Formulation systems and methods employing target coating data results

Patent metadata

Field	Value
Publication number	US-10970879-B2
Application number	US-201815963686-A
Country	US
Kind code	B2
Filing date	Apr 26, 2018
Priority date	Apr 26, 2018
Publication date	Apr 6, 2021
Grant date	Apr 6, 2021

Abstract

A computer system for seeding a formulation engine receives spectrometric data from a target coating. The computer system processes the spectrometric data through a probabilistic colorant analysis. The probabilistic colorant analysis generates a set of colorants. Each colorant within the set of colorants is associated with a calculated probability that the associated colorant is present within the target coating. Additionally, the computer system adds at least a portion of the colorants within the set of colorants to a formulation engine. The portion of the colorants is added to the formulation engine in order of decreasing probability. Further, the computer system generates, from an output of the formulation engine, a coating formulation that is calculated to match the target coating within a predetermined qualitative threshold.

First claim

The invention claimed is:

1. A computer system for seeding a formulation engine, comprising:
one or more processors; and
one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform at least the following:
receive spectrometric data from a target coating;
process the spectrometric data through a probabilistic colorant analysis, the probabilistic colorant analysis generating a set of final colorants, each final colorant within the set of final colorants being associated with a calculated probability that the associated final colorant is present within the target coating, wherein processing the spectrometric data through a probabilistic colorant analysis comprises:
initiating a set of colorant decision points, wherein each colorant decision point comprises a set of independent calculations of the spectrometric data that each provide an independent assessment about the presence of a particular effect pigment type within the target coating,
calculating in parallel each colorant decision point within the set of colorant decision points, wherein each colorant decision point provides a probability that a different effect pigment type is present within the target coating,
calculating a set of final colorant probabilities, wherein each final colorant probability within the set of final colorant probabilities is calculated by combining a unique subset of probabilities calculated by the set of colorant decision points, and
associating each final colorant probability with a final colorant from within the set of final colorants;

add at least a portion of the final colorants within the set of final colorants to a formulation engine, wherein the portion of the final colorants are added to the formulation engine in order of decreasing probability; and
generate, from an output of the formulation engine, a coating formulation that is calculated to match the target coating within a predetermined threshold.

2. The computer system of claim 1 , wherein adding at least a portion of the final colorants within the set of final colorants to a formulation engine comprises:
iteratively adding final colorants selected from the set of final colorants to the formulation engine in order of decreasing probability until the predetermined threshold is met.

3. The computer system of claim 2 , wherein iteratively adding colorants comprises:
adding to the formulation engine a first colorant associated with a highest probability within the set of final colorants; and
when the predetermined threshold is not met, continuing to iteratively add additional colorants selected from the set of final colorants in order of decreasing probability.

4. The computer system of claim 1 , wherein each final colorant probability within the set of final colorant probabilities is calculated using a Bayesian analysis.

5. The computer system of claim 1 , wherein the formulation engine applies a Kubelka-Munk analysis.

6. The computer system of claim 1 , wherein the executable instructions include instructions that are executable to configure the computer system to communicate the coating formulation to a coating mixing machine for production.

7. The computer system of claim 1 , wherein the executable instructions include instructions that are executable to configure the computer system to:
prior to adding the at least the portion of the final colorants within the set of final colorants to the formulation engine, receive input from a user removing one or more colorants from the set of final colorants.

8. The computer system of claim 1 , wherein the predetermined threshold is user definable.

9. The computer system of claim 1 , wherein each colorant within the at least a portion of the final colorants is associated with calculated probabilities above a threshold probability.

10. The computer system of claim 1 , wherein each independent calculation within the set of independent calculations comprises an independent assessment of a presence of a particular effect pigment type within the target coating that does not require as an input the output of any other independent calculation within a respective colorant decision point.

11. A method for seeding a formulation engine, comprising:
receiving spectrometric data from a target coating;
processing the spectrometric data through a probabilistic colorant analysis, wherein the probabilistic colorant analysis generates a set of final colorants, each final colorant within the set of final colorants being associated with a calculated probability that the associated final colorant is present within the target coating;
adding to the formulation engine a first colorant associated with a highest probability within the set of final colorants;
when a predetermined threshold is not met, continuing to iteratively add additional colorants selected from the set of final colorants in order of decreasing probability; and
generating, from an output of the formulation engine, a coating formulation that is calculated to match the target coating within a predetermined threshold.

12. The method of claim 11 , wherein processing the spectrometric data through a probabilistic colorant analysis comprises:
initiating a set of colorant decision points, wherein each colorant decision point comprises a set of independent calculations of the spectrometric data that each provide an independent assessment about the presence of a particular effect pigment type within the target coating;
calculating in parallel each colorant decision point within the set of colorant decision points, wherein each colorant decision point provides a probability that a different effect pigment type is present within the target coating;
calculating a set of final colorant probabilities, wherein each final colorant probability within the set of final colorant probabilities is calculated by combining a unique subset of probabilities calculated by the first set of colorant decision points; and
associating each final colorant probability with a final colorant from within the set of final colorants.

13. The method of claim 12 , wherein each independent calculation within the set of independent calculations comprises an independent assessment of a presence of a particular effect pigment type within the target coating that does not require as an input the output of any other independent calculation within a respective colorant decision point.

14. The method of claim 12 , wherein each final colorant probability within the set of final colorant probabilities is calculated using a Bayesian analysis.

15. The method of claim 11 , wherein the formulation engine applies a Kubelka-Munk analysis.

16. The method of claim 11 , further comprising communicating the coating formulation to a coating mixing machine for production.

17. The method of claim 11 , further comprising:
prior to adding the at least the portion of the final colorants within the set of final colorants to the formulation engine, receiving input from a user removing one or more colorants from the set of final colorants.

18. The method of claim 11 , wherein the predetermined threshold is user definable.

19. A computer program product comprising one or more computer storage media having stored thereon computer-executable instructions that, when executed at a processor, cause the computer system to perform a method for seeding a formulation engine, the method comprising:
receiving spectrometric data from a target coating;
proc

Assignees

• Ppg Ind Ohio Inc

Inventors

• Norris Alison M
• Beymore Paul

Classifications

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G01J3/504

  Goniometric colour measurements, for example measurements of metallic or flake based paints · CPC title

• G01N21/251

  Colorimeters; Construction thereof · CPC title

• G06T7/0004

  Industrial image inspection · CPC title