Automated detection and sorting of microencapsulation via machine learning
Automated detection and sorting of microencapsulation via machine learning
复制标题
DOI：
10.1039/c8lc01394b
复制
发表时间：
2019-05-21
期刊：
影响因子：
6.1
通讯作者：
Giera, Brian
中科院分区：
文献类型：
--
作者：
Chu, Albert;Du Nguyen;Giera, Brian
基于微流体的微胶囊化需要大量的监督，以防止由于流体流动中的偶发中断而导致的材料和质量损失。最先进的微胶囊生产是费力的，并且依赖于专家来监控该过程，例如通过显微镜。未注意到的缺陷会降低收集材料的质量和/或可能导致不可逆的堵塞。为了解决这些问题，我们开发了一个自动监控和分拣系统，该系统可在消费级硬件上实时运行。使用在典型操作期间获得的人类标记的显微镜图像，我们训练了一个卷积神经网络来评估微胶囊化。基于机器学习算法的输出，集成阀系统收集所需的微胶囊或相应地转移废料。虽然系统会通知操作员进行必要的调整以恢复微胶囊化，但我们可以扩展系统以自动纠正。由于基于微流体的生产平台通常收集图像和传感器数据，机器学习可以帮助扩大和改进微流体技术，而不仅仅是微胶囊化。
Microfluidic-based microencapsulation requires significant oversight to prevent material and quality loss due to sporadic disruptions in fluid flow that routinely arise. State-of-the-art microcapsule production is laborious and relies on experts to monitor the process, e.g. through a microscope. Unnoticed defects diminish the quality of collected material and/or may cause irreversible clogging. To address these issues, we developed an automated monitoring and sorting system that operates on consumer-grade hardware in realtime. Using human-labeled microscope images acquired during typical operation, we train a convolutional neural network that assesses microencapsulation. Based on output from the machine learning algorithm, an integrated valving system collects desirable microcapsules or diverts waste material accordingly. Although the system notifies operators to make necessary adjustments to restore microencapsulation, we can extend the system to automate corrections. Since microfluidic-based production platforms customarily collect image and sensor data, machine learning can help to scale up and improve microfluidic techniques beyond microencapsulation.