Deep learning study of induced stochastic pattern formation in the gravure printing fluid splitting process

Abstract We use deep learning (DL) algorithms for the phenomenological classification of Saffman-Taylor-instability-driven spontaneous pattern formation at liquid meniscus in fluid splitting a gravure printing press. The DL are applied to high-speed video recordings process between rotating cylinder and co-moving planar target substrate. Depending on rotation velocity or raster engraved cylinder, variety transient wetting patterns, e.g., separate drops, viscous fingers, more complex, branched bridges appear nip. discuss how these patterns classified with methods, this could serve identification different hydrodynamic flow regimes nip, point lamella splitting.