Paper
28 July 2023 Prediction analysis of vertical displacement of pipe jacking crossing existing subway tunnel based on LSTM algorithm
Author Affiliations +
Proceedings Volume 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023); 1275651 (2023) https://doi.org/10.1117/12.2686338
Event: 2023 3rd International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2023), 2023, Tangshan, China
Abstract
Aiming at the development and utilization of underground space in soft soil area, in order to study the influence of pipe jacking construction on the deformation disturbance of existing subway tunnels in soft soil area, the LSTM deep learning algorithm is used to train and verify the LSTM network model, and the settlement deformation of measuring points is predicted. The calculation results show that the variation law of the predicted value is very close to the measured value. The model predicts that the error range of the existing subway tunnel deformation during the pipe jacking construction process can be controlled at the millimeter level, within the allowable error range, and the implementation process is convenient and quick, without too much manual intervention. Under certain conditions, it can replace numerical calculations that are time-consuming and sensitive to grid and constitutive parameters.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shuai Tao, Jun-bo Zhang, Xi-bing Han, Jian-qiang Yu, Ling-zhi Xi, and Shu-yi Li "Prediction analysis of vertical displacement of pipe jacking crossing existing subway tunnel based on LSTM algorithm", Proc. SPIE 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023), 1275651 (28 July 2023); https://doi.org/10.1117/12.2686338
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Pipes

Data modeling

Deformation

Deep learning

Education and training

Engineering

Neural networks

Back to Top