Prediction of pinch-off height from dip-coated hydrophobic surface

When an irregular solid shape is removed from a liquid, it causes a layer of fluid to adhere to the surface of the solid. After a droplet is generated, the ligament connecting the drop to the solid thins down and eventually pinches off. In this paper, we experimentally investigate the thinning and pinch-off of drops from dip-coated surfaces with different sizes of solids and liquids. The selection of system variables such as the velocity and surface area of the solid, viscosity and surface tension of the liquid modulates the appearance of a different pinch-off height. We predict pinch-off height due to the upward velocity of the solid using an ensemble learning algorithm comprised of four base algorithms. We train and test our algorithm with original experimental data. Our approach permits the determination of the relative importance of the input features in producing variation of pinch-off heights.