Explore the vast range of titles available.

To accurately estimate the rock shear strength parameters of cohesion (C) and friction angle (φ), triaxial tests must be carried out at different stress levels so that a failure envelope can be obtained to be linearized. However, this involves a higher budget and time requirements that are often unavailable at the early stage of a project. To address this problem, faster and more inexpensive indirect techniques such as artificial intelligence algorithms are under development. This paper first aims to utilize four machine learning techniques of Gaussian process regression (GPR), support vector regression (SVR), decision trees (DT), and long-short term memory (LSTM) to develop a predictive model to estimate parameters C and φ. To this aim, 244 datasets are available in the RockData software for intact Sandstone, including three input parameters of uniaxial compressive strength (UCS), uniaxial tensile strength (UTS), and confining stress (σ3) are employed in the models. The dropout technique is used to overcome the overfitting problem in LSTM-based models. A comprehensive evaluation is adopted for the performance indices of the prediction models. In this step, the most accurate results are produced by the LSTM model (C: R2 = 0.9842; RMSE = 1.295; MAPE = 0.009/φ: R2 = 0.8543; RMSE = 1.857; MAPE = 1.4301). In the second step, we improve the performance of the proposed LSTM model by fine-tuning the LSTM hyper-parameters, using six metaheuristic algorithms of grey wolf optimization (GWO), particle swarm optimization (PSO), social spider optimization (SSO), sine cosine algorithm (SCA), multiverse optimization (MVO), and moth flame optimization (MFO). The developed models' prediction performance for predicting parameter C from high to low was PSO-LSTM, GWO-LSTM, MVO-LSTM, MFO-LSTM, SCA-LSTM SSO-LSTM, and LSTM with ranking scores of 34, 29, 24, 21, 14, 12, and 5, respectively. Also, the models' prediction performance for predicting parameter φ from high to low was PSO-LSTM, GWO-LSTM, MVO-LSTM, MFO-LSTM, SCA-LSTM SSO-LSTM, and LSTM with ranking scores of 34, 31, 23, 18, 15, 14, and 5, respectively. However, the most robust results are produced by the PSO-LSTM model. Finally, the results indicate that applying a metaheuristic algorithm to tune the hyper-parameters of the LSTM model can significantly improve the prediction results. In the last step, the mutual information test method is applied to sensitivity analysis of the input parameters to predict parameters C and φ. Finally, it is revealed that parameters σ3 and UCS have the highest and lowest impact on the parameters C and φ, respectively.HighlightsEmploying a large dataset consists of 244 data.Using six ML algorithms that most of them had not been tested before for this issue.Applying 5-fold CV to validate the results.Application of feature selection to find the most effective parameters on the water inflow into tunnels.Recognition of the best prediction method.

Aiming at the slope stability problem caused by the change in the water level in an open pit mine tailings pond, the weakening of the rock shear strength parameters (i.e. cohesion and internal friction angle) and the variation of Drucker–Prager strength yield criterion parameters have been analyzed. Based on the results of the tri-axial compression tests under different water invasion-loss cycles, they show the following: (1) The shear strength parameters decrease with increasing number of cycles. The cohesion of altered granite-1 has been reduced from 5.61 to 0.35 MPa, and the internal friction angle has been reduced from 49.24° to 22.70°. As for altered granite-2, the cohesion has been reduced from 7.18 to 1.07 MPa, and the internal friction angle has been reduced from 51.16° to 25.64°. (2) The degree of deterioration the shear strength parameters decreases with number of cycles. The cohesion decreases by 93.76%, and 85.09%, the internal friction angle decreases 53.89% and 49.88%. (3) According to the value of shear strength parameter subjected to water invasion-loss cycles, the variation law of different types of Drucker–Prager strength yield criterion has been determined. The exponential functions between the parameters and the number of cycles have been developed.

