Hydropower is one of the most important renewable energy sources. However, the safe construction of hydropower stations is seriously affected by disasters like rockburst, which, in turn, restricts the sustainable development of hydropower energy. In this paper, a method for rockburst prediction in the deep tunnels of hydropower stations based on the use of real-time microseismic (MS) monitoring information and an optimized probabilistic neural network (PNN) model is proposed. The model consists of the mean impact value algorithm (MIVA), the modified firefly algorithm (MFA), and PNN (MIVA-MFA-PNN model). The MIVA is used to reduce the interference from redundant information in the multiple MS parameters in the input layer of the PNN. The MFA is used to optimize the parameter smoothing factor in the PNN and reduce the error caused by artificial determination. Three improvements are made in the MFA compared to the standard firefly algorithm. The proposed rockburst prediction method is tested by 93 rockburst cases with different intensities that occurred in parts of the deep diversion and drainage tunnels of the Jinping II hydropower station, China (with a maximum depth of 2525 m). The results show that the rates of correct rockburst prediction of the test samples and learning samples are 100% and 86.75%, respectively. However, when a common PNN model combined with monitored microseismicity is used, the related rates are only 80.0% and 61.45%, respectively. The proposed method can provide a reference for rockburst prediction in MS monitored deep tunnels of hydropower projects.

With the increasing number of deep rock engineering projects, many different types of tunnels have emerged, such as cross-tunnels. These tunnels intersect with each other in rock, which causes potential safety hazards. We must analyze the stability of the surrounding rock, to ensure worker safety. This article presents a method for dynamically assessing the stability of the surrounding rock in deep-buried cross-tunnels. The method consists of two main analysis steps: (1) P-wave velocity field inversion; and (2) Stability analysis of the surrounding rock. The P-wave velocity field inversion involves inverting the S-wave velocity field by Rayleigh wave and inverting the P-wave velocity field by adjoint state traveltime tomography. Then, a method of stability analysis is proposed which is used to update the mechanical properties of the rock (based on the continuously updated wave velocity field). The elastic modulus of the surrounding rock is approximated throughout the excavation process. CASRock V1.0 (Cellular Automation Software for engineering Rockmass fracturing processes) is used to assess rock damage via the equivalent plastic shear strain and local energy release rate. The new method is used to analyze the stability of a new tunnel excavated in Jinping (in China). The results reveal the severity and spatial distribution of the damage caused. The yield depth is concentrated near the sidewalls, while the top and bottom of the tunnel exhibit a smaller depth. The yield depths present a particular pattern of change (high–low–high–low) with increasing distance from tunnel #2. Finally, this research enriches our understanding of excavating deep cross-tunnels and makes an important contribution to improving worker safety in deep cross-tunnels.

Microseismic monitoring is an effective and widely used technology for dynamic fault disaster early warning and prevention in deep-buried hard rock tunnels. However, the insufficient understanding of the distribution of native faults poses a major challenge to yielding precise early warnings of disasters using an MS (Microseismic Monitoring System). Velocity field inversion is a reliable means to reflect fault information, and there is an urgent need to establish a real-time velocity field inversion method during tunnel excavation. In this paper, a method based on an MS is proposed to achieve the inversion of the velocity field in the monitoring area using microseismic event and excavation blasting data. The velocity field inversion method integrates the reflected wave ray-tracing method based on PSO (Particle Swarm Optimization) theory and FWI (Full-Waveform Inversion) theory. The accuracy of the proposed velocity inversion method was verified by various classic numerical simulation cases. In numerical simulations, the robustness of our method is evident in its ability to identify anomalous structural surfaces and velocity discontinuities ahead of the tunnel face.

Rock mechanical parameters are essential to design, stability analysis, and safety construction in rock underground engineering. Inverse analysis is an effective tool for determining the mechanical properties of rock masses in deep underground engineering. Given that conventional methods cannot accurately solve such problems, proxy models are widely used. This study proposes a novel inverse analysis framework integrating the CatBoost algorithm and Simplicial Homology Global Optimization (SHGO) to overcome limitations of conventional methods. CatBoost efficiently constructs a proxy model, replacing time-consuming numerical simulations. SHGO then searches for optimal rock parameters using this proxy. The method was validated in the D2 laboratory of the second phase project of the Jinping Underground Laboratory (CJPL–II) in China and applied to invert surrounding rock parameters using field displacement monitoring data and numerical simulations. Investigations examined inversion accuracy under varying excavation steps, numbers of monitoring points, and wider parameter ranges. Results show inverted parameters converge towards true values as excavation steps and monitoring points increase. Crucially, even within the most extensive parameter range, relative errors between inversion results and true values remain below 20%. This integrated CatBoost–SHGO framework provides a feasible, scientific, and promising approach for determining rock mechanical parameters.