A Transfer Learning‐Based Method for Facilitating the Prediction of Unsteady Crystal Growth. Issue 9 (3rd July 2022)

• Record Type: Journal Article
• Authors: Dang, Yifan; Kutsukake, Kentaro; Liu, Xin; Inoue, Yoshiki; Liu, Xinbo; Seki, Shota; Zhu, Can; Harada, Shunta; Tagawa, Miho; Ujihara, Toru
• Is Part Of: Advanced theory and simulations. Volume 5:Issue 9(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-07-03
• Subjects: crystal growth -- Transfer learning -- TSSG SiC -- Unsteady simulation; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.202200204
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: 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. Abstract : Process optimization is crucial for obtaining high‐quality crystal with large size, but is always time and data consuming. Transfer learning is employed to inherit the time‐independent features and predict the unsteady crystal growth. The data amount required by the machine learning models can be reduced up to 80%, which facilitates the generation of "digital twin" of real crystal growth experiment.