Traditional laboratory tests for measuring rock uniaxial compressive strength (UCS) are tedious and time-consuming. There is a pressing need for more effective methods to determine rock UCS, especially in deep mining environments under high <i>in-situ</i> stress. Thus, this study aims to develop an advanced model for predicting the UCS of rock material in deep mining environments by combining three boosting-based machine learning methods with four optimization algorithms. For this purpose, the Lead-Zinc mine in Southwest China is considered as the case study. Rock density, P-wave velocity, and point load strength index are used as input variables, and UCS is regarded as the output. Subsequently, twelve hybrid predictive models are obtained. Root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (<i>R<sup>2</sup></i>), and the proportion of the mean absolute percentage error less than 20% (A-20) are selected as the evaluation metrics. Experimental results showed that the hybrid model consisting of the extreme gradient boosting method and the artificial bee colony algorithm (XGBoost-ABC) achieved satisfactory results on the training dataset and exhibited the best generalization performance on the testing dataset. The values of <i>R<sup>2</sup></i>, A-20, RMSE, and MAE on the training dataset are 0.98, 1.0, 3.11 MPa, and 2.23 MPa, respectively. The highest values of <i>R<sup>2</sup></i> and A-20 (0.93 and 0.96), and the smallest RMSE and MAE values of 4.78 MPa and 3.76 MPa, are observed on the testing dataset. The proposed hybrid model can be considered a reliable and effective method for predicting rock UCS in deep mines.
Abstract Rockburst is a severe geological hazard that restricts deep mine operations and tunnel constructions. To overcome the shortcomings of widely used algorithms in rockburst prediction, this study investigates the ensemble trees, i.e., random forest (RF), extremely randomized tree (ET), adaptive boosting machine (AdaBoost), gradient boosting machine, extreme gradient boosting machine (XGBoost), light gradient boosting machine, and category gradient boosting machine, for rockburst estimation based on 314 real rockburst cases. Additionally, Bayesian optimization is utilized to optimize these ensemble trees. To improve performance, three combination strategies, voting, bagging, and stacking, are adopted to combine multiple models according to training accuracy. ET and XGBoost receive the best capabilities (85.71% testing accuracy) in single models, and except for AdaBoost, six ensemble trees have high accuracy and can effectively foretell strong rockburst to prevent large-scale underground disasters. The combination models generated by voting, bagging, and stacking perform better than single models, and the voting 2 model that combines XGBoost, ET, and RF with simple soft voting, is the most outstanding (88.89% testing accuracy). The performed sensitivity analysis confirms that the voting 2 model has better robustness than single models and has remarkable adaptation and superiority when input parameters vary or miss, and it has more power to deal with complex and variable engineering environments. Eventually, the rockburst cases in Sanshandao Gold Mine, China, were investigated, and these data verify the practicability of voting 2 in field rockburst prediction.
The fracture behavior of the disc specimens in the Brazilian test is closely related to the reliability and accuracy of the experimental results. To comprehensively investigate the effect of various loading methods and rock material types on the failure mechanism of the Brazilian discs, five different rock types tested with three typical loading methods were employed in this work. The digital image correlation (DIC) method was applied to record and analyze the strain and displacement field of the specimens during the loading process. Experimental results indicate that the peak load and deformation characteristics of the Brazilian discs are strongly affected by the loading types. The Brazilian test with the Chinese standard is evidently not suitable for measuring the tensile strength of rocks, and the other two testing methods may lead to an invalid failure mode for rock materials with high stiffness and tensile to compressive strength ratio. Furthermore, it revealed that the maximum equivalent stress point of a disc specimen is co-controlled by the material stiffness and its tensile–compression ratio. The present work shows that it is necessary to select a suitable loading configuration for each rock type in the Brazilian test.
