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 thi...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.展开更多
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 cons...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.展开更多
基金We acknowledge the funding support from the National Natural Science Foundation of China(Grant No.51778575)Postdoctoral Science Foundation of China(Grant No.2021M692481)Fundamental Research Funds for the Central Universities of China(Grant No.2042021kf0055).The authors would like to thank the anonymous reviewers and editors for their constructive suggestions which greatly improve the quality of this paper.The authors are also grateful for the permission from Elsevier.
文摘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.
基金sponsored by the National Natural Science Foundation of China (Nos. 42177158, 11902249 and 11872301)Natural Science Foundation of Shaanxi Province (Shaanxi Province Natural Science Foundation) (No. 2019JQ395)Education Bureau of Shaanxi Province | Scientific Research Plan Projects of Shaanxi Education Department in China (No. 20JS093)。
文摘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.
