Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Prediction of ground subsidence by shield tunneling using ensemble learning
Highlights 1800 sets of data to study shield tunnelling–ground subsidence relationship. XGBoost model established for ground subsidence prediction, better than DT and RF. Nonlinear complex relationships between parameters and ground subsidence analysed. Key parameters for controlling ground subsidence were identified. MAE and RMSE used to analyse performance of intelligent prediction model.
Abstract This study addresses a significant issue related to shield construction, namely the impact of shield construction parameters on ground subsidence. Shield tunnels, owing to their concealed construction, often lead to ground subsidence, causing severe disruptions to ground facilities, potential collapse, and consequent casualties and property loss. Most calculation methods for ground subsidence have a delay, making it difficult to predict ground subsidence in advance based on construction parameters. Therefore, this study collates over 1500 cases of shield construction in China and summarises the impact mechanisms of shield construction on ground subsidence through a detailed study of natural factors, engineering geology, types of structures, and types of construction parameters. Based on the influence law of the data, this study establishes three intelligent prediction methods to forecast ground subsidence. To select the hyperparameters in the models more effectively, a Bayesian optimisation algorithm was utilised. Through a comparative analysis of the models, a subsidence prediction method that is more in line with the construction characteristics and exhibits high accuracy was determined. The findings of this study serve as a valuable resource for predicting ground subsidence resulting from shield construction, enabling timely adjustments to construction parameters and the implementation of preventive measures to mitigate excessive subsidence.
Prediction of ground subsidence by shield tunneling using ensemble learning
Highlights 1800 sets of data to study shield tunnelling–ground subsidence relationship. XGBoost model established for ground subsidence prediction, better than DT and RF. Nonlinear complex relationships between parameters and ground subsidence analysed. Key parameters for controlling ground subsidence were identified. MAE and RMSE used to analyse performance of intelligent prediction model.
Abstract This study addresses a significant issue related to shield construction, namely the impact of shield construction parameters on ground subsidence. Shield tunnels, owing to their concealed construction, often lead to ground subsidence, causing severe disruptions to ground facilities, potential collapse, and consequent casualties and property loss. Most calculation methods for ground subsidence have a delay, making it difficult to predict ground subsidence in advance based on construction parameters. Therefore, this study collates over 1500 cases of shield construction in China and summarises the impact mechanisms of shield construction on ground subsidence through a detailed study of natural factors, engineering geology, types of structures, and types of construction parameters. Based on the influence law of the data, this study establishes three intelligent prediction methods to forecast ground subsidence. To select the hyperparameters in the models more effectively, a Bayesian optimisation algorithm was utilised. Through a comparative analysis of the models, a subsidence prediction method that is more in line with the construction characteristics and exhibits high accuracy was determined. The findings of this study serve as a valuable resource for predicting ground subsidence resulting from shield construction, enabling timely adjustments to construction parameters and the implementation of preventive measures to mitigate excessive subsidence.
Prediction of ground subsidence by shield tunneling using ensemble learning
Zhao, Dukun (Autor:in) / Sun, Zhangang (Autor:in) / He, Yueji (Autor:in) / Chen, Xin (Autor:in) / Liu, Rentai (Autor:in)
29.07.2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Prediction of shield tunneling-induced ground settlement using machine learning techniques
| Springer Verlag | 2019
Prediction of shield tunneling-induced ground settlement using machine learning techniques
| Springer Verlag | 2019