Generative design of microfluidic channel geometry using evolutionary approach

In this paper, we propose the evolutionary approach for the generative design of microfluidic channel geometry. Sets of candidate solutions for geometry of single cell analysis devices can be used to simplify the decision-making process for micro-devices design. The algorithmic core is based on continuous optimization of coordinates of a polygons set. The proposed approach is validated experimentally with the fabricated microfluidic device. The experiments confirm the correctness and effectiveness of the proposed methods.