摘要
为有效地进行隧道围岩类别超前分类,提出基于TSP203系统和遗传-支持向量机的围岩类别超前分类方法。以TSP203系统为基础,从探测结果中提取有用信息,建立围岩类别超前分类指标体系,并采用支持向量机进行围岩超前分类预测。建立围岩类别超前分类指标体系时,采用TSP203中可有效识别的围岩分类参数来实现:岩体完整性系数、泊松比、静态扬氏模量、主要结构面与洞轴线的夹角、不连续结构面状态和地下水发育情况。确定支持向量机参数时,采用遗传算法在解空间里进行全局搜索,以改善支持向量机在围岩分类中的识别精度。最后将该方法应用于实际工程,结果表明该方法实际可行,在围岩类别超前分类中具有较高的准确性,为围岩类别超前分类提供了一种新思路。
In order to conduct surrounding rock classification ahead tunnel advancing effectively, the advanced surrounding rock classification method based on TSP 203 system and genetic algorithm（GA）-support vector machine（SVM） is put forward. The method extracts the useful information from the detection results of TSP 203, and it establishes the indicators system of advanced surrounding rock classification. In the progress of establishing advanced surrounding rock classification index system, six rock classification parameters are adopted, which TSP203 could identify effectively, i.e. rock mass integrity coefficient, .Poisson＇s ratio, static Young＇s modulus, the angle between main structural surface and the tunnel axis, discontinuous structural surface and the state of groundwater. GA was adopted to optimize the SVM parameters in solution space, which improves the discrimination precision of SVM in surrounding rock classification. Finally, the method is applied to practical engineering and the results show that the method has higher prediction accuracy in predicting advanced surrounding rock classification and provides a new idea for advanced surrounding rock classification.
出处
《岩石力学与工程学报》
EI
CAS
CSCD
北大核心
2010年第A01期3221-3226,共6页
Chinese Journal of Rock Mechanics and Engineering
基金
教育部科学技术研究重点项目(108158)
山东省自然开学基金面上项目(Y2007F53)
中国博士后科学基金项目(20090461203)
关键词
岩石力学
围岩分类
超前预测
支持向量机
遗传算法
rock mechanics surrounding rock classification advanced prediction support vector machine（SVM）
genetic algorithm（GA）
