High-Efficiency TBM Tunnelling and Intelligent Control in Deep and Complex Geological Formations

With the rapid advancement of major engineering projects in China, including deeply buried long-distance tunnels, inter-basin water-transfer schemes, and deep resource development, tunnel boring machine (TBM) construction is increasingly extending into environments characterized by kilometre-scale overburden and highly complex geological conditions. Extreme conditions, such as high in situ stress, elevated ground temperature, high gas pressure, interbedded soft and hard rock, and fault-fracture zones, severely constrain rock-breaking efficiency and tunnelling safety. Consequently, hazards and operational failures, including rockbursts, large deformation, TBM jamming, and abnormal cutter damage, have become increasingly frequent, rendering the conventional experience-driven construction approach unsustainable. Meanwhile, the rapid development of artificial intelligence, big data, and digital twin technologies has created new opportunities for intelligent perception, autonomous decision-making, and adaptive control throughout the entire TBM tunnelling process. In early 2026, a TBM in China completed 200 m of continuous excavation without human intervention, marking an important transition of intelligent control from theoretical research to engineering application. Nevertheless, several fundamental scientific and technical challenges remain unresolved, including the poorly understood rock–machine interaction mechanism in deep and complex formations, the lack of effective real-time sensing and information-acquisition methods, and the limited generalization capability of intelligent control models. Against this background, this Special Issue on “High-Efficiency TBM Tunnelling and Intelligent Control in Deep and Complex Geological Formations” aims to bring together cutting-edge theories, advanced methodologies, and innovative research achievements. Such a systematic collection is of major strategic significance for promoting intelligent construction in deep underground engineering.

This Special Issue focuses on the full-chain intelligence of TBM tunnelling under deep and extreme geological conditions, encompassing sensing, decision-making, control, and operation and maintenance. It covers the fine characterization of geological formations, self-optimization of tunnelling parameters, autonomous tunnelling, intelligent hazard prevention and control, and adaptability-oriented TBM design, with the aim of facilitating the transition of TBM construction toward a data-driven and intelligent autonomous paradigm. 

Topics of interest include, but are not limited to:

1. Fine-Scale Characterization and Advanced Geological Prediction in Deep and Complex Formations

2. Intelligent TBM Control and Autonomous Tunnelling

3. Rock–Machine Interaction Mechanisms and Rock-Breaking Efficiency under Deep Underground Conditions

4. Hazard Development Mechanisms and Intelligent Prevention and Control during Deep TBM Tunnelling

5. Adaptability-Oriented Design and Life-Cycle Management of TBM Equipment for Deep Geological Formations

Original Research Papers, State-of-the-Art Review, Commentary, Correspondence, or Short Communications are all welcome.

Guest Editor:

• Wei Wu, Associate Professor, Nanyang Technological University
• Bingqian Yan, Associate Professor, University of Science and Technology Beijing
• Wenbo Zheng, Associate Professor, University of Northern British Columbia
• Zhenliang Zhou, Associate Professor, Beijing Jiaotong University

Submission Guidelines:

Manuscripts should be submitted online 

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process.

No Article Process Cost (APC) is required for articles.

Please contact the Guest Editors or DRE editorial office (deepre@mail.neu.edu.cn) for any question or query on this SI.

Submission Deadline: February 28, 2027