Chen-hao Zhang , Yu Wang , Xu Li , Kostas Senetakis
{"title":"Bayesian sequential learning of rock mass classifications along tunnel trajectory using TBM operational data and geo-data spatial correlation","authors":"Chen-hao Zhang , Yu Wang , Xu Li , Kostas Senetakis","doi":"10.1016/j.tust.2025.106709","DOIUrl":null,"url":null,"abstract":"<div><div>During tunnel construction by a tunnel boring machine (TBM), it is a critical task to repeatedly predict rock mass classifications ahead of the tunnel face for each excavation step as the TBM advances along the designed tunnel trajectory. Such a prediction process is referred to as sequential prediction of rock mass classifications in this study. Previous studies have demonstrated the values of TBM operational data for predicting rock mass classifications using machine learning methods. However, although both TBM data and rock mass classifications are spatial data (i.e., with specific spatial coordinates along the tunnel trajectory), spatial correlation of geo-spatial data has not been utilized in existing machine learning models. To leverage geo-data spatial correlation, a data-driven Bayesian sequential learning method is proposed in this study for sequentially predicting rock mass classifications along the TBM tunnel trajectory. The proposed Bayesian method effectively integrates TBM data, rock mass classifications, and their corresponding spatial coordinates and correlation from completed tunnel segments for improving model fidelity. The proposed method is illustrated using data from the Songhua River water conveyance project in China and performs well.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"163 ","pages":"Article 106709"},"PeriodicalIF":6.7000,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tunnelling and Underground Space Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0886779825003475","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
During tunnel construction by a tunnel boring machine (TBM), it is a critical task to repeatedly predict rock mass classifications ahead of the tunnel face for each excavation step as the TBM advances along the designed tunnel trajectory. Such a prediction process is referred to as sequential prediction of rock mass classifications in this study. Previous studies have demonstrated the values of TBM operational data for predicting rock mass classifications using machine learning methods. However, although both TBM data and rock mass classifications are spatial data (i.e., with specific spatial coordinates along the tunnel trajectory), spatial correlation of geo-spatial data has not been utilized in existing machine learning models. To leverage geo-data spatial correlation, a data-driven Bayesian sequential learning method is proposed in this study for sequentially predicting rock mass classifications along the TBM tunnel trajectory. The proposed Bayesian method effectively integrates TBM data, rock mass classifications, and their corresponding spatial coordinates and correlation from completed tunnel segments for improving model fidelity. The proposed method is illustrated using data from the Songhua River water conveyance project in China and performs well.
期刊介绍:
Tunnelling and Underground Space Technology is an international journal which publishes authoritative articles encompassing the development of innovative uses of underground space and the results of high quality research into improved, more cost-effective techniques for the planning, geo-investigation, design, construction, operation and maintenance of underground and earth-sheltered structures. The journal provides an effective vehicle for the improved worldwide exchange of information on developments in underground technology - and the experience gained from its use - and is strongly committed to publishing papers on the interdisciplinary aspects of creating, planning, and regulating underground space.