Rock fragmentation is an important evaluation indicator for field blasting operations. This paper applies a deep learning-based method, the Segment Anything Model (SAM), to automatically segment rock fragments. To review the SAM’s segmentation performance, 83 images of rock fragment collected from the mine site were used as the test dataset. Pixel-level accuracy (PA), intersection over union (IOU), and dice coefficient (Dice) were employed to evaluate the model pixel-level segmentation performance. The results showed that the SAM exhibited excellent segmentation performance on the test data (PA = 94.5%, IOU = 94.4%, Dice = 95.4%). The coefficient of determination (R2) values for the 50% and 80% passing sizes (X50 and X80) were 0.970 and 0.991, respectively, which demonstrated that the SAM could achieve high precision measurement of rock fragmentation. Additionally, the effectiveness of the SAM was further evaluated by comparing it to commercial software, and the generalizability of the SAM was verified on two other datasets. The findings revealed that the SAM not only outperformed the Split-Desktop V 4.0 on the test dataset but also achieved comparable accuracy to previous studies on the two other datasets. The SAM could be regarded as a useful tool to provide fast and accurate feedback for field blasting.
The rockburst prediction becomes more and more challenging due to the development of deep underground projects and constructions. Increasing numbers of intelligent algorithms are used to predict and prevent rockburst. This paper investigated the drawbacks of neural networks in rockburst prediction, and aimed at these shortcomings, Bayesian optimization and the synthetic minority oversampling technique + Tomek Link (SMOTETomek) were applied to efficiently develop the feedforward neural network (FNN) model for rockburst prediction. In this regard, 314 real rockburst cases were collected to establish a database for modeling. The database was divided into a training set (80%) and a test set (20%). The maximum tangential stress, uniaxial compressive strength, tensile strength, stress ratio, brittleness ratio, and elastic strain energy were selected as input parameters. Bayesian optimization was implemented to find the optimal hyperparameters in FNN. To eliminate the effects of imbalanced category, SMOTETomek was adopted to process the training set to obtain a balanced training set. The FNN developed by the balanced training set received 90.48% accuracy in the test set, and the accuracy improved 12.7% compared to the imbalanced training set. For interpreting the FNN model, the permutation importance algorithm was introduced to analyze the relative importance of input variables. The elastic strain energy was the most essential variable, and some measures were proposed to prevent rockburst. To validate the practicability, the FNN developed by the balanced training set was utilized to predict rockburst in Sanshandao Gold Mine, China, and it had outstanding performance (accuracy 100%).
Abstract Based on three‐dimensional digital image correlation (3D‐DIC) technique, the deformation behavior, damage and fracture characteristics of the granite specimens have been tested and observed by the short core in compression (SCC) method. The test results show that (1) the damage degree of rock in the region of interest (ROI) increases with axial stress. Before peak stress, damage factor based on apparent principal strain increases slowly, then rises rapidly; (2) relative displacements in both horizontal and vertical directions are observed, indicating that the fracture mode for SCC specimens subjected to uniaxial compression is the tensile‐shear mixed mode fracture; (3) new fracture initiates from the middle part of the expected shear fracture band (ESFB) then propagates along the loading direction. A dominant macro‐fracture, linking up the tips of two notches, eventually forms. Meanwhile, a calculation method based on the energy conservation law for the fracture energy of SCC specimens is proposed. The fracture energy of granite is estimated as 1760.4 J/m 2 .
Abstract In the field of deep mining engineering, it poses a challenge to promptly determine the mechanical properties of rocks under poor geological conditions through in-situ tests. However, the indirect determination of uniaxial compressive strength (UCS) of rocks can be achieved through the point load strength index (PLSI) test on irregular samples. In the present study, laboratory uniaxial compressive and field PLSI tests were carried out on irregular ore and rock blocks extracted through mechanical mining methods from a stope at a lead–zinc mine in Yunnan Province, China, with a depth of approximately 1000 m. The effects of mechanical excavation and drilling-blasting methods on the PLSI of rocks and ores are compared. It is found that there are significant differences in the point load strength indexes obtained by different excavation methods, and the I s (50) obtained after the mechanical excavation method approximates the actual value of ore and surrounding rocks. Two correction methods were utilized to obtain the point load strength indexes I s (50)-1 and I s (50)-2 of irregular rock samples. The correlation factors ( k ) linking I s (50) to UCS and Brazilian splitting strength are derived based on testing results. The findings indicate that using the conversion factor ( k ) recommended by ISRM to predict the UCS of rocks may significantly underestimate the actual strength of rocks in intricate mining environments. This study can serve as a benchmark for analogous deep mining projects.
