Rockburst is an extremely hazardous geological disaster. In order to accurately predict the hazardous degree of rockbursts, this paper proposes eight new classification models for predicting the intensity level of rockbursts based on intelligent optimisation algorithms and deep learning techniques and collects 287 sets of real rockburst data to form a sample database, in which six quantitative indicators are selected as feature parameters. In order to validate the effectiveness of the constructed eight machine learning prediction models, the study selected Accuracy, Precision, Recall and F1 Score to evaluate the prediction performance of each model. The results show that the NGO-CNN-BiGRU-Attention model has the best prediction performance, with an accuracy of 0.98. Subsequently, engineering validation of the model is carried out using eight sets of real rockburst data from Daxiangling Tunnel, and the results show that the model has a strong generalisation ability and can satisfy the relevant engineering applications. In addition, this paper also uses SHAP technology to quantify the impact of different factors on the rockburst intensity level and found that the elastic strain energy index and stress ratio have the greatest impact on the rockburst intensity level.

Signal denoising is one of the most important issues in signal processing, and various techniques have been proposed to address this issue. A combined method involving wavelet decomposition and multiscale principal component analysis (MSPCA) has been proposed and exhibits a strong signal denoising performance. This technique takes advantage of several signals that have similar noises to conduct denoising; however, noises are usually quite different between signals, and wavelet decomposition has limited adaptive decomposition abilities for complex signals. To address this issue, we propose a signal denoising method based on ensemble empirical mode decomposition (EEMD) and MSPCA. The proposed method can conduct MSPCA-based denoising for a single signal compared with the former MSPCA-based denoising methods. The main steps of the proposed denoising method are as follows: First, EEMD is used for adaptive decomposition of a signal, and the variance contribution rate is selected to remove components with high-frequency noises. Subsequently, the Hankel matrix is constructed on each component to obtain a higher order matrix, and the main score and load vectors of the PCA are adopted to denoise the Hankel matrix. Next, the PCA-denoised component is denoised using soft thresholding. Finally, the stacking of PCA- and soft thresholding-denoised components is treated as the final denoised signal. Synthetic tests demonstrate that the EEMD-MSPCA-based method can provide good signal denoising results and is superior to the low-pass filter, wavelet reconstruction, EEMD reconstruction, Hankel–SVD, EEMD-Hankel–SVD, and wavelet-MSPCA-based denoising methods. Moreover, the proposed method in combination with the AIC picking method shows good prospects for processing microseismic waves.

Construction-induced ground settlement is a serious hazard in underground tunnel construction. Accurate ground settlement prediction has great significance in ensuring the surface building’s stability and human safety. To that end, 148 sets of data were collected from the Singapore Circle Line rail traffic project containing seven defining parameters to create a database for predicting ground settlement. These parameters are the tunnel depth (H), the tunnel advance rate (AR), the EPB earth pressure (EP), the mean SPTN value from the soil crown to the surface (Sm), the mean water content of the soil layer (MC), the mean modulus of elasticity of the soil layer (E), and the grout pressure used for injecting grout into the tail void (GP). Three hybrid models consisting of random forest (RF) and three types of meta-heuristics, Ant Lion Optimizier (ALO), Multi-Verse Optimizer (MVO), and Grasshopper Optimization Algorithm (GOA), were developed to predict ground settlement. Furthermore, the mean absolute error (MAE), the mean absolute percentage error (MAPE), the coefficient of determination (R²) and the root mean square error (RMSE) were used to assess predictive performance of the constructed models for predicting ground settlement. The evaluation results demonstrated that the GOA-RF with a population size of 10 has achieved the most outstanding predictive capability with the indices of MAE (Training set: 2.8224; Test set: 2.3507), MAPE (Training set: 40.5629; Test set: 38.5637), R² (Training set: 0.9487; Test set: 0.9282), and RMSE (Training set: 4.93; Test set: 3.1576). Finally, the sensitivity analysis results indicated that MC, AR, Sm, and GP have a significant impact on ground settlement prediction based on the GOA-RF model.

Slabbing failure and strain rock burst are the main failure patterns during the excavation and construction phases of deep tunnels in hard and brittle rock, which cause unexpected equipment damage and casualties. This study presents a numerical simulation with an unloading central hole within a hard rock specimen in the laboratory scale. A combined finite element/discrete element method (FEM/DEM) reproduces the crack initiation, propagation, and coalescence around the central hole during the entire failure process. The influence of sectional shapes, unloading rates of holes, and in situ stresses on the failure characteristics and mechanical response of typical hard and brittle rocks were investigated by analysis of the failure pattern, displacement distribution (average velocity) of monitoring elements, and released strain energy value. The numerical results indicate that the sectional shapes, unloading rates, and in situ stresses have a significant impact on the severity of destruction and failure range in hard rock under the excavation unloading conditions. Slabbing failure (stable failure) is always the dominant failure pattern around a circular hole, which shows higher bearing capacities and self‐stabilization. With the increase in unloading rates, more visible cracks are generated around the holes, and the displacement and average velocity of discrete blocks are further raised. This is particularly evident in rock specimens with holes having vertical walls, leading to intense unstable failure (strain rock burst) accompanied by a large amount of strain energy released. In situ stresses affect considerably the stability of the surrounding rock during the excavation unloading process. With constant in situ stress, the order of destruction severity around the central hole according to its sectional shape is cube > trapezoid > U‐shape > ellipse > circle. The destruction intensity is further aggravated with the increase in lateral pressure coefficient, and the failure regions are always observed in the roof and floor of the central hole. This study confirms that strain rock burst tends to be induced in hard and brittle rock tunnels with polygonal roadway section under high unloading rates and lateral pressure coefficients.

Energy is an important research parameter in rock mechanics. To explore the law of energy evolution of coal, a one‐time loading and unloading test under uniaxial compression was conducted on coal taken from four different coal mines. By utilizing the area integral method, the total input, elastic, and dissipated energy densities in coal at different unloading levels were calculated. The correlation between various energy densities and the evolution law of energy density with different unloading levels was attained. The peak strengths of the coal slowly declined with an increasing unloading level, which conforms to the relation of a linearly decreasing function. The energy dissipation rate has nonlinear characteristics, and the shape of the dissipation rate fitting curve changed from an upper concave to a downward concave with increasing strength. In all the coal samples, the energy density grew nonlinearly with the unloading level. Moreover, the growth rate of the total energy density was the highest, followed by the growth rates of the elastic and dissipated energy densities. All ratios of the elastic and dissipated energy densities to the total input energy density and the ratio of the dissipated energy density to the elastic energy density were constant. As the strength increased, the input energy and the elastic energy density increased at a faster rate, and they observed the same law. There is an insignificant relationship between the degree of destruction of the coal and the level of unloading. Energy is a major factor that drives the failure of a test piece, but this is not the main factor that determines the degree of damage to the test piece.