Machine learning method for the supplement, correction, and prediction of the nonlinear dynamics in pattern formation

doi:10.1063/5.0036762

IMECH-IR > 微重力重点实验室

	Machine learning method for the supplement, correction, and prediction of the nonlinear dynamics in pattern formation
	Chen Y(陈一)1,2; Wu D(吴笛)1,2 ; Duan L(段俐)1,2 ; Kang Q(康琦)1,2
通讯作者	Duan, Li(duanli@imech.ac.cn) ; Kang, Qi(kq@imech.ac.cn)
发表期刊	PHYSICS OF FLUIDS
	2021-02-01
卷号	33 期号:2 页码:17
ISSN	1070-6631
摘要	The pattern formation and spatial-temporal chaos are interesting issues in nonlinear dynamics. A novel model based on machine learning methods is designed to learn and imitate the pattern evolution in Benard-Marangoni convection (BM convection). There is a supercritical process, which is an inevitable and unique experimental phenomenon, on the way to chaos in BM convection. A single layer of fluid uniformly heated at the bottom is used as the experimental system. During the experiment, the temperature difference between top and bottom of the liquid layer is increased first to make the system enter the supercritical convection state and then decreased after a while; surface temperature distribution of the liquid layer is measured in real time with an infrared thermal imager, which visualized the formation and re-organization of cellular convection during the supercritical state. The temperature data are used as the material that meets the conditions of machine learning and then the machine learning method in charge of predicting the picture of temperature distribution that it never has seen before in two steps. The experimental data are used to train an auto-encoder model based on convolutional neural networks and an RNN-CNN joint model, in which the former is used for extracting low-dimensional features of the temperature field, and the latter is used for predicting evolution results of the low-dimensional features and recovering them back to the temperature field. The models have finally achieved the objectives of supplementing the missing experimental data and correcting actual experimental data by comparing the actual experimental results with the prediction results of the machine learning approach and theoretical analysis results. On the other hand, active exploration has been undertaken in predicting physical experimental results that have never happened before.
DOI	10.1063/5.0036762
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000630504000005
WOS研究方向	Mechanics ; Physics
WOS类目	Mechanics ; Physics, Fluids & Plasmas
资助项目	National Natural Science Foundation of China[12032020] ; National Natural Science Foundation of China[12072354] ; Manned Space Program of China ; Strategic Priority Research Program on Space Science of the Chinese Academy of Sciences
项目资助者	National Natural Science Foundation of China ; Manned Space Program of China ; Strategic Priority Research Program on Space Science of the Chinese Academy of Sciences
论文分区	一类/力学重要期刊
力学所作者排名	1
RpAuthor	Duan, Li ; Kang, Qi
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/86175
专题	微重力重点实验室
作者单位	1.Chinese Acad Sci, Inst Mech, Natl Micrograv Lab, Beijing 100190, Peoples R China; 2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Chen Y,Wu D,Duan L,et al. Machine learning method for the supplement, correction, and prediction of the nonlinear dynamics in pattern formation[J]. PHYSICS OF FLUIDS,2021,33,2,:17.
APA	陈一,吴笛,段俐,&康琦.(2021).Machine learning method for the supplement, correction, and prediction of the nonlinear dynamics in pattern formation.PHYSICS OF FLUIDS,33(2),17.
MLA	陈一,et al."Machine learning method for the supplement, correction, and prediction of the nonlinear dynamics in pattern formation".PHYSICS OF FLUIDS 33.2(2021):17.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Jp2021123.pdf（5849KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载