Method for matching sparkle appearance of coatings

A system for producing one or more predicted target sparkle values of a target coating composition, said system comprising:

• (i) a computing device;
• (ii) an artificial neural network computing program product residing on said computing device or a host computer functionally coupled to said computing device, said artificial neural network computing program product comprises:
• a) an input layer having one or more input nodes for receiving inputs;
• b) at least one hidden layer having one or more hidden nodes;
• c) an output layer having one or more output nodes for producing outputs;
• (iii) an input device and an output device functionally coupled to said computing device;
• and
• (iv) a computer program product comprising computing codes functionally coupled to said computing device for performing a computing process, said computing process comprises the steps of:
• (1) receiving training data of a plurality of training coatings into said one or more input nodes of said artificial neural network computing program product, said training data comprise measured color characteristics, measured sparkle values and an individual training coating formulation associated with each of the training coatings, and
• (2) training said artificial neural network computing program product with said training data to produce a trained artificial neural network that is capable of producing a predicted sparkle value from said output nodes 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.