Scholarlink

<p>This paper reviewed the geological exploration, inference, and prediction methods in tunnelling. We summarised many types of geological exploration equipment, which can directly obtain the geotechnical parameters and provide the point data for geological estimation and prediction at various measured points. Then, the geological estimation approaches based on statistical-probabilistic methods were compared to show their capability to evaluate the geological conditions between different boreholes. Additionally, we reviewed various artificial intelligence (AI) methods applied to establish the relationship between shield parameters and geotechnical parameters for the geological types classification, geotechnical parameters prediction, and real-time geological feature identification ahead of the shield cutterhead. Finally, we proposed the next-generation intelligent geological exploration framework for smart shield tunnelling. By implementing the space-air-ground-machine intelligent monitoring and detection system, the construction 4.0 system is established based on Digital Twins, Internet of Things (IoT) techniques, Building Information Model (BIM) technology and Physics-informed neural network (PINN) prediction models. The engineers can adjust tunelling parameters in various formations using a Geographic Information System (GIS) platform and virtual reality technology to improve the efficiency and safety of smart shield tunnelling.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Geological information in shield tunnelling: exploration, estimation, prediction, and perspectives

  • 期刊论文

  • 发表日期：

    2026年5月9日

查看全文
  • Tao Yan,
  • Shui-Long Shen,
  • Annan Zhou,
  • Zhen-Yu Yin

摘要

This paper reviewed the geological exploration, inference, and prediction methods in tunnelling. We summarised many types of geological exploration equipment, which can directly obtain the geotechnical parameters and provide the point data for geological estimation and prediction at various measured points. Then, the geological estimation approaches based on statistical-probabilistic methods were compared to show their capability to evaluate the geological conditions between different boreholes. Additionally, we reviewed various artificial intelligence (AI) methods applied to establish the relationship between shield parameters and geotechnical parameters for the geological types classification, geotechnical parameters prediction, and real-time geological feature identification ahead of the shield cutterhead. Finally, we proposed the next-generation intelligent geological exploration framework for smart shield tunnelling. By implementing the space-air-ground-machine intelligent monitoring and detection system, the construction 4.0 system is established based on Digital Twins, Internet of Things (IoT) techniques, Building Information Model (BIM) technology and Physics-informed neural network (PINN) prediction models. The engineers can adjust tunelling parameters in various formations using a Geographic Information System (GIS) platform and virtual reality technology to improve the efficiency and safety of smart shield tunnelling.