Prediction of architectural coating performance using titanium dioxide characterization applying artificial neural networks

Prediction of paint properties is a critical issue for the coatings industry, since experimentation is time consuming and a lot of financial and human resources are needed to test or develop new products. In current market conditions, cost savings and product innovation are critical issues. In this article, an artificial neural network, of the feed forward type, was trained using as inputs key properties of titanium dioxide and two formulation parameters (pigment volume concentration and titanium dioxide content) for a water-based architectural coating. The outputs of this research were spread rate, color (L*, a*, b*) and tinting strength. Test data were used to check the accuracy of the model, demonstrating the viability of paint properties prediction related to the properties of the titanium dioxide formulation with high correlation (>95%).