An efficient framework for controllable micromixer design through the fusion of data-driven modeling and machine learning insights: Numerical and experimental analysis

Abstract

Micromixers are inevitable components in microfluidics, micro-electro-mechanical devices, and numerous bio-chemical assays. By assays, we mean diverse analytical procedures encompassing gene engineering, the manipulation of genetic material; nanoparticle synthesis, focusing on the controlled creation of nanoparticles; and cell lysis, involving cell membranes disruption for the release of intracellular substances for diagnostic purposes. In these assays, the homogeneous mixture of two or more fluids is crucial. However, designing an efficient micromixer providing high homogeneity and low pressure drop, while maintaining controllability, is challenging. Controllability refers to the design of a micro-system tailored to meet the specific requirements of a given assay. This study proposes a controllable framework, combining machine learning and statistical modeling. The framework begins with the generation of a reference parametric micro-structure, herein a microchannel with L-shaped baffles and featuring seven variables. A response surface method, a data-driven modeling scheme, is used to establish functional relationships between design variables and objective functions. The study reveals that the baffle height significantly impacts the system functionality, increasing the mixing index by over 40% and the pressure drop by more than 220% when reaching its upper limit. Dean-like secondary vortexes are generated in the microchannel at Re = 10, demonstrating the efficiency of the implemented baffles. Subsequently, multi-objective optimization methods, non-dominated sorting genetic algorithm (NSGA-II) and differential evolution (DE), are employed, with adaptable variable constraints. Comparative analysis of the methods shows that DE finds superior optimum solutions in fewer iterations. Finally, an optimum structure is fabricated using soft lithography, and experimental tests are conducted for validation.

Controllable Microfluidic System through Intelligent Framework: Data-Driven Modeling, Machine Learning Energy Analysis, Comparative Multiobjective Optimization, and Experimental Study

“…More details on the algorithm can be found in previous research. The specifics of the algorithm employed in this study are detailed in prior research works. , …”

“…The scale factor decreases over generations to promote convergence and maintain diversity for fine-tuning and exploration of a wider solution space depicted in Figure a. The algorithm’s details, as used in this research, are elaborated in previous publications. , …”

“…The efficacy of this proposed sampling technique was evaluated in an optimization setting, which demonstrated the superiority of the proposed method. In the field of nanoparticle synthesis and micromixer design, genetic algorithm optimiza-tion methods, such as Nondominated Sorting Genetic Algorithm II (NSGA-II) 62 and Differential Evolution (DE), 52 can be utilized to find the optimum system suitable for synthesis purposes. In the realm of optimization methods such as NSGA-II and DE, the Response Surface Method (RSM) plays a role as a surrogate model.…”

“…As a result, the clogging issue in microchannels remains a focal point in synthesis processes as it disrupts proper mixing and can ultimately lead to system failures . Thus, designing an optimal micromixer for nanoparticle synthesis involves identifying key design parameters that balance efficient mixing with minimal pressure drop, avoiding clogs, and achieving Pareto-optimal solutions through a detailed understanding of operational principles. , …”

“…50 Thus, designing an optimal micromixer for nanoparticle synthesis involves identifying key design parameters that balance efficient mixing with minimal pressure drop, avoiding clogs, and achieving Pareto-optimal solutions through a detailed understanding of operational principles. 51,52 Machine learning (ML) and data-driven modeling designs, such as fuzzy modeling, 53,54 Response Surface Method (RSM), 55 Neural Networks, 56 and support vector machines (SVMs), 57 can be employed to establish relationships between system variables and objective functions. Moreover, they can be utilized to optimize the design parameters, in order to achieve nanoparticles with desired characteristics.…”