Predictive modelling of drop ejection from damped, dampened wings by machine learning

Predictive modelling of drop ejection from damped, dampened wings by machine learning
复制标题

通过机器学习对阻尼、阻尼机翼喷射液滴进行预测建模

DOI:
10.1098/rspa.2020.0467
复制
发表时间:
2020
期刊:
Physical and Engineering Sciences
影响因子:
--
通讯作者:
Dickerson, Andrew K.
Dickerson, Andrew K.
中科院分区:
--
文献类型:
--
作者:
Alam, MD Erfanul;Wu, Dazhong;Dickerson, Andrew K.

文献摘要

参考文献

被引文献

相似文献

蚊子用高频率、低振幅的翅膀运动来干燥翅膀,这激发了对毫米级、强制悬臂释放水滴的研究。我们的模拟系统是一个10毫米聚四氟乙烯悬臂梁,在85赫兹的频率下通过±1毫米的基本振幅驱动,通过三种主要的弹射模式来置换下降:正常到悬臂的弹射、滑动和夹断。系统变量的选择,如悬臂刚度、液滴位置、液滴大小和润湿特性,可以调节特定弹射模式的外观。然而,大量的系统特征使模态发生的预测以及完全和部分脱液之间的过渡变得复杂。在本研究中,我们建立了两个基于集成学习的预测模型,分别用于预测弹射模式(分类问题)和最小惯性力弹射悬臂(回归问题)。对于弹射模式预测,我们使用装袋分类器实现了85%的准确率。对于惯性力预测,使用集成学习回归模型实现的最小均方根误差为0.037。结果还表明,弹射时间和悬臂湿润特性是预测弹射模式和弹射所需最小惯性力的主要特征。
The high frequency, low amplitude wing motion that mosquitoes employ to dry their wings inspires the study of drop release from millimetric, forced cantilevers. Our mimicking system, a 10-mm polytetrafluoroethylene cantilever driven through ±1 mm base amplitude at 85 Hz, displaces drops via three principal ejection modes: normal-to-cantilever ejection, sliding and pinch-off. The selection of system variables such as cantilever stiffness, drop location, drop size and wetting properties modulates the appearance of a particular ejection mode. However, the large number of system features complicate the prediction of modal occurrence, and the transition between complete and partial liquid removal. In this study, we build two predictive models based on ensemble learning that predict the ejection mode, a classification problem, and minimum inertial force required to eject a drop from the cantilever, a regression problem. For ejection mode prediction, we achieve an accuracy of 85% using a bagging classifier. For inertial force prediction, the lowest root mean squared error achieved is 0.037 using an ensemble learning regression model. Results also show that ejection time and cantilever wetting properties are the dominant features for predicting both ejection mode and the minimum inertial force required to eject a drop.
DOI: 10.1039/b617391h
发表时间: 2007-01-01
期刊: LAB ON A CHIP
影响因子: 6.1
作者:
Kinoshita, Haruyuki;Kaneda, Shohei;Oshima, Marie
通讯作者: Oshima, Marie
使用 SVM 分类早期筛查 DDH
DOI: 10.1109/southeastcon42311.2019.9020565
发表时间: 2019
期刊: 2019 SoutheastCon
影响因子: --
作者:
MD Erfanul Alam;N. Smith;Daren Watson;T. Hassan;Kishan Neupane
通讯作者: Kishan Neupane
关于移动接触线
DOI: 10.1061/(asce)0733-9399(1992)118:4(735
发表时间: 1992
期刊: Journal of Engineering Mechanics-asce
影响因子: --
作者:
Shih;A. Chwang
通讯作者: A. Chwang
DOI: 10.1021/la970467w
发表时间: 1997
期刊: Langmuir
影响因子: 3.9
作者:
C. Slevin;P. Unwin
通讯作者: P. Unwin
DOI: 10.1016/j.jfluidstructs.2016.02.005
发表时间: 2016-04
影响因子: 3.6
作者:
R. Bleischwitz;R. Kat;B. Ganapathisubramani
通讯作者: R. Bleischwitz;R. Kat;B. Ganapathisubramani