Rock bolt support systems are central to ground control in tunnels, mines, underground excavations, and slope-stabilization projects, but their design remains limited by geological uncertainty, installation variability, sparse long-term monitoring, and fragmented digital records. This systematic review examines how artificial intelligence (AI), AI-assisted optimization, monitoring, building information modelling (BIM), digital-twin concepts, and generative design and optimization (GD&O) where directly evidenced are being connected in rock bolt support research. A Web of Science Core Collection search completed on 3 July 2026 identified 137 records from 2015 to 2026. After six conference papers were excluded, 131 journal records (127 articles and four reviews) were retained for bibliometric mapping and thematic synthesis. VOSviewer analysis and manual coding show a mature base in numerical modelling, monitoring, optimization, and materials/durability research, whereas direct BIM and digital-twin applications remain sparse. AI and optimization are increasingly used for parameter selection, bolt detection, compliance checking, and capacity prediction, but most studies rely on small datasets, limited cross-site validation, and weak links to as-built records. The review proposes a staged pathway from digitization and data integration to supervised optimization and guarded autonomy, positioning rock bolt systems as a testbed for auditable, human-governed AI-for-engineering workflows rather than fully autonomous design.
No takes yet. Share an insight, caveat, or question.
Ping et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: