Interfacial Tension of Complex Fluids with Micro uidics and Machine Learning

界面张力是一种对自然界和工业中的许多系统都非常重要的现象。界面张力的影响存在于日常生活中，食品、家居、化妆品和化工等领域的产品也是如此。界面有力学和热力学的定义。一个多世纪以来，各种技术被用来测量不相容流体相间的界面张力。本项目研究的技术包括吊坠滴法和泰勒曲线法。泰勒曲线是一种微流控技术，以G.I.Taylor的名字命名，用于测量两种不相容流体的界面张力。该技术检查液滴接近微流体收缩时的变形。深度学习是一组在监督学习下的机器学习算法，几乎总是具有神经网络(NN)的形式。第一个深度学习算法是在几十年前建立的，最近随着与算法相关的问题的解决而变得越来越受欢迎。卷积神经网络(CNN)被用于各种复杂的计算机视觉应用。CNN的最大优势是它们不受空间限制。这种空间不变性是由于汇聚的层只传递重要的信息。这在两个方面对这个项目很重要：第一，图像中的液滴可以在收缩处的不同点处捕捉到。第二个可能也是更重要的原因是液滴的变形模式将是可移动的。本研究项目的目的是将微流体学和机器学习相结合，创建一个快速、连续运行的系统，以准确测量软物质系统的界面张力。然后这项技术将被用来检验软物质系统的静态和动态界面张力。

Interfacial tension is a phenomenon that is extremely important to many systems in both nature and industry. The effects of interfacial tension are present in everyday life with products in the food, household, cosmetic and chemical sectors, among many more. Interfacial has a mechanical and thermodynamic definition. For more than a century, a variety of techniques have been used to measure interfacial tensions between immiscible fluid phases. The technqiues examined for this project include the pendant drop method and the Taylor plot method. The Taylor plot, named after G.I. Taylor, is a microfluidic technique to measure the interfacial tension of two immiscible fluids. The technique examines the deformation of droplets as they approach a microfluidic constriction.Deep learning is a group of machine learning algorithms under supervised learning that almost always have the form of neural networks (NN's). The first deep learning algorithms were established decades ago, with a recent increase in popularity as problems associated with the algorithms are overcome.Convolutional neural networks (CNN's) are used in a wide variety of complex computer vision applications. The greatest advantage of CNN's is that they are not spatially constrained. This spatial invariance is due to the pooling layers passing only the important information on. This is important for this project in two ways: the first being the fact that the droplets present in images can be captured at different points along the constriction. The second, and potentially more important reason is that deformation patterns of the droplets will be mobile.The aim of this research project is to combine microfluidics and machine learning to create a rapid, continuously operated system to accurately measure the interfacial tension of soft matter systems. This technique will then be used to examine the static and dynamic interfacial tension of soft matter systems.