基于改进的距离判别分析法的南水北调西线工程TBM施工围岩分级

 对马氏距离判别法和层次分析法存在的不足进行改进，将改进的距离判别分析法应用于南水北调西线工程TBM施工围岩分级中。根据TBM施工特点和相关研究成果，将TBM施工围岩分级标准定为4级。选用岩石强度、岩组特征、结构面间距、结构面与洞轴线夹角以及石英含量5项指标作为判别因子，以南水北调西线工程杜柯河-玛柯河段实例数据作为学习样本进行训练，建立TBM施工围岩分级的改进的距离判别分析模型，利用得到的线性判别函数对待判样本进行分级。最后，将改进的距离判别分析法得到的判定结果与传统马氏距离判别法、RTBM法以及RMR方法得到的判别结果进行对比分析，验证了改进的距离判别分析法的有效性。研究结果表明，改进的距离判别分析法具有预测精度高等优点，为TBM施工围岩分级提供了一种新的有效方法。

CLASSIFICATION OF SURROUNDING ROCK MASS BY TBM TUNNELING BASED ON IMPROVED DISTANCE DISCRIMINANT ANALYSIS METHOD IN WEST ROUTE OF SOUTH-TO-NORTH WATER TRANSFER PROJECT

The shortages of Mahalanobis distance discriminant method and analytic hierarchy process are improved;and the improved distance discriminant analysis method is applied to the classification of surrounding rock mass by TBM tunneling in west route of South-to-North Water Transfer Project.The standard of surrounding rock mass classification cut by TBM is divided into four classes according to the characters of TBM tunneling and some corresponding research results.The improved distance discriminant analysis model of surrounding rock mass classification of tunnel by TBM tunneling is established,which considers five indexes,that are rock strength,petrofabric characters,the distance of structure faces,the included angle between structure face and tunnel axis and quartz content.The linear discriminant functions are obtained by training with a large of case data which come from Duke River-Make River reaches in west route of South-to-North Water Transfer Project.And the classification of waiting discriminant samples is carried out with the discriminant functions.At last,the judged results of improved distance discriminant analysis method are compared with the results of traditional Mahalanobis distance discriminant method,RTBM(rating of TBM) method and RMR(rock mass rating) method.The effectiveness of improved distance discriminant analysis method is verified.The research results show that the improved distance discriminant analysis model has many advantages,such as high prediction accuracy,and provides a new effective method for surrounding rock mass classification of tunnel by TBM tunneling.