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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F21%3A00541776" target="_blank" >RIV/67985807:_____/21:00541776 - isvavai.cz</a>

Výsledek na webu

<a href="http://hdl.handle.net/11104/0319303" target="_blank" >http://hdl.handle.net/11104/0319303</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/cryst11020138" target="_blank" >10.3390/cryst11020138</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA18-18080S" target="_blank" >GA18-18080S: Objevování znalostí v datech o aktivitě člověka založené na fúzi</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Crystals

ISSN

2073-4352

e-ISSN

2073-4352

Svazek periodika

11

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

13

Strana od-do

138

Kód UT WoS článku

000622430500001

EID výsledku v databázi Scopus

2-s2.0-85103909154