Real Time Predictions of VGF-GaAs Growth Dynamics by LSTM Neural Networks

0541776 - ÚI 2022 RIV CH eng J - Journal Article
Dropka, N. - Ecklebe, S. - Holeňa, Martin
Real Time Predictions of VGF-GaAs Growth Dynamics by LSTM Neural Networks.
Crystals. Roč. 11, č. 2 (2021), č. článku 138. ISSN 2073-4352. E-ISSN 2073-4352
R&D Projects: GA ČR(CZ) GA18-18080S
Institutional support: RVO:67985807
Keywords : neural networks * crystal growth * GaAs * process control * digital twins
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 2.670, year: 2021
Method of publishing: Open access

The aim of this study was to assess the aptitude of the recurrent Long Short-Term Memory (LSTM) neural networks for fast and accurate predictions of process dynamics in vertical-gradient-freeze growth of gallium arsenide crystals (VGF-GaAs) using datasets generated by numerical transient simulations. Real time predictions of the temperatures and solid–liquid interface position in GaAs are crucial for control applications and for process visualization, i.e., for generation of digital twins. In the reported study, an LSTM network was trained on 1950 datasets with 2 external inputs and 6 outputs. Based on network performance criteria and training results, LSTMs showed the very accurate predictions of the VGF-GaAs growth process with median root-mean-square-error (RMSE) values of 2 × 10−3. This deep learning method achieved a superior predictive accuracy and timeliness compared with more traditional Nonlinear AutoRegressive eXogenous (NARX) recurrent networks.
Permanent Link: http://hdl.handle.net/11104/0319303