Neural Network Coating Sparkle Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The traditional method for matching the color and appearance of coatings containing effect pigments, such as metallic flakes, is labor-intensive and inefficient, requiring repeated spraying and visual comparison of test panels to achieve satisfactory color and sparkle matching at various angles of illumination and viewing.

Innovation Solution

A process utilizing an artificial neural network trained with data on color characteristics and sparkle values of training coatings to predict and produce target sparkle values for a target coating composition, allowing for the automated generation of matching coatings without the need for repetitive testing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional manual method with repeated spraying and visual comparison is used, then color and sparkle matching can be achieved, but labor time and processing time are excessive

Engineering Contradiction:
Improvecolor and sparkle matching accuracyVSAvoidtime for repeated spraying and visual comparison
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of spraying and visual comparison with an automated optical measurement system using a spectrophotometer to measure color values (L*, a*, b*) and sparkle values, and a neural network algorithm to calculate flake parameters, thereby eliminating the need for repeated manual spraying and visual assessment

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a digital model (neural network) that learns from training data the relationship between coating formulation and appearance properties, allowing the system to predict and match sparkle appearance without physically creating multiple test panels through repeated spraying cycles

Inventive Principle:
Principle #26Copying

2Measurement precision

If traditional manual selection of effect pigments is used, then expertise-based matching can be achieved, but the process requires experienced shaders and is not scalable

Engineering Contradiction:
Improveflake selection accuracyVSAvoiddependence on experienced shader expertise
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the human expert's manual selection process with an automated neural network system that objectively measures color and sparkle values and calculates optimal flake parameters based on learned relationships from training data, eliminating dependence on individual shader expertise

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the subjective expert judgment process into an objective parameter-based system that measures and optimizes specific quantifiable parameters (L*, a*, b* color values, sparkle values, flake size distribution, flake concentration) through automated measurement and calculation

Inventive Principle:
Principle #35Parameter changes

3Manufacturing precision

If repeated test panel spraying is performed to achieve satisfactory match, then color and appearance matching can be improved, but material waste and cost increase

Engineering Contradiction:
Improvecolor and appearance matching qualityVSAvoidwaste of coating materials in test panels
Core Design Contradiction:
Manufacturing precisionVSLoss of substance

Solution Approach 1:

The patent performs preliminary measurement and calculation using the neural network model to predict the optimal coating formulation and sparkle appearance before actual production spraying, thereby avoiding the need for multiple test panel sprays that waste coating materials

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach significantly reduces the labor and time required for matching coatings by enabling the prediction of sparkle values, allowing for precise formulation adjustments and eliminating the need for laborious spray-out and drying cycles, while improving the accuracy of color and sparkle matching across different angles.

Implementation Method 1

a spectrophotometer to measure the spectral reflectance of a standard panel and a plurality of coating samples

Methodology Applied
Scientific EffectSpectral reflectance measurement: Reflection

Implementation Method 2

The sparkle appearance of a coating can be enhanced by the addition of a fluorescent brightener to the coating formulation

Methodology Applied
Scientific EffectFluorescence: Fluorescence

Data Source

PatentEP2721542B1Method for matching sparkle appearance of coatings
Publication Date: 2019.09.18 COATINGS FOREIGN IP CO LLC
  • EP2721542B1 patent drawingFigure 1
  • EP2721542B1 patent drawingFigure 2
  • EP2721542B1 patent drawingFigure 3A

AI summary

This disclosure is directed to a process for producing one or more predicted target sparkle values of a target coating composition. An artificial neural network can be used in the process. The process disclosed herein can be used for color and appearance matching in the coating industry including vehicle original equipment manufacturing (OEM) coatings and refinish coatings. A system for producing one or more predicted target sparkle values of a target coating composition is also disclosed.