摘要
为了建立易于理解和应用的围岩稳定性分类模型,采用主成分分析法对围岩样本数据进行降维处理,以Logistic模型来描述围岩稳定性影响因素与围岩稳定性之间的经验关系。选取影响围岩分类的5个主要因素,根据分类标准,采用在每级标准中随机内插的方法,得到100个标准样本,用于建立PCA-Logistic模型。分析结果显示,PCA-Logistic模型拟合效果良好,对工程实例的预测结果同投影寻踪模型和分形-插值模型完全一致,表明该模型在围岩稳定性评价中具有可行性和有效性。
For establishing a more understanding and applicable classification model of stability of surrounding rock,principal component a-nalysis （PCA）was carried out on dimension reduction of the surrounding rock sample data and Logistic model was adopted to describe the mapping relationship between stability of surrounding rock and its influent factors. Five key factors were chosen to construct the model. In addition,because of few standard samples,100 standard samples were produced by the way of stochastic interpolation on the basis of classifi-cation standard. Analysis results show that the fitting effect of PCA-Logistic model is excellent,and the prediction result of some engineer-ing examples is consistent with those of the projection pursuit model and fractal interpolation model,indicating that the model is feasible and effective in the evaluation of surrounding rock stability.
出处
《人民黄河》
CAS
北大核心
2015年第2期107-110,115,共5页
Yellow River
关键词
围岩
稳定性
分类
主成分
PCA-Logistic模型
surrounding rock
stability
classification
principal component analysis
PCA-Logistic model
