• Energy Research

Rock strength, specifically the uniaxial compressive strength (UCS), is a critical parameter mostly used in the effective and sustainable design of tunnels and other engineering structures. This parameter is determined using direct and indirect methods. The direct methods involve acquiring an NX core sample and using sophisticated laboratory procedures to determine UCS. However, the direct methods are time-consuming, expensive, and can yield uncertain results due to the presence of any flaws or discontinuities in the core sample. Therefore, most researchers prefer indirect methods for predicting rock strength. In this study, UCS was predicted using seven different artificial intelligence techniques: Artificial Neural Networks (ANNs), XG Boost Algorithm, Random Forest (RF), Support Vector Machine (SVM), Elastic Net (EN), Lasso, and Ridge models. The input variables used for rock strength prediction were moisture content (MC), P-waves, and rebound number (R). Four performance indicators were used to assess the efficacy of the models: coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE). The results show that the ANN model had the best performance indicators, with values of 0.9995, 0.2634, 0.0694, and 0.1642 for R2, RMSE, MSE, and MAE, respectively. However, the XG Boost algorithm model performance was also excellent and comparable to the ANN model. Therefore, these two models were proposed for predicting UCS effectively. The outcomes of this research provide a theoretical foundation for field professionals in predicting the strength parameters of rock for the effective and sustainable design of engineering structures

Rock failure is the root cause of geological disasters such as slope failure, civil tunnel collapse, and water inrush in roadways and mines. Accurate and effective monitoring of the loaded rock failure process can provide reliable precursor information for water inrushes in underground engineering structures such as in mines, civil tunnels, and subways. The water inrush may affect the safe and efficient execution of these engineering structures. Therefore, it is essential to predict the water inrush effectively. In this paper, the water inrush process of the roadway was simulated by laboratory experiments. The multiparameters such as strain energy field and infrared radiation temperature field were normalized based on the normalization algorithm of linear function transformation. On the basis of analyzing the variation characteristics of the original parameters, the evolution characteristics after the parameters normalization algorithm were studied, and the precursor of roadway water inrush was predicted comprehensively. The results show that the dissipation energy ratio, the infrared radiation variation coefficient (IRVC), the average infrared radiation temperature (AIRT), and the variance of successful minor infrared image temperature (VSMIT) are all suitable for the prediction of roadway water inrushes in the developing face of an excavation. The intermediate mutation of the IRVC can be used as an early precursor of roadway water inrush in the face of an excavation that is being developed. The inflection of the dissipation energy ratio from a declining amount to a level value and the mutation of VSMIT during rock failure can be used as the middle precursor of roadway water inrush. The mutation of AIRT and VSMIT after rock failure can be used as the precursor of roadway imminent water inrush. Combining with the early precursor and middle precursor of roadway water inrush, the graded warning of “early precursor–middle precursor–final precursor” of roadway water inrush can be obtained. The research results provide a theoretical basis for water inrush monitoring and early warning in the sustainable development of mine, tunnel, shaft, and foundation pit excavations.

It is significant to monitor the leakage at the joints of the diaphragm walls of subway station foundation pits to check the weak links in the waterproof quality of the diaphragm wall structure. It is essential to take effective waterproof measurements timely to improve the overall waterproof quality of the diaphragm wall in the foundation pit to prevent accidents and reduce the operation and maintenance costs. This paper used ground penetrating radar (GPR) to detect the Lishan North Road Station section of Jinan Rail Transit Line R2 during construction. The abnormal waveform image is obtained after processing radar detection data with Reflexw software. This abnormal waveform image is used to identify the abnormal area. In order to accurately predict the location of leakage at the joint of diaphragm wall, MATLAB is used to calculate the average wave velocity amplitude and single channel signal of the electromagnetic wave velocity of geological radar at different mileages and draw the trend chart of average wave velocity amplitude with mileage and the corresponding relationship curve of electromagnetic wave amplitude and depth of radar. It is proposed that sudden changes in the area of the average wave velocity amplitude cause a change in the trend chart. Furthermore, the radar electromagnetic wave velocity amplitude curve is taken as the area where seepage may occur at the joints of the diaphragm wall, so as to determine the corresponding mileage and depth of the leakage area. On this basis, the grey correlation analysis for the analysis of the source of the water leakage at the joints of the diaphragm wall of the subway foundation pit is proposed. The research results show that the leakage water at the joints of the diaphragm wall of the subway foundation pit is not connected to the rivers around the foundation pit, which confirms that the construction of the subway station has not affected the groundwater resources around the station. The proposed approach has successfully predicted the location of the foundation pit leakage disaster and has been verified on the project site. The research results provide a reference for the monitoring and early warning of leakage at the joints of diaphragm walls in foundation pits with similar geological conditions.

