201. 基于机器学习的盾构掘进地表变形 预测研究与展望.
- Author
-
丁智, 李鑫家, and 张霄
- Subjects
- *
FEATURE selection , *DEFORMATION of surfaces , *TUNNEL design & construction , *DATA quality , *SPACE research , *MACHINE learning - Abstract
In order to clarify the key points of machine learning in surface deformation prediction of shield tunneling, the development background of machine learning was introduced, and the engineering application of machine learning was summarized from the aspects of database establishment, data preprocessing, model framework construction and model evaluation. It was pointed out that the shortcomings of the current relevant research were the lack of professional public database and the uneven quality of engineering data; for engineering with different stratum types, the model was prone to over fitting. At the same time, the further development direction of machine learning in shield tunneling surface deformation prediction was discussed, including the effective combination of algorithms could learn from each other; there was still a large research and application space for feature selection and super parameter optimization. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF