Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation

Abstract

Shape morphing of liquid droplets is important for advances in both medical and industrial applications. However current manipulation techniques lack methods to control shapes other than elliptical-shaped droplets. Here we propose using Long Short-Term Memory (LSTM) based model to learn and predict the evolution of the shape of a non-magnetic liquid droplet at an air-ferrofluid interface deformed with programmed sequential actuation of electromagnets. The resulting droplet shapes can be convex or concave. We can also predict the actuation sequences for a given shape sequence with an accuracy of 79.1 %. The proposed method could also be applied to a variety of other liquid droplet shape-morphing systems which utilize arrays of electromagnetic or electric actuators.