The risk of a coal burst rises with the excavation depth and other mining-related activities. These devastating coal burst activities are a major concern during deep coal mining. During such activities, the loading rate is a major cause of damage. Different indexes, including the elastic strain modulus index (Wet), bursting energy index (Ke), dynamic failure time index (DT), and compressive strength index (Rc), are used for coal bursting intensity; however, the loading rate and damage factors are not included in these indexes. In this study, a new coal bursting liability index called the elastic modulus damage index (EMDI) was developed using rock damage variables and the elastic strain modulus index, and is based on energy evolution characteristics under different loading rates. The results of this new index were compared with the existing indexes, and their range was proposed to evaluate coal bursting liability. The EDMI shows a positive polynomial second order degree relationship with Wet and Ke, having a determination factor of 0.99, while DT shows a negative polynomial second order degree relationship with a determination factor of 0.94. The EDMI and Rc show a positive power relationship having a determination factor of 0.99. The relationships with other indexes revealed that the EDMI can be effectively used in evaluating the coal bursting liabilities in different stress environments.

Coal mining often causes periodic disruption in the rock mass around the stope. The study of the deformation and failure characteristics of cyclic loading and unloading sandstone is very critical for gaining a thorough understanding of the mechanisms of rock damage, degradation, and failure. This kind of investigation is very helpful in determining the precursors of rock failure and the instability of engineering structures. In this research study, the properties of acoustic emission and infrared radiation of cyclic loading and unloading sandstone are explored using a cyclic loading and unloading sandstone experiment. Based on acoustic emission and infrared radiation, the loading–unloading response ratio of rock is established. It is found that the response variables of sandstone during the loading stage based on acoustic emission (AE) counts and the loading–unloading response ratio based on average infrared radiation temperature (AIRT) both rise suddenly in the last cycle, which may be a precursor of “acoustic-thermal” approaching rock failure. On this basis, the quantitative analysis index of infrared radiation of differential infrared energy change rate (DIECR) is proposed, that is, the change of square of ΔAIRT in unit time, and based on AE counts and DIECR, the loading–unloading response ratio of “acoustic-thermal” is defined. It is found that the “acoustic-thermal” loading–unloading response ratio suddenly increases during the penultimate cycle of loading and unloading. This feature can be taken as the initial precursor of rock failure. Together with the “acoustic-thermal” imminent failure precursor of rock, it constitutes the “initial precursor-imminent failure precursor” combined with the internal fracture and surface infrared radiation temperature field during the cyclic loading and unloading process of rock, realizing the hierarchical monitoring and early warning of cyclic loading and unloading rock failure. The research results lay a theoretical and practical foundation for using infrared radiation to monitor engineering disasters caused by rock fracture and failure in mining engineering.

