# US 2021/0279510 A1 · Coating quality prediction device and learned model generation method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279510 A1
- Document ID: US20210279510A1
- Status: Published application
- Kind: A1
- Application number: 17/101,035
- Filed: 2020-11-23
- Published: 2021-09-09
- Earliest claimed: 2020-03-04
- Assignees: Toyota Jidosha Kabushiki Kaisha
- Applicants: Toyota Jidosha Kabushiki Kaisha
- Inventors: Mamoru KOUZAKI; Hideaki MORITA; Akira NISHIMURA; Shin YAHIRO; Kazuyuki OKAZAKI; Tomohiro MURAI; Daichi NISHIWAKI
- Web page: https://patentgrep.com/patent/US20210279510A1

## CPC

- G06V 10/56: relating to colour
- C09D 5/035: {Coloring agents, e.g. pigments (C09D5/032 takes precedence)}
- G01N 21/8851: {Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges (G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002)}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 20/00: Machine learning
- G06T 7/0004: {Industrial image inspection}
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 40/162: {using pixel segmentation or colour matching}
- G01N 2021/8427: {Coatings}
- G01N 2021/8883: {involving the calculation of gauges, generating models}
- G06T 2207/20081: Training; Learning
- G06T 2207/30156: Vehicle coating
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- C09D: COATING COMPOSITIONS, e.g. PAINTS, VARNISHES OR LACQUERS; FILLING PASTES; CHEMICAL PAINT OR INK REMOVERS; INKS; CORRECTING FLUIDS; WOODSTAINS; PASTES OR SOLIDS FOR COLOURING OR PRINTING; USE OF MATERIALS THEREFOR (cosmetics A61K; processes for applying liquids or other fluent materials to surfaces, in general, B05D; staining wood B27K5/02; glazes or vitreous enamels C03C; natural resins, French polish, drying-oils, driers, turpentine, per se, C09F; polishing compositions other than French polish, ski waxes C09G; adhesives or use of materials as adhesives C09J; materials for sealing or packing joints or covers C09K3/10; materials for stopping leaks C09K3/12; processes for the electrolytic or electrophoretic production of coatings C25D)
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The coating quality prediction device includes: a learned model that has learned a relationship between characteristics of a paint, conditions at a time of applying the paint, and a smoothness of a surface of a coating film obtained by applying the paint under the conditions; and a calculation unit that uses the learned model to calculate the smoothness of the surface of the coating film from the characteristics of the paint and the conditions at the time of applying the paint.

## Claims

### Claim 1

A coating quality prediction device comprising:
a learned model that has learned a relationship between characteristics of a paint, conditions at a time of applying the paint, and a smoothness of a surface of a coating film obtained by applying the paint under the conditions; and
a calculation unit that uses the learned model to calculate the smoothness of the surface of the coating film from the characteristics of the paint and the conditions at the time of applying the paint.

### Claim 2 (depends on 1)

The coating quality prediction device according to claim 1, wherein the learned model has learned a relationship between the characteristics of the paint, the conditions at the time of applying the paint, and a value in each of a plurality of wavelength regions, the value being obtained by decomposing a result of measurement on the surface of the coating film obtained by applying the paint under the conditions.

### Claim 3 (depends on 1)

The coating quality prediction device according to claim 1, wherein the conditions at the time of applying the paint include a direction in which a surface of an object to be coated faces.

### Claim 4 (depends on 1)

The coating quality prediction device according to claim 1, wherein:
the paint includes an intermediate paint, a base paint, and a clear paint; and
the coating film includes an intermediate coating film, a base coating film provided on the intermediate coating film, and a clear coating film provided on the base coating film.

### Claim 5 (depends on 4)

The coating quality prediction device according to claim 4, wherein the characteristics of the base paint are calculated based on ingredients of the base paint.

### Claim 6

A coating quality prediction device comprising:
a learned model that has learned a relationship between information regarding a paint, conditions at a time of applying the paint, and a variation in a coating color among a plurality of objects to be coated on which the paint is applied under the conditions; and
a calculation unit that uses the learned model to calculate the variation in the coating color from the information regarding the paint and the conditions at the time of applying the paint.

### Claim 7 (depends on 6)

The coating quality prediction device according to claim 6, wherein the variation in the coating color includes a variation in each of values in CIE 1976 L*a*b* color system.

### Claim 8 (depends on 6)

The coating quality prediction device according to claim 6, wherein the information regarding the paint includes a standard color of the paint.

### Claim 9

A method for generating a learned model, the method comprising:
acquiring training data including characteristics of a paint, conditions at a time of applying the paint, and a smoothness of a surface of a coating film obtained by applying the paint under the conditions; and
using the training data to generate a learned model that outputs the smoothness of the surface of the coating film when the characteristics of the paint and the conditions at the time of applying the paint are input.

### Claim 10

A method for generating a learned model, the method comprising:
acquiring training data including information regarding a paint, conditions at a time of applying the paint, and a variation in a coating color among a plurality of objects to be coated on which the paint is applied under the conditions; and
using the training data to generate a learned model that outputs the variation in the coating color when the information regarding the paint and the conditions at the time of applying the paint are input.
