Performance prediction of magnetorheological fluid?based liquid gating membrane by kriging machine learning method

A smart liquid gating membrane is a responsive structural material as pressure-driven system that consists of solid and dynamic liquid, responding to the external field. An accurate prediction rheological mechanical properties important for designs membranes various applications. However, high predicted accuracy by traditional sequential method requires large amount experimental data, which not practical in some situations. To conquer these problems, artificial intelligence has promoted rapid development science recent years, bringing hope solve challenges. Here we propose Kriging machine learning model with an active candidate region, can be smartly updated expected improvement probability increase local near most sensitive search predict performance minimal size data. Besides this, this new instruct our experiments optimal size. The methods are then verified magnetorheological fluids, would wide interest design potential applications drug release, microfluidic logic, fluid control, beyond.