Method for matching sparkle appearance of coatings

Abstract

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.

1 . A process for producing one or more predicted target sparkle values of a target coating composition, said process comprising the steps of:
 (A) obtaining training data of a plurality of training coatings, said training data comprise measured color characteristics, measured sparkle values and an individual training coating formulation associated with each of the training coatings; and   (B) training an artificial neural network with said training data to produce a trained artificial neural network that is capable of producing a predicted sparkle value based on a coating formulation and color characteristics associated with said coating formulation, wherein said trained artificial neural network is trained based on said measured color characteristics, said measured sparkle values and said individual training coating formulation associated with each of the training coatings.   
     
     
         2 . The process of  claim 1  further comprising the steps of:
 (C) producing the predicted target sparkle values from said trained artificial neural network based on the target coating formulation and target color characteristics associated with said target coating formulation; and 
 (D) outputting said predicted target sparkle values to an output device. 
 
     
     
         3 . The process of  claim 2 , wherein said one or more predicted target sparkle values are produced based on one or more illumination angles, one or more viewing angles, or a combination thereof. 
     
     
         4 . The process of  claim 2 , wherein said one or more predicted target sparkle values are produced based on a viewing angle of 15°, 25°, 45°, 75°, or a combination thereof, said viewing angle being an aspecular angle. 
     
     
         5 . The process of  claim 2 , wherein said target color characteristics are selected from: measured target color characteristics obtained by measuring a target coating produced from said target coating composition, retrieved target color characteristics retrieved based on said target coating composition from a color database comprising color characteristics associated with coating compositions, predicted target color characteristics obtained based on said target coating composition from a color predicting computing program product that predicts coating colors based on coating compositions, or a combination thereof. 
     
     
         6 . The process of  claim 2  further comprising the steps of:
 (E) generating a target image having R,G,B values based on said predicted target sparkle values and said target color characteristics, optionally, a shape of an article coated with the target coating composition; and 
 (F) displaying said target image having said R,G,B values on a display device. 
 
     
     
         7 . The process of  claim 6 , wherein said target image is displayed based on one or more illumination angles, one or more viewing angles, or a combination thereof. 
     
     
         8 . The process of  claim 6 , wherein said target image is generated as a high dynamic range (HDR) target image. 
     
     
         9 . The process of  claim 8 , wherein said HDR target image is generated using bidirectional reflectance distribution function (BRDF). 
     
     
         10 . The process of  claim 8 , wherein said HDR target image is displayed on a HDR image display device, a non-HDR image display device, or a combination thereof. 
     
     
         11 . The process of  claim 6 , wherein said article is a vehicle or portion of the vehicle. 
     
     
         12 . The process of  claim 1 , wherein said measured color characteristics comprise color data values selected from L,a,b color values, L*,a*,b* color values, XYZ color values, L,C,h color values, spectral reflectance values, K,S values, or a combination thereof. 
     
     
         13 . The process of  claim 12 , wherein said color data values are obtained at one or more illumination angles, one or more viewing angles, or a combination thereof. 
     
     
         14 . The process of  claim 12 , wherein said color data values are obtained at a viewing angle of 15°, 25°, 45°, 110°, or a combination thereof, said viewing angle being an aspecular angle. 
     
     
         15 . The process of  claim 1 , wherein said measured sparkle values are obtained at one or more illumination angles, one or more viewing angles, or a combination thereof. 
     
     
         16 . The process of  claim 15 , wherein said measured sparkle values are obtained at a viewing angle of 15°, 45°, 75°, or a combination thereof, said viewing angle being an aspecular angle. 
     
     
         17 . The process of  claim 1 , wherein at least one of said training coatings comprises at least one effect pigment. 
     
     
         18 . The process of  claim 1 , wherein said trained artificial neural network comprises:
 a) an input layer having one or more input nodes for receiving color characteristics and coating formulations;   b) at least one hidden layer having one or more hidden nodes;   c) an output layer having one or more output nodes for producing said predicted sparkle values;   d) individual trained input connection weights connecting each of the input nodes with the hidden nodes in a first of said hidden layers;   e) individual trained output connection weights connecting each of the output nodes with each of the hidden nodes in a last of said hidden layers;   wherein said first and the last of the hidden layers are the same when there is only one hidden layer and said first and the last of the hidden layers are different when there are two or more hidden layers.   
     
     
         19 . The process of  claim 18 , wherein said trained artificial neural network comprises two or more hidden layers. 
     
     
         20 - 31 . (canceled)