for determining the model to be used does not necessarily have to be generated using machine learning. The model used for determining the model to be used may be determined using a predetermined formula.

[0039] The model determination output unit 150 outputs the generated model determination model.

[0040] In the estimation device 20 according to the second embodiment, the storage unit 290 stores two paint performance estimation models and a model for determining usage, which are generated by the estimation model generation device 10. Figure 6 shows the configuration of the estimation device 20 according to the second embodiment. The estimation device 20 according to the second embodiment includes a model for determining usage unit 240 in addition to the estimation device 20 according to the first embodiment.

[0041] The model determination unit 240 determines the estimation model to be used to estimate paint performance by inputting paint data into the model determination model stored in the memory unit 290. The paint performance measurement result estimation unit 220 estimates the paint performance measurement result by inputting paint data into the estimation model determined by the model determination unit 240 and outputting an estimated value of the paint performance measurement result.

[0042] Figure 7 is a flowchart showing the operation of the estimation model generation device 10 according to the second embodiment. The operation of steps S301 to S303 is the same as the operation of steps S101 to S103 shown in Figure 2. The model generation unit 140 modifies the dataset and generates a dataset that includes information on the range in which the measured values ​​of the paint formulation and / or paint properties and paint performance are included as variables (step S304). At this point, the dataset acquisition unit 110 may acquire a dataset that newly includes information on the range in which the measured values ​​of the paint formulation and / or paint properties and paint performance are included as variables.

[0043] The model determination model generation unit 140 generates a model determination model based on the dataset (step S305). The model determination model output unit 150 outputs the generated model determination model (step S306). Note that the generation and output of the model determination model may be performed independently of the generation and output of the estimation model, and the model determination model does not necessarily have to be generated after the estimation model has been generated.

[0044] Figure 8 is a flowchart showing the operation of the estimation device 20 according to the second embodiment. The paint data acquisition unit 210 acquires paint data (step S401). The model determination unit 240 determines the estimation model to be used to estimate paint performance based on the paint data (step S402). The paint performance measurement result estimation unit 220 estimates the paint performance measurement result based on the paint data using the determined estimation model (step S403). The paint performance measurement result output unit 230 outputs the estimated value of the paint performance measurement result (step S404).

[0045] In the above explanation, for the sake of clarity, the values ​​representing the measured paint performance are divided into two ranges, and the explanation describes the case where one of the two estimation models is used. However, the values ​​representing the measured paint performance may be divided into three or more ranges, and one of the three or more estimation models may be used.

[0046] (Example of experiment) The experiments conducted are described below. In this experiment, the circulation properties of the paint were estimated based on paint data. First, a dataset was created that included paint data, measurement results of the paint's circulation properties, and data on the paint's measurement test conditions. For the paint data, paint formulation data was used. For the paint formulation data, data on the type of glossing agent contained in the paint, the amount of glossing agent contained in the paint, the type of coloring pigment contained in the paint, the amount of coloring pigment contained in the paint, the type of resin contained in the paint, the amount of resin contained in the paint, the type of dispersant contained in the paint, and the amount of dispersant contained in the paint were used. For the paint's measurement test conditions, turn number data was used. Circulation properties were evaluated using the viscosity value (sometimes referred to as the B60 value in this specification) measured at 60 rpm for 1 minute at a temperature of 20°C using an "LVDV-I" (product name, manufactured by BROOKFIELD, type B viscometer). In this experiment, the estimation model generation device 10 generates a model for determining the model to be used. Based on paint data, it estimates whether the B60 value is less than 960 mPa·s, and determines the estimation model based on whether the estimated B60 value is less than 960 mPa·s. In this experiment, the estimation model generation device 10 generates two estimation models: an estimation model used when the B60 value is less than 960 mPa·s (low viscosity model) and an estimation model used when the B60 value is 960 mPa·s or greater (high viscosity model). Here, the low viscosity model is generated using data from the dataset where the B60 value is less than 960 mPa·s. The high viscosity model is generated using all the data in the dataset. The estimation accuracy was examined by performing 5-fold cross-validation on the dataset data. The number of data points was 1418.

[0047] Figure 9 shows the experimental results. The estimation accuracy of the estimation model was verified using 5-fold cross-validation (5FoldCV). In the graph shown in Figure 9, the vertical axis shows the estimation results by the estimation model, and the horizontal axis shows the measured values. The training data (train) and test data (test) are shown at different points in the graph. The mean absolute percentage error (MAPE) calculated for the training data and test data for each validation is shown in the graph. In this experiment, the average MAPE for the test data was 6.19%.

[0048] <Other Embodiments> Although one embodiment of this invention has been described in detail above with reference to the drawings, the specific configuration is not limited to that described above, and various design changes can be made without departing from the spirit of this invention.

[0049] In the experimental example, the case in which the estimation model generation device 10 generates a model for estimating circulation and the estimation device 20 estimates circulation was described, but it is not limited to this, and the estimation model generation device 10 may also generate a model for estimating paint performance, and the estimation device 20 may also estimate paint performance other than circulation. Not only circulation, but also storage stability, dispersion stability, repellency, stickiness, adhesion, flammability, combustibility, odor, non-combustibility, flame retardancy, foaming, and curing properties, which are included in paint performance, change depending on the paint formulation and / or properties of the paint, and can therefore be estimated in the same way as circulation by the embodiment described above. The estimation model generation device 10 may generate multiple estimation models that differ depending on the range of values ​​indicated by the paint performance, and the estimation device 20 may determine which estimation model to use for estimating the paint performance based on the paint data and estimate the paint performance. In addition, the candidate estimation models used for estimating the paint performance may include estimation models that do not use elements from the paint data that have little influence on the paint performance. Furthermore, the candidate estimation models used for estimating the paint performance may include three or more estimation models that differ from several elements from the elements included in the paint data.

