Advances in artificial intelligence and digital twin for tunnel boring machines
Guangyuan Liu, Yuanshou Tang, Huiping Zhang, Runqi Li, Hongmei Wang, Bright Liu, Siyong Zhang, Hongtao Zhu, Dun Liu, Sai Ma
Abstract
Abstract The deep integration of artificial intelligence (AI) and tunnel boring machine (TBM) has emerged as a critical research direction in intelligent tunnel construction. However, variable geological conditions, numerous electromechanical systems, and complex rock-machine interactions pose significant challenges to its implementation. This paper systematically reviews the latest research advances of AI in the TBM field, focusing on key technologies such as environmental perception, automated control, and predictive health management. Additionally, an intelligent TBM system architecture based on Digital Twin (DT) technology is proposed. The architecture integrates and coordinates a perception layer, an analysis layer, a decision-making layer, and an execution layer, enabling full-process autonomous control from environmental perception to intelligent decision-making. Finally, several critical issues and prospects in developing intelligent TBM, including data integration, model interpretability, and computational efficiency are discussed. This study aims to provide theoretical references and practical guidance for researchers in related fields, further promoting the in-depth application and development of digital twin technology in the intelligent TBM domain.