Modeling of Tunnel Boring Machine Performance Employing Random Forest Algorithm


Geotechnical and Geological Engineering, vol.41, no.7, pp.4205-4231, 2023 (ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 41 Issue: 7
  • Publication Date: 2023
  • Doi Number: 10.1007/s10706-023-02516-3
  • Journal Name: Geotechnical and Geological Engineering
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Aerospace Database, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Compendex, Computer & Applied Sciences, Geobase, INSPEC, Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.4205-4231
  • Keywords: Geological and geotechnical parameters, Random forest, Rate of penetration, TBM, Tunnel
  • Hacettepe University Affiliated: Yes


Prediction of tunnel boring machine (TBM) performance is still a challenging research subject in engineering geology, geotechnical engineering, and tunnel engineering communities. The longest railway tunnel with approximately 10 km, the Bahce-Nurdagi tunnel, was projected as twin tubes and TBM excavation. One of these tubes was successfully completed and the other is under construction. In this study, the geological and geotechnical parameters of the tunnel route and basic TBM parameters were used to predict the TBM performance. For the purpose of the study, a data set including 5334 cases was compiled. The analyses were performed in two phases, the first phase was performed employing only geological and geotechnical parameters while the basic TBM parameters were considered in the second phase analyses. Although the ANN and ANN-fuzzy models yielded acceptable results, the results clearly showed that the random forest algorithm was superior among all other methods for the data used. The results also revealed that the basic TBM parameters should be considered with advanced modeling techniques needed for a successful prediction model for TBM performance.