Prediction of shield tunneling parameters using a BO-XGBoost machine learning method

Tiejun Li; Bin Chen; Hao Huang; Wen Xu

doi:10.1117/12.3009581

16 October 2023 Prediction of shield tunneling parameters using a BO-XGBoost machine learning method

Tiejun Li, Bin Chen, Hao Huang, Wen Xu

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128033U (2023) https://doi.org/10.1117/12.3009581
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

Due to the uncertainty of external factors such as the complexity of geological conditions, the subjectivity of personnel operation, and the loss of machinery and equipment, the efficiency, cost and safety of construction will be affected. It is of great significance to predict the parameters of shield tunneling and provide advance information for construction adjustment and control. In this paper, a prediction method of shield construction parameters combining Bayesian optimization and XGBOOST is proposed, and the effectiveness of the proposed method is verified by engineering cases. The following conclusions are obtained: (1) BO-XGBoost model can accurately predict cutterhead wear, penetration and energy consumption during shield tunneling; (2) SHAP can evaluate the importance of input variables of the prediction model, which improves the unexplainability of the prediction model.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tiejun Li, Bin Chen, Hao Huang, and Wen Xu "Prediction of shield tunneling parameters using a BO-XGBoost machine learning method", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128033U (16 October 2023); https://doi.org/10.1117/12.3009581

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available