Transient global modeling for the pulling process of Czochralski silicon crystal growth. II. Investigation on segregation of oxygen and carbon

Liu, Xin; Harada, Hirofumi; Miyamura, Yoshiji; Nakano, Satoshi; Nishizawa, Shin Ichi; Kakimoto, Koichi

doi:10.1016/j.jcrysgro.2019.125404

Cited by 7 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 4 ] Numerical simulations have served as a complement to experiments to reveal the unsteady flow and thermal and chemical phenomena in various crystal growth systems. [ 5‐9 ] Nevertheless, numerical simulations alone cannot provide a quantitative guide for a practical unsteady growth process because the design and optimization of a time‐dependent recipe require a considerable number of trials and searches, and numerical simulation to support these activities would be very time‐consuming. It is expected that a high‐speed digital twin will allow quick prediction of the real‐time conditions inside an evolutionary system, based on which the optimal control recipe can be derived.…”

Section: Introductionmentioning

confidence: 99%

A Transfer Learning‐Based Method for Facilitating the Prediction of Unsteady Crystal Growth

Dang

Kutsukake

Liu

et al. 2022

Advcd Theory and Sims

Self Cite

View full text Add to dashboard Cite

Real-time prediction and dynamic control systems that can adapt to an unsteady environment are necessary for material fabrication processes, especially crystal growth. Recent studies have demonstrated the effectiveness of machine learning in predicting an unsteady crystal growth process, but its wider application is hindered by the large amount of training data required for sufficient accuracy. To address this problem, this study investigates the capability of transfer learning to predict geometric evolution in an unsteady silicon carbide (SiC) solution growth system based on a small amount of data. The performance of transferred models is discussed regarding the effect of the transfer learning method, training data amount, and time step length. The transfer learning strategy yields the same accuracy as that of training from scratch but requires only 20% of the training data. The accuracy is stably inherited through successive time steps, which demonstrates the effectiveness of transfer learning in reducing the required amount of training data for predicting evolution in an unsteady crystal growth process. Moreover, the transferred models trained with relatively more data (no more than 100%) further improve the accuracy inherited from the source model through multiple time steps, which broadens the application scope of transfer learning.

show abstract

Section: Introductionmentioning

confidence: 99%