JRMGE / Vol 14 / Issue 4

Article

Machine learning-based automatic control of tunneling posture of shield machine

Hongwei Huang, Jiaqi Chang, Dongming Zhang, Jie Zhang, Huiming Wu, Gang Li

Show More

a Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education, Tongji University, Shanghai, China
b Department of Geotechnical Engineering, Tongji University, Shanghai, China
c Shanghai Tunnel Engineering Co., Ltd., Shanghai, China


2022, 14(4): 1153-1164. doi:10.1016/j.jrmge.2022.06.001


Received: 2021-12-31 / Revised: 2022-05-02 / Accepted: 2022-06-14 / Available online: 2022-06-22

2022, 14(4): 1153-1164.

doi:10.1016/j.jrmge.2022.06.001


Received: 2021-12-31

Revised: 2022-05-02

Accepted: 2022-06-14

Available online: 2022-06-22


Abstract:

For a tunnel driven by a shield machine, the posture of the driving machine is essential to the construction quality and environmental impact. However, the machine posture is controlled by the experienced driver of shield machine by setting hundreds of tunneling parameters empirically. Machine learning (ML) algorithm is an alternative method that can let the computer to learn from the driver's operation and try to model the relationship between parameters automatically. Thus, in this paper, three ML algorithms, i.e. multi-layer perception (MLP), support vector machine (SVM) and gradient boosting regression (GBR), are improved by genetic algorithm (GA) and principal component analysis (PCA) to predict the tunneling posture of the shield machine. A set of the parameters for shield tunneling is extracted from the construction site of a Shanghai metro. In total, 53,785 pairwise data points are collected for about 373 d and the ratio between training set, validation set and test set is 3:1:1. Each pairwise data point includes 83 types of parameters covering the shield posture, construction parameters, and soil stratum properties at the same time. The test results show that the averaged R2 of MLP, SVM and GBR based models are 0.942, 0.935 and 0.6, respectively. Then the automatic control for the posture of shield tunnel is illustrated with an application example of the proposed models. The proposed method is proved to be helpful in controlling the construction quality with optimized construction parameters.

Download PDF:


Keywords: Shield tunneling, Machine learning (ML), Construction parameters, Optimization

Show Figure(s)


Share and Cite

Hongwei Huang, Jiaqi Chang, Dongming Zhang, Jie Zhang, Huiming Wu, Gang Li, 2022. Machine learning-based automatic control of tunneling posture of shield machine. J. Rock Mech. Geotech. Eng. 14 (4), 1153-1164.

Author(s) Information

Hongwei Huang

Hongwei Huang obtained his BSc degree in Mine Construction Engineering from Taiyuan University of Technology, China, in 1987, his Master degree in Geotechnical Engineering from Xi'an University of Science and Technology, China, in 1990 and his PhD in Structural Engineering from Tongji University (TJU), China, in 1993. He was employed by TJU as a lecturer in the Department of Geotechnical Engineering, College of Civil Engineering. He obtained the position of professor of TJU in 2000. He has been distinguished professor of “Changjiang Scholar” of the Ministry of Education of the People's Republic of China since 2014. His research interests cover risk management and assessment of tunnel and underground engineering, risk-based design method for lining structure of rock tunnel and supporting structure of deep excavation, dynamic information construction method of tunnel and underground engineering, longitudinal stability and long-term settlement of tunnel in soft soils, etc.