Subway track foundation settlement deformation prediction based on the BiLSTM-AdaBoost model

The rapid economic expansion has spurred extensive construction near subway networks, impacting the stability of their track foundations. Consequently, it’s crucial to monitor and predict settlement in subway track foundations. However, the dynamic deformation patterns often exhibit nonlinearity and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering Research Express Jg. 6; H. 2; S. 25116 - 25126
Hauptverfasser: Dang, Xifeng, Yin, Xiao, Liu, Jianwei, Wu, Jincheng, Wang, Xin, Liu, Yongqiang, Sun, Shoubin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IOP Publishing 01.06.2024
Schlagworte:
AdaBoost ensemble learning algorithm
bidirectional long short-term memory (BiLSTM)
settlement deformation
subway track foundation
ISSN:2631-8695, 2631-8695
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The rapid economic expansion has spurred extensive construction near subway networks, impacting the stability of their track foundations. Consequently, it’s crucial to monitor and predict settlement in subway track foundations. However, the dynamic deformation patterns often exhibit nonlinearity and non-stationarity, posing challenges for traditional linear regression models. To tackle this, our study integrates the BiLSTM (bi-directional long short-term memory) network with the AdaBoost ensemble learning algorithm. Using settlement data from Shanghai metro monitoring points, the model is trained and evaluated employing R 2 (coefficient of determination), MAE (mean absolute error), and RMSE (root mean square error). Results show that our proposed model displays superior predictive accuracy compared to the LSTM and the BiLSTM, with an average training set R 2 of 0.99, test set R 2 of 0.78, average MAE of 0.32 mm, and average RMSE of 0.4 mm. Consequently, for forecasting subway track foundation deformations, employing our network model ensures highly accurate predictive capabilities.
Bibliographie:ERX-104363.R1
ISSN:2631-8695
2631-8695
DOI:10.1088/2631-8695/ad4cb6