Neural network-based UV adjustment of the photopolymer surface for modification of coating properties printed in flexography.

Processes of coating deposition often rely on printing techniques, with flexography being the most common one because of its ability to adjust the medium for the coating transfer (printing plate) to the specific type of coating and substrate by using photopolymer materials with different properties. Qualitative requirements for many types of coatings, especially in the printing industry, include uniformity, achieving desired thickness, definition of the edges of printed coating and optical density of colored coatings. This research was focused on the modification of the mechanical and surface properties of the common styrene–diene-based photopolymer materials in order to optimize the properties of the deposited coating—flexographic ink—by applying the UV post-treatment of the photopolymer. After the analyses of modified photopolymers, neural networks were built with the aim of finetuning of the photopolymer's surface properties by the UV post-treatment. The results of the research enabled the analysis of the influence of changes that occur in the modified photopolymer material's mechanical and surface properties on the coating thickness, optical density and printed element edge definition. Once the neural network was built, it enabled fast adjustment of the UV post-treatment of the photopolymer with the aim of optimizing the properties of the specific coating. [ABSTRACT FROM AUTHOR]