The index mechanical properties, strength, and stiffness parameters of rock materials (i.e., uniaxial compressive strength, c, ϕ, E, and G) are critical factors in the proper geotechnical design of rock structures. Direct procedures such as field surveys, sampling, and testing are used to estimate these properties, and are time-consuming and costly. Indirect methods have gained popularity in recent years due to their time-saving and highly accurate results, which are comparable to those obtained through direct approaches. This study presents a procedure for establishing a deep learning-based predictive model (DNN) for obtaining the geomechanical characteristics of marlstone samples that have been recovered from the South Pars region of southwest Iran. The model was implemented on a dataset resulting from the execution of numerous geotechnical tests and the evaluation of the geotechnical parameters of a total of 120 samples. The applied model was verified by using benchmark learning classifiers (e.g., Support Vector Machine, Logistic Regression, Gaussian Naïve Bayes, Multilayer Perceptron, Bernoulli Naïve Bayes, and Decision Tree), Loss Function, MAE, MSE, RMSE, and R-square. According to the results, the proposed DNN-based model led to the highest accuracy (0.95), precision (0.97), and the lowest error rate (MAE = 0.13, MSE = 0.11, and RMSE = 0.17). Moreover, in terms of R2, the model was able to accurately predict the geotechnical indices (0.933 for UCS, 0.925 for E, 0.941 for G, 0.954 for c, and 0.921 for φ).

To overcome the limitations of single models in addressing complex, nonlinear problems in predicting rock shear strength parameters and the hyperparameter random selection problem, this study constructed a novel prediction framework for rock shear strength parameters. First, the light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and random forest (RF) algorithms are employed as the base-learners for the ensemble model, with XGBoost serving as the meta-learner to build a stacking ensemble model. On the basis of the sparrow search algorithm (SSA), tent chaotic mapping is used to initialize the sparrow population, the Cauchy‒Gaussian hybrid mutation mechanism is used to dynamically select the probability control mutation type, the dynamic adaptive weight is used to adjust the balance between global exploration and local development, and Levy flight is used to help the sparrow population individuals jump out of the local optimum to construct the chaos-improved sparrow search algorithm (CISSA) to optimize the hyperparameters of the stacking model. Second, based on the 199 datasets of different rock types, the model was trained via fivefold cross-validation and evaluated based on the coefficient of determination ( R ²), root mean square error (RMSE) and mean absolute error (MAE). Concurrently, the Shapley additive explanations (SHAP) method was employed to analyse the degree of contribution of each predictive index. The results demonstrate that the CISSA-Stacking model achieves R ² values of 0.9936 and 0.9744 for c and φ , respectively, with corresponding RMSE of 0.4303 and 0.7635 and MAE of 0.2161 and 0.5867, indicating significantly superior overall performance compared with benchmark models. SHAP interpretability analysis revealed that the importance rankings for c are V p , UCS, BTS, and ρ , whereas those for φ are ρ , UCS, V p , and BTS. Finally, intelligent prediction software based on the CISSA-Stacking model was developed. The software is simple in operation, intuitive in results and excellent in performance, enables rapid and accurate prediction of c and φ through manual input of the V p , ρ , UCS, and BTS indices or by importing tabular data containing these four indices. The engineering application further confirmed the accuracy and practical utility of both the model and the software, providing a new efficient method for engineers to quickly and accurately estimate rock shear strength parameters.

Shear strength (SS) parameters are essential for understanding the mechanical behavior of materials, particularly in geotechnical engineering and rock mechanics. This study proposes a novel hierarchical ensemble model (HEM) to predict SS parameters: cohesion ( C ) and angle of internal friction ( φ ). The HEM addresses the limitations of traditional machine learning models. Its performance was validated using leave-one-out cross-validation (LOOCV) and out-of-bag (OOB) evaluation methods. The model's accuracy was assessed with R-squared correlation (R 2 ), absolute average relative error percentage (AAREP), Taylor diagrams, and quantile–quantile plots. The computational results demonstrated that the proposed HEM outperforms previous studies using the same database. The model predicted φ and C with R 2 values of 0.93 and 0.979, respectively. The AAREP values were 1.96% for φ and 4.7% for C . These results indicate that the HEM significantly improves the prediction quality of φ and C , and exhibits strong generalization capability. Sensitivity analysis revealed that σ_3maxσ3max (maximum principal stress) had the greatest impact on modeling both φ and C . According to uncertainty analysis, the LOOCV and OOB had the widest uncertainty bands for the φ and C parameters, respectively.

