The stability type and spatial distribution of surrounding rock are an important basis for the layout of hae tunuels and the selection of support patterns in a mine design. Based on a lot of investigations and testing...The stability type and spatial distribution of surrounding rock are an important basis for the layout of hae tunuels and the selection of support patterns in a mine design. Based on a lot of investigations and testing studies,a new engineering geological classification scheme of surrounding rock stability is put forward,which is easy to be applied,and reliable verified by examples. According to the classification system,the spatial divisions of surrounding rock stability can be delineated in an exploration progamme, providing relevant engineering geological informations for mine designers to prevent them from making the uurealistic tunnel layout and support展开更多
The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-s...The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-situ stresses, uniaxial compressive strength and tensile strength of rock, and the elastic energy index of rock, were selected in the analysis. The traditional indicators were summarized and divided into indexes I and 1I. Random Forest model and criterion were obtained through training 36 sets of rockburst samples which come from underground rock projects in domestic and abroad. Another 10 samples were tested and evaluated with the model. The evaluated results agree well with the practical records. Comparing the results of support vector machine （SVM） method, and artificial neural network （ANN） method with random forest method, the corresponding misjudgment ratios are 10%, 20%, and 0, respectively. The misjudgment ratio using index I is smaller than that using index II. It is suggested that using the index I and RF model can accurately classify rockburst grade.展开更多
The mechanical effects of bolt-mesh-anchor coupling support in deep tunnels were studied by using a numerical method, based on deep tunnel coupling supporting techniques and non-linear deformation mechanical theory of...The mechanical effects of bolt-mesh-anchor coupling support in deep tunnels were studied by using a numerical method, based on deep tunnel coupling supporting techniques and non-linear deformation mechanical theory of rock mass at great depths.It is shown that the potential of a rigid bolt support can be efficiently activated through the coupling effect between a bolt-net support and the surrounding rock.It is found that the accumulated plastic energy in the surrounding rock can be sufficiently transformed by the coupling effect of a bolt-mesh-tray support.The strength of the surrounding rock mass can be mobilized to control the deforma-tion of the surrounding rock by a pre-stress and time-space effect of the anchor support.The high stress transformation effect can be realized by the mechanical coupling effect of the bolt-mesh-anchor support, whereby the force of the support and deformation of the surrounding rock tends to become uniform, leading to a sustained stability of the tunnel.展开更多
In terms of rock engineering and technology in hydropower construction,the slope stability and monitoring techniques for high slopes of Three Gorges Project,the stability and support technology for high slopes of hydr...In terms of rock engineering and technology in hydropower construction,the slope stability and monitoring techniques for high slopes of Three Gorges Project,the stability and support technology for high slopes of hydropower projects in deep river valley,the stabilization techniques for underground cavern group with large span and high side walls are introduced in this paper.As for rock engineering and technology in highway and railway construction,the Qinghai-Tibet Railway — new construction techniques in permafrost,the support techniques for large squeezing deformation in Wuqiaoling Tunnel,the construction techniques for tunnels in alpine and high-altitude region,the geological prediction techniques for tunnels in karst region,the microseismic monitoring and early warning techniques for rockbursts in deep and long tunnels are presented.For rock engineering and technology inmining engineering,the innovative techniques for roadway support inmines,the simultaneous extraction technique of pillarless coal and gas in coal seams with low permeability,the safe and efficient deep openmining technology,advances in monitoring,early warning and treatment ofmine dynamic disasters are discussed.In addition,the new anchorage techniques and precision blasting technique in rock engineering are introduced.展开更多
针对岩爆样本数据噪声高、数量少从而导致岩爆等级预测准确率较低的问题,提出了基于非线性分数阶中值鉴别空间学习(nonlinear fractional-order median discriminative space learning,NFMDSL)的岩爆预测方法。该方法用类中值代替类均值...针对岩爆样本数据噪声高、数量少从而导致岩爆等级预测准确率较低的问题,提出了基于非线性分数阶中值鉴别空间学习(nonlinear fractional-order median discriminative space learning,NFMDSL)的岩爆预测方法。该方法用类中值代替类均值,构建了中值鉴别空间学习方法,更好地保留了样本的有效信息,降低了噪声对预测效果的影响。为了有效捕捉岩爆数据间的非线性鉴别结构,进一步借助核技术将样本数据投影到核空间中。此外,引入分数阶对散度矩阵的特征值和奇异值进行重新估计,可以从少量样本中提取出具有良好区分能力的岩爆特征。结果表明,NFMDSL方法在岩爆等级预测中的平均准确率达到了95.75%,相比其他方法具有更高的准确率和更强的鲁棒性。该方法能够有效应用于矿山和隧道工程领域的岩爆预测。展开更多
