Predicting triaxial compressive strength of high-temperature treated rock using machine learning techniques

The accurate prediction of the strength of rocks after high-temperature treatment is important for the safety maintenance of rock in deep underground engineering.Five machine learning(ML)techniques were adopted in this study,i.e.back propagation neural network(BPNN),AdaBoost-based classification and regression tree(AdaBoost-CART),support vector machine(SVM),K-nearest neighbor(KNN),and radial basis function neural network(RBFNN).A total of 351 data points with seven input parameters(i.e.diameter and height of specimen,density,temperature,confining pressure,crack damage stress and elastic modulus)and one output parameter(triaxial compressive strength)were utilized.The root mean square error(RMSE),mean absolute error(MAE)and correlation coefficient(R)were used to evaluate the prediction performance of the five ML models.The results demonstrated that the BPNN shows a better prediction performance than the other models with RMSE,MAE and R values on the testing dataset of 15.4 MPa,11.03 MPa and 0.9921,respectively.The results indicated that the ML techniques are effective for accurately predicting the triaxial compressive strength of rocks after different high-temperature treatments.

Strength and deformation behaviors of cemented tailings backfill under triaxial compression

It is of great significance for safety reason to obtain the triaxial compressive properties of cemented tailings backfill(CTB).The influence of cement content,curing age and confining pressure on strength and deformation properties of CTB was examined and discussed.Results indicate that the triaxial compressive and deformation behavior of CTB is strongly affected by the cement content,curing age and confining pressure.The increase in cement content,curing age and confining pressure leads to a change in stress−strain behavior and an increase in the axial strain at failure and post-peak strength loss.The cohesion of CTB rises as the curing age and cement content increase.However,the enhancement in internal friction angle is trivial and negligible.It should be noted that the failure pattern of CTB samples in triaxial compression is mainly along a shear plane,the confining pressure restrains the lateral expansion and the bulging failure pattern is dominantly detected in CTB samples as curing age length and cement content increase.The results will help to better understand the triaxial mechanical and deformation behavior of CTB.

A new nonlinear empirical strength criterion for rocks under conventional triaxial compression

The failure criterion of rocks is a critical factor involved in reliability design and stability analysis of geotechnical engineering.In order to accurately evaluate the triaxial compressive strength of rocks under different confining pressures,a nonlinear empirical strength criterion based on Mohr-Coulomb criterion was proposed in this paper.Through the analysis of triaxial test strength of 11 types of rock materials,the feasibility and validity of proposed criterion was discussed.For a further verification,six typical strength criteria were selected,and the prediction results of each criterion and test results were statistically analyzed.The comparative comparison results show that the prediction results obtained by applying this new criterion to 97 conventional triaxial compression tests of 11 different rock materials are highly consistent with the experimental data.Statistical analysis was executed to assess the application of the new criterion and other classical criteria in predicting the failure behavior of rock.This proposed empirical criterion provides a new reference and method for the determination of triaxial compressive strength of rock materials.

Determination of the constant m_(i) in the Hoek-Brown criterion of rock based on drilling parameters

The constant m_(i) in the Hoek-Brown(H-B) criterion is a fundamental parameter required for determining the compressive strength of rock. In this paper, drilling parameters provide a new basis for determining the constant mi. An analytical relationship between the drilling parameters and constant miis established in consideration of the contact response between the drilling bit and the cut rock in the crushed zone.New models are developed to predict the triaxial compressive strength(TCS), internal friction angle φand cohesion c of rock. Drilling tests are carried out on 6 rock types to study the correlation between φ and m_(i). A comparison between the predicted values of rock mechanical properties and the measured values from the laboratory is performed to verify the accuracy of the proposed model(yielding an error less than 10%). The TCSs and constant m_(i) values of fifteen rocks are cited to validate the accuracy of the proposed model. The result shows that the proposed model predicts the TCS and constant m_(i) within a maximum error of 20%. The method can be conveniently applied to the rock mechanical properties.