Prediction model of tunnel boring machine performance by ensemble neural networks

Zhiye Zhao, Qiuming Gong, Yun Zhang, Jian Zhao

Research output: Contribution to journalArticleResearchpeer-review

61 Citations (Scopus)


The penetration rate of a tunnel boring machine (TBM) depends on many factors ranging from the machine design to the geological properties. Therefore it may not be possible to capture this complex relationship in an explicit mathematical expression. In this paper, we propose an ensemble neural network (ENN) to predict TBM performance. Based on site data, a four-parameter ENN model for the prediction of the specific rock mass boreability index is constructed. Such a neural-network-based model has the advantages of taking into account the uncertainties embedded in the site data and making appropriate inferences using very limited data via the re-sampling technique. The ENN-based prediction model is compared with a non-linear regression model derived from the same four parameters. The ENN model outperforms the non-linear regression model.

Original languageEnglish
Pages (from-to)123-128
Number of pages6
JournalGeomechanics and Geoengineering
Issue number2
Publication statusPublished - 1 Jun 2007
Externally publishedYes


  • Ensemble neural network
  • Specific rock mass boreability index
  • Tunnel boring machine performance

Cite this