This work demonstrates droplet manipulation using bio-inspired micropumps in microfluidic applications, indicating the role of machine learning in optimizing performance.
Miniaturized functional fluidic pumps have found broad applications across various fields; however, the fabrication and dimensional limitations of their electrodes remain a significant challenge. Conventional manufacturing techniques often fail to achieve high aspect ratio structures exceeding 2 and electrode heights greater than 1 mm. In this work, we propose a novel extreme microfabrication strategy that integrates flexible molding techniques with advanced microfabrication processes to develop high‐precision pump electrodes. These electrodes are successfully implemented in droplet manipulation applications. First, we selected suitable microfabrication‐compatible materials and developed a conductive, flexible liquid elastomer, along with a tailored fabrication process. Next, a functional working fluid compatible with the electrodes was synthesized and characterized in terms of its viscosity, electrical conductivity, dielectric constant, and interfacial behavior with aqueous phases. A corresponding microfluidic chip was also fabricated to assess its droplet generation performance. Both duty cycle‐based and frequency‐based droplet manipulation strategies were investigated using this chip. Finally, a machine learning approach was employed to model the droplet generation process and evaluate the influence of four key parameters on device performance. This study establishes a foundational platform and design pathway for future development of integrated on‐chip pumping systems in microfluidic applications.
No takes yet. Share an insight, caveat, or question.
Mao et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: