基于支持向量机的岩爆识别模型

岩爆的发生受多种因素的影响,这些因素关系错综复杂,以不同的特征和组合对岩爆产生综合影响,为科学、充分地利用现有的有限工程资料,本文从地下洞室围岩最大切向应力、岩石的单轴抗压强度和抗拉强度以及岩石冲击倾向指数四个主要因素出发,提出了基于支持向量机的岩爆识别模型,较好地解决小样本、非线性、高维数、局部极小点等的实际问题。

Model of rockburst identification based on SVM

The rockburst is synthetically affected by many factors which are in very complex relations through different characters and combinations.In order to use the limited engineering data scientifically and fully,the model of rockburst identification based on support vector machine(SVM) is proposed.In the model,four major factors such as the maximum tangent stress of adjoining rock,uniaxial compressive strength,uniaxial tensile strength and impact tendency index of rock are considered,the model is very useful to the problems such as small sample,nonlinearity,high dimension,local minimization.