Machine Learning-Aided Microdroplets Breakup Characteristic Prediction in Flow-Focusing Microdevices by Incorporating Variations of Cross-Flow Tilt Angles

Abstract

Controlling droplet breakup characteristics such as size, frequency, regime, and droplet quality within flow-focusing microfluidic devices is critical for different biomedical applications of droplet microfluidics such as drug delivery, biosensing, and nanomaterial preparation. The development of a prediction platform capable of forecasting droplet breakup characteristics can significantly improve the iterative design and fabrication processes required for achieving desired performance. The present study aims to develop a multipurpose platform capable of predicting the working conditions of user-specific droplet size and frequency and reporting the quality of the generated droplets, regime, and hydrodynamical breakup characteristics in flow-focusing microdevices with different cross-junction tilt angles. Four different neural network-based prediction platforms were compared to accurately estimate capsule size, generation rate, uniformity, and circle metric. The trained capsule size and frequency networks were optimized using the heuristic optimization approach for establishing the Pareto optimal solution plot. To investigate the transition of the droplet generation regime (i.e., squeezing, dripping, and jetting), two different classification models (LDA and MLP) were developed and compared in terms of their prediction accuracy. The MLP model outperformed the LDA model with a cross-validation measure evaluated as 97.85%, demonstrating that the droplet quality and regime prediction models can provide an engineering judgment for the decision maker to choose between the suggested solutions on the Pareto front. The study followed a comprehensive hydrodynamical analysis of the junction angle effect on the dispersed thread formation, pressure, and velocity domains in the orifice.