U-Net-Based Surrogate Model For Evaluation of Microfluidic Channels

TL;DR

This paper presents a U-Net-based surrogate model that rapidly predicts flow velocity and pressure fields in microfluidic channels, offering an efficient alternative to traditional CFD methods with high accuracy.

Contribution

The study introduces a novel U-Net neural network approach for predicting microfluidic flow fields, reducing computational effort and enabling easy assessment of new designs.

Findings

Prediction errors less than 1% for velocity and pressure fields.

The model can be trained to predict pressure from velocity data.

The surrogate model is fast, easy to set up, and accurate.

Abstract

Microfluidics have shown great promise in multiple applications, especially in biomedical diagnostics and separations. While the flow properties of these microfluidic devices can be solved by numerical methods such as computational fluid dynamics (CFD), the process of mesh generation and setting up a numerical solver requires some domain familiarity, while more intuitive commercial programs such as Fluent and StarCCM can be expensive. Hence, in this work, we demonstrated the use of a U-Net convolutional neural network as a surrogate model for predicting the velocity and pressure fields that would result for a particular set of microfluidic filter designs. The surrogate model is fast, easy to set-up and can be used to predict and assess the flow velocity and pressure fields across the domain for new designs of interest via the input of a geometry-encoding matrix. In addition, we demonstrate that the same methodology can also be used to train a network to predict pressure based on velocity data, and propose that this can be an alternative to numerical algorithms for calculating pressure based on velocity measurements from particle-image velocimetry measurements. Critically, in both applications, we demonstrate prediction test errors of less than 1%, suggesting that this is indeed a viable method.