The deformation and failure of rock materials are closely related to the strain energy characteristics during the loading process. These strain energy characteristics and rock properties are greatly affected when the rock is subjected to the acidic solution. To study the effects of chemical solutions with different pH on the mechanical properties and strain energy mechanism of mudstone, the chemical corrosion mudstone samples are subjected to a uniaxial loading testing machine (CN64 electro-hydraulic servo). The corrosive effects of the acidic solution on the porosity, strain energy characteristics, and failure mode of mudstone samples were thoroughly investigated. The findings of this research indicate that: (1) The rate of change in the porosity and chemical damage coefficient of rock samples after chemical corrosion decreases, which is closely linear with the increase of solution pH; (2) The total strain energy, elastic strain energy, and dissipative strain energy decrease with the increase of pH, and, as a result, it is proposed that the observed turning point of the proportion curve of dissipated strain energy from decline to rise is used as a precursor point of the rock failure; (3) The stress value of the failure precursor point increases and the strain value decreases with the increase in pH value. However, the ratio of the stress value of the failure precursor point to the peak stress hardly changes with pH value, and its value is about 0.883; and (4) Rock samples soaked in a weak acidic chemical solution (pH 7.3 and 5.3) are damaged by tensile crack, while rock samples soaked in a strong acidic chemical solution (pH 3.3 and 1.3) are mainly damaged by the combination of tensile and shear. The findings of this study can be used to provide an experimental and theoretical foundation for monitoring rock engineering disasters such as slope, tunnel, and coal mine failures.

In order to better understand the failure process of water-bearing rocks, samples of water-bearing sandstone were tested uniaxially. The failure process and the development of internal cracks were studied through the evolution characteristics of dissipated strain energy and particle flow simulation. In this study, we found that: (1) The presence of water in sandstone results in a reduction in energy storage capacity as well as strength. (2) The dissipated energy ratio curve of sandstone samples and simulated samples’ internal fracture development curve has obvious stages. The dissipated energy ratio turning point and the rapid fracture development point are defined as the failure precursor points of sandstone samples and simulated samples, respectively. In both sandstone samples and simulated samples, the ratio between failure precursor stress and peak strength remains almost unchanged under various water conditions. (3) The ratio of fracture to dissipated energy (RFDE) of sandstone is proposed, and interpreted as the increased number of cracks in the rock under the unit dissipated. On this basis, the fracture initiation dissipated energy (FIDE) of sandstone under different water cut conditions is determined, that is, the dissipation threshold corresponding to the start of the development of sandstone internal cracks. (4) The analysis shows that RFDE increases exponentially and FIDE decreases negatively with the scale-up in moisture content. Further, high moisture content sandstone consumes the same dissipative strain energy, which will lead to more fractures in its interior. The research in this paper can lay a theoretical and experimental foundation for monitoring and early warning of rock engineering disasters such as coal mining, tunnel excavation, slope sliding, and instability.

The rock mass deformation modulus (Em) is an essential input parameter in numerical modeling for assessing the rock mass behavior required for the sustainable design of engineering structures. The in situ methods for determining this parameter are costly and time consuming. Their results may not be reliable due to the presence of various natures of joints and following difficult field testing procedures. Therefore, it is imperative to predict the rock mass deformation modulus using alternate methods. In this research, four different predictive models were developed, i.e., one statistical model (Muti Linear Regression (MLR)) and three Artificial Intelligence models (Artificial Neural Network (ANN), Random Forest Regression (RFR), and K-Neighbor Network (KNN)) by employing Rock Mass Rating (RMR89) and Point load index (I50) as appropriate input variables selected through correlation matrix analysis among eight different variables to propose an appropriate model for the prediction of Em. The efficacy of each predictive model was evaluated by using four different performance indicators: performance coefficient R2, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Median Absolute Error (MEAE). The results show that the R2, MAE, MSE, and MEAE for the ANN model are 0.999, 0.2343, 0.2873, and 0.0814, respectively, which are better than MLR, KNN, and RFR. Therefore, the ANN model is proposed as the most appropriate model for the prediction of Em. The findings of this research will provide a better understanding and foundation for the professionals working in fields during the prediction of various engineering parameters, especially Em for sustainable engineering design in the rock engineering field.