Hybrid-driven modeling using a BiLSTM–AdaBoost algorithm for diameter prediction in the constant diameter stage of Czochralski silicon single crystals

During the preparation of electronic-grade silicon single crystals (SSC), accurately predicting the crystal diameter is crucial for obtaining high-quality crystals. In this paper, a hybrid-driven modeling method integrating Bidirectional Long Short-Term Memory network (BiLSTM) and Adaptive Boosting...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Scientific reports Jg. 15; H. 1; S. 18100 - 20
Hauptverfasser: Liu, Yu-Yu, Liu, Ding, Wu, Shi-Hai, Jing, Yi-Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 24.05.2025
Nature Publishing Group
Nature Portfolio
Schlagworte:
Adaptive boosting algorithms
Algorithms
Crystals
Czochralski silicon single crystals
Humanities and Social Sciences
Hybrid drive modeling
Long short-term memory
Long short-term memory network
Mechanistic modeling
multidisciplinary
Predictions
Science
Science (multidisciplinary)
Silicon
Single crystals
Time series
Long short-term memory network
Mechanistic modeling
Adaptive boosting algorithms
Czochralski silicon single crystals
Hybrid drive modeling
ISSN:2045-2322, 2045-2322
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:During the preparation of electronic-grade silicon single crystals (SSC), accurately predicting the crystal diameter is crucial for obtaining high-quality crystals. In this paper, a hybrid-driven modeling method integrating Bidirectional Long Short-Term Memory network (BiLSTM) and Adaptive Boosting (AdaBoost) algorithm is proposed, aiming to improve the accuracy and stability of crystal diameter prediction in the medium diameter stage of the SSC growth by the Czochralski (CZ) method. First, the initial prediction of SSC diameter is performed using a mechanistic model and the prediction error is calculated; then, the time series data are processed using a BiLSTM network to generate the predicted values at each time point. Subsequently, the prediction results of the BiLSTM network are weighted and fused by the AdaBoost algorithm to obtain the final time series prediction output, and the prediction performance is further enhanced by iterative optimization. Compared with the traditional mechanistic model or a single data-driven model, this hybrid model retains the explanatory nature of the mechanistic model while also ensuring the accuracy of the data-driven model, which effectively overcomes the challenges posed by complex coupling and nonlinear problems.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-96982-9