文摘The stability type and spatial distribution of surrounding rock are an important basis for the layout of hae tunuels and the selection of support patterns in a mine design. Based on a lot of investigations and testing studies,a new engineering geological classification scheme of surrounding rock stability is put forward,which is easy to be applied,and reliable verified by examples. According to the classification system,the spatial divisions of surrounding rock stability can be delineated in an exploration progamme, providing relevant engineering geological informations for mine designers to prevent them from making the uurealistic tunnel layout and support
基金Projects (50934006, 10872218) supported by the National Natural Science Foundation of ChinaProject (2010CB732004) supported bythe National Basic Research Program of China+1 种基金Project (kjdb2010-6) supported by Doctoral Candidate Innovation Research Support Program of Science & Technology Review, ChinaProject (201105) supported by Scholarship Award for Excellent Doctoral Student,Ministry of Education, China
文摘The method of Random Forest （RF） was used to classify whether rockburst will happen and the intensity of rockburst in the underground rock projects. Some main control factors of rockburst, such as the values of in-situ stresses, uniaxial compressive strength and tensile strength of rock, and the elastic energy index of rock, were selected in the analysis. The traditional indicators were summarized and divided into indexes I and 1I. Random Forest model and criterion were obtained through training 36 sets of rockburst samples which come from underground rock projects in domestic and abroad. Another 10 samples were tested and evaluated with the model. The evaluated results agree well with the practical records. Comparing the results of support vector machine （SVM） method, and artificial neural network （ANN） method with random forest method, the corresponding misjudgment ratios are 10%, 20%, and 0, respectively. The misjudgment ratio using index I is smaller than that using index II. It is suggested that using the index I and RF model can accurately classify rockburst grade.
基金Projects 2006CB202200 supported by the National Basic Research Program of ChinaNCET07-0800 by the Program for New Century Excellent Talents in Universities
文摘The mechanical effects of bolt-mesh-anchor coupling support in deep tunnels were studied by using a numerical method, based on deep tunnel coupling supporting techniques and non-linear deformation mechanical theory of rock mass at great depths.It is shown that the potential of a rigid bolt support can be efficiently activated through the coupling effect between a bolt-net support and the surrounding rock.It is found that the accumulated plastic energy in the surrounding rock can be sufficiently transformed by the coupling effect of a bolt-mesh-tray support.The strength of the surrounding rock mass can be mobilized to control the deforma-tion of the surrounding rock by a pre-stress and time-space effect of the anchor support.The high stress transformation effect can be realized by the mechanical coupling effect of the bolt-mesh-anchor support, whereby the force of the support and deformation of the surrounding rock tends to become uniform, leading to a sustained stability of the tunnel.
文摘In terms of rock engineering and technology in hydropower construction,the slope stability and monitoring techniques for high slopes of Three Gorges Project,the stability and support technology for high slopes of hydropower projects in deep river valley,the stabilization techniques for underground cavern group with large span and high side walls are introduced in this paper.As for rock engineering and technology in highway and railway construction,the Qinghai-Tibet Railway — new construction techniques in permafrost,the support techniques for large squeezing deformation in Wuqiaoling Tunnel,the construction techniques for tunnels in alpine and high-altitude region,the geological prediction techniques for tunnels in karst region,the microseismic monitoring and early warning techniques for rockbursts in deep and long tunnels are presented.For rock engineering and technology inmining engineering,the innovative techniques for roadway support inmines,the simultaneous extraction technique of pillarless coal and gas in coal seams with low permeability,the safe and efficient deep openmining technology,advances in monitoring,early warning and treatment ofmine dynamic disasters are discussed.In addition,the new anchorage techniques and precision blasting technique in rock engineering are introduced.
文摘针对岩爆样本数据噪声高、数量少从而导致岩爆等级预测准确率较低的问题,提出了基于非线性分数阶中值鉴别空间学习(nonlinear fractional-order median discriminative space learning,NFMDSL)的岩爆预测方法。该方法用类中值代替类均值,构建了中值鉴别空间学习方法,更好地保留了样本的有效信息,降低了噪声对预测效果的影响。为了有效捕捉岩爆数据间的非线性鉴别结构,进一步借助核技术将样本数据投影到核空间中。此外,引入分数阶对散度矩阵的特征值和奇异值进行重新估计,可以从少量样本中提取出具有良好区分能力的岩爆特征。结果表明,NFMDSL方法在岩爆等级预测中的平均准确率达到了95.75%,相比其他方法具有更高的准确率和更强的鲁棒性。该方法能够有效应用于矿山和隧道工程领域的岩爆预测。
