The residual elastic energy index is a scientific evaluation index for rockburst proneness.In laboratory test,it is sometimes difficult to obtain the post-peak curve or to test the rock sample several times,which make...The residual elastic energy index is a scientific evaluation index for rockburst proneness.In laboratory test,it is sometimes difficult to obtain the post-peak curve or to test the rock sample several times,which makes it impossible to calculate the residual elastic energy index accurately.Based on 241 sets of experimental data and four input indexes of density,elastic modulus,peak intensity and peak input strain energy,this study proposed a machine learning model combining k-means clustering algorithm and random forest regression model:cluster forest(CF)model.The research employed a stratified sampling method on the dataset to ensure the representativeness and balance of the samples.Subsequently,grid search and five-fold cross-validation were utilized to optimize the model’s hyperparameters,aiming to enhance its generalization capability and prediction accuracy.Finally,the performance of the optimal model was evaluated using a test set and compared with five other commonly used models.The results indicate that the CF model outperformed the other models on the testing set,with a mean absolute error of 6.6%,and an accuracy of 93.9%.The results of sensitivity analyses reveal the degree of influence of each variable on rockburst proneness and the applicability of the CF model when the input parameters are missing.The robustness and generalization ability of the model were verified by introducing experimental data from other studies,and the results confirmed the reliability and applicability of the model.Therefore,the model not only effectively simplifies the acquisition of the residual elastic energy index,but also shows excellent performance and wide applicability.展开更多
To review the rockburst proneness(or tendency)criteria of rock materials and compare the judgment accuracy of them,twenty criteria were summarized,and their judgment accuracy was evaluated and compared based on the la...To review the rockburst proneness(or tendency)criteria of rock materials and compare the judgment accuracy of them,twenty criteria were summarized,and their judgment accuracy was evaluated and compared based on the laboratory tests on fourteen types of rocks.This study begins firstly by introducing the twenty rockburst proneness criteria,and their origins,definitions,calculation methods and grading standards were summarized in detail.Subsequently,to evaluate and compare the judgment accuracy of the twenty criteria,a series of laboratory tests were carried out on fourteen types of rocks,and the rockburst proneness judgment results of the twenty criteria for the fourteen types of rocks were obtained accordingly.Moreover,to provide a unified basis for the judgment accuracy evaluation of above criteria,a classification standard(obtained according to the actual failure results and phenomena of rock specimen)of rockburst proneness in laboratory tests was introduced.The judgment results of the twenty criteria were compared with the judgment results of this classification standard.The results show that the judgment results of the criterion based on residual elastic energy(REE)index are completely consistent with the actual rockburst proneness,and the other criteria have some inconsistent situations more or less.Moreover,the REE index is based on the linear energy storage law and defined in form of a difference value and considered the whole failure process,and these superior characteristics ensure its accuracy.It is believed that the criterion based on REE index is comparatively more accurate and scientific than other criteria,and it can be recommended to be applied to judge the rockburst proneness of rock materials.展开更多
The ejection velocity of rock fragments during rock burst, one of the important indexes representing the rock burst strength, is used most conveniently in the supporting design of tunnel with rock burst tendency and i...The ejection velocity of rock fragments during rock burst, one of the important indexes representing the rock burst strength, is used most conveniently in the supporting design of tunnel with rock burst tendency and is often determined by means of observation devices. In order to calculate the average ejection velocity of rock fragments theoretically, the energy of rock burst was divided into damage consuming energy and kinetic energy gained by unit volume of rock firstly, and then the rock burst kinetic proportional coefficient η was brought up which could be determined according to the rock-burst damage energy index W_D , at last the expression of the average ejection velocity of rock fragments during rock burst was obtained and one deep level underground tunnel was researched using the mentioned method. The results show that the calculation method is valid with or without considering the tectonic stress of tunnels, and that the method can be a reference for supporting design of deep mining.展开更多
