Answers are grounded in this paper and cite their sources.
Rockbursts are frequently encountered during the excavation of deep underground rock masses, posing serious threats to personnel, equipment, and tunnel integrity. They have become a critical bottleneck for safe and efficient tunnelling operations. Therefore, it is essential to early warn rockbursts based on precursory microseismic activities in engineering practices. This paper proposes an intelligent early warning method for predicting rockbursts in deeply buried tunnels, utilising multiple indices that characterise the temporal, spatial and intensity features of microseismic events captured through monitoring systems. Using the Jinping II Hydropower Station as a case study, a microseismic monitoring system was first deployed to collect microseismic activities during tunnelling. The inherent relationship between monitored microseismic activities and subsequent rockbursts was then investigated through innovative neural network models and adaptive optimisation algorithms. Based on this analysis, a multi-index early-warning evaluation system was developed, integrating time, space and intensity parameters. This system was subsequently applied to back analyse monitored data and issue early warnings for rockbursts during deep tunnelling. It is concluded that the time-space-intensity multi-indices early warning method can objectively predict rockbursts according to an integrated early warning index, which accounts for not only the membership degree of each index but also its prediction efficiency.
No takes yet. Share an insight, caveat, or question.
Kang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: