Journal
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
Volume 118, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.tust.2021.104196
Keywords
TBM excavation; Parameter prediction framework; Working phase extraction; Machine learning; Rock-machine interaction
Funding
- National Key Basic Research and Development Program of China [2018YFB2101000]
- Special Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China [41827807]
- China Scholarship Council [201906260211]
Ask authors/readers for more resources
A comprehensive parameter prediction framework has been proposed in this study to effectively predict critical TBM operational parameters in hard rock tunneling. The framework was validated in a water conveyance tunnel project in China, demonstrating good predictive performance. Compared to traditional methods, the introduced TBM working phase extraction method helps accurately capture data characteristics.
The adjustment of TBM operational parameters with regard to different strata significantly affects the safety, time and cost in tunnel construction. To assist TBM operation, this paper develops an integrated parameter prediction framework for hard rock tunneling based on combined pre-construction geological information and TBM operational data. The method involves three steps: extraction of TBM working phases based on operational data, selection of input feature from geological information and operational data, and development of prediction model using four machine learning algorithms. The proposed framework has been demonstrated and verified by applying it to a water conveyance tunnel project in China. The results show that the proposed framework performs well in predicting three critical TBM operational parameters, thrust, cutterhead torque and net advance rate, with the determination coefficient R-2 all exceeding 0.8. A comparison study proves that the introduced TBM working phase extraction method is conductive for capturing data characteristics and making predictions, because it unveils the complex rock-machine interaction information underlying the operational data.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available