The nonlinear Hoek-Brown failure criterion was introduced to limit analysis by applying the tangent method. Based on the failure mechanism of double-logarithmic spiral curves on the face of deep rock tunnels, the anal...The nonlinear Hoek-Brown failure criterion was introduced to limit analysis by applying the tangent method. Based on the failure mechanism of double-logarithmic spiral curves on the face of deep rock tunnels, the analytical solutions of collapse pressure were derived through utilizing the virtual power principle in the case of pore water, and the optimal solutions of collapse pressure were obtained by using the optimization programs of mathematical model with regard of a maximum problem. In comparison with existing research with the same parameters, the consistency of change rule shows the validity of the proposed method. Moreover, parametric study indicates that nonlinear Hoek-Brown failure criterion and pore water pressure have great influence on collapse pressure and failure shape of tunnel faces in deep rock masses, particularly when the surrounding rock is too weak or under the condition of great disturbance and abundant ground water, and in this case, supporting measures should be intensified so as to prevent the occurrence of collapse.展开更多
The alkali-rich rocks, spreading along the suture zone of Jingsha River, refer to the alkali-rich porphyry rocks, which emplace during the Himalaya epoch in northwest of Yunnan Province, and consist of syenit, syenit ...The alkali-rich rocks, spreading along the suture zone of Jingsha River, refer to the alkali-rich porphyry rocks, which emplace during the Himalaya epoch in northwest of Yunnan Province, and consist of syenit, syenit porphyry, monzonite porphyry and granite porphyry. Petrological chemical analysis results suggest that silica is poor and aluminum is rich, and high potassium large ion lithophile elements （LILE）, light rare earth element （LREE） and Sr are obviously detracted in these rocks. High field strength elements （HFSE） and heavy rare earth element （HREE） are depleted, especially Nb, Ta, P and Ti. 8Eu： 0.09--1.64 shows that plagioclase does not appear fractional crystallization during the formation of alkali-rich rocks, t^348, H and O isotopes and Pb isotopes suggest that ore-forming fluid is derived from the mantle, and Pb is possibly mixed by mantle, wall rock and crust. The age of Pb in alkali-rich rocks is about 250-220 Ma. The age of alkali porphyry rock （dykes） varies from 30 Ma to 50 Ma. Alkali rocks have strong metallogenetic relation. Au mineralization is associated to the alkali magrnatic activities with a relatively high temperature, low pressure and high oxygen fugacity. However, copper mineralization is mainly associated with alkali-sub-alkali magmatic activities in a process of relatively low temperature, high pressure and lower oxygen fugacity.展开更多
基金Project(42077244)supported by the National Natural Science Foundation of ChinaProject(SDGZK2431)supported by the State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering,Sichuan University,China。
文摘The residual elastic energy index is a scientific evaluation index for rockburst proneness.In laboratory test,it is sometimes difficult to obtain the post-peak curve or to test the rock sample several times,which makes it impossible to calculate the residual elastic energy index accurately.Based on 241 sets of experimental data and four input indexes of density,elastic modulus,peak intensity and peak input strain energy,this study proposed a machine learning model combining k-means clustering algorithm and random forest regression model:cluster forest(CF)model.The research employed a stratified sampling method on the dataset to ensure the representativeness and balance of the samples.Subsequently,grid search and five-fold cross-validation were utilized to optimize the model’s hyperparameters,aiming to enhance its generalization capability and prediction accuracy.Finally,the performance of the optimal model was evaluated using a test set and compared with five other commonly used models.The results indicate that the CF model outperformed the other models on the testing set,with a mean absolute error of 6.6%,and an accuracy of 93.9%.The results of sensitivity analyses reveal the degree of influence of each variable on rockburst proneness and the applicability of the CF model when the input parameters are missing.The robustness and generalization ability of the model were verified by introducing experimental data from other studies,and the results confirmed the reliability and applicability of the model.Therefore,the model not only effectively simplifies the acquisition of the residual elastic energy index,but also shows excellent performance and wide applicability.
