摘要
分类区分度常用来度量评价指标对区分样本所属类别所作的贡献程度。基于分类区分度及灰色聚类法原理,对传统白化权函数的分类区分度及指标分类权重的确定方法进行优化,从理论上合理解决了分类区分度和指标分类权重法在某些情况下不适用的问题。在此基础上,选取岩石质量指标、岩石单轴饱和抗压强度、岩体完整性系数、结构面强度系数和地下水渗水量等5个影响因素作为地下工程岩体质量评价指标,建立基于改进分类区分度及权重的地下工程岩体质量评价灰评估模型(GEM-MCD-WCI模型)。利用改进模型对广州抽水蓄能电站一期地下工程岩体若干组初始实测数据进行等级评价,并将其判定结果与传统模型的分析结果进行对比,发现改进模型的结果与实际情况吻合较好,预测精度更高。为进一步考察改进模型的有效性和实用性,运用该模型对该电站二期工程岩体质量进行分析,并与突变级数法和支持向量机法进行对比。研究结果表明,改进模型的判别结果与突变级数法和支持向量机法获得的结果较一致,预测精度高。研究方法为地下工程岩体质量分级评价提供一种切实可行的途径。
Classification degree is usually used to measure the contribution of the evaluation indexes in distinguishing the sample classification. Based on the theory of classification degree and grey clustering method,the formula for determining the classification degree and weight of classification of index of the white nization weight function is modified. Compared with the traditional formula,the modified formula is suitable under any conditions,which is more reasonable in theory. On the basis,the evaluation indexes including rock quality designation,uniaxial compressive strengthen,rock mass integrality coefficient,strengthen coefficient of structural plane and seepage measurement of groundwater are chosen to establish the grey evaluation model for rock mass quality evaluation by modifying classification degree and weight of classification of index（GEM-MCD-WCI model）. Based on the measured data of the first stage project in Guangzhou pump accumulator electricity station,the GEM-MCD-WCI model is adopted to predict the evaluation of rock mass quality. Compared with the traditional model,the prediction error of the GEM-MCD-WCI model is smaller. Furthermore,the GEMMCD-WCI model is applied to predict the evaluation of the second stage project. The results show that the evaluation results of the model in the paper agree well with those of the catastrophe progression method and support vector machine method. Therefore,the proposed method provides a practical way to accurately evaluate the quality of rock mass in underground engineering.
出处
《岩石力学与工程学报》
EI
CAS
CSCD
北大核心
2016年第A02期3671-3679,共9页
Chinese Journal of Rock Mechanics and Engineering
基金
国家自然科学基金重点资助项目(51539002)
国家自然科学基金青年基金资助项目(51609018)
国家重点研发计划项目(2016YFC0401802)~~
关键词
岩石力学
地下工程
岩体质量评价
分类区分度
指标分类权重
灰色聚类法
rock mechanics
underground engineering
rock mass quality evaluation
classification degree
weight of classification of index
grey clustering method