[0050] All or part of the functions of the estimation model generation device 10 and estimation device 20 in the above-described embodiment may be implemented by a computer. In that case, the functions may be implemented by recording a program for implementing these functions on a computer-readable recording medium, loading the program recorded on this recording medium into a computer system, and executing it. Here, "computer system" includes the OS and peripheral hardware. Furthermore, "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and recording devices such as hard disks built into a computer system. In addition, "computer-readable recording medium" may include those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and those that hold programs for a certain period of time, such as volatile memory inside a computer system that acts as a server or client in such a case. Furthermore, the above-mentioned program may be for implementing some of the functions described above, and may also be able to implement the above-mentioned functions in combination with a program already recorded in the computer system. Furthermore, all or part of the functions of the estimation model generation device 10 and estimation device 20 may be implemented using a programmable logic device such as an FPGA (Field Programmable Gate Array). [Explanation of Symbols]

[0051] 10 Estimation model generation device, 110 Data set acquisition unit, 120 Estimation model generation unit, 130 Estimation model output unit, 140 Model used determination model generation unit, 150 Model used determination model output unit, 20 Estimation device, 210 Paint data acquisition unit, 220 Paint performance measurement result estimation unit, 230 Paint performance measurement result output unit, 240 Model used determination unit, 290 Storage unit

Claims

1. Using a paint performance estimation model trained with variables including information on the paint formulation and / or properties of the paint, and the measurement results of the paint performance, the paint performance estimation model is made to output an estimated value of the measurement results of the paint performance by inputting information on the paint formulation and / or properties of the paint. Estimation method.

2. An estimation method using a model for determining the paint to be used and a plurality of paint performance estimation models, wherein the model for determining the paint to be used is a model that, upon input of information regarding the paint formulation and / or properties of the paint, determines which of the plurality of paint performance estimation models will be used for estimation. By inputting information regarding the paint formulation and / or properties of the paint into the aforementioned model determination model, the model to be used for estimation is determined from among the multiple paint performance estimation models. By inputting information regarding the paint formulation and / or properties of the paint into the determined paint performance estimation model, an estimated value of the measured paint performance is output. The estimation method according to claim 1.

3. The aforementioned model selection model calculates estimated values ​​of the measured paint performance and determines which of the multiple paint performance estimation models will be used for the estimation based on the range of the estimated values. The estimation method according to claim 2.

4. The aforementioned multiple paint performance estimation models are paint performance estimation models that are generated based on data included in the dataset, where the values ​​indicating the measured results of paint performance fall within corresponding ranges. The estimation method according to claim 2.

5. The aforementioned plurality of paint performance estimation models include a paint performance estimation model generated based on data in the dataset whose values ​​indicating the measured results of paint performance fall within a corresponding range, and a paint performance estimation model generated based on all the data in the dataset. The estimation method according to claim 2.

6. The aforementioned model used for determining the model is a model generated by machine learning. The estimation method according to claim 2.

7. The information regarding the formulation of the aforementioned paint is, The information includes at least one piece of information selected from the group consisting of: the type of glossing agent contained in the paint, the amount of glossing agent contained in the paint, the color of the glossing agent contained in the paint, the particle size of the glossing agent contained in the paint, the thickness of the glossing agent contained in the paint, the type of surface treatment of the glossing agent contained in the paint, the type of coloring pigment contained in the paint, the amount of coloring pigment contained in the paint, the color of the coloring pigment contained in the paint, the chemical structure of the coloring pigment contained in the paint, the particle size of the coloring pigment contained in the paint, the amount of resin contained in the paint, the chemical structure of the resin contained in the paint, the amount of dispersant contained in the paint, the chemical structure of the dispersant contained in the paint, the amount of thickener contained in the paint, and the chemical structure of the thickener contained in the paint. The estimation method according to any one of claims 1 to 6.

8. The information relating to the properties of the aforementioned paint is, The paint includes at least one selected from the group consisting of the viscosity of the paint, the elasticity of the paint, the solids content of the paint, the pH of the paint, the color of the paint, the transmittance of the paint, the surface tension of the paint, and the drying conditions of the paint. The estimation method according to any one of claims 1 to 6.

9. The aforementioned variables further include the measurement test conditions for the paint, By inputting information regarding the paint's composition and / or properties, as well as the paint's measurement test conditions, the aforementioned paint performance estimation model outputs an estimated value of the measured paint performance. The estimation method according to any one of claims 1 to 6.

10. The information relating to the measurement test conditions of the aforementioned paint includes at least one selected from the group consisting of test temperature, test time, stirring speed, coating temperature, and coating humidity. The estimation method according to claim 9.

11. The aforementioned paint performance includes at least one selected from the group consisting of circulation, storage, dispersion stability and repellency, adhesion, flammability, combustibility, odor, non-combustibility, flame retardancy, foaming, and curability. The estimation method according to any one of claims 1 to 6.

12. By acquiring and training information regarding the paint formulation and / or properties of the paint, as well as the measurement results of the paint performance, This system generates a machine learning model that takes information about the paint's composition and / or properties as input and outputs an estimated value of the measured paint performance. A method for generating a paint performance estimation model.

13. By acquiring and training information on the paint formulation and / or the properties and performance of the paint, Based on information on the paint formulation and / or properties of the paint, a model determination model is generated to determine the estimation model used to estimate the measurement results of paint performance. Method for generating a model for determining which model to use.

Images