基金Project(41877272)supported by the National Natural Science Foundation of ChinaProject(2020zzts715)supported by the Fundamental Research Funds for the Central Universities of Central South University,ChinaProject(2242020R10023)supported by the Fundamental Research Funds for the Central Universities of Southeast University,China。
文摘To review the rockburst proneness(or tendency)criteria of rock materials and compare the judgment accuracy of them,twenty criteria were summarized,and their judgment accuracy was evaluated and compared based on the laboratory tests on fourteen types of rocks.This study begins firstly by introducing the twenty rockburst proneness criteria,and their origins,definitions,calculation methods and grading standards were summarized in detail.Subsequently,to evaluate and compare the judgment accuracy of the twenty criteria,a series of laboratory tests were carried out on fourteen types of rocks,and the rockburst proneness judgment results of the twenty criteria for the fourteen types of rocks were obtained accordingly.Moreover,to provide a unified basis for the judgment accuracy evaluation of above criteria,a classification standard(obtained according to the actual failure results and phenomena of rock specimen)of rockburst proneness in laboratory tests was introduced.The judgment results of the twenty criteria were compared with the judgment results of this classification standard.The results show that the judgment results of the criterion based on residual elastic energy(REE)index are completely consistent with the actual rockburst proneness,and the other criteria have some inconsistent situations more or less.Moreover,the REE index is based on the linear energy storage law and defined in form of a difference value and considered the whole failure process,and these superior characteristics ensure its accuracy.It is believed that the criterion based on REE index is comparatively more accurate and scientific than other criteria,and it can be recommended to be applied to judge the rockburst proneness of rock materials.
文摘The ejection velocity of rock fragments during rock burst, one of the important indexes representing the rock burst strength, is used most conveniently in the supporting design of tunnel with rock burst tendency and is often determined by means of observation devices. In order to calculate the average ejection velocity of rock fragments theoretically, the energy of rock burst was divided into damage consuming energy and kinetic energy gained by unit volume of rock firstly, and then the rock burst kinetic proportional coefficient η was brought up which could be determined according to the rock-burst damage energy index W_D , at last the expression of the average ejection velocity of rock fragments during rock burst was obtained and one deep level underground tunnel was researched using the mentioned method. The results show that the calculation method is valid with or without considering the tectonic stress of tunnels, and that the method can be a reference for supporting design of deep mining.
基金Project(2013CB036004)supported by National Basic Research Program of ChinaProjects(51178468,51378510)supported by National Natural Science Foundation of ChinaProject(CX2013B077)supported by Hunan Provincial Innovation Foundation for Postgraduate,China
文摘The nonlinear Hoek-Brown failure criterion was introduced to limit analysis by applying the tangent method. Based on the failure mechanism of double-logarithmic spiral curves on the face of deep rock tunnels, the analytical solutions of collapse pressure were derived through utilizing the virtual power principle in the case of pore water, and the optimal solutions of collapse pressure were obtained by using the optimization programs of mathematical model with regard of a maximum problem. In comparison with existing research with the same parameters, the consistency of change rule shows the validity of the proposed method. Moreover, parametric study indicates that nonlinear Hoek-Brown failure criterion and pore water pressure have great influence on collapse pressure and failure shape of tunnel faces in deep rock masses, particularly when the surrounding rock is too weak or under the condition of great disturbance and abundant ground water, and in this case, supporting measures should be intensified so as to prevent the occurrence of collapse.
基金Project(1343-74334000019) supported by the PhD Innovation Subject of Central south University,ChinaProject(1960-71131100088 (CX2010B085)) supported by the Hunan Provincial Innovation Foundation For Postgraduate Students,China
文摘The alkali-rich rocks, spreading along the suture zone of Jingsha River, refer to the alkali-rich porphyry rocks, which emplace during the Himalaya epoch in northwest of Yunnan Province, and consist of syenit, syenit porphyry, monzonite porphyry and granite porphyry. Petrological chemical analysis results suggest that silica is poor and aluminum is rich, and high potassium large ion lithophile elements （LILE）, light rare earth element （LREE） and Sr are obviously detracted in these rocks. High field strength elements （HFSE） and heavy rare earth element （HREE） are depleted, especially Nb, Ta, P and Ti. 8Eu： 0.09--1.64 shows that plagioclase does not appear fractional crystallization during the formation of alkali-rich rocks, t^348, H and O isotopes and Pb isotopes suggest that ore-forming fluid is derived from the mantle, and Pb is possibly mixed by mantle, wall rock and crust. The age of Pb in alkali-rich rocks is about 250-220 Ma. The age of alkali porphyry rock （dykes） varies from 30 Ma to 50 Ma. Alkali rocks have strong metallogenetic relation. Au mineralization is associated to the alkali magrnatic activities with a relatively high temperature, low pressure and high oxygen fugacity. However, copper mineralization is mainly associated with alkali-sub-alkali magmatic activities in a process of relatively low temperature, high pressure and lower oxygen fugacity.
