基于Bayes判别分析方法的地下工程岩爆发生及烈度分级预测

在岩爆发生和烈度分级预测的距离判别分析模型的基础上，结合地下工程岩爆的特点和Bayes判别分析理论，提出了地下工程岩爆发生及烈度分级预测的Bayes判别分析方法。综合分析影响岩爆主要因素，选取最大切向应力 、岩石抗压强度 、岩石抗拉强度 和弹性能量指数 作为判别因子建立岩爆预测的Bayes判别分析模型，并利用回代估计法对误判概率进行估计。利用国内外一些重大深部地下工程实例作为学习的样本进行训练建模，经过训练后的模型回判估计的误判率为0。利用该模型对国内3处典型的隧道岩爆情况进行预测，结果与实际情况符合得很好。研究结果表明，Bayes判别模型在岩爆发生可能性及烈度分级预测中具有良好的适用性和有效性。

Rockburst prediction of underground engineering based on Bayes discriminant analysis method

Based on the distance discriminant analysis model of rockburst prediction, and combined the characteristics and the principle of Bayes discriminant analysis theory, a Bayes discriminant analysis method to predict rockburst in underground engineering is presented. Some main control factors of rockburst, such as the values of in-situ stresses , the compressive strength and tensile strength of rock, the elastic energy index of rock , are selected as the discriminant factors of the Bayes discriminant analysis model; and the resubstitution method is used to estimate the ratio of mistake-distinguish. The data of a series of underground rock projects at home and abroad are taken as the training and testing samples. Rockburst of three tunnels are used to verify this model. The results show that the Bayes discriminant analysis model of rockburst has excellent performance and high prediction accuracy.