An integrated parameter prediction framework for intelligent TBM excavation in hard rock

Xin Wang, Hehua Zhu, Mengqi Zhu, Lianyang Zhang, J. Woody Ju

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

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 R2 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.

Original languageEnglish (US)
Article number104196
JournalTunnelling and Underground Space Technology
Volume118
DOIs
StatePublished - Dec 2021

Keywords

  • Machine learning
  • Parameter prediction framework
  • Rock-machine interaction
  • TBM excavation
  • Working phase extraction

ASJC Scopus subject areas

  • Building and Construction
  • Geotechnical Engineering and Engineering Geology

Fingerprint

Dive into the research topics of 'An integrated parameter prediction framework for intelligent TBM excavation in hard rock'. Together they form a unique fingerprint.

Cite this