Multi-input convolutional network for ultrafast simulation of field evolvement

Zhuo Wang; Wenhua Yang; Linyan Xiang; Xiao Wang; Yingjie Zhao; Yaohong Xiao; Pengwei Liu; Yucheng Liu; Mihaela Banu; Oleg Zikanov; Lei Chen

doi:10.1016/j.patter.2022.100494

Multi-input convolutional network for ultrafast simulation of field evolvement

Patterns (N Y). 2022 Apr 21;3(6):100494. doi: 10.1016/j.patter.2022.100494. eCollection 2022 Jun 10.

Authors

Zhuo Wang¹, Wenhua Yang^{1

2}, Linyan Xiang¹, Xiao Wang³, Yingjie Zhao⁴, Yaohong Xiao¹, Pengwei Liu⁴, Yucheng Liu^{2

5}, Mihaela Banu⁶, Oleg Zikanov¹, Lei Chen¹

Affiliations

¹ Department of Mechanical Engineering, University of Michigan-Dearborn, Dearborn, MI 48128, USA.
² Department of Mechanical Engineering, Mississippi State University, Starkville, MS 39762, USA.
³ School of Mechatronic Engineering, Jiangsu Normal University, Xuzhou, Jiangsu 221116, China.
⁴ College of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China.
⁵ Department of Mechanical Engineering, South Dakota State University, Brookings, SD 57007, USA.
⁶ Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI 48128, USA.

Abstract

There is a compelling need for the regression capability of mapping the initial field and applied conditions to the evolved field, e.g., given current flow field and fluid properties predicting next-step flow field. Such a capability can provide a maximum to full substitute of a physics-based model, enabling fast simulation of various field evolvements. We propose a conceptually simple, lightweight, but powerful multi-input convolutional network (ConvNet), yNet, that merges multi-input signals by manipulating high-level encodings of field/image input. yNet can significantly reduce the model size compared with its ConvNet counterpart (e.g., to only one-tenth for main architecture of 38-layer depth) and is as much as six orders of magnitude faster than a physics-based model. yNet is applied for data-driven modeling of fluid dynamics, porosity evolution in sintering, stress field development, and grain growth. It consistently shows great extrapolative prediction beyond training datasets in terms of temporal ranges, spatial domains, and geometrical shapes.

Keywords: additive manufacturing; convolutional network; data-driven modeling; fluid dynamics; grain growth; microstructure; porosity; scientific machine learning; selective laser sintering; stress.