This study investigates the mechanical and microstructural properties of loose sandy soil stabilized with alkali-activated Ground Granulated Blast Furnace Slag (GGBFS). To examine the effects of varying GGBFS contents, curing times, and confining pressures on mechanical behavior, undrained triaxial and unconfined compressive strength (UCS) tests were conducted. Microstructural analyses using FE-SEM, EDX, and FTIR were performed to elucidate the nature and development of cementation. The results of mechanical behavior demonstrate that even with limited GGBFS content (1–6%), the treated samples exhibited significant improvements in strength, stiffness, and energy absorption, underscoring the efficiency of alkali-activated GGBFS as a soil stabilizer. Moreover, mechanical parameters from triaxial tests revealed a nearly constant internal friction angle with increasing GGBFS content and curing duration, while cohesion showed remarkable enhancement. A strong linear correlation between UCS and cohesion was also identified, enabling cost-effective estimation of shear strength parameters. These findings highlight the potential of alkali-activated GGBFS for improving granular soils, offering practical implications for sustainable geotechnical applications, particularly in road construction.

Expansive clay soils cause structural failures in construction due to volume changes with moisture, but hydrated lime effectively stabilizes them by improving shear strength and reducing plasticity. To address environmental concerns with traditional stabilizers like cement, silica fume, a byproduct of the silicon industry, is now being used as a supplementary additive to enhance stabilization. In this study, the combined effects of hydrated lime and silica fume addition on the shear strength and consolidation behaviour of expansive clay soils are presented. An experimental programme was performed in the laboratory using different ratios of lime and silica fume to determine changes in soil properties. Experimental results indicate that the inclusion of silica fume and lime leads to a 35% increase in shear strength and a 28% reduction in compressibility compared to untreated soil. Moreover, the peak deviatoric stress increased from 540.55 kPa in untreated soil to 624.95 kPa in soil stabilized with 9% lime and 9% silica fume. The results clearly demonstrated that the union of these two additives improves shear strength and consolidation characteristics to stabilize expansive clays which is eco-friendlier and more promising solution. The insights obtained from this research will help us to develop soil stabilization techniques for better in-situ soil performances and hence, sustainable construction.

Shear strength parameters such as cohesion are the most significant rock parameters which can be utilized for initial design of some geotechnical engineering applications. In this study, evaluation and prediction of rock material cohesion is presented using different approaches i.e., simple and multiple regression, artificial neural network (ANN) and genetic algorithm (GA)-ANN. For this purpose, a database including three model inputs i.e., p-wave velocity, uniaxial compressive strength and Brazilian tensile strength and one output which is cohesion of limestone samples was prepared. A meaningful relationship was found for all of the model inputs with suitable performance capacity for prediction of rock cohesion. Additionally, a high level of accuracy (coefficient of determination, R2 of 0.925) was observed developing multiple regression equation. To obtain higher performance capacity, a series of ANN and GA-ANN models were built. As a result, hybrid GA-ANN network provides higher performance for prediction of rock cohesion compared to ANN technique. GA-ANN model results (R2 = 0.976 and 0.967 for train and test) were better compared to ANN model results (R2 = 0.949 and 0.948 for train and test). Therefore, this technique is introduced as a new one in estimating cohesion of limestone samples.

Strength and deformation characteristics of jointed rocks are important parameters for the design of many civil and mining engineering structures. These parameters are difficult to obtain from direct testing of jointed rocks; hence it is usual practice to derive them through indirect approaches. In the present study, an attempt is made to obtain rough estimates of strength and modulus of jointed rocks through P wave velocity. Jointed specimens of a model rock were prepared for laboratory testing. Joints at different orientations and comprising of different joint roughness coefficients were used (JRC = 2–4, 12–14 and 14–16). Ultrasonic P-wave velocity and UCS tests were conducted on the specimens. The effect of joint orientation and joint wall roughness on P-wave velocity was studied. An index, Joint Factor was used to quantify the effect of joint attributes on strength and modulus of jointed rock. It was observed that P-wave velocity is closely linked with Joint Factor. This study suggests a correlation to obtain Joint Factor J f from P-wave velocity. P-wave velocity may be measured in the field and J f may be computed through the suggested correlation. The computed J f may then be used to get the strength and modulus values of jointed rocks. Charts are also suggested to roughly assess the shear strength parameters, c mass and ϕ mass of the jointed rock.