摘要
将Bayes判别分析方法应用于岩体质量等级判别与分类中,建立了岩体质量综合评判的Bayes判别分析模型.模型选用岩石质量指标、完整性系数、单轴饱和抗压强度、纵波波速、弹性抗力系数和结构面摩擦因数等6个指标作为判别因子;将岩体质量分为4个等级作为Bayes判别分析的4个正态总体;以隧道围岩实测数据作为训练样本,建立Bayes线性判别函数;以Bayes线性判别函数计算待判样品的Bayes判别函数值,以最大值对应的总体作为样品所归属的总体;最后以刀切法对判别准则进行评价以检验模型的优良性.研究表明,Bayes判别分析模型误判率低,识别正确率达96.67%.
Based on the principle of Bayes discriminant analysis, Bayes discriminant model for evaluating rock-mass quality was established. Six indexes including the rock quality designation, integrity coefficient, uniaxial compressive strength under saturation, longitudinal wave velocity, elasticity resisting coefficient, and friction coefficient of joint planes were selected as the factors for synthetic evaluation of rock-mass quality. The grade of rock-mass quality was divided into four grades that were considered as four normal populations in Bayes discriminant analysis. Bayes discriminant functions obtained through training a set of surrounding rock samples in tunnel were employed to compute the Bayes function values of the evaluating samples, and the maximal function value was used to judge which population the evaluating sample belongs to. The optimality of the proposed model is verified by Jackknife method. The study shows that the average prediction accuracy is 96.67%.
出处
《煤炭学报》
EI
CAS
CSCD
北大核心
2008年第4期395-399,共5页
Journal of China Coal Society
关键词
岩体质量
分类
Bayes判别分析
岩石力学
rock-mass quality
classification
Bayes discriminant analysis